{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [], "machine_shape": "hm" }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "ff16b7ea26274755b31504f3841b4ac3": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_9ab690f7f3eb477a909463095a78276d", "IPY_MODEL_597959c3bc8442d3a838655fd228c5ad", "IPY_MODEL_dd691017b5d64040bff35031078c630c" ], "layout": "IPY_MODEL_35d1f8e9f2ab434ebfb498de2023ea6e" } }, "9ab690f7f3eb477a909463095a78276d": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_cece92dedb7a473b96a9452bfdb5bcc5", "placeholder": "​", "style": "IPY_MODEL_f091ae8f5ca640d3b595a0476991107e", "value": "Downloading data: 100%" } }, "597959c3bc8442d3a838655fd228c5ad": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_cdf0240c06b848949d3ca5c8d0a34f8c", "max": 22043834, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_ac92d334f2bc4b3d922f85d4bf627302", "value": 22043834 } }, "dd691017b5d64040bff35031078c630c": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_fca0ac05d6ed49869667a85f32624a98", "placeholder": "​", "style": "IPY_MODEL_0ae396aa65464429842b77adee0a9050", "value": " 22.0M/22.0M [00:04<00:00, 5.12MB/s]" } }, "35d1f8e9f2ab434ebfb498de2023ea6e": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "cece92dedb7a473b96a9452bfdb5bcc5": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f091ae8f5ca640d3b595a0476991107e": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "cdf0240c06b848949d3ca5c8d0a34f8c": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ac92d334f2bc4b3d922f85d4bf627302": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "fca0ac05d6ed49869667a85f32624a98": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "0ae396aa65464429842b77adee0a9050": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "fc8bbe84dbe945b4a4db924ebcde787c": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_b083581b899b4f8d8d1df397204089b5", "IPY_MODEL_6070bdaf204f4badb8c67a740b773b53", "IPY_MODEL_afe8225db9824b3a83796acfdc7e6b92" ], "layout": "IPY_MODEL_874723296da14e499229805c54dc59fb" } }, "b083581b899b4f8d8d1df397204089b5": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_8c025973dcd54c3cb56ea46b92d9b220", "placeholder": "​", "style": "IPY_MODEL_c5ec38fd376b41779f70ce7f2c09c6ad", "value": "Downloading data: 100%" } }, "6070bdaf204f4badb8c67a740b773b53": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_b105ae619c05472290ba636d580c82ae", "max": 21632094, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_d6438b7b6e01420f94340dabf727dc0d", "value": 21632094 } }, "afe8225db9824b3a83796acfdc7e6b92": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_08288fde273c44538807b717a241fa9b", "placeholder": "​", "style": "IPY_MODEL_095d6b09045b427f9283773a1b1e5366", "value": " 21.6M/21.6M [00:05<00:00, 3.88MB/s]" } }, "874723296da14e499229805c54dc59fb": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8c025973dcd54c3cb56ea46b92d9b220": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c5ec38fd376b41779f70ce7f2c09c6ad": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "b105ae619c05472290ba636d580c82ae": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d6438b7b6e01420f94340dabf727dc0d": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "08288fde273c44538807b717a241fa9b": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "095d6b09045b427f9283773a1b1e5366": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "e354a7d581f048be8801823e0f9e4867": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_cc43fb9e0c474bd1a2a840a4f9affcf0", "IPY_MODEL_1edc3373e4814499bf4c128b5a257f55", "IPY_MODEL_c6cf43e95e664e57b20c2371f138c0df" ], "layout": "IPY_MODEL_b6f588e832f6409bb21f6c4a1a0494e1" } }, "cc43fb9e0c474bd1a2a840a4f9affcf0": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d947ff590a104876880e73688e38f50d", "placeholder": "​", "style": "IPY_MODEL_fff695e7db274ef197d436b111d5b33b", "value": "Generating train split: 100%" } }, "1edc3373e4814499bf4c128b5a257f55": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_c397d241c8be4a53b5f5bc146c720de2", "max": 6505, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_5f1a856860144e6eb3996d2159c46881", "value": 6505 } }, "c6cf43e95e664e57b20c2371f138c0df": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_ed54a37ac6094f2daf1ed40662fd57e8", "placeholder": "​", "style": "IPY_MODEL_457e4338e2d04daebc8af38847bd8071", "value": " 6505/6505 [00:07<00:00, 1181.19 examples/s]" } }, "b6f588e832f6409bb21f6c4a1a0494e1": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d947ff590a104876880e73688e38f50d": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "fff695e7db274ef197d436b111d5b33b": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "c397d241c8be4a53b5f5bc146c720de2": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5f1a856860144e6eb3996d2159c46881": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "ed54a37ac6094f2daf1ed40662fd57e8": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "457e4338e2d04daebc8af38847bd8071": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "4acbe7a3618446fe9650378dda05db96": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_fe8329236fc348e9a6a051978d9219b6", "IPY_MODEL_c9de8b3681694a81a899d5170db37ff7", "IPY_MODEL_0acb7d83a3404646bbbd3a777516e06b" ], "layout": "IPY_MODEL_9064714656db452f9faae2edfaecf346" } }, "fe8329236fc348e9a6a051978d9219b6": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_bcea807846b74bdc86e0ba758977de06", "placeholder": "​", "style": "IPY_MODEL_ee3e6c29d15342b6a3fc81a9b80962b1", "value": "Generating test split: 100%" } }, "c9de8b3681694a81a899d5170db37ff7": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_59b56e5dfc184d228c673189740dca42", "max": 172, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_defeadbf5789498f8868654c7c2b1ca9", "value": 172 } }, "0acb7d83a3404646bbbd3a777516e06b": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_b7b0767e16e04fe5b345080e6fd9f1df", "placeholder": "​", "style": "IPY_MODEL_004d01aeb1df41e1bb384f8f6e169a6a", "value": " 172/172 [00:00<00:00, 551.63 examples/s]" } }, "9064714656db452f9faae2edfaecf346": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "bcea807846b74bdc86e0ba758977de06": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ee3e6c29d15342b6a3fc81a9b80962b1": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "59b56e5dfc184d228c673189740dca42": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "defeadbf5789498f8868654c7c2b1ca9": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "b7b0767e16e04fe5b345080e6fd9f1df": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "004d01aeb1df41e1bb384f8f6e169a6a": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "de140d1e611a40beaff294dc67cfc786": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_d9407e45fcf44b09bad1e6ff4691390c", "IPY_MODEL_f6403d743ab7426aaf4c8ff329ec303c", "IPY_MODEL_fd75dfdff49e4267aae68c26d9722717" ], "layout": "IPY_MODEL_4bad9cc659c64a3783dae79e49814392" } }, "d9407e45fcf44b09bad1e6ff4691390c": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_5baf03fd553940afaf354a8a706fcb4f", "placeholder": "​", "style": "IPY_MODEL_819aa1c06d2f4c069e2b1770c5340284", "value": "Generating validation split: 100%" } }, "f6403d743ab7426aaf4c8ff329ec303c": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_6e23c8c904244d9a92ad1c165279b327", "max": 170, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_df42f9c8cf6247018844b7130233897c", "value": 170 } }, "fd75dfdff49e4267aae68c26d9722717": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_5f9ff29008b7441a9dac2dc6f1cf3595", "placeholder": "​", "style": "IPY_MODEL_1e2f7144133f42d093e49ff958623cf6", "value": " 170/170 [00:00<00:00, 633.48 examples/s]" } }, "4bad9cc659c64a3783dae79e49814392": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5baf03fd553940afaf354a8a706fcb4f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "819aa1c06d2f4c069e2b1770c5340284": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "6e23c8c904244d9a92ad1c165279b327": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "df42f9c8cf6247018844b7130233897c": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "5f9ff29008b7441a9dac2dc6f1cf3595": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "1e2f7144133f42d093e49ff958623cf6": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "5010d96346e54031af6e5a058b66fbe0": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_1d24774a6002450e8980d9cac66fe31c", "IPY_MODEL_536b45d61785460293fcf265fe94bd5f", "IPY_MODEL_7e23e67ed5374633b3734483d6e48999" ], "layout": "IPY_MODEL_ac405a0310c84846b97ca3b9c4d61aa8" } }, "1d24774a6002450e8980d9cac66fe31c": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d45c3c190d684ce2ae22df41e788604d", "placeholder": "​", "style": "IPY_MODEL_760d7b9193f6498b9357d608a333afc7", "value": "Map (num_proc=4): 100%" } }, "536b45d61785460293fcf265fe94bd5f": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_4576962378194faf9da38dc7c38f756f", "max": 6505, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_e31f2f07eb174a50be7dcf402e31acfd", "value": 6505 } }, "7e23e67ed5374633b3734483d6e48999": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_f92e5ac3fe894e319b1ceb954df84ab8", "placeholder": "​", "style": "IPY_MODEL_1baef785723442cdbc27d2cd03081145", "value": " 6505/6505 [00:08<00:00, 429.16 examples/s]" } }, "ac405a0310c84846b97ca3b9c4d61aa8": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d45c3c190d684ce2ae22df41e788604d": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "760d7b9193f6498b9357d608a333afc7": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "4576962378194faf9da38dc7c38f756f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e31f2f07eb174a50be7dcf402e31acfd": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "f92e5ac3fe894e319b1ceb954df84ab8": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "1baef785723442cdbc27d2cd03081145": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "058f25370320440b8a91c2e8502e6f20": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_b6f5cca1a0374f10a0e90e80939acb08", "IPY_MODEL_cc58d0d0e793487ba6c53a9e12e7cb9e", "IPY_MODEL_329e16292c764317bf3b3df5039a7e4f" ], "layout": "IPY_MODEL_241675fa9d0b41deb27d3bea3519abad" } }, "b6f5cca1a0374f10a0e90e80939acb08": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_14c4952ccfc14f5494b7e03bf34ca6c9", "placeholder": "​", "style": "IPY_MODEL_92e26a366e2a4d298f1b1bad54f6872e", "value": "Map (num_proc=4): 100%" } }, "cc58d0d0e793487ba6c53a9e12e7cb9e": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_70dd2c7eaa2c44609a6941bd24ead639", "max": 172, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_0c586bf30fea4d26be6f12b46025bc4b", "value": 172 } }, "329e16292c764317bf3b3df5039a7e4f": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_33889d21c6e14a6dba1a00da4098362f", "placeholder": "​", "style": "IPY_MODEL_4e7bce698221409eaa50338c8cee6d86", "value": " 172/172 [00:00<00:00, 637.52 examples/s]" } }, "241675fa9d0b41deb27d3bea3519abad": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "14c4952ccfc14f5494b7e03bf34ca6c9": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "92e26a366e2a4d298f1b1bad54f6872e": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "70dd2c7eaa2c44609a6941bd24ead639": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "0c586bf30fea4d26be6f12b46025bc4b": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "33889d21c6e14a6dba1a00da4098362f": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4e7bce698221409eaa50338c8cee6d86": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "438c5b4b50bf415cb075c7a67e29e953": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_24a5121706544413bab2508eb5b3883a", "IPY_MODEL_9130f66ff9af4e4a8b082f3eaa6fd65d", "IPY_MODEL_03f353f3ef0c4be797b6bce056bef3a1" ], "layout": "IPY_MODEL_9737e8cdd1c74a3cb1b266ce21530177" } }, "24a5121706544413bab2508eb5b3883a": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d59676997c0e47ae906cdb48e05aac19", "placeholder": "​", "style": "IPY_MODEL_9898ecff0b4445988931ac6855a47c82", "value": "Map (num_proc=4): 100%" } }, "9130f66ff9af4e4a8b082f3eaa6fd65d": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_0a7bb1947ec5417b8ce389a97d875ca3", "max": 170, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_8cce964a85804abfb244d6289944f3c9", "value": 170 } }, "03f353f3ef0c4be797b6bce056bef3a1": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_2b5be7dcdabf47aa850f497eb14f3165", "placeholder": "​", "style": "IPY_MODEL_cd17329cae5b47b4b0779180af279949", "value": " 170/170 [00:00<00:00, 371.49 examples/s]" } }, "9737e8cdd1c74a3cb1b266ce21530177": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d59676997c0e47ae906cdb48e05aac19": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "9898ecff0b4445988931ac6855a47c82": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "0a7bb1947ec5417b8ce389a97d875ca3": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8cce964a85804abfb244d6289944f3c9": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "2b5be7dcdabf47aa850f497eb14f3165": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "cd17329cae5b47b4b0779180af279949": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } } } } }, "cells": [ { "cell_type": "markdown", "source": [ "# clustering edgar - example\n", "\n", "- embeddings from https://huggingface.co/BEE-spoke-data/mega-small-embed-syntheticSTS-16384 (on first 16384 tokens)\n", "- summaries on first 25,000 chars\n", "\n", "\n", "---" ], "metadata": { "id": "b9_fczYH96sf" } }, { "cell_type": "code", "execution_count": null, "metadata": { "cellView": "form", "id": "LrDWdEzv3LaX" }, "outputs": [], "source": [ "#@markdown add auto-Colab formatting with `IPython.display`\n", "from IPython.display import HTML, display\n", "# colab formatting\n", "def set_css():\n", " display(\n", " HTML(\n", " \"\"\"\n", " \n", " \"\"\"\n", " )\n", " )\n", "\n", "get_ipython().events.register(\"pre_run_cell\", set_css)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "DAiGxkCEPD99", "colab": { "base_uri": "https://localhost:8080/", "height": 17 }, "outputId": "b1796cf8-c079-4026-e354-88b425239872" }, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " " ] }, "metadata": {} } ], "source": [ "!pip install -U -q sentence-transformers datasets" ] }, { "cell_type": "code", "source": [ "from huggingface_hub import notebook_login\n", "# notebook_login()" ], "metadata": { "id": "k3fpezvqPk9l", "colab": { "base_uri": "https://localhost:8080/", "height": 17 }, "outputId": "ab6b4e17-c33b-4b93-f151-8256356ab34e" }, "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " " ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "from datasets import load_dataset\n", "\n", "ds_name = \"pszemraj/edgar-corpus-htm2020\"\n", "ds_config='embedding-all-distilroberta-v1'\n", "dataset = load_dataset(ds_name, ds_config, num_proc=4 )\n", "dataset" ], "metadata": { "id": "JyTYKPFCPsIQ", "colab": { "base_uri": "https://localhost:8080/", "height": 489, "referenced_widgets": [ "ff16b7ea26274755b31504f3841b4ac3", "9ab690f7f3eb477a909463095a78276d", "597959c3bc8442d3a838655fd228c5ad", "dd691017b5d64040bff35031078c630c", "35d1f8e9f2ab434ebfb498de2023ea6e", "cece92dedb7a473b96a9452bfdb5bcc5", "f091ae8f5ca640d3b595a0476991107e", "cdf0240c06b848949d3ca5c8d0a34f8c", "ac92d334f2bc4b3d922f85d4bf627302", "fca0ac05d6ed49869667a85f32624a98", "0ae396aa65464429842b77adee0a9050", "fc8bbe84dbe945b4a4db924ebcde787c", "b083581b899b4f8d8d1df397204089b5", "6070bdaf204f4badb8c67a740b773b53", "afe8225db9824b3a83796acfdc7e6b92", "874723296da14e499229805c54dc59fb", "8c025973dcd54c3cb56ea46b92d9b220", "c5ec38fd376b41779f70ce7f2c09c6ad", "b105ae619c05472290ba636d580c82ae", "d6438b7b6e01420f94340dabf727dc0d", "08288fde273c44538807b717a241fa9b", "095d6b09045b427f9283773a1b1e5366", "e354a7d581f048be8801823e0f9e4867", "cc43fb9e0c474bd1a2a840a4f9affcf0", "1edc3373e4814499bf4c128b5a257f55", "c6cf43e95e664e57b20c2371f138c0df", "b6f588e832f6409bb21f6c4a1a0494e1", "d947ff590a104876880e73688e38f50d", "fff695e7db274ef197d436b111d5b33b", "c397d241c8be4a53b5f5bc146c720de2", "5f1a856860144e6eb3996d2159c46881", "ed54a37ac6094f2daf1ed40662fd57e8", "457e4338e2d04daebc8af38847bd8071", "4acbe7a3618446fe9650378dda05db96", "fe8329236fc348e9a6a051978d9219b6", "c9de8b3681694a81a899d5170db37ff7", "0acb7d83a3404646bbbd3a777516e06b", "9064714656db452f9faae2edfaecf346", "bcea807846b74bdc86e0ba758977de06", "ee3e6c29d15342b6a3fc81a9b80962b1", "59b56e5dfc184d228c673189740dca42", "defeadbf5789498f8868654c7c2b1ca9", "b7b0767e16e04fe5b345080e6fd9f1df", "004d01aeb1df41e1bb384f8f6e169a6a", "de140d1e611a40beaff294dc67cfc786", "d9407e45fcf44b09bad1e6ff4691390c", "f6403d743ab7426aaf4c8ff329ec303c", "fd75dfdff49e4267aae68c26d9722717", "4bad9cc659c64a3783dae79e49814392", "5baf03fd553940afaf354a8a706fcb4f", "819aa1c06d2f4c069e2b1770c5340284", "6e23c8c904244d9a92ad1c165279b327", "df42f9c8cf6247018844b7130233897c", "5f9ff29008b7441a9dac2dc6f1cf3595", "1e2f7144133f42d093e49ff958623cf6" ] }, "outputId": "97dc6ef0-8d20-456c-a9c0-60fedb2baa74" }, "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " " ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "Downloading data: 0%| | 0.00/22.0M [00:00 torch.Tensor:\n", " \"\"\"\n", " Normalize embeddings using L2 norm and an epsilon to avoid division by zero.