Merge pull request #1 from pietrolesci/new_app

.streamlit/config.toml

@@ -1,4 +1,7 @@
 [server]
 # Max size, in megabytes, for files uploaded with the file_uploader.
 # Default: 200
-maxUploadSize = 10
+maxUploadSize = 20
+
+[browser]
+gatherUsageStats = false

LICENSE

@@ -1 +1,201 @@
-TODO: placeholder
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2018-2020 Grid AI
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

app.py

@@ -1,70 +0,0 @@
-import streamlit as st
-from src.utils import get_logo
-from src import session_state
-from src.pages import (
-    home,
-    faq,
-    about,
-)
-from src.configs import SupportedFiles
-
-# app configs
-st.set_page_config(
-    page_title="Wordify",
-    layout="wide",
-    page_icon="./assets/logo.png",
-)
-
-# session state
-session = session_state.get(
-    process=False, run_id=0, posdf=None, negdf=None, uploaded_file_id=0
-)
-
-
-# ==== SIDEBAR ==== #
-# LOGO
-client_logo = get_logo("./assets/logo.png")
-with st.sidebar.beta_container():
-    st.image(client_logo)
-
-# NAVIGATION
-PAGES = {
-    "Home": home,
-    "FAQ": faq,
-    "About": about,
-}
-
-st.sidebar.header("Navigation")
-# with st.sidebar.beta_container():
-selection = st.sidebar.radio("Go to", list(PAGES.keys()))
-page = PAGES[selection]
-
-# FILE UPLOADER
-st.sidebar.markdown("")
-st.sidebar.markdown("")
-st.sidebar.header("Upload file")
-# with st.sidebar.beta_container():
-uploaded_file = st.sidebar.file_uploader(
-    "Select file", type=[i.name for i in SupportedFiles]
-)
-
-
-# FOOTER
-# with st.sidebar.beta_container():
-st.sidebar.markdown("")
-st.sidebar.markdown("")
-st.sidebar.markdown(
-    """
-    <span style="font-size: 0.75em">Built with &hearts; by [`Pietro Lesci`](https://pietrolesci.github.io/) and [`MilaNLP`](https://twitter.com/MilaNLProc?ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5Eauthor)</span>
-    """,
-    unsafe_allow_html=True,
-)
-st.sidebar.info("Something not working? Consider [filing an issue](https://github.com/MilaNLProc/wordify-webapp-streamlit/issues/new)")
-
-
-# ==== MAIN ==== #
-with st.beta_container():
-    st.title("Wordify")
-
-
-page.write(session, uploaded_file)

main.py

@@ -0,0 +1,56 @@
+import streamlit as st
+
+from src.components import faq, footer, form, presentation
+from src.utils import convert_df, get_logo, read_file
+
+# app configs
+st.set_page_config(
+    page_title="Wordify",
+    initial_sidebar_state="expanded",
+    layout="centered",
+    page_icon="./assets/logo.png",
+    menu_items={
+        "Get Help": "https://github.com/MilaNLProc/wordify-webapp-streamlit/issues/new",
+        "Report a Bug": "https://github.com/MilaNLProc/wordify-webapp-streamlit/issues/new",
+        "About": "By the __Wordify__ team.",
+    },
+)
+
+# logo
+st.sidebar.image(get_logo("./assets/logo.png"))
+
+# title
+st.title("Wordify")
+
+# file uploader
+uploaded_fl = st.sidebar.file_uploader(
+    label="Choose a file",
+    type=["csv", "parquet", "tsv", "xlsx"],
+    accept_multiple_files=False,
+    help="""
+        Supported formats:
+        - CSV
+        - TSV 
+        - PARQUET
+        - XLSX (do not support [Strict Open XML Spreadsheet format](https://stackoverflow.com/questions/62800822/openpyxl-cannot-read-strict-open-xml-spreadsheet-format-userwarning-file-conta))
+    """,
+)
+
+if not uploaded_fl:
+    presentation()
+    faq()
+else:
+    df = read_file(uploaded_fl)
+    new_df = form(df)
+    if new_df is not None:
+        payload = convert_df(new_df)
+        st.download_button(
+            label="Download data as CSV",
+            data=payload,
+            file_name="wordify_results.csv",
+            mime="text/csv",
+        )
+
+
+# footer
+footer()

notebooks/wordifier_nb.ipynb

@@ -1,67 +1,589 @@
 {
- "metadata": {
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.3"
-  },
-  "orig_nbformat": 2,
-  "kernelspec": {
-   "name": "python383jvsc74a57bd01cb9a1c850fd1d16c5b98054247a74b7b7a12849bcfa00436ba202c2a9e2bbb2",
-   "display_name": "Python 3.8.3 64-bit ('py38': conda)"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2,
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 65,
    "metadata": {},
    "outputs": [],
    "source": [
     "import sys\n",
-    "nb_dir = os.path.split(os.getcwd())[0]\n",
-    "if nb_dir not in sys.path:\n",
-    "    sys.path.append(nb_dir)\n",
+    "sys.path.insert(0, \"..\")\n",
+    "import vaex\n",
+    "from vaex.ml import LabelEncoder\n",
+    "import spacy\n",
+    "import pandas as pd\n",
+    "from tqdm import tqdm\n",
+    "import os\n",
+    "import multiprocessing as mp\n",
+    "from src.preprocessing import PreprocessingPipeline, encode\n",
+    "from src.wordifier import ModelConfigs\n",
+    "from sklearn.pipeline import Pipeline\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pipe = PreprocessingPipeline(\n",
+    "    language=\"English\",\n",
+    "    pre_steps=list(PreprocessingPipeline.pipeline_components().keys()),\n",
+    "    lemmatization_step=list(PreprocessingPipeline.lemmatization_component().keys())[1],\n",
+    "    post_steps=list(PreprocessingPipeline.pipeline_components().keys()),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def fn(t):\n",