\n", "\n", " Args:\n", " embeddings (array-like): The embeddings tensor to normalize.\n", " epsilon (float): small value added to norms to avoid division by zero.\n", "\n", " Returns:\n", " torch.Tensor: The normalized embeddings.\n", " \"\"\"\n", " embeddings = torch.Tensor(embeddings)\n", " # L2 norm, keep dimension for broadcasting\n", " norms = torch.norm(embeddings, p=2, dim=1, keepdim=True)\n", "\n", " # Add epsilon to norms to avoid division by zero\n", " norms = torch.clamp(norms, min=epsilon)\n", "\n", " return embeddings / norms\n", "\n", "\n", "# Example usage\n", "corpus_embeddings = safe_normalize(dataset[\"train\"][\"embedding\"])\n", "corpus_embeddings.shape" ], "metadata": { "id": "7qihITaKP7VQ", "cellView": "form", "colab": { "base_uri": "https://localhost:8080/", "height": 34 }, "outputId": "af05ccc1-138b-4655-ff38-4e7649c5f097" }, "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " " ] }, "metadata": {} }, { "output_type": "execute_result", "data": { "text/plain": [ "torch.Size([6505, 768])" ] }, "metadata": {}, "execution_count": 5 } ] }, { "cell_type": "code", "source": [ "import random\n", "import re\n", "\n", "\n", "def fast_wc(text):\n", " return len(re.findall(r\"\\w+\", text))\n", "\n", "\n", "sample = random.choice(dataset[\"train\"])\n", "textwc = fast_wc(sample[\"text\"]) - fast_wc(sample[\"text\"][:500])\n", "print(\"text:\\n\", f\"\\n```\\n{sample['text'][:500]} ...\\n```\\n and {textwc} more words\")\n", "print(\"\\n\", \"-\" * 80)\n", "print(\"summary:\\n\\n\", sample[\"summary_first_25k\"])" ], "metadata": { "id": "Y-ZsPUxp4oVi", "colab": { "base_uri": "https://localhost:8080/", "height": 486 }, "outputId": "1bb634c2-0387-43b3-daac-a630948d7b8f" }, "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " " ] }, "metadata": {} }, { "output_type": "stream", "name": "stdout", "text": [ "text:\n", " \n", "```\n", "## SEC EDGAR Filing\n", "\n", "- **Filename**: 1037646_2020.htm\n", "- **CIK**: 1037646\n", "- **Year**: 2020\n", "\n", "---\n", "\n", "### Business\n", "\n", "Item 1.Business\n", "We are a leading global supplier of precision instruments and services. We have strong leadership positions in all of our businesses and believe we hold global number-one market positions in most of them. We are recognized as an innovation leader and our solutions are critical in key research and development, quality control, and manufacturing processes for customers in a ...\n", "```\n", " and 38917 more words\n", "\n", " --------------------------------------------------------------------------------\n", "summary:\n", "\n", " The SEC's annual report on Form 10-K for the year ended December 31, 2020 is a compilation of financial statements and related notes. These reports provide detailed information about Mettler Toledo International, Inc., a leading global precision instruments and service provider, focusing on research and development in various industries. The company has strong leadership positions across all its businesses, with sales and service reaching 140 countries and direct presence in 40 countries.\n" ] } ] }, { "cell_type": "code", "source": [ "!pip install clean-text[gpl] yake sentence-splitter -q\n", "from cleantext import clean" ], "metadata": { "id": "nSAGcLb1Q_Dr", "colab": { "base_uri": "https://localhost:8080/", "height": 17 }, "outputId": "63ea5d05-d46c-40d1-9f57-5d7e8e3d2d4e" }, "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " " ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "# @title helper fns\n", "import random\n", "\n", "def sp(text: str, max_n: int = 45):\n", " \"\"\"\n", " Shortens a given text to a specified maximum number of characters.\n", "\n", " Args:\n", " text: The text to be shortened.\n", " max_n: Maximum number of characters to keep.\n", "\n", " Returns:\n", " Shortened text with '...' appended if longer than max_n.\n", " \"\"\"\n", " return text.strip() if len(str(text)) < max_n else text[:max_n].strip() + \"...\"\n", "\n", "def print_cluster_summary(\n", " clusters,\n", " corpus_sentences,\n", " title=\"Cluster Summary\",\n", " top_n=3,\n", " random_sample=False,\n", " max_n=45,\n", " max_clusters_printed=100\n", "):\n", " \"\"\"\n", " Prints details for each cluster, including its size and individual sentences\n", " from the top, bottom, and optionally random samples, with a limit on the total number\n", " of clusters printed.\n", "\n", " Args:\n", " clusters: List of clusters.\n", " corpus_sentences: The corpus of sentences.\n", " title: Title for the summary printout.\n", " top_n: Number of sentences to display from the top and bottom.\n", " random_sample: If True, prints 2*top_n random sentences from each cluster.\n", " max_n: Maximum number of characters for each sentence to be displayed.\n", " max_clusters_printed: Maximum number of clusters to print.\n", " \"\"\"\n", " print(f\"{title}:\\n\\ttotal clusters:\\t{len(clusters)}\\n\")\n", " for i, cluster in enumerate(clusters[:max_clusters_printed]):\n", " print(f\"Cluster #{i+1}, Size: {len(cluster)}\")\n", " print(\"-\" * 20)\n", "\n", " if random_sample and len(cluster) > 2 * top_n:\n", " print(f\"Random {2*top_n} Sentences:\")\n", " random_indices = random.sample(cluster, 2 * top_n)\n", " for sentence_id in random_indices:\n", " print(f\"\\t- {sp(corpus_sentences[sentence_id], max_n)}\")\n", " else:\n", " print(f\"Top {top_n} Sentences:\")\n", " for sentence_id in cluster[:top_n]:\n", " print(f\"\\t- {sp(corpus_sentences[sentence_id], max_n)}\")\n", "\n", " if len(cluster) > top_n: # Ensure there are enough sentences for a bottom printout\n", " print(f\"Bottom {top_n} Sentences:\")\n", " for sentence_id in cluster[-top_n:]:\n", " print(f\"\\t- {sp(corpus_sentences[sentence_id], max_n)}\")\n", " print(\"\\n\" + \"-\" * 60)\n", "\n", " if i + 1 == max_clusters_printed:\n", " print(f\"Printing limited to the first {max_clusters_printed} clusters.\")\n", " break" ], "metadata": { "cellView": "form", "id": "-hY1H2KKCdwI", "colab": { "base_uri": "https://localhost:8080/", "height": 17 }, "outputId": "7c98cdc4-c79d-4765-dc14-d0a86ff3f8a2" }, "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " " ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "import re\n", "from sentence_splitter import split_text_into_sentences\n", "#@title filter_and_join_sentences\n", "\n", "def filter_and_join_sentences(text, n=2):\n", " \"\"\"\n", " Filter out non-useful sentences from the text based on specific patterns indicating\n", " non-informative content (e.g., repetitive legal or formal disclosures), then join and\n", " return the first n useful sentences.\n", "\n", " :param text: String containing the original text.\n", " :param n: Number of useful sentences to return.\n", " :return: A string of the first n useful sentences joined together.\n", " \"\"\"\n", "\n", " # Split text into sentences\n", " sentences = split_text_into_sentences(text, language='en')\n", "\n", " # Patterns for sentences to be excluded, targeting SEC-related disclosures and similar\n", " exclusion_patterns = [\n", " \"The SEC's annual report on the Securities and Exchange Commission \\(SEC\\) is a compilation of\",\n", " \"covers various risk factors\",\n", " \"filed a Form 10-K\",\n", " \"SEC's filing\",\n", " \"SEC's Annual Report\",\n", " \"The SEC also provides\",\n", " \"Securities and Exchange Commission (SEC)\",\n", "\n", " ]\n", "\n", " # Compiling regex patterns for efficiency\n", " compiled_patterns = [re.compile(pattern, re.IGNORECASE) for pattern in exclusion_patterns]\n", "\n", " def is_sentence_useful(sentence):\n", " \"\"\"Check if a sentence is not matching exclusion patterns and thus considered useful.\"\"\"\n", " return not any(pattern.search(sentence) for pattern in compiled_patterns)\n", "\n", " # Filter out non-useful sentences and limit to the first n sentences\n", " useful_sentences = [s for s in sentences if is_sentence_useful(s)][:n]\n", "\n", " # Join and return the useful sentences\n", " return ' '.join(useful_sentences)\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 17 }, "cellView": "form", "id": "Xb_9tPwE5PWX", "outputId": "3312a18f-e5f7-4cc2-80d9-bb5cf3853e30" }, "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " " ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "from sentence_splitter import SentenceSplitter, split_text_into_sentences\n", "\n", "dataset = dataset.map(\n", " lambda x: {\n", " \"display_text\":\n", " # \" \".join(\n", " # split_text_into_sentences(x[\"summary_first_25k\"], language=\"en\")[:2]\n", " # )\n", " filter_and_join_sentences(x[\"summary_first_25k\"])\n", " + \" ...\"\n", " + f\" cik: {x['cik']}\"\n", " },\n", " num_proc=4,\n", ")\n", "display_text = dataset[\"train\"][\"display_text\"]" ], "metadata": { "id": "z83NJbdTC8PR", "colab": { "base_uri": "https://localhost:8080/", "height": 113, "referenced_widgets": [ "5010d96346e54031af6e5a058b66fbe0", "1d24774a6002450e8980d9cac66fe31c", "536b45d61785460293fcf265fe94bd5f", "7e23e67ed5374633b3734483d6e48999", "ac405a0310c84846b97ca3b9c4d61aa8", "d45c3c190d684ce2ae22df41e788604d", "760d7b9193f6498b9357d608a333afc7", "4576962378194faf9da38dc7c38f756f", "e31f2f07eb174a50be7dcf402e31acfd", "f92e5ac3fe894e319b1ceb954df84ab8", "1baef785723442cdbc27d2cd03081145", "058f25370320440b8a91c2e8502e6f20", "b6f5cca1a0374f10a0e90e80939acb08", "cc58d0d0e793487ba6c53a9e12e7cb9e", "329e16292c764317bf3b3df5039a7e4f", "241675fa9d0b41deb27d3bea3519abad", "14c4952ccfc14f5494b7e03bf34ca6c9", "92e26a366e2a4d298f1b1bad54f6872e", "70dd2c7eaa2c44609a6941bd24ead639", "0c586bf30fea4d26be6f12b46025bc4b", "33889d21c6e14a6dba1a00da4098362f", "4e7bce698221409eaa50338c8cee6d86", "438c5b4b50bf415cb075c7a67e29e953", "24a5121706544413bab2508eb5b3883a", "9130f66ff9af4e4a8b082f3eaa6fd65d", "03f353f3ef0c4be797b6bce056bef3a1", "9737e8cdd1c74a3cb1b266ce21530177", "d59676997c0e47ae906cdb48e05aac19", "9898ecff0b4445988931ac6855a47c82", "0a7bb1947ec5417b8ce389a97d875ca3", "8cce964a85804abfb244d6289944f3c9", "2b5be7dcdabf47aa850f497eb14f3165", "cd17329cae5b47b4b0779180af279949" ] }, "outputId": "5c918266-f842-4e46-830d-87c6bb60d8f2" }, "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " " ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "Map (num_proc=4): 0%| | 0/6505 [00:00" ], "text/html": [ "\n", " \n", " " ] }, "metadata": {} }, { "output_type": "stream", "name": "stdout", "text": [ "Start clustering: min_cluster_size=6, threshold=0.85\n", "Clustering done after 0.87 sec\n", "Documents not clustered: 3817 of 6505\n" ] } ] }, { "cell_type": "code", "source": [ "print(f\"Params:\\tmin_cluster_size={mcs}, threshold={threshold}\")\n", "print(f\"Documents not clustered: {num_unclustered} of {len(corpus_embeddings)}\")\n", "print_cluster_summary(clusters, display_text, random_sample=True,\n", " max_n=128)" ], "metadata": { "id": "DFu7FxhBQSkI", "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "outputId": "6fff534f-a80a-40c8-9eba-85f1cdadd6d4" }, "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "\n", " \n", " " ] }, "metadata": {} }, { "output_type": "stream", "name": "stdout", "text": [ "Params:\tmin_cluster_size=6, threshold=0.85\n", "Documents not clustered: 3817 of 6505\n", "Cluster Summary:\n", "\ttotal clusters:\t131\n", "\n", "Cluster #1, Size: 590\n", "--------------------\n", "Random 6 Sentences:\n", "\t- In addition, the SEC has provided information regarding Wells Fargo Bank's compliance with applicable servicing criteria, which...\n", "\t- The report covers various aspects of the Trust, including business, risk factors, governance, financial statements, and market f...\n", "\t- The report also discusses the impact of litigation on the trustee and RMBS trusts, as well as U.S Bank National Association's la...\n", "\t- This SEC filing is a compilation of information from the Securities and Exchange Commission (SEC) regarding various aspects of t...\n", "\t- It also includes certain relationships and related transactions, director independence, executive compensation, security ownersh...\n", "\t- It also includes a summary of legal proceedings, an overview of U.S Bank National Association's lawsuit against it, and a brief...\n", "\n", "------------------------------------------------------------\n", "Cluster #2, Size: 244\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The company, founded in August 2020, is a Delaware corporation seeking an initial investment in life sciences, including medical...\n", "\t- The SEC filing for Foley Trasimen Acquisition Corp. (the \"Company\"), a Delaware-based blank check company, focuses on identifyin...\n", "\t- Crucible Acquisition Corporation (the \"Company\" or \"Solvay Acquisition\") is a Delaware corporation that intends to merge, capita...\n", "\t- GreenVision Acquisition Corporation (NASDAQ: GWA) is a Delaware corporation formed in September 2019 for the purpose to engage i...\n", "\t- The company, formed on July 15, 2020, is an early-stage and emerging growth business with a focus on identifying a potential tar...\n", "\t- The Business Combination is expected to result in Nerdy owning approximately 60% of Nerdy shares and 90% of OpCo units, with Ner...\n", "\n", "------------------------------------------------------------\n", "Cluster #3, Size: 134\n", "--------------------\n", "Random 6 Sentences:\n", "\t- These statements involve risks and uncertainties, such as changes in economic conditions, competition, inflation, interest rate...\n", "\t- The Securities and Exchange Commission (SEC) has issued a report on Form 10K for Benchmark Corporation (Benchmark), a leading pr...\n", "\t- Trend Innovations Holding, Inc., formerly FreeCook, is a Lithuanian holding company specializing in innovative websites for user...\n", "\t- The Securities and Exchange Commission (SEC) has filed its Annual Report for the fiscal year ended December 31, 2019 with the SE...\n", "\t- It focuses on our operations and assets, including the sale of certain assets to an unaffiliated third party, as well as potenti...\n", "\t- The report contains \"Business Item 1. Cautionary Statement Regarding Forward-looking Statements\" regarding the potential impact...\n", "\n", "------------------------------------------------------------\n", "Cluster #4, Size: 125\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Condor Hospitality Trust (the \"Company\" or \"Condor Hospitality\"), a self-regulated real estate investment trusts (REIT) with 15...\n", "\t- The company is a leading global commercial property services firm, providing services to investors, occupiers, and occupiers. It...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 20-F for the fiscal year ending December 31, 2020,...\n", "\t- The Business Item 1 of General American Realty, Inc.'s (ARL) annual report on Form 20-F for the fiscal year ending December 31,...\n", "\t- Colony Capital, a global investment firm focused on digital real estate, is a leading global REIT with a vision to establish the...\n", "\t- The Company focuses on acquiring, managing, leasing, and managing open air shopping centers in suburban, High Household Income C...\n", "\n", "------------------------------------------------------------\n", "Cluster #5, Size: 109\n", "--------------------\n", "Random 6 Sentences:\n", "\t- FNB Corporation (FNB) is a Pennsylvania corporation and financial holding company, with three business segments: community banki...\n", "\t- The Securities and Exchange Commission (SEC) filed its Form 10-K for the fiscal year ended December 31, 2020, with a focus on Co...\n", "\t- The SEC filing, \"Business Item 1. Business Item 1. ... cik: 1391933\n", "\t- Mid Penn Bancorp (Mid Penn) is a Pennsylvania-based financial holding company, incorporated in 1991. Mid Penn has three nonbanki...\n", "\t- Amalgamated Financial Corporation, a Delaware Public Benefit Corporation, was formed in August 2020, serving as the parent compa...\n", "\t- Hancock Whitney Corporation is a financial products company that offers comprehensive financial services, including traditional...\n", "\n", "------------------------------------------------------------\n", "Cluster #6, Size: 101\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The SEC's Form 10-K for the fiscal year ended March 26, 2021 is filed with the Securities and Exchange Commission (SEC) under Re...\n", "\t- The report covers significant obligors in pool assets, credit enhancement and other support, derivative instruments, financial i...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 10K for the fiscal year ending December 31, 2020, w...\n", "\t- The report focuses on legal proceedings against the company, its affiliates, and certain servicers related to the transaction. R...\n", "\t- The SEC's Form 10-K for the fiscal year ending December 31, 2020 is a summary of disclosures received by Verizon Owner Limited L...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 10K for the fiscal year ended December 31, 2020, wi...\n", "\n", "------------------------------------------------------------\n", "Cluster #7, Size: 47\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Sierra Income Corporation (the \"Company\" or \"Sierra\") is a closed-end managed investment company, offering equity and debt inves...\n", "\t- The SEC filing for Capitala Investment Advisers, LLC (the \"Company\"), a Maryland-based business development company, is availabl...\n", "\t- It covers various topics, including: business operations, risks related to US or global economic conditions, market conditions,...\n", "\t- Stellus Capital Investments Corporation (the \"Company\") is a private, externally managed business development company (BDC) with...\n", "\t- Gladstone Capital Corporation (the \"Adviser\") is a private equity investment company, established in 2001, with an initial offer...\n", "\t- SuRo Capital Corporation (the \"Company\") is an internally managed closed-end investment company, with a focus on high-growth ven...\n", "\n", "------------------------------------------------------------\n", "Cluster #8, Size: 37\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Harvest Capital Credit, LLC (the \"Company\" or \"Harvest Capital Credit\") is a managed, nondiversified business development compan...\n", "\t- S|T-O|R |E is a publicly traded REIT, with an investment portfolio of 2,634 STORE Properties in the U.s., primarily serving serv...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 10-K for the year ended March 31, 2020, with a focu...\n", "\t- The business statement is a summary of CNL Healthcare's operations and financial condition, focusing on its diversified portfoli...\n", "\t- American Finance Properties (REIT) is an externally managed, publicly traded real estate trust with a focus on managing a divers...\n", "\t- The text is a summary of the business and operations of Oaktree Real estate Income Trust, LLC (a Maryland corporation) with a fo...\n", "\n", "------------------------------------------------------------\n", "Cluster #9, Size: 30\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Cayman Islands exempted blank check company, 1809353, is a Cayman Islands-registered company that intends to capitalize on 6...\n", "\t- The Cayman Islands-based blank check company, 1816613, is a Cayman Islands limited liability company offering an alternative pat...\n", "\t- The company's annual report is filed with the Securities and Exchange Commission (SEC) under the Securities Act of 1933, as amen...\n", "\t- Upstream Biosciences, Inc., a California-based company, is a small reporting company with no operations and limited management r...\n", "\t- The text is a compilation of financial statements from Cetrone Inc., an energy company incorporated in Nevada on January 28, 200...\n", "\t- The SEC filing for 1836154, a Delaware corporation, focuses on the company and its business model, focusing on mergers, capital...\n", "\n", "------------------------------------------------------------\n", "Cluster #10, Size: 26\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The report also covers FBFS' financial condition and results of operations, which are presented in tabular form. ... cik: 152195...\n", "\t- The SEC filing for New York City Community Bank, Inc. (the \"Company\") is a Delaware-based bank holding company with 237 branches...\n", "\t- The SEC filing for Great Western Bank, Inc.'s (Great Western) financial statements for the fiscal year ending September 30, 2020...\n", "\t- West Bancorporation (the Company) is a Iowa corporation and financial holding company with a focus on banking, focusing on small...\n", "\t- The Capital City Financial Corporation (the \"Company\" or \"CFFN\") is a savings bank with assets of $10 billion and operations in...\n", "\t- UMB Financial Corp., a Kansas City, Mo.-based financial holding company, provides banking services to customers in the US and ar...\n", "\n", "------------------------------------------------------------\n", "Cluster #11, Size: 26\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Tampa Electric Company (TEC) is a Florida-based public utility operating in West Central, Florida. TEC operates two operating se...\n", "\t- The report covers various aspects of the company, including its business operations, regulatory requirements, energy efficiency...\n", "\t- DESC, which is headquartered at Cayce, SC, is a public utility engaged in generation, transmission, distribution, and natural ga...\n", "\t- The Securities and Exchange Commission (SEC) filed its 2020 Annual Report on American Electric Power (AEP) with the SEC on Decem...\n", "\t- Alliant Energy Corporation (AEF) and its subsidiaries, IPL, and WPL, operate as regulated investor-controlled public utility hol...\n", "\t- The Securities and Exchange Commission (SEC) filed its 2020 Annual Report on American Electric Power (AEP) with the SEC on Decem...\n", "\n", "------------------------------------------------------------\n", "Cluster #12, Size: 24\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Spindletop Oil and Gas Co., a Texas-based oil and gas exploration company, operates in six states: Texas, Alabama, Louisiana, Ne...\n", "\t- The SEC filing for General Prime Energy Resources Corporation (NYSE:GP) is a business item. It focuses on the company's oil and...\n", "\t- Quantum Energy, a Nevada corporation, was incorporated in 2004, focusing on energy industry and oil and gas exploration. The com...\n", "\t- The company's financial statements for the year ending June 30, 2020 are presented in a Business Item 1. This document provides...\n", "\t- The SEC filing for the fiscal year ended January 31, 2020 is a business item titled \"Business Item 1. Business Overview - The KL...\n", "\t- Oasis Petroleum, Inc., a Delaware corporation (together with its consolidated subsidiaries), is an independent oil and gas explo...\n", "\n", "------------------------------------------------------------\n", "Cluster #13, Size: 23\n", "--------------------\n", "Random 6 Sentences:\n", "\t- VitaSpring Biomedical Company Ltd., a Nevada-based start-up company specializing in leather fashion design products, has been in...\n", "\t- The text is a compilation of documents filed by High Sierra Technologies Inc. (High Sierra), a company incorporated in Colorado...\n", "\t- Steampunk Wizards (OTCQB: CIK) is a Nevada-based \"shell company,\" with no significant assets and operations other than its effor...\n", "\t- Imagine Media Ltd., incorporated in 2007, is a Colorado-based company focused on creating and promoting entertainment guides for...\n", "\t- The company's history and business highlights its acquisition of SBS in July 2018, which resulted in the consolidation of SBS in...\n", "\t- Quture International Inc., a Nevada corporation (the \"Company\" or \"Quture\") is a healthcare knowledge solutions company that dev...\n", "\n", "------------------------------------------------------------\n", "Cluster #14, Size: 23\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Chesapeake Granite Wash (Trust) is a Delaware statutory trust established in June 2011 to own and hold royalty interests in vari...\n", "\t- Marine Petroleum Trust, a royalty trust established in 1956 under Texas law, is a company that manages and liquidates rights to...\n", "\t- The SEC filing for the Business General PerMRock Royalty Trust, a Delaware trust formed in November 2017, is a comprehensive ove...\n", "\t- Frontier Funds, a Delaware Statutory Trust, is a multiadvisor commodity pool with seven separate and distinct Series of Units is...\n", "\t- Frontier Funds, a Delaware Statutory Trust, is a multiadvisor commodity pool with seven separate and distinct Series of Units is...\n", "\t- Texas Pacific Land (TPL) is a leading landowner in West Texas with 880,000 acres, including 85,000 acres and 1/16 NPRI. The Comp...\n", "\n", "------------------------------------------------------------\n", "Cluster #15, Size: 22\n", "--------------------\n", "Random 6 Sentences:\n", "\t- ENGlobal Corporation (\"ENGlobal\" or the \"Company\") is a Nevada-based company specializing in engineered modular solutions for en...\n", "\t- Jabil, a leading provider of electronics design, manufacturing, and product management solutions, is a global leader in providin...\n", "\t- UFP Industries (the \"Company\") is a leading manufacturer, marketer, and distributor of wood, wood, and other non-wood composite...\n", "\t- Dana Incorporated is a global leader in power management solutions for vehicles, machinery, and stationary industrial markets. T...\n", "\t- The text is a comprehensive overview of Meritor, Incorporated (Meritor), a leading global supplier of integrated systems and com...\n", "\t- LCI Industries (LCII) is a leading manufacturer of engineered components in the recreational vehicle, transportation, and afterm...\n", "\n", "------------------------------------------------------------\n", "Cluster #16, Size: 21\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Securities and Exchange Commission (SEC) has issued a report on the impact of the Global Coventry Virus (COVID-19) pandemic...\n", "\t- The Securities and Exchange Commission's (SEC) annual report on Form 10K for the fiscal year ending December 31, 2020, includes...\n", "\t- The Securities and Exchange Commission (SEC) has filed its annual report on Form 10-K for the year ended December 31, 2020, with...\n", "\t- The US Securities and Exchange Commission (SEC) has issued a report on the COVID 19 pandemic, which has had significant adverse...\n", "\t- These risks include the impact of the CoVID-19 pandemic on its business operations, financial conditions, and trading price, and...\n", "\t- ... cik: 1574596\n", "\n", "------------------------------------------------------------\n", "Cluster #17, Size: 21\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Maryland Real Estate Investment Trust (REIT) is a self-managed multifamily apartment community company that owns and operates 56...\n", "\t- Kilroy Realty Corp., a real estate investment trusts (REIT) with interests in various real estate assets located along the West...\n", "\t- The Company is a self-administered, Maryland real estate Investment Trust (REIT) that owns 103 hotel properties and 22,700 rooms...\n", "\t- The company's primary revenue sources are rental income from commercial real estate operations, interest income derived from sec...\n", "\t- PREIT (NYSE: PREIT) is a fully integrated real estate investment trust (REIT) with a primary investment objective in retail shop...\n", "\t- Sabra Healthcare REIT (Sabra) is a self-managed real estate investment trust (REIT) that invests in healthcare facilities, prima...\n", "\n", "------------------------------------------------------------\n", "Cluster #18, Size: 21\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Columbia Bank, Inc., headquartered in Tacoma, Wash., is a registered banking subsidiary of Columbia State Bank (Columbia Bank),...\n", "\t- The Business Item 1 of the Securities and Exchange Commission's (SEC) Annual Report on Form 20-F for the year ending December 31...\n", "\t- The company is a full-scale commercial bank with 19 branches in Alabama, Texas, Virginia, and New York. It offers a suite of loa...\n", "\t- Business Item 1 of the Securities and Exchange Commission's (SEC) Form 1527383 is a business report covering Bank of Guam. The r...\n", "\t- Bank of Marin is a California-based bank with operations in seven Bay Areas, including Marin, Sonoma and Napa counties. The comp...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 10K, Quarterly Report on Form 8-Q, and Amendments t...\n", "\n", "------------------------------------------------------------\n", "Cluster #19, Size: 21\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The SEC's \"Risk Factors\" section discusses the risks and uncertainties associated with the company's business operations, financ...\n", "\t- These risks include: *The COVID-19 epidemic has negatively impacted the global economy; *Lower future commodity prices may force...\n", "\t- The Securities and Exchange Commission (SEC) has issued a risk factor report on its Annual Report for the fiscal year ended Dece...\n", "\t- The SEC's Form 1748773 Risk Factors for Diamondback Energy Company (NYSE:DNR) includes risks related to the COVID 19 pandemic, r...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 10-K for the year ended December 31, 2020, with a r...\n", "\t- These risks include, but are not limited to, potential reductions in or slowing development programs, financial condition and ma...\n", "\n", "------------------------------------------------------------\n", "Cluster #20, Size: 19\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Investview Inc., a Utah-based company specializing in financial technology, services, and research, is a leading provider of fin...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report for the fiscal year ended June 30, 2020, covering Global Wh...