+    "    return pipe.post(pipe.lemma(pipe.nlp(pipe.pre(t))))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vdf = vaex.from_pandas(df)\n",
+    "vdf[\"processed_text\"] = vdf.apply(fn, arguments=[vdf[\"text\"]], vectorize=False)\n",
+    "df = vdf.to_pandas_df()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2021-11-28 17:01:36.883 \n",
+      "  \u001b[33m\u001b[1mWarning:\u001b[0m to view this Streamlit app on a browser, run it with the following\n",
+      "  command:\n",
+      "\n",
+      "    streamlit run /Users/pietrolesci/miniconda3/envs/wordify/lib/python3.7/site-packages/ipykernel_launcher.py [ARGUMENTS]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import streamlit as st\n",
+    "pbar = st.progress(0)\n",
+    "N = 100\n",
+    "for i, _ in enumerate(range(N)):\n",
+    "    if i % N == 0:\n",
+    "        pbar.progress(1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "configs = ModelConfigs\n",
+    "clf = Pipeline(\n",
+    "    [\n",
+    "        (\"tfidf\", TfidfVectorizer()),\n",
+    "        (\n",
+    "            \"classifier\",\n",
+    "            LogisticRegression(\n",
+    "                penalty=\"l1\",\n",
+    "                C=configs.PENALTIES.value[np.random.randint(len(configs.PENALTIES.value))],\n",
+    "                solver=\"liblinear\",\n",
+    "                multi_class=\"auto\",\n",
+    "                max_iter=500,\n",
+    "                class_weight=\"balanced\",\n",
+    "            ),\n",
+    "        ),\n",
+    "    ]\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Pipeline(steps=[('tfidf', TfidfVectorizer()),\n",
+       "                ('classifier',\n",
+       "                 LogisticRegression(C=1, class_weight='balanced', max_iter=500,\n",
+       "                                    penalty='l1', solver='liblinear'))])"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clf.fit(df[\"text\"], df[\"label\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['00', '000', '00001', ..., 'ís', 'über', 'überwoman'], dtype=object)"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def wordifier(df, text_col, label_col, configs=ModelConfigs):\n",
+    "\n",
+    "    n_instances, n_features = X.shape\n",
+    "    n_classes = np.unique(y)\n",
+    "\n",
+    "    # NOTE: the * 10 / 10 trick is to have \"nice\" round-ups\n",
+    "    sample_fraction = np.ceil((n_features / n_instances) * 10) / 10\n",
+    "\n",
+    "    sample_size = min(\n",
+    "        # this is the maximum supported\n",
+    "        configs.MAX_SELECTION.value,\n",
+    "        # at minimum you want MIN_SELECTION but in general you want\n",
+    "        # n_instances * sample_fraction\n",
+    "        max(configs.MIN_SELECTION.value, int(n_instances * sample_fraction)),\n",
+    "        # however if previous one is bigger the the available instances take\n",
+    "        # the number of available instances\n",
+    "        n_instances,\n",
+    "    )\n",
+    "\n",
+    "    # TODO: might want to try out something to subsample features at each iteration\n",
+    "\n",
+    "    # initialize coefficient matrices\n",
+    "    pos_scores = np.zeros((n_classes, n_features), dtype=int)\n",
+    "    neg_scores = np.zeros((n_classes, n_features), dtype=int)\n",
+    "\n",
+    "    for _ in range(configs.NUM_ITERS.value):\n",
+    "\n",
+    "        # run randomized regression\n",
+    "        clf = Pipeline([\n",
+    "            ('tfidf', TfidfVectorizer()), \n",
+    "            ('classifier', LogisticRegression(\n",
+    "                penalty=\"l1\",\n",
+    "                C=configs.PENALTIES.value[\n",
+    "                    np.random.randint(len(configs.PENALTIES.value))\n",
+    "                ],\n",
+    "                solver=\"liblinear\",\n",
+    "                multi_class=\"auto\",\n",
+    "                max_iter=500,\n",
+    "                class_weight=\"balanced\",\n",
+    "            ))]\n",
+    "        )\n",
+    "\n",
+    "        # sample indices to subsample matrix\n",
+    "        selection = resample(\n",
+    "            np.arange(n_instances), replace=True, stratify=y, n_samples=sample_size\n",
+    "        )\n",
+    "\n",
+    "        # fit\n",
+    "        try:\n",
+    "            clf.fit(X[selection], y[selection])\n",
+    "        except ValueError:\n",
+    "            continue\n",
+    "\n",
+    "        # record coefficients\n",
+    "        if n_classes == 2:\n",
+    "            pos_scores[1] = pos_scores[1] + (clf.coef_ > 0.0)\n",
+    "            neg_scores[1] = neg_scores[1] + (clf.coef_ < 0.0)\n",
+    "            pos_scores[0] = pos_scores[0] + (clf.coef_ < 0.0)\n",
+    "            neg_scores[0] = neg_scores[0] + (clf.coef_ > 0.0)\n",
+    "        else:\n",
+    "            pos_scores += clf.coef_ > 0\n",
+    "            neg_scores += clf.coef_ < 0\n",
+    "\n",
+    "\n",
+    "        # normalize\n",
+    "        pos_scores = pos_scores / configs.NUM_ITERS.value\n",
+    "        neg_scores = neg_scores / configs.NUM_ITERS.value\n",
+    "\n",
+    "        # get only active features\n",