\n", "\t- Light Tech, Inc. (Light Tech) is a Nevada corporation incorporated on May 24, 1984, with a business history and business develop...\n", "\t- Sow Good, Inc., a freeze-drying food products company, has changed its name from BlackRidge Oil & Gas (OTCQB:SOWG) to Sow Good (...\n", "\t- Fortune Valley Treasures (OTCQB: CIK) is a leading food and beverage company in Guangdong Province, China, with eight stores ser...\n", "\t- It covers various topics, including business history, financial position, and risks related to our business. The company has two...\n", "\n", "------------------------------------------------------------\n", "Cluster #21, Size: 19\n", "--------------------\n", "Random 6 Sentences:\n", "\t- These comments were made pursuant to Item 1B of the Securities Exchange Act of 1934 (the \"SEC\"), which requires a thorough revie...\n", "\t- The text is a summary of RadNet, Inc.'s financial statements for the year-ended December 31, 2020, which includes unresolved sta...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 20-F for the fiscal year ending September 30, 2020,...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 10-K for OceanFirst Financial Corporation (OCFC) on...\n", "\t- Seacoast Bank of Florida (Nasdaq:SBCF) is a community bank in Florida, offering integrated financial services and digital bankin...\n", "\t- The text is a summary of the Interpublic Group's (IPG) financial results for the year ending December 31, 2020, including transa...\n", "\n", "------------------------------------------------------------\n", "Cluster #22, Size: 19\n", "--------------------\n", "Random 6 Sentences:\n", "\t- AEI Income Fund 25 LLC, a Delaware limited liability company, was organized on June 24, 2002, with Robert P. J. Johnson as Manag...\n", "\t- The Ridgewood Energy Corporation (\"Ridgewood Energy\" or the \"Fund\") is a Delaware Limited Liability Company (LLC) with interests...\n", "\t- The Ridgewood Energy Corporation (\"Ridgewood Energy\" or the \"Fund\") is a Delaware Limited Liability Company (LLC) formed in 2006...\n", "\t- The SEC filing for the Commonwealth Income and Growth Fund VI (CIGF6), a limited partnership formed in 2006, focuses on acquirin...\n", "\t- The Ridgewood Energy Corporation (\"Ridgewood Energy\" or the \"Fund\") is a Delaware Limited Liability Company (LLC) formed in 2006...\n", "\t- The Ridgewood Energy Corporation (\"Ridgewood Energy\" or the \"Fund\") is a Delaware Limited Liability Company (LLC) with interests...\n", "\n", "------------------------------------------------------------\n", "Cluster #23, Size: 18\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The company aims to create exceptional value for stockholders through strategic growth capital infusions, strategic leadership,...\n", "\t- New UpHealth is a Delaware corporation, formed in November 2020, seeking to merge with one or multiple businesses for the purpos...\n", "\t- The company aims to create a leading global technology investment platform with a strong focus on technology sector investments....\n", "\t- The SEC filing for the 2020 Annual Report on Form 8-K provides a detailed overview of Delaware Technology, Media & Telecommunica...\n", "\t- The report focuses on a Cayman Islands-based blank check company that is engaged in mergers, share exchange transactions, asset...\n", "\t- Eldridge Industries (Eldridge) is a Cayman Islands-registered company that intends to merge, share exchange or asset acquisition...\n", "\n", "------------------------------------------------------------\n", "Cluster #24, Size: 18\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Audax Credit BankDC Inc., a Delaware corporation, is an externally managed business development company (BDC) that invests prima...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 20-F for the year ended December 31, 2020, with a f...\n", "\t- The Blackstone Private Credit fund (the \"Company\") is a Delaware business development company (BDC) with no operating experience...\n", "\t- Business General is a privately managed, closed end, non-subsidiary management investment company, with an investment objective...\n", "\t- The Delaware corporation (the \"Company\") is a newly incorporated specialty finance company, focusing on lending to mid-market co...\n", "\t- BlackRock Capital Investment, LLC (BlackRock) is a Delaware Limited Liability Company (\"BDC\" or \"Registrant\") with $8.7 Trillion...\n", "\n", "------------------------------------------------------------\n", "Cluster #25, Size: 18\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Business Item 1.Business Principal Financial Group (PFG) is a leading global investment management company offering financial pr...\n", "\t- The SEC filing for First Western Financial (NASDAQ: MYFW) is a financial company that offers a comprehensive suite of services,...\n", "\t- Lazard Ltd., a leading global financial advisory firm, offers financial advisory services to corporate, partnership and institut...\n", "\t- AssetMark, a leading wealth management platform and technology solutions provider, has grown from $29 billion in 2015 through $7...\n", "\t- Moelis & Co., a leading global financial advisory firm, offers comprehensive, globally-integrated financial advisory services to...\n", "\t- The SEC's Form 10-K for the year ended December 31, 2020 provides a comprehensive overview of Ally Financial Inc, a leading digi...\n", "\n", "------------------------------------------------------------\n", "Cluster #26, Size: 17\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The filing is part of the Securities and Exchange Commission's (SEC) annual report on Form 8-K for the fiscal year ended January...\n", "\t- The text is a compilation of financial statements prepared by Interdyne Company, a California-based company that was incorporate...\n", "\t- The SEC filing for Yumba Records, LLC (the \"Company\"), a company that operates in India, focuses on providing records management...\n", "\t- Rambus Corporation (NASDAQ:RMBS), a leading provider of high-performance semiconductor chips and IP, reported its financial resu...\n", "\t- ALTAIR INTERNATIONAL CORPORATION (OTCQB:ATAO) is a Nevada-based nutraceutical company, which has been engaged in identifying new...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 20-F for the fiscal year ended October 31, 2020, wi...\n", "\n", "------------------------------------------------------------\n", "Cluster #27, Size: 15\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Loop Media (NASDAQ: LMT) is a Nevada-based company that offers music video services to businesses and consumers, primarily in th...\n", "\t- Kintara Therapeutics Inc., formerly DelMar Pharmaceuticals (formerly Adgero) has filed the Securities and Exchange Commission's...\n", "\t- Legacy Education Alliance (Legacy) is a Nevada corporation that was incorporated in 2010 under Streamline Resources Inc.'s name,...\n", "\t- Coeptis (OTCQB: CIK) is a biopharmaceutical company focused on developing and/or acquiring pharmaceutical products, technologies...\n", "\t- Quanta Inc. (NASDAQ:QNTA) is a leading applied science company that harnesses quantum biology to enhance active ingredients, wit...\n", "\t- Ecoark Holdings (the \"Company\" or \"Ecoark\") is a diversified company incorporated in Nevada on November 19 2007. The Company has...\n", "\n", "------------------------------------------------------------\n", "Cluster #28, Size: 15\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Securities and Exchange Commission (SEC) has issued a risk statement regarding the Company of Commerce (COVID-19) pandemic,...\n", "\t- These risks include: (i) global economic conditions; (ii) regulatory agencies with respect to product development, manufacturing...\n", "\t- The Securities and Exchange Commission (SEC) has issued a report on the Company's business in China, focusing on Covid-19 outbre...\n", "\t- The US Securities and Exchange Commission (SEC) has issued a risk factor report on the Company's financial condition, operations...\n", "\t- The Securities and Exchange Commission (SEC) has issued a risk statement regarding Diamondback Energy Corporation (Diamondback),...\n", "\t- The risk factors include the Coronavirus Disease (COVID-19) pandemic, which has reduced demand for petroleum and transportation...\n", "\n", "------------------------------------------------------------\n", "Cluster #29, Size: 15\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Air Transport Services (ATSG) is a leading supplier of aircraft leasing, air cargo transportation, and support services in the U...\n", "\t- R.R.Donnelley and Sons Company (RRD) is a leading multichannel business communications company, offering customized solutions to...\n", "\t- Atlas Technical Consultants Inc., headquartered in Austin, TX, is a leader in professional testing, inspections, engineering, en...\n", "\t- SMG Industries, Inc. (SMG) is a leading domestic logistics company with a focus on the domestic transportation market, focusing...\n", "\t- USA Truck (NASDAQ: USAK) is a North American truckload carrier with 2,065 tractor fleet and 6,263 trailer fleet. The company's t...\n", "\t- The SEC filing for the year ended December 31, 2020 provides a comprehensive overview of Fastenals Company, a Minnesota-based co...\n", "\n", "------------------------------------------------------------\n", "Cluster #30, Size: 15\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Vince Holding Corporation (VHC) is a global contemporary brand with three brands, including Vince, Rebecca T., and Parker, which...\n", "\t- The text is a compilation of Big Lots' financial statements for the fiscal year ending on January 31, 2020. The company operates...\n", "\t- Dillard's (the \"Company\"), a leading fashion apparel retailer in the US, operates 285 stores, an Internet store, and general con...\n", "\t- This Form 10-K is a condensed financial statement prepared by General American Eagle, Inc. (the \"Company\" or \"Aerie\") for the fi...\n", "\t- The company, founded in 1976, is a specialty retailer with 228 stores across the US and Canada, offering high-quality big & tall...\n", "\t- Albertsons Companies, a leading food and drug retailer in the US, operates 2,252 grocery stores across 34 States and District of...\n", "\n", "------------------------------------------------------------\n", "Cluster #31, Size: 14\n", "--------------------\n", "Random 6 Sentences:\n", "\t- First Equity Properties (FEPI) is a Nevada real estate investment company, which operates three motel properties and manages rel...\n", "\t- It also covers risks related to COVID-19 and other respiratory diseases, including potential disruptions in capital markets, rec...\n", "\t- The text is a compilation of documents filed with the Securities and Exchange Commission (SEC) for the year 2020, including CM F...\n", "\t- Lazuriton nano Biotechnology Co. Ltd., headquartered in Taiwan, has not generated revenues and an accumulated deficit since its...\n", "\t- Business General is a specialty finance firm that focuses on lending to mid-market companies through debt and equity investments...\n", "\t- Dongfang City Holdings Group Company Limited (the \"Company\" or \"DongFang\") is a Delaware-based company that has been in developm...\n", "\n", "------------------------------------------------------------\n", "Cluster #32, Size: 14\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Somerset Transition Corporation (OTCQB: TLVA) is a Nevada-based company that was incorporated in 2013 and has since merged with...\n", "\t- Altitude International Holdings (ALTD) is a Wisconsin-based company specializing in creating appropriately engineered, membrane...\n", "\t- Bravo Multinational Incorporated (BRVO) is a Delaware corporation engaged in the leasing and sale of gaming equipment for profes...\n", "\t- Uranium Energy Corporation (UEC) is a Nevada-based company engaged in uranium exploration and mining, primarily in the US. The c...\n", "\t- Ozop Energy (NASDAQ: OZOP) is a Nevada corporation specializing in high-power electronic solutions, including battery chargers,...\n", "\t- Phoenix Rising Companies, Inc., a Nevada-based company, is a publicly traded company with a history of business operations and s...\n", "\n", "------------------------------------------------------------\n", "Cluster #33, Size: 14\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 10K for the fiscal year ended December 31, 2020, wi...\n", "\t- Hersha Hospitality REIT (HT) is a Maryland real estate trust, organized in 1998, with a focus on high-quality luxury, upscale an...\n", "\t- The company is a global vacation ownership and exchange, rental, and property management company, with operations in two segment...\n", "\t- The text is a compilation of financial statements prepared in accordance with SEC rules and regulations, covering various aspect...\n", "\t- The InnSuiteS Hospitality Trust (Trust) is a real estate trust with a focus on recovery from COVID-19 and severe impact on trave...\n", "\t- The SEC filing for EPR Properties' (NYSE:EPR) annual report on Form 10-K for the fiscal year ending December 31, 2020 provides a...\n", "\n", "------------------------------------------------------------\n", "Cluster #34, Size: 13\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Securities and Exchange Commission (SEC) has filed a Form 8-K for the year 2020, listing Origin Materials, Inc. as a Cayman...\n", "\t- Ionix Technology (formerly Cambridge Projects Inc) is a Nevada corporation focused on the development, manufacturing and marketi...\n", "\t- EVMO, Inc. (\"EVMO\" or the \"Company\") is a Delaware corporation that operates primarily through two wholly owned subsidiaries: Ri...\n", "\t- Clancy Corp., a Nevada-based company, was incorporated on March 22, 2016, with a change in control resulting from a stock purcha...\n", "\t- HarborOne Bancorp (the \"Company\" or \"HarborOne\") is a financial services company headquartered in Brockton, Massachusetts. The C...\n", "\t- The Securities and Exchange Commission (SEC) has filed its annual report on Form 20-F for the fiscal year ended December 31, 201...\n", "\n", "------------------------------------------------------------\n", "Cluster #35, Size: 13\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Securities and Exchange Commission's (SEC) Form 10-K for the year ended December 31, 2020, includes risks related to crude o...\n", "\t- The Securities and Exchange Commission's (SEC) Annual Report on Form 10-K for the fiscal year ended December 31, 2020 contains r...\n", "\t- The SEC's \"Risk Factors\" section discusses risks and uncertainties associated with the COVID 19 pandemic, which has impacted oil...\n", "\t- The Securities and Exchange Commission (SEC) has issued a Form 10-K for the year 2020, covering risks related to the oil and gas...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 10-K for the year ended March 31, 2020, with a focu...\n", "\t- The SEC's \"Risk Factors\" section discusses risks associated with investing in General Business Development Corporation (BDCA), a...\n", "\n", "------------------------------------------------------------\n", "Cluster #36, Size: 13\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Business Item 1 of the Duke Energy Corporation's (Duke Energy) consolidated financial statements is a business statement tha...\n", "\t- Wisconsin Public Service Corp. (WEC Energy Group) is a Wisconsin-based utility company that provides electric energy services to...\n", "\t- The Securities and Exchange Commission (SEC) has filed a Form 8-k with the SEC for its annual report on Form 10-K for the year e...\n", "\t- The Business Item 1 of the Duke Energy Corporation's (Duke Energy) consolidated financial statements is a summary of its busines...\n", "\t- The Securities and Exchange Commission (SEC) has issued a Form 6-K for PPL Corporation (PPL), a Pennsylvania utility holding com...\n", "\t- Chesapeake Utilities Corporation (CUBE) is a Delaware company engaged in natural gas distribution, transmission, and related ser...\n", "\n", "------------------------------------------------------------\n", "Cluster #37, Size: 13\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Invesco DB Base Metal Fund, a Delaware statutory Trust, is a diversified fund that seeks to track various indices over time,...\n", "\t- The Invesco DB US DOLLAR Index Bullish fund (the \"fund\") is a Delaware statutory Trust, offering common units and beneficial int...\n", "\t- The Invesco DB Silver ETF (the \"INVESCO DB Silver Fund\") is a Delaware statutory Trust, organized in seven series, offering comm...\n", "\t- The Invesco DB Oil fund (the \"fund\") is a Delaware statutory Trust, organized in seven series, with an unlimited share of common...\n", "\t- The Invesco DB Gold ETF (the \"INVESCO DB Gold Fund\") is a Delaware statutory Trust, organized in seven series, offering common u...\n", "\t- The Invesco DB Agricultural Fund, a Delaware statutory Trust, is a diversified agriculture index fund that invests in futures tr...\n", "\n", "------------------------------------------------------------\n", "Cluster #38, Size: 13\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Aberdeen Standard Precious Metal Basket ETF Trust is a managed investment vehicle that aims to provide investors with a cost...\n", "\t- The Van Eck Merk GOLD Trust (Trust) is a New York State-registered investment trust, offering investors an opportunity to purcha...\n", "\t- The iShares Silver Trust, a Delaware Trust, is a silver-backed grantor trust that aims to provide investors with a cost-effectiv...\n", "\t- The Aberdeen Standard ETF Trust, formed in 2009, is a silver bullion trust that aims to provide investors with a cost-effective...\n", "\t- WGC USA's World Gold Trust, a Delaware statutory corporation, was formed in August 2014, with six separate Funds. The Trust oper...\n", "\t- The iShares Delaware Trust, a statutory trust, seeks to track results of a diversified, full collateralized investment on index...\n", "\n", "------------------------------------------------------------\n", "Cluster #39, Size: 12\n", "--------------------\n", "Random 6 Sentences:\n", "\t- LIV Capital is a Cayman Islands-based blank check company, formed in 2000 to facilitate a business combination between two or mo...\n", "\t- The SEC filing for a Delaware corporation's initial business combination is titled \"Initial Business Combination\" and focuses on...\n", "\t- The Cayman Islands-based Catcha Group, founded in 1999 by Patrick Grove (founder and CEO) and Luke Elliott (chairman), is a glob...\n", "\t- Investindustrial, a Cayman Islands-based investment firm, is seeking to merge with one or multiple businesses in order to create...\n", "\t- The SEC filing for Thoma Bravo's initial business combination, which was completed on January 20, 2021 and is expected to genera...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 20-F for the fiscal year ending February 29, 2020,...\n", "\n", "------------------------------------------------------------\n", "Cluster #40, Size: 12\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The business description of DCP Midstream LP, a Delaware limited partnership formed in 2005, focuses on the midstream energy sec...\n", "\t- The SEC filing for the year 2020 is a comprehensive overview of Sempra Energy (Sesa)'s businesses, focusing on energy infrastruc...\n", "\t- The company focuses on electric utility operations, natural gas storage, and transmission and distribution systems, with a focus...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 20-F for the fiscal year ending December 31, 2020 w...\n", "\t- NorthWestern Energy Corporation (NorthWestern) is a regulated utility serving 743,000 Montana and South Dakota customers. The co...\n", "\t- The Company Natural gas Services Group, a Colorado corporation, is a leading supplier of natural gas compressor equipment and se...\n", "\n", "------------------------------------------------------------\n", "Cluster #41, Size: 12\n", "--------------------\n", "Random 6 Sentences:\n", "\t- M/I Home, Inc. (the \"Company\" or \"M/I Homes\") is a leading builder of single family homes, offering high-quality construction an...\n", "\t- Taylor Morrison Home Corp., a leading public homebuilder in the US, is a land developer with a diverse range of homes for entry-...\n", "\t- Hovnanian Enterprise, Inc. (HEI) is a leading builder of residential homes in the Northeast and Mid-Atlantic regions of the Unit...\n", "\t- Tri Pointe Homes, headquartered in Phoenix, Arizona, is a leading national homebuilder focused on high-growth core markets with...\n", "\t- The Securities and Exchange Commission (SEC) has filed its annual report on Form 10-K for the fiscal year ended December 31, 202...\n", "\t- Dream Finders Home, Inc., a Delaware corporation, designs, builds and sells homes in high-growth markets across the United State...\n", "\n", "------------------------------------------------------------\n", "Cluster #42, Size: 12\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Ross Stores Inc., a leading off-price retailer with 1,546 stores in 39 states as of Feb. 1, 2020, operates two brands: Ross Dres...\n", "\t- The company's financial statements for the fiscal year ended February 1, 2020, are presented in a business note titled Business...\n", "\t- Business Item 1 of Business ReTech Corporation's SEC filing highlights the company's acquisition of three operating entities in...\n", "\t- The company's business strategy focuses on enhancing customer shopping experience, improving marketing and promotional efficienc...\n", "\t- This Form 10-K is a condensed financial statements prepared in accordance with SEC rules and regulations. The company's business...\n", "\t- Ulta Beauty, a leading beauty retailer with 1,254 stores in 50 states, is a specialty retail company offering cosmetics, fragran...\n", "\n", "------------------------------------------------------------\n", "Cluster #43, Size: 12\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The text is a compilation of financial statements prepared in accordance with US Securities and Exchange Commission (SEC) rules,...\n", "\t- Selective Insurance Group (Parent), a New Jersey-based holding company, is a leading provider of insurance products in the U.s.,...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report for the fiscal year ending December 31, 2020, listing a div...\n", "\t- The report also highlights the importance of managing well-defined product niches and focusing on individual performance. ... ci...\n", "\t- Safety Insurance Group (NASDAQ: SIR) is a leading private passenger automobile and commercial automobile insurer in Massachusett...\n", "\t- Protective Insurance Corporation, incorporated under the Indiana law in 1930, is a leading provider of property, liability, work...\n", "\n", "------------------------------------------------------------\n", "Cluster #44, Size: 11\n", "--------------------\n", "Random 6 Sentences:\n", "\t- ... cik: 1592057\n", "\t- The Securities and Exchange Commission (SEC) has issued a Form 10-K, \"Risk Factors\" for Silver Bull Exploration Company (Silver...\n", "\t- The SEC's \"Risk Factors\" report on Cheniere Energy Co.'s (Cheniere) financial condition, results of operations, cash flows and p...\n", "\t- The SEC's risk factors include the following: potential risks related to the Company's limited operating history; challenges in...\n", "\t- The report covers risks, uncertainties, and other factors that could affect the company's financial condition, results of operat...\n", "\t- The Securities and Exchange Commission (SEC) has filed its Annual Report on the Company, dated December 31, 2020, with a focus o...\n", "\n", "------------------------------------------------------------\n", "Cluster #45, Size: 11\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Securities and Exchange Commission (SEC) filed a Form 8-K on March 18, 2020, listing Goldman Sachs BDC as a closed-ended man...\n", "\t- GECM is an externally managed closed-end investment company (BDC) regulated as a Business Development Company under the Investme...\n", "\t- White Horse Finance, LLC, is a direct lender focused on debt investments in private, lower middle-market companies. The company'...\n", "\t- Great Elm Capital (GECC) is a Delaware corporation seeking to acquire businesses, securities, and assets with attractive long-te...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report for the fiscal year ended December 31st, 2019, with a focus...\n", "\t- The Securities and Exchange Commission (SEC) filed its Form 10-K for the year 2020 with the SEC on December 23, 2019. The compan...\n", "\n", "------------------------------------------------------------\n", "Cluster #46, Size: 11\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The SEC filing for a Cayman Islands-based blank check company, 1829797, focuses on the formation of a business to acquire and op...\n", "\t- TriState Capital, Inc., a Pittsburgh, Pennsylvania-based bank holding company, has three subsidiaries: Tristate Capital Bank (Ba...\n", "\t- Boxer Capital is a Delaware corporation, formed in May 2020 to effect a merger or capital stock exchange transaction with one or...\n", "\t- HF Enterprises, Inc., incorporated in the US on March 7, 2018, is a diversified company with operations in various countries, fo...\n", "\t- Founders Metalmark, a Delaware corporation incorporated in 2020, is seeking to merge with existing businesses through a share ex...\n", "\t- The company is a Delaware corporation formed as a blank check for effecting a merger or capital stock exchange transaction, asse...\n", "\n", "------------------------------------------------------------\n", "Cluster #47, Size: 11\n", "--------------------\n", "Random 6 Sentences:\n", "\t- These financial measures are presented in accordance with accounting principles that require us to make significant judgments, e...\n", "\t- This Form 10-K for the E.W-Scripps Company (NASDAQ:SSP) is a comprehensive financial report covering various aspects of the comp...\n", "\t- Westell Technologies (NASDAQ:WSTL), a leader in network infrastructure solutions, has filed its Form 10-K for the fiscal year en...\n", "\t- The Securities and Exchange Commission (SEC) has filed its annual report on Form 10K for fiscal year 2020, with a focus on EnerS...\n", "\t- The company has a corporate headquarters in New York, an office in North Carolina, a 130,000-square-foot research and developmen...\n", "\t- These statements are not guarantees of future performance or results, and involve risks and uncertainties that could cause actua...\n", "\n", "------------------------------------------------------------\n", "Cluster #48, Size: 11\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The SEC has identified SC as a servicer for the asset pools held by SC, and SC has completed compliance with applicable Servicin...\n", "\t- The SEC has identified SC as the servicers for certain residential mortgages backed securities trusts, and SC has completed comp...\n", "\t- The SEC has identified SC as a servicer for the asset pools held by SC, and SC has completed compliance with applicable Servicin...\n", "\t- The SEC has identified SC as the servicers with respect their asset pool held in the issuing entity, and SC has completed compli...\n", "\t- The report covers various aspects of SC's operations, including directors, executive officers, and corporate governance, as well...\n", "\t- The SEC has identified SC as the servicers with respect their asset pool held in the issuing entity, and SC has completed compli...\n", "\n", "------------------------------------------------------------\n", "Cluster #49, Size: 11\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The SEC filing for General Art'-Way Manufacturing Company, Inc.'s 2020 fiscal year is titled \"Business Item 1. Business Overview...\n", "\t- H&E, a Delaware-based company, is one of the nation's largest equipment services companies, providing parts and services for spe...\n", "\t- Business Overview.\" The Company, founded in 1883, has grown into a diversified manufacturer with a focus on engineered component...\n", "\t- Titan Machinery, Inc. (Titan) is a leading agricultural equipment manufacturer and supplier in the United State and Europe, with...\n", "\t- The SEC filing for Park-Ohio Holding Corp.'s annual report on Form 10-K for the fiscal year ending December 31, 2020 provides a...\n", "\t- Alta Equipment Group (Alta) is a leading provider of integrated equipment dealership solutions in the United States, offering pa...\n", "\n", "------------------------------------------------------------\n", "Cluster #50, Size: 11\n", "--------------------\n", "Random 6 Sentences:\n", "\t- South Jersey Industries (SJI) is a New Jersey company that owns and operates various energy-related businesses, including SJIU,...\n", "\t- The SEC filing for Business Item 1 of the 2020 Form 10-F is a comprehensive overview of NRG Energy, LLC., or \"NRG\" (the Company)...\n", "\t- The report focuses on Eversource's energy delivery business, which includes the Connecticut Light & Power Company (CCL&P) and NS...\n", "\t- This Form 10-K contains financial information for CenterPoint Energy (NYSE: C) and its subsidiaries, including Houston Electric,...\n", "\t- This Form 10-K (the \"Form 10-K\") is a business statement by three registrants, CenterPoint Resources Corp., Houston Electric, an...\n", "\t- This Form 10-K contains financial information for CenterPoint Energy (NYSE: C) and its subsidiaries, including Houston Electric,...\n", "\n", "------------------------------------------------------------\n", "Cluster #51, Size: 11\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Reliance Steel Corporation (RS) is a leading diversified metals solutions provider, serving customers for 80 years. The company'...\n", "\t- The company has nine operating segments, with seven reportingable segments in Electronics, Engraving, Scientific, Engineering Te...\n", "\t- TPT Global Technologies, Inc. (TPT Global) is a San Diego-based technology company that operates as a media content hub for dome...\n", "\t- Iron Mountain Incorporated (NYSE: IMT) is a leading provider of records and information services, offering comprehensive records...\n", "\t- ScanSource (NASDAQ: SCSC) is a leading technology solutions provider, offering hardware, software services and connectivity to i...\n", "\t- Flex, a global leader in technology innovation and supply chain solutions to various industries and end-markets, is a leading su...\n", "\n", "------------------------------------------------------------\n", "Cluster #52, Size: 10\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Mark Ein, founder and CEO of Capitol Investment Corp V, and Dyson Dryden, a partner in Capitol V, have established Capitol Inves...\n", "\t- Mill Rock Capital LLC, a Delaware corporation, is seeking to merge with an Advanced Materials or Specialty Chemicals industry. T...\n", "\t- The SEC filing of 1819438, a Cayman Islands-based blank check company seeking to merge, share exchange or asset acquisition, is...\n", "\t- Wall Street Media Company, Inc. is a Nevada-based consulting and management company providing consulting services to entities se...\n", "\t- The SEC filing for the year 2020 provides a comprehensive overview of the company's business strategy, including its advisory se...