+    "        pos_positions = np.where(\n",
+    "            pos_scores >= configs.SELECTION_THRESHOLD.value, pos_scores, 0\n",
+    "        )\n",
+    "        neg_positions = np.where(\n",
+    "            neg_scores >= configs.SELECTION_THRESHOLD.value, neg_scores, 0\n",
+    "        )\n",
+    "\n",
+    "        # prepare DataFrame\n",
+    "        X_names = clf.steps[0][1].get_feature_names_out()\n",
+    "        pos = [\n",
+    "            (X_names[i], pos_scores[c, i], y_names[c])\n",
+    "            for c, i in zip(*pos_positions.nonzero())\n",
+    "        ]\n",
+    "        neg = [\n",
+    "            (X_names[i], neg_scores[c, i], y_names[c])\n",
+    "            for c, i in zip(*neg_positions.nonzero())\n",
+    "        ]\n",
+    "\n",
+    "    posdf = pd.DataFrame(pos, columns=\"word score label\".split()).sort_values(\n",
+    "        [\"label\", \"score\"], ascending=False\n",
+    "    )\n",
+    "    negdf = pd.DataFrame(neg, columns=\"word score label\".split()).sort_values(\n",
+    "        [\"label\", \"score\"], ascending=False\n",
+    "    )\n",
+    "\n",
+    "    return posdf, negdf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "res = vdf.apply(wordifier, arguments=[vdf.processed_text, vdf.encoded_label], vectorize=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from vaex.ml.sklearn import Predictor"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "clf = Pipeline(\n",
+    "    [\n",
+    "        (\n",
+    "            \"tfidf\",\n",
+    "            TfidfVectorizer(\n",
+    "                input=\"content\",  # default: file already in memory\n",
+    "                encoding=\"utf-8\",  # default\n",
+    "                decode_error=\"strict\",  # default\n",
+    "                strip_accents=None,  # do nothing\n",
+    "                lowercase=False,  # do nothing\n",
+    "                preprocessor=None,  # do nothing - default\n",
+    "                tokenizer=None,  # default\n",
+    "                stop_words=None,  # do nothing\n",
+    "                analyzer=\"word\",\n",
+    "                ngram_range=(1, 3),  # maximum 3-ngrams\n",
+    "                min_df=0.001,\n",
+    "                max_df=0.75,\n",
+    "                sublinear_tf=True,\n",
+    "            ),\n",
+    "        ),\n",
+    "        (\n",
+    "            \"classifier\",\n",
+    "            LogisticRegression(\n",
+    "                penalty=\"l1\",\n",
+    "                C=configs.PENALTIES.value[np.random.randint(len(configs.PENALTIES.value))],\n",
+    "                solver=\"liblinear\",\n",
+    "                multi_class=\"auto\",\n",
+    "                max_iter=500,\n",
+    "                class_weight=\"balanced\",\n",
+    "            ),\n",
+    "        ),\n",
+    "    ]\n",
+    ")\n",
     "\n",
+    "vaex_model = Predictor(\n",
+    "    features=[\"processed_text\"],\n",
+    "    target=\"encoded_label\",\n",
+    "    model=clf,\n",
+    "    prediction_name=\"prediction\",\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "TypeError",
+     "evalue": "unhashable type: 'list'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m/var/folders/b_/m81mmt0s6gv48kdvk44n2l740000gn/T/ipykernel_52217/687453386.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mvaex_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvdf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;32m~/miniconda3/envs/wordify/lib/python3.7/site-packages/vaex/ml/sklearn.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, df, **kwargs)\u001b[0m\n\u001b[1;32m    103\u001b[0m         '''\n\u001b[1;32m    104\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 105\u001b[0;31m         \u001b[0mX\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfeatures\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    106\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtarget\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    107\u001b[0m             \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mevaluate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtarget\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/miniconda3/envs/wordify/lib/python3.7/site-packages/vaex/dataframe.py\u001b[0m in \u001b[0;36mvalues\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   6897\u001b[0m         \u001b[0mIf\u001b[0m \u001b[0many\u001b[0m \u001b[0mof\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mcolumns\u001b[0m \u001b[0mcontain\u001b[0m \u001b[0mmasked\u001b[0m \u001b[0marrays\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mmasks\u001b[0m \u001b[0mare\u001b[0m \u001b[0mignored\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mmasked\u001b[0m \u001b[0melements\u001b[0m \u001b[0mare\u001b[0m \u001b[0mreturned\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mwell\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   6898\u001b[0m         \"\"\"\n\u001b[0;32m-> 6899\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__array__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   6900\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   6901\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/miniconda3/envs/wordify/lib/python3.7/site-packages/vaex/dataframe.py\u001b[0m in \u001b[0;36m__array__\u001b[0;34m(self, dtype, parallel)\u001b[0m\n\u001b[1;32m   5989\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0mcolumn_type\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   5990\u001b[0m                     \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Cannot cast %r (of type %r) to %r\"\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata_type\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 5991\u001b[0;31m         \u001b[0mchunks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mevaluate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcolumn_names\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparallel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mparallel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0marray_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'numpy'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   5992\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0many\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mma\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misMaskedArray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mchunk\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mchunk\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mchunks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   5993\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mma\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mchunks\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mT\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/miniconda3/envs/wordify/lib/python3.7/site-packages/vaex/dataframe.py\u001b[0m in \u001b[0;36mevaluate\u001b[0;34m(self, expression, i1, i2, out, selection, filtered, array_type, parallel, chunk_size, progress)\u001b[0m\n\u001b[1;32m   2962\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mevaluate_iterator\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexpression\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0ms1\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mi1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0ms2\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mi2\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mout\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mselection\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mselection\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfiltered\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfiltered\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0marray_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0marray_type\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparallel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mparallel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mchunk_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mchunk_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mprogress\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mprogress\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2963\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2964\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_evaluate_implementation\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexpression\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mi1\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mi1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mi2\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mi2\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mout\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mselection\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mselection\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfiltered\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfiltered\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0marray_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0marray_type\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparallel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mparallel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mchunk_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mchunk_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mprogress\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mprogress\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2965\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2966\u001b[0m     \u001b[0;34m@\u001b[0m\u001b[0mdocsubst\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/miniconda3/envs/wordify/lib/python3.7/site-packages/vaex/dataframe.py\u001b[0m in \u001b[0;36m_evaluate_implementation\u001b[0;34m(self, expression, i1, i2, out, selection, filtered, array_type, parallel, chunk_size, raw, progress)\u001b[0m\n\u001b[1;32m   6207\u001b[0m             \u001b[0;31m# TODO: For NEP branch: dtype -> dtype_evaluate\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   6208\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 6209\u001b[0;31m             \u001b[0mexpression_to_evaluate\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexpressions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# lets assume we have to do them all\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   6210\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   6211\u001b[0m             \u001b[0;32mfor\u001b[0m \u001b[0mexpression\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexpressions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mTypeError\u001b[0m: unhashable type: 'list'"