\n", "\t- Corvus Gold Inc. is a mineral exploration and development company engaged in acquiring, exploring, and developing mineral proper...\n", "\n", "------------------------------------------------------------\n", "Cluster #53, Size: 10\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The SEC filing for National Bankshares (NBI) is a comprehensive overview of the company's history and business, focusing on its...\n", "\t- MetaBank, a Delaware-based bank holding company (the \"Company\"), is a full-service financial institution offering banking soluti...\n", "\t- Customers Bancorp, a Pennsylvania bank holding company, is a diversified lending organization with diverse lending activities, i...\n", "\t- Prime Meridian Bank (\"PMHG\" or the \"Company\") is a Florida commercial banking company, offering a broad range in banking service...\n", "\t- United Bancshares (UBOH), an Ohio company, is a financial holding and operating subsidiary of Union Bank Company (Union Bank), w...\n", "\t- The Securities and Exchange Commission (SEC) has filed a Form 8-K for the year 2020, covering PCB Bancorp, a California corporat...\n", "\n", "------------------------------------------------------------\n", "Cluster #54, Size: 10\n", "--------------------\n", "Random 6 Sentences:\n", "\t- IF Bancorp (the \"Company\" or \"IF Bancorp\") is a financial holding company with consolidated assets of $735 million and $723 mill...\n", "\t- WVS Financial Corporation (the \"Company\" or \"WVS\") is a financial holding company with operations in Pittsburgh, Pennsylvania. T...\n", "\t- The Securities and Exchange Commission (SEC) filed its Form 10-K for the fiscal year ending December 31, 2020 with the SEC. WAB,...\n", "\t- The text is a summary of Home Bancorp Inc.'s financial statements for the fiscal year ended December 31, 2018 (the \"2018 Annual...\n", "\t- Marlin Business Services Corporation (MBB), a Pennsylvania-based financial holding company, is a leading provider of small-ticke...\n", "\t- First Financial Bancorp (First Financial) is an Ohio corporation, formed in 1982, with a focus on commercial banking and banking...\n", "\n", "------------------------------------------------------------\n", "Cluster #55, Size: 10\n", "--------------------\n", "Random 6 Sentences:\n", "\t- First Busey Corporation (First Busey), a Nevada corporation, is a financial holding company with a $10.5 Billion market capitali...\n", "\t- Heartland Bank & Trust Company, a Delaware corporation, is a bank-owned company with assets of $3.7B and loans held for $2.2B as...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 10-K for the year ended December 31, 2020, with a f...\n", "\t- The text is a compilation of financial statements from F & M Bancorp, Inc., a Virginia-based bank holding company, and its subsi...\n", "\t- FG Financial Group (FGF) is a reinsurance company focused on collateralized and lost capped reinsurance, with capital allocated...\n", "\t- The report, \"Business Item 1\", is a comprehensive overview of PennyMac's business, focusing on mortgage banking and investments....\n", "\n", "------------------------------------------------------------\n", "Cluster #56, Size: 10\n", "--------------------\n", "Random 6 Sentences:\n", "\t- GP Strategies Corporation (GPS) is a leading global workforce transformation partner, offering custom workforce performance serv...\n", "\t- The SEC filing for the year 2020 contains a business statement, which discusses Business assurant Inc.'s strategy to grow its po...\n", "\t- ASGN Incorporated, a leading provider of information technology and professional services, is a Fortune 1000-based company with...\n", "\t- Mastech Digital (the \"Company\" or \"Mastech\") is a leading provider of digital transformation IT services, offering data and anal...\n", "\t- Information Services Group (ISG) is a global technology research, consulting, and advisory firm that specializes in automation,...\n", "\t- The Securities and Exchange Commission (SEC) has filed its annual report on Form 20-F for the year 2020 with a focus on financia...\n", "\n", "------------------------------------------------------------\n", "Cluster #57, Size: 10\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Exelon Corporation (NYSE: EXC), a utility services company engaged in generating, delivery, marketing, and selling energy throug...\n", "\t- Exelon Corporation (NYSE: EXC), a utility services company engaged in generating, delivery, marketing, and selling energy throug...\n", "\t- Exelon Corporation (NYSE: EXC), a utility services company engaged in generating, delivery, marketing, and managing energy throu...\n", "\t- Exelon Corporation (NYSE: EXC), a utility services company engaged in generating, delivery, marketing, and selling energy throug...\n", "\t- Exelon Corporation (NYSE: EXC), a utility services company engaged in generating, delivery, marketing, and selling energy throug...\n", "\t- These comments were made pursuant to Rule 144A under the Securities Act of 1933, as amended. ... cik: 72903\n", "\n", "------------------------------------------------------------\n", "Cluster #58, Size: 10\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The company is a technology leader in conversational AI (AI) and ambient clinical Intelligence (CAIR), offering intuitive soluti...\n", "\t- The Boston Scientific Corporation (Boston Scientific) is a global medical technology leader with a focus on minimally invasive m...\n", "\t- Labcorp® (NASDAQ: LABC) is a leading life sciences company with over 72,400 professionals serving clients in 100 countries. The...\n", "\t- Tactile Systems Technologies, Inc. is a medical device company focused on improving patient outcomes and healthcare costs throug...\n", "\t- The business highlights the company's long-term strategy to transform it from the global radiation therapy leader to the global...\n", "\t- The company is a biopharmaceutical company focused on the discovery and development of novel therapeutics, innovative approaches...\n", "\n", "------------------------------------------------------------\n", "Cluster #59, Size: 10\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The company has diversified its revenue base through multiple media platforms, including print advertising, distribution service...\n", "\t- QuinStreet, a leading performance marketplace company, is a global leader in digital media and traffic engagement for high-value...\n", "\t- It also highlights the challenges faced by the company in addressing these challenges, such as evolving federal, state, and fore...\n", "\t- The company is a diversified media company that owns, operates, and provides services to 198 television stations in various mark...\n", "\t- J2 Global (J2) is a leading online information and services provider with a focus on the technology, retail, gaming, healthcare,...\n", "\t- Townsquare Media Inc., headquartered in San Francisco, is a digital media and digital marketing solutions company that owns and...\n", "\n", "------------------------------------------------------------\n", "Cluster #60, Size: 10\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 20-F for the fiscal year ending December 31, 2020,...\n", "\t- The company is known for its full-service approach to clinical development, which includes pre-clinical testing, regulatory revi...\n", "\t- Dare Bioscience is a clinical-phase biopharmaceutical company focused on advancing innovative products in the women health marke...\n", "\t- Business Item 1 of Business ITEM 1 is a business statement by General Bioanalytical System, Inc., which focuses on providing dru...\n", "\t- Agilent Technologies, Inc., headquartered in Delaware, is a leading global life sciences and diagnostics company with three busi...\n", "\t- Catalent is a global provider of innovative delivery technologies and manufacturing solutions, including softgel capsules for sm...\n", "\n", "------------------------------------------------------------\n", "Cluster #61, Size: 10\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Ingevity (NYSE:NGVT) is a global leader in the purification, protection, and enhancement of the world around it, offering produc...\n", "\t- UFP Technologies Inc., a Delaware-based designer and custom manufacturing company specializing in foams, film, and plastics for...\n", "\t- The SEC's Form 10-K for the fiscal year ended December 31, 2018 is filed under the Securities Exchange Act of 1934, with a focus...\n", "\t- Novanta, Inc., a global supplier of photonics, optics, vision, and precision motion products to medical and advanced original eq...\n", "\t- OrthoPediatrics Corporation (NASDAQ: KIDS) is a medical devices company that designs, develops, and markets anatomically appropr...\n", "\t- LivaNova plc (Nasdaq: LIVN), a global medical devices company, is engaged in cardiovascular and neuromodulation. The Company's p...\n", "\n", "------------------------------------------------------------\n", "Cluster #62, Size: 9\n", "--------------------\n", "Random 6 Sentences:\n", "\t- OFF Line International (NASDAQ: OFFL) is a Delaware corporation incorporated under the law of the United States on November 22,...\n", "\t- NexPoint Capital is an externally-managed, closed-ended management investment company with a focus on middle-market Healthcare C...\n", "\t- The registrant's annual report on Form 10K for the fiscal year ending December 31, 2020 (the \"2019 Annual Report\") was filed by...\n", "\t- The business overview of Gladstone Investment Company (the \"Adviser\") is a Delaware-based, externally managed, nondiversified in...\n", "\t- Wall Street Acquisitions Corporation (the \"company\"), a Delaware corporation, is an exploration stage company focused on develop...\n", "\t- General Farmers & Merchants Bancshares (the \"Company\") is a Maryland-based bank holding company with a diversified loan portfoli...\n", "\n", "------------------------------------------------------------\n", "Cluster #63, Size: 9\n", "--------------------\n", "Random 6 Sentences:\n", "\t- First Interstate Bank (FIBK), headquartered in Montana, is a financial and banking holding company that operates 150 banking off...\n", "\t- Robb Knie's blank check company is a Delaware corporation incorporated in 2021 for effecting a business combination, share excha...\n", "\t- The report focuses on the initial business combination between VGAC and its sponsor, Virgin Group, which resulted in $480,000,00...\n", "\t- The BorgWarner Company (BorgWarner) is a global leader in clean, efficient technology solutions to improve vehicle performance a...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 1638833 for the fiscal year ending December 31, 202...\n", "\t- The company, SVAC, is a Delaware corporation incorporated in 2019 for the purpose to effect a merger, stock exchange, or asset a...\n", "\n", "------------------------------------------------------------\n", "Cluster #64, Size: 9\n", "--------------------\n", "Random 6 Sentences:\n", "\t- It covers risk factors, properties, legal proceedings, mine safety disclosures, and substitute information provided in complianc...\n", "\t- The SEC's Form 10-K for the fiscal year ending December 31, 2020 is a report on Discover Bank, its subsidiaries, and affiliates....\n", "\t- The SEC's Form 10-K for the fiscal year ending December 31, 2020 is a report on Discover Bank, its subsidiaries, and affiliates....\n", "\t- The report covers World Omni Financial Corporation's (World Omni) automobile lease Securitization trust 2018-B, which was formed...\n", "\t- Risk factors include risks related to the company's operations, financial condition, and results of operations, as well as its r...\n", "\t- The report covers various topics, such as risk factors, business, not applicable, legal proceedings, properties, and mine safety...\n", "\n", "------------------------------------------------------------\n", "Cluster #65, Size: 9\n", "--------------------\n", "Random 6 Sentences:\n", "\t- These segments include lending, leasing, deposit products, and ancillary services, such as interest-rate risk management, foreig...\n", "\t- Randolph Bancorp (the \"Company\"), a Massachusetts corporation, is a financial services company that offers financial services th...\n", "\t- The First BanCorp Corporation (the \"Corporation\" or \"FirstBank\") is a publicly-owned financial holding company with assets of $1...\n", "\t- The report, \"Business Item 1\", focuses on First Financial Northwest (the \"Bank\"), a Seattle-based bank that was formed in 2007 a...\n", "\t- The SEC filing for the fiscal year ended September 30th, 2020, provides a summary of Washington Federal Bank's operations and fi...\n", "\t- Plumas Bancorp (the \"Company\" or \"Plumas\") is a California bank holding company that operates in the Northeastern and Northweste...\n", "\n", "------------------------------------------------------------\n", "Cluster #66, Size: 9\n", "--------------------\n", "Random 6 Sentences:\n", "\t- SGC Corporation (SGC) is a leading technology-based content provider for the gaming industry, with revenue generating activities...\n", "\t- The company is a publicly traded company focused on developing advanced technologies and energy solutions, medical devices, and...\n", "\t- Arch Therapeutics, a biotechnology company, is a Massachusetts corporation incorporated under Nevada law in 2009 with a focus on...\n", "\t- Ficaar Inc., incorporated in 2001, is a company that operates through its wholly-owned subsidiary, Standard Canna, INC., and its...\n", "\t- Thunder Mountain Gold (TMRI) is a Nevada corporation, with no mining operations. The company's primary goal is to further develo...\n", "\t- The report focuses on three main areas: 1) Business Overview; 2) Business Corporate Information; and 3) Business Combination/Rel...\n", "\n", "------------------------------------------------------------\n", "Cluster #67, Size: 9\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Jialijia, Inc., formerly Rizzen, was incorporated on October 21, 2015, and has since been inactive since its change in control....\n", "\t- Legacy Ventures International (Legacy) is a Nevada-based company that operates through RM Fresh Brands, Inc., with no current op...\n", "\t- America Great Health (formerly Crown Marketing) is a Wyoming company that has changed its corporate name to \"America Great Healt...\n", "\t- Odenza Corporation (OTCQB:ODZA) is a Nevada-based company that has limited business operations since January 31, 2020, with no r...\n", "\t- Synergy Empire Limited (the \"Company\"), a Nevada corporation, is engaged in the manufacture and sale of dessert products through...\n", "\t- The text is a compilation of audited financial statements for Bally, Corporation (BALLY), a Nevada-based small farming and house...\n", "\n", "------------------------------------------------------------\n", "Cluster #68, Size: 9\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Ferrellgas Partners (FPGR) is a publicly-traded Delaware limited partnership that operates primarily in the propane and equipmen...\n", "\t- Willis Lease Finance Corp., a Delaware corporation with a focus on acquiring and managing commercial aircraft and engine assets,...\n", "\t- Ferrellgas Partners (FPGR) is a publicly-traded Delaware limited partnership that operates primarily in the propane and equipmen...\n", "\t- Green Plains Partners, LP (GPP) is a master limited partnerships formed in 2015 with interests in ethanol storage and leasing ra...\n", "\t- Ferrellgas Partners (FPGR) is a publicly-traded Delaware limited partnership that operates primarily in the propane and equipmen...