+     ]
+    }
+   ],
+   "source": [
+    "vaex_model.fit(vdf)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "b'\\x80\\x03c__main__\\nwordifier\\nq\\x00.'"
+      ]
+     },
+     "execution_count": 52,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pickle\n",
+    "pickle.dumps(wordifier)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "TypeError",
+     "evalue": "unhashable type: 'list'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m/var/folders/b_/m81mmt0s6gv48kdvk44n2l740000gn/T/ipykernel_52217/687453386.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mvaex_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvdf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;32m~/miniconda3/envs/wordify/lib/python3.7/site-packages/vaex/ml/sklearn.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, df, **kwargs)\u001b[0m\n\u001b[1;32m    103\u001b[0m         '''\n\u001b[1;32m    104\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 105\u001b[0;31m         \u001b[0mX\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfeatures\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    106\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtarget\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    107\u001b[0m             \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mevaluate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtarget\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/miniconda3/envs/wordify/lib/python3.7/site-packages/vaex/dataframe.py\u001b[0m in \u001b[0;36mvalues\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   6897\u001b[0m         \u001b[0mIf\u001b[0m \u001b[0many\u001b[0m \u001b[0mof\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mcolumns\u001b[0m \u001b[0mcontain\u001b[0m \u001b[0mmasked\u001b[0m \u001b[0marrays\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mmasks\u001b[0m \u001b[0mare\u001b[0m \u001b[0mignored\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mmasked\u001b[0m \u001b[0melements\u001b[0m \u001b[0mare\u001b[0m \u001b[0mreturned\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mwell\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   6898\u001b[0m         \"\"\"\n\u001b[0;32m-> 6899\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__array__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   6900\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   6901\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/miniconda3/envs/wordify/lib/python3.7/site-packages/vaex/dataframe.py\u001b[0m in \u001b[0;36m__array__\u001b[0;34m(self, dtype, parallel)\u001b[0m\n\u001b[1;32m   5989\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0mcolumn_type\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   5990\u001b[0m                     \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Cannot cast %r (of type %r) to %r\"\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata_type\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 5991\u001b[0;31m         \u001b[0mchunks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mevaluate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcolumn_names\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparallel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mparallel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0marray_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'numpy'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   5992\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0many\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mma\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misMaskedArray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mchunk\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mchunk\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mchunks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   5993\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mma\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mchunks\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mT\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/miniconda3/envs/wordify/lib/python3.7/site-packages/vaex/dataframe.py\u001b[0m in \u001b[0;36mevaluate\u001b[0;34m(self, expression, i1, i2, out, selection, filtered, array_type, parallel, chunk_size, progress)\u001b[0m\n\u001b[1;32m   