\n", "\t- The CrossAmerica Partners LP (CAPL) is a Delaware limited partner engaged in wholesale distribution and ownership of motor fuel,...\n", "\n", "------------------------------------------------------------\n", "Cluster #69, Size: 9\n", "--------------------\n", "Random 6 Sentences:\n", "\t- EPAM (EPAM) is a leading provider of software engineering, business consulting, and digital engagement services to customers in...\n", "\t- TTEC Holdings (NASDAQ: TTEC) is a leading provider of customer experience services (CXaaS) to Fortune 1000 companies and governm...\n", "\t- The company has 96,500 employees in various industries, with a strong focus on client engagement, diversity, equity, and inclusi...\n", "\t- Upland Software, a leading provider of software applications for digital transformation in various business functions, has grown...\n", "\t- GoDaddy, a leading provider and global leader in cloud-based software solutions, is committed to empowering everyday entrepreneu...\n", "\t- The Securities and Exchange Commission (SEC) has filed its annual report on Form 10-K for the year ended March 30, 2020, with a...\n", "\n", "------------------------------------------------------------\n", "Cluster #70, Size: 9\n", "--------------------\n", "Random 6 Sentences:\n", "\t- White Mountains is a Bermuda-based limited liability company engaged in the acquisition, management, and disposition of business...\n", "\t- ICC is a Pennsylvania-based specialty insurance carrier specializing in commercial multi-persil, liquor liabilities, workers' co...\n", "\t- Heritage Insurance Holdings (the \"Company\" or \"Heritage\") is a property and casualty insurer with a strong focus on personal and...\n", "\t- The company's business model, entrepreneurial approach, and employee incentive programs have contributed to strong underwriting...\n", "\t- Conifer Holdings (Nasdaq:CNFR), a Michigan-based insurance holding company, is a leading provider of specialty commercial and pe...\n", "\t- Hanover Insurance Group (THG), a Delaware corporation, is a leading property and casualty insurer in the U.s., offering competit...\n", "\n", "------------------------------------------------------------\n", "Cluster #71, Size: 9\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Boeing Company (NYSE: BA) is a leading global aerospace company, providing products and services to commercial airlines, defense...\n", "\t- The company, headquartered in Reston, Virginia, is a leading technical, engineering, and enterprise information (IT) provider wi...\n", "\t- Vectrus Inc., headquartered in Indianapolis, Indiana, is a global provider of facility and base operation, supply chain, logisti...\n", "\t- The Securities and Exchange Commission (SEC) has filed a Form 40533 for the fiscal year 2020 under Item 1. Business Overview. .....\n", "\t- Air Industries Group (AIM), a Nevada corporation and wholly-owned subsidiary of Air Industries, is engaged in the design, manufa...\n", "\t- The SEC filing for the fiscal year ended May 31, 2020 includes a business description, financial statements, and related notes....\n", "\n", "------------------------------------------------------------\n", "Cluster #72, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The company, a Maryland Real Estate Investment Trust (\"REIT\"), owns and operates self-storage businesses with a recognizable ora...\n", "\t- Arvana, Inc. (the \"Company\" or \"AVNI\") is a Nevada-based company specializing in Dim Sum Food Products, with a focus on securing...\n", "\t- The report covers various risks and uncertainties related to the acquisition of Lockheed Martin Corporation by Lockheed Martin (...\n", "\t- American Cannabis Company (OTCQB: AMMJ), a publicly traded company, offers consulting services to regulated cannabis businesses...\n", "\t- These statements are based on management's current expectations and assumptions about future events, such as the impact of CoVID...\n", "\t- The SEC filing for Marvell Semiconductor, Inc.'s (Marvell) acquisition of Marvell Corporation is a comprehensive report covering...\n", "\n", "------------------------------------------------------------\n", "Cluster #73, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Lithium Corporation (OTCQB: LTUM) is an exploration stage company engaged in developing and marketing call-back services using a...\n", "\t- Century Cobalt Corporation (CCOB) is a Nevada-based exploration stage company focused on acquiring, exploring, and developing co...\n", "\t- Marijuana Company, Inc. (MCOA) is a Utah-based company specializing in hemp and CBD products, with a focus on developing, manufa...\n", "\t- This Annual Report on the Form 10-K of NeoPhotonnics Corporation (NASDAQ: NEOOPN) is a compilation of financial statements and r...\n", "\t- The Securities and Exchange Commission (SEC) has issued a \"Risk Factors Item 1A\" report covering the company's business, financi...\n", "\t- Wolverine Technologies Corporation (Wolverine) is a Nevada corporation engaged in the exploration, development, and acquisition...\n", "\n", "------------------------------------------------------------\n", "Cluster #74, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Fearless Films (USA) is a Nevada-based company that specializes in short film, feature film, and television production services....\n", "\t- The company's business is focused on land development, with a focus on Alset Ehome Inc.'s Black Oak sub-division and Ballenger R...\n", "\t- Porter Holding International (PGL) is a company incorporated in Nevada in 2013, with a business plan to sell freshly-squeeze jui...\n", "\t- The company, founded in 2012, focuses on the development of personalized cannabinoids-based therapies and treatments for cancer....\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 20-F for the fiscal year ending December 31, 2020 w...\n", "\t- These financial statements reflect management's assessment of the company's financial condition and results of operations, as we...\n", "\n", "------------------------------------------------------------\n", "Cluster #75, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Winmark Corporation (Winmark) has experienced the impact of the corona virus (COVID-19), which has spread to many countries, inc...\n", "\t- The report also covers risks associated with the COVID-19) pandemic, which has had a material adverse impact on Baxter's busines...\n", "\t- The report focuses on diseases impacting the back of eye, such as diabetic macular edema (\"DME\"), non-proliferative diabetic ret...\n", "\t- NeoGenomics (NASDAQ: NEO), a Nevada corporation, has filed its Annual Report on Form 10-K for the fiscal year ended December 31,...\n", "\t- These risks include: * COVID-19 strains have had a significant impact on Extreme's businesses; * extended closures in China may...\n", "\t- Telidyne, a technology company offering digital payments to consumers and merchants through its proprietary TELI mobile payment...\n", "\n", "------------------------------------------------------------\n", "Cluster #76, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Crawford United Corporation (Crawford) is a diversified industrial products company, offering specialty industrial products in h...\n", "\t- The Item 1A of the Securities Exchange Act of 1934 (the \"SEC\") is a business statement by General Electric Tool Group Corporatio...\n", "\t- The Company is a global materials company with leading market positions, manufacturing operations, and diversified end-markets....\n", "\t- The company, founded in 2001, is a Cayman Islands-based blank check company with a focus on energy and natural resource investme...\n", "\t- The Belden Company (Belden) is a global leader in specialty networking solutions, offering data, sound and video to mission-crit...\n", "\t- This SEC filing is a comprehensive overview of Acacia Research Corporation's business, focusing on acquiring businesses and oper...\n", "\n", "------------------------------------------------------------\n", "Cluster #77, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Edge Data Solutions (EDSI), a Delaware corporation, is a leading provider of next-generation data center solutions for high-perf...\n", "\t- LegacyXchange, a Nevada-based e-commerce company, has ceased operations and is seeking business opportunities. Its articles auth...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 20-F for the fiscal year ended November 30, 2020, w...\n", "\t- Repay Holdings, LLC is a payments technology company that offers integrated payment solutions to various vertical markets. The c...\n", "\t- UBN, a Nevada-based company, is a leading provider of plant-based products for the brain, with five unique formulations and pate...\n", "\t- MCX Technologies Corporation (\"MCX\" or \"we\") is a customer-centric digital transformation company, focused on providing digital...\n", "\n", "------------------------------------------------------------\n", "Cluster #78, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Desert Hawk Gold Corporation, a Nevada corporation, is engaged in the mining and processing of gold and precious metals from its...\n", "\t- Palayan Resources (Nevada) is a Nevada-based start-up exploration stage company, with no subsidiaries. The company acquired SMG...\n", "\t- Magellan Gold Mining Corporation (Magellan) is a Nevada-based exploration stage company focused on acquiring, exploring, and eva...\n", "\t- DynaResource Inc., a minerals investment and management company, is a Mexican company with a focus on precious metals in Sinaloa...\n", "\t- Norman Cay Development Inc. (the \"Company\") is a Nevada-based company that operates as an authorized retailer and service plan r...\n", "\t- Athena Gold Corporation is engaged in acquiring and exploring mineral resources, primarily through its mining operations in Cali...\n", "\n", "------------------------------------------------------------\n", "Cluster #79, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Tellurian is developing a low-carbon, global business that aims to deliver natural gas to consumers worldwide through its Driftw...\n", "\t- Suburban Propane Partners (L.P.) is a Delaware limited partner with operations in 41 states, primarily concentrated in the easte...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 10-K for the fiscal year ended December 31, 2020, w...\n", "\t- Sunoco LP (NYSE: SUN) is a master limited partnership with operations in 30 states, primarily engaged in motor fuels distributio...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 10-K for the fiscal year ending December 31, 2020 w...\n", "\t- The Delaware limited partnership (Delaware) is a midstream energy company that transports, store, markets, and provides transpor...\n", "\n", "------------------------------------------------------------\n", "Cluster #80, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The text is a compilation of financial statements from Waterfall Real Estate Finance Company (Fres.), a real estate finance firm...\n", "\t- The company, Terra Property Trust II, is a real estate investment trust (REIT) focused on originating, structuring, and managing...\n", "\t- The Bancorp Bank (the \"Bank\") is a Delaware financial institution that offers specialty lending, securities-backed line of credi...\n", "\t- Colony Capital, LLC (Colony Capital) is a Maryland corporation and its subsidiaries, focused on CRE debt investments, net leased...\n", "\t- Great Ajax Corporation, a Maryland corporation, is organized and operates in a manner to qualify as Real Estate Investment Trust...\n", "\t- Dynex Capital Inc., an internally managed real estate investment company, invests in residential mortgage-backed (MBS) and comme...\n", "\n", "------------------------------------------------------------\n", "Cluster #81, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 1685040 for the fiscal year ending December 31, 202...\n", "\t- The Securities and Exchange Commission (SEC) has filed a Form 8-K for the year 2020 with respect to its business, including CNA...\n", "\t- Kinsale, Inc. is a Delaware-based property and casualty company specializing in excess and surplus line (E&S) insurance products...\n", "\t- It operates two segments: VITAS segment, which provides hospice services to its patient population through physicians, registere...\n", "\t- American National Group (NYSE: ANAT) is a leading financial services company with operations in five business segments: life, an...\n", "\t- CNO Financial, Inc. (CNO), a Delaware corporation, develops, market, and administers health insurance, annuities, personal life...\n", "\n", "------------------------------------------------------------\n", "Cluster #82, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Vidler Water, Inc., incorporated in 1981 and headquartered in Carson City, NV, is a water resource company focused on sustainabl...\n", "\t- The Business Item 1 of Pioneer Natural Resources Company (NYSE:PXD) is a large, independent oil and natural gas exploration comp...\n", "\t- Unit Corporation (NYSE: UNIT) is an oil and gas contract driller with operations in exploration and production, mid-stream, and...\n", "\t- Deep Down Inc., headquartered in Nevada, is a leading provider of oilfield products and solutions for the global energy and offs...\n", "\t- Oil States International (NASDAQ:OILS), headquartered in Houston and operating through three segments, is a leading global suppl...\n", "\t- Chesapeake Energy Corporation (NYSE: CHK) is an independent oil and gas company engaged in acquiring, exploration, and developme...\n", "\n", "------------------------------------------------------------\n", "Cluster #83, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Comstock Mining Company (the \"Company\" or \"Comstock\") is a leading climate-smart resource development and production company...\n", "\t- Liberty Star Uranium and Metals Corp. is a Nevada-based company engaged in mineral properties acquisition, exploration, developm...\n", "\t- The text is a compilation of the SEC filings for USA Rare Earth Resources (USARE), a company engaged in acquiring, exploring, an...\n", "\t- Star Gold Corporation (the \"Company\" or \"Star Gold\") is a Nevada-based company engaged in acquiring and exploring precious metal...\n", "\t- CONSOL Energy Corporation (NYSE: CONSOL) is a leading producer of high quality bituminous coal in the Eastern United States, foc...\n", "\t- NACCO is a diversified mining and natural resource company with three business segments, Coal Mining, NAMining, and Minerals Man...\n", "\n", "------------------------------------------------------------\n", "Cluster #84, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Securities and Exchange Commission (SEC) has filed a Form 8-K for the fiscal year ended February 29, 2020, containing inform...\n", "\t- These segments include closures, dispensing system applicators, polythene films, bottles and canisters, foodservice, containers,...\n", "\t- Prestige Consumer Healthcare, Inc., a Delaware corporation, is engaged in developing, manufacturing, selling, and distributing O...\n", "\t- The company is a Utah corporation engaged in the manufacture and direct sale of nutritional products, primarily through its four...\n", "\t- This report is a summary of General Mills' financial results for the fiscal year ending May 31, 2020, covering five operating se...\n", "\t- United Natural Foods (UNFI) is a leading distributor and retailer services company with approximately 275,000 products in North...\n", "\n", "------------------------------------------------------------\n", "Cluster #85, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Managed Futures Premier (formerly Warrington Fund) is a partnership that trades commodity interests, primarily futures and o...\n", "\t- The Ceres Orion Limited Partnership (Partnership) is a partnership that engages in speculative trading of commodity interests th...\n", "\t- Altegris Winston Futures Fund (L.P.) is a speculative investment company, offering three classes of interest: class A, class B,...\n", "\t- AltegrisQIM Futures Fund (the \"Company\"), a Delaware limited partner, operates as a speculative commodity pool with three classe...\n", "\t- Ceres Tactical Commodity LP., formerly managed futures Premier Aventis I L.P (the \"Company\"), is a limited company that engages...\n", "\t- Ceres Tactical Systematic LP., a Delaware-based limited partnership, is engaged in speculative trading of commodity interests th...\n", "\n", "------------------------------------------------------------\n", "Cluster #86, Size: 8\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The SEC filing for the year 2020 is a business item focusing on the Federal Home Loans Bank of San Fransisco (FHLbank), which se...\n", "\t- The SEC filing contains a business overview of the Federal Home Loans Bank of Dallas, which is a federally chartered corporation...\n", "\t- The Federal Home Loans Bank of Chicago is a federally chartered organization and one of eleven FHLBs that, with its Office of Fi...\n", "\t- The SEC filing for the year 2020 contains a business statement by the Federal Home Loans Bank of Boston (FHLBank), which is a fe...\n", "\t- The FHLB (Federal Home Loan Bank) is a wholesale bank serving the public interest in Kentucky, Ohio, Tennessee, and the Fifth Di...\n", "\t- The Federal Home Loans Bank of New Zealand (FHLBNY) is a federally-chartered corporation exempt from local real property tax. Th...\n", "\n", "------------------------------------------------------------\n", "Cluster #87, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The SEC filing for the year 2020 is a business statement by Owl Rock Technology Financial Corp., a Maryland corporation (the \"Co...\n", "\t- The SEC filing for a Delaware Corporation (Delaware corporation) is titled \"Business Item 1. Business\" and focuses on acquiring...\n", "\t- MIC, a Delaware corporation, is a diversified energy company with operations in the United Kingdom and Hawaii. The company's pri...\n", "\t- The company is a \"blank check\" company, incorporated in November 2020, with a business purpose to effect a mergers, capital stoc...\n", "\t- First Midwest Bancorp (the Company), a Delaware corporation, is an Illinois-based bank offering financial products and service t...\n", "\t- Poema Global (the \"Company\"), a Cayman Islands-based company, is seeking investment opportunities in the technology industry. Th...\n", "\n", "------------------------------------------------------------\n", "Cluster #88, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- China Herb Group Holdings Corp. (the \"Company\" or \"China Herb\") is a Nevada-based company that has no business operations, but i...\n", "\t- Verde Bio Holdings (formerly Appiophany Technologies) is a Nevada-based oil and gas company focused on acquiring non-operating w...\n", "\t- Madison Avenue Holdings (MAHI) is a Delaware corporation that has been engaged in various lawful corporate undertakings, includi...\n", "\t- The company aims to capitalize on its founders' combined operating, investment, and financing experience in the TMT industry, in...\n", "\t- The Securities and Exchange Commission (SEC) filed its Form 8-K for the fiscal year ended December 31, 2020, with a focus on Pow...\n", "\t- Photozou Holdings is a Delaware corporation, incorporated in 2014, with the purpose to engage in lawful acts or activities for w...\n", "\n", "------------------------------------------------------------\n", "Cluster #89, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The company's primary objective is to enhance liquidity and long-term earnings through a combination between a business and an u...\n", "\t- The Cayman Islands-based blank check company, LOACU, aims to capitalize on its expertise in the management of businesses and the...\n", "\t- Corner Ventures is a Cayman Islands-based blank check company formed in October 2020 for effecting a merger or share exchange tr...\n", "\t- The Cayman Islands-based blank check company, QVTVM, is a Cayman Islands limited liability company with a focus on industrial an...\n", "\t- The Cayman Islands-based blank check company, GPAC, is seeking and completing a business combination with an enterprise value be...\n", "\t- Noble Rock Advisors is a Cayman Islands-registered blank check company, formed in November 2020, aiming to acquire and operate b...\n", "\n", "------------------------------------------------------------\n", "Cluster #90, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Securities and Exchange Commission (SEC) filed its Form 10-K for the fiscal year ending December 31, 2020, with a descriptio...\n", "\t- The SEC's Form 10-K for the fiscal year ending December 31, 2020 contains risk factors related to the Company's business, includ...\n", "\t- The Securities and Exchange Commission's (SEC) annual report on Form 10-Q for the fiscal year ended December 31, 2020 is a compr...\n", "\t- The SEC's \"Risk Factors\" section discusses the risks and uncertainties of investing in Cooper Group, Inc., a leading provider of...\n", "\t- The report discusses risks associated with investing in Class A Common Stock, such as potential defects, interruptions/delays, p...\n", "\t- The Securities and Exchange Commission (SEC) has issued a risk factor report on \"Risk Factors\" in its annual report on Form 10K...\n", "\n", "------------------------------------------------------------\n", "Cluster #91, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The Company, ATEL 17, is a Nevada limited-liability company with a focus on equipment financing and acquisition. The Company aim...\n", "\t- The text is a business statement of CNLStrategic Capital, LLC (\"CNL Strategic Capital\" or \"the Company\") that focuses on acquiri...\n", "\t- TriLinc, a Delaware limited-liability company, is a global impact investment firm focused on providing financing to small and me...\n", "\t- The Business Organization Boston Capital Limited Partnership (the \"fund\") is a Delaware limited partnership that invests in othe...\n", "\t- ASIF GP LLC, a Delaware limited company, is engaged in the ownership and/or investment of leased equipment and asset financings....\n", "\t- The text is a compilation of information provided by Equus, Inc., a Delaware corporation formed in 1991 to invest in debt and eq...\n", "\n", "------------------------------------------------------------\n", "Cluster #92, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Digital Media Solutions (DMS) Inc., a leading digital performance marketing platform, is a Cayman Islands-based company that spe...\n", "\t- The SEC filing for Legg Mason Inc.'s 2020 annual report on Form 20-F is a summary of the company's operations, financial conditi...\n", "\t- Hemp Technology, Incorporated (the \"Company\" or \"Hemp Technology\") is a vertically-integrated, publicly traded company with oper...\n", "\t- The Globe.com, Inc., a company incorporated in 1995 and headquartered in Boston, Massachusetts, is a shell company that has no m...\n", "\t- PQ Group Holdings, Inc., headquartered in Delaware, is a global provider of catalysts, chemicals, and services that help compani...\n", "\t- The company operates approximately 1,330 convenience stores across 33 states, with over 70 regional store brands and foodservice...\n", "\n", "------------------------------------------------------------\n", "Cluster #93, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- China Media, Inc., headquartered in Las Vegas, Nevada, is a Nevada corporation that produces feature-length films, television se...\n", "\t- Enertopia Corporation (OTCQB: EERTP) is a Nevada-based company focused on natural resource sector business opportunities, utiliz...\n", "\t- Chengda Technology Company. Ltd., formerly New Leap, is a Delaware corporation with limited financial resources and no equity or...\n", "\t- Arion Group Corporation (the Company) is a Nevada-based start-up manufacturing and distribution company exploring various busine...\n", "\t- Electromedical Technologies, LLC (OTCQB: EMED) is a bio-electronics manufacturing company that offers U.S Food and Drug Adminisa...\n", "\t- Cardax Pharmaceuticals (NASDAQ: CGX), a biopharmaceutical firm, is a Delaware corporation engaged in the research, development,...\n", "\n", "------------------------------------------------------------\n", "Cluster #94, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The report covers risks related to the Company including its financial condition, future operations, potential conflicts of inte...\n", "\t- Vanadium is a Nevada-based company focused on the exploration and development of vanadium exploration opportunities, focusing on...\n", "\t- Boxxy Inc, a Nevada-based online beauty sample service provider, has filed its annual report on Form 20-F for the fiscal year en...\n", "\t- Minaro Corporation, a Nevada-based start-up company specializing in 3D design services for commercial spaces, has filed its annu...\n", "\t- Bigeon Corporation (OTCQB: BIGE) is developing a messenger application that enables users to draw pictures or writing instead of...\n", "\t- The SEC filing for Black Rock Petroleum Co., a Nevada-based start-up company, is dated April 30, 2020, with the accompanying not...\n", "\n", "------------------------------------------------------------\n", "Cluster #95, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Target Group, Inc. (Target Group) is a Delaware-based company specializing in the development, operation, and maintenance of a c...\n", "\t- NetPay International Inc., a Nevada-based company specializing in the development, manufacture, marketing, and sale of natural o...\n", "\t- The SEC filing for ZHRH Corp., a Nevada-based company, highlights the history of the company and its current status as a shell c...\n", "\t- Summit Networks, Inc. (the \"Company\") is a Nevada-based company engaged in the production and distribution of glass products in...\n", "\t- Han Logistics, Inc., a Nevada-based company specializing in diamond jewelry, is a holding company with operations in Hong Kong,...\n", "\t- The company, Eco Science Solutions Inc. (ESSI), is a vertically integrated consumer and enterprise software provider offering fi...\n", "\n", "------------------------------------------------------------\n", "Cluster #96, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- PetVivo Holdings is a Minnesota-based biomedical device company, focusing on the licensing of innovative medical products and th...\n", "\t- Gateway Certifications (OTCQB: GMAC) is a Nevada corporation that designs, marketing, and distributing alcohol base clean fuels...\n", "\t- The Securities and Exchange Commission (SEC) filed its annual report on Form 20-F for the year ending December 31, 2020, with a...\n", "\t- China Advanced Technology, Inc. (Goliath) is a Nevada-based company that develops, produces, and licenses for digital content in...\n", "\t- The business description of PHI Group Inc., incorporated in 1982 and headquartered in Wyoming, focuses on corporate finance serv...\n", "\t- The SEC filing is a comprehensive overview of the company's business, focusing on e-Commerce, petroleum products distribution, a...\n", "\n", "------------------------------------------------------------\n", "Cluster #97, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The company, Contango Mining Co., formed in 2010, has a primary focus on the exploration of mineral properties in Alaska for gol...\n", "\t- Atlantica, Incorporated (Atlantica) is a Utah-based shell company seeking to acquire assets, property, or businesses through reo...\n", "\t- Premier Products Group (PMPG), a Utah-based energy, mining, and natural resources company, is a publicly traded company with a f...\n", "\t- The company is a mineral exploration stage company with no established reserves, and has sustained losses for two years. The com...\n", "\t- Patriot Gold Corporation is a Nevada-based company engaged in the exploration, development, and acquisition of natural resource...\n", "\t- Energy Fuels (TSX: EFR) is a Canadian company engaged in conventional uranium extraction and processing, with operations in Wyom...\n", "\n", "------------------------------------------------------------\n", "Cluster #98, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Kona Gold Beverage Inc., headquartered in Delaware, is a lifestyle company specializing in developing hemp-infused products in f...\n", "\t- Nexien Biopharma, Inc. (OTCQB: CIK) is a Delaware corporation focused on developing and commercializing novel FDA-approved canna...\n", "\t- The company is a diversified life science company, focusing on the financing and development of products and services for human...\n", "\t- Nunzia Pharmaceuticals Company (OTCQB:NUNZ) is a Utah-based nutraceutical company that manufactures, markets, and distributes Nu...\n", "\t- Kannalife Sciences Inc., incorporated in the state of Delaware in 2013, is a developmental-stage phyto-medical and pharmaceutica...\n", "\t- Heska Corporation (Nasdaq: HES) is a leading provider of veterinary and animal healthcare diagnostic products, offering Point of...\n", "\n", "------------------------------------------------------------\n", "Cluster #99, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- The business statement of Mewbourne Energy Partnership 10-A, LP. is a Delaware limited partnership that engages in oil and gas a...\n", "\t- The SEC filing for the year 2020 is a business item, focusing on Lime & Limestone Operations, which provides lime and limestone...\n", "\t- The Reserve Petroleum Co., a Delaware corporation, is engaged in managing its own mineral properties and exploration for and dev...\n", "\t- Whiting Petroleum Corporation (Whiting) is a Delaware Limited Partnership formed in 2013 to acquire producing oil and gas assets...\n", "\t- Dakota Territory (the \"Company\" or \"Dakota\") is a Nevada-based mining company engaged in the acquisition and exploration busines...\n", "\t- The business of Mewbourne Energy Partnership (the \"Partnership\") was organized under Delaware law on February 26, 2009, with lim...\n", "\n", "------------------------------------------------------------\n", "Cluster #100, Size: 7\n", "--------------------\n", "Random 6 Sentences:\n", "\t- Stem Holdings (NASDAQ:STEM), a Nevada corporation, is a vertically integrated cannabis company that owns 22 state-issued cannabi...\n", "\t- Flexible Solutions, Inc. is a Nevada corporation incorporated on January 26, 1991 with a focus on water-soluble chemical (TPA) p...\n", "\t- EnerTeck Corp., formerly known as Gold Bond Mining Co. and Gold Bond Resources Inc., is a company specializing in sales and mark...\n", "\t- NexTier is a land-focused oilfield service company that provides integrated solutions to E&P customers through its operating sub...\n", "\t- Indoor Harvest Corp., a Texas corporation, is a technology and planning company focused on vertical farming, building integrated...\n", "\t- Good Hemp (OTCQB: GOODH) is a company focused on developing and marketing hemp-derived beverages, including Good Hemp® 2oh!. Goo...\n", "\n", "------------------------------------------------------------\n", "Printing limited to the first 100 clusters.\n" ] } ] }, { "cell_type": "code", "source": [], "metadata": { "id": "MTmj30pNPag6" }, "execution_count": null, "outputs": [] } ] }