2962\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mevaluate_iterator\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexpression\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0ms1\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mi1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0ms2\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mi2\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mout\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mselection\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mselection\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfiltered\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfiltered\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0marray_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0marray_type\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparallel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mparallel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mchunk_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mchunk_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mprogress\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mprogress\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2963\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2964\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_evaluate_implementation\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexpression\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mi1\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mi1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mi2\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mi2\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mout\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mselection\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mselection\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfiltered\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfiltered\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0marray_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0marray_type\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparallel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mparallel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mchunk_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mchunk_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mprogress\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mprogress\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2965\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2966\u001b[0m     \u001b[0;34m@\u001b[0m\u001b[0mdocsubst\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/miniconda3/envs/wordify/lib/python3.7/site-packages/vaex/dataframe.py\u001b[0m in \u001b[0;36m_evaluate_implementation\u001b[0;34m(self, expression, i1, i2, out, selection, filtered, array_type, parallel, chunk_size, raw, progress)\u001b[0m\n\u001b[1;32m   6207\u001b[0m             \u001b[0;31m# TODO: For NEP branch: dtype -> dtype_evaluate\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   6208\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 6209\u001b[0;31m             \u001b[0mexpression_to_evaluate\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexpressions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# lets assume we have to do them all\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   6210\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   6211\u001b[0m             \u001b[0;32mfor\u001b[0m \u001b[0mexpression\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexpressions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mTypeError\u001b[0m: unhashable type: 'list'"
+     ]
+    }
+   ],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "res = []\n",
+    "with tqdm(total=len(df)) as pbar:\n",
+    "    for doc in tqdm(nlp.pipe(df[\"text\"].values, batch_size=500, n_process=n_cpus)):\n",
+    "        res.append([i.lemma_ for i in doc])\n",
+    "        pbar.update(1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pickle"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def fn(t):\n",
+    "    return "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%timeit\n",
+    "with mp.Pool(mp.cpu_count()) as pool:\n",
+    "    new_s = pool.map(nlp, df[\"text\"].values)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import List\n",
     "import numpy as np\n",
     "import pandas as pd\n",
-    "# import modin.pandas as mpd\n",
-    "import spacy\n",
-    "from src.configs import ModelConfigs, Languages\n",
-    "from src.utils import wordifier, TextPreprocessor, encode\n",
-    "\n",
-    "from textacy.preprocessing import make_pipeline, remove, replace, normalize\n",
-    "from tqdm import trange\n",
-    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "import streamlit as st\n",
     "from sklearn.linear_model import LogisticRegression\n",
-    "from sklearn.preprocessing import LabelEncoder\n",
     "from sklearn.utils import resample\n",
-    "import multiprocessing as mp\n",
-    "# import dask.dataframe as dask_df\n",
-    "from stqdm import stqdm\n",
-    "stqdm.pandas()\n",
     "\n",
-    "from tqdm import trange\n",
+    "from src.configs import ModelConfigs\n",
     "\n",
-    "import os\n",
-    "# os.environ[\"MODIN_ENGINE\"] = \"ray\"  # Modin will use Ray\n",
     "\n",
-    "import vaex\n",
-    "pd.set_option(\"display.max_colwidth\", None)"
+    "def wordifier(X, y, X_names: List[str], y_names: List[str], configs=ModelConfigs):\n",
+    "\n",
+    "    n_instances, n_features = X.shape\n",
+    "    n_classes = len(y_names)\n",
+    "\n",
+    "    # NOTE: the * 10 / 10 trick is to have \"nice\" round-ups\n",
+    "    sample_fraction = np.ceil((n_features / n_instances) * 10) / 10\n",
+    "\n",
+    "    sample_size = min(\n",
+    "        # this is the maximum supported\n",
+    "        configs.MAX_SELECTION.value,\n",
+    "        # at minimum you want MIN_SELECTION but in general you want\n",
+    "        # n_instances * sample_fraction\n",
+    "        max(configs.MIN_SELECTION.value, int(n_instances * sample_fraction)),\n",
+    "        # however if previous one is bigger the the available instances take\n",
+    "        # the number of available instances\n",
+    "        n_instances,\n",
+    "    )\n",
+    "\n",
+    "    # TODO: might want to try out something to subsample features at each iteration\n",
+    "\n",
+    "    # initialize coefficient matrices\n",
+    "    pos_scores = np.zeros((n_classes, n_features), dtype=int)\n",
+    "    neg_scores = np.zeros((n_classes, n_features), dtype=int)\n",
+    "\n",
+    "    with st.spinner(\"Wordifying!\"):\n",
+    "        pbar = st.progress(0)\n",
+    "\n",
+    "        for i, _ in enumerate(range(configs.NUM_ITERS.value)):\n",
+    "\n",
+    "            # run randomized regression\n",
+    "            clf = LogisticRegression(\n",
+    "                penalty=\"l1\",\n",
+    "                C=configs.PENALTIES.value[\n",
+    "                    np.random.randint(len(configs.PENALTIES.value))\n",
+    "                ],\n",
+    "                solver=\"liblinear\",\n",
+    "                multi_class=\"auto\",\n",
+    "                max_iter=500,\n",
+    "                class_weight=\"balanced\",\n",
+    "            )\n",
+    "\n",
+    "            # sample indices to subsample matrix\n",
+    "            selection = resample(\n",
+    "                np.arange(n_instances), replace=True, stratify=y, n_samples=sample_size\n",
+    "            )\n",
+    "\n",
+    "            # fit\n",
+    "            try:\n",
+    "                clf.fit(X[selection], y[selection])\n",
+    "            except ValueError:\n",
+    "                continue\n",
+    "\n",
+    "            # record coefficients\n",
+    "            if n_classes == 2:\n",
+    "                pos_scores[1] = pos_scores[1] + (clf.coef_ > 0.0)\n",
+    "                neg_scores[1] = neg_scores[1] + (clf.coef_ < 0.0)\n",
+    "                pos_scores[0] = pos_scores[0] + (clf.coef_ < 0.0)\n",
+    "                neg_scores[0] = neg_scores[0] + (clf.coef_ > 0.0)\n",
+    "            else:\n",
+    "                pos_scores += clf.coef_ > 0\n",
+    "                neg_scores += clf.coef_ < 0\n",
+    "\n",
+    "            pbar.progress(i + 1)\n",
+    "\n",
+    "        # normalize\n",
+    "        pos_scores = pos_scores / configs.NUM_ITERS.value\n",
+    "        neg_scores = neg_scores / configs.NUM_ITERS.value\n",
+    "\n",
+    "        # get only active features\n",
+    "        pos_positions = np.where(\n",
+    "            pos_scores >= configs.SELECTION_THRESHOLD.value, pos_scores, 0\n",
+    "        )\n",
+    "        neg_positions = np.where(\n",
+    "            neg_scores >= configs.SELECTION_THRESHOLD.value, neg_scores, 0\n",
+    "        )\n",
+    "\n",
+    "        # prepare DataFrame\n",
+    "        pos = [\n",
+    "            (X_names[i], pos_scores[c, i], y_names[c])\n",
+    "            for c, i in zip(*pos_positions.nonzero())\n",
+    "        ]\n",
+    "        neg = [\n",
+    "            (X_names[i], neg_scores[c, i], y_names[c])\n",
+    "            for c, i in zip(*neg_positions.nonzero())\n",
+    "        ]\n",
+    "\n",
+    "    posdf = pd.DataFrame(pos, columns=\"word score label\".split()).sort_values(\n",
+    "        [\"label\", \"score\"], ascending=False\n",
+    "    )\n",
+    "    negdf = pd.DataFrame(neg, columns=\"word score label\".split()).sort_values(\n",
+    "        [\"label\", \"score\"], ascending=False\n",
+    "    )\n",
+    "\n",
+    "    return posdf, negdf\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -70,7 +592,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -79,7 +601,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -91,7 +613,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -104,24 +626,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stderr",
-     "text": [
-      "100%|██████████| 9939/9939 [00:06<00:00, 1431.09it/s]\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "df[\"p_text\"] = prep.fit_transform(df[\"text\"])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -130,7 +644,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -146,28 +660,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": [
-      "CPU times: user 1.45 s, sys: 10.6 ms, total: 1.46 s\nWall time: 1.46 s\n"
-     ]
-    },
-    {
-     "output_type": "execute_result",
-     "data": {
-      "text/plain": [
-       "LogisticRegression(C=0.05, class_weight='balanced', max_iter=500, penalty='l1',\n",
-       "                   solver='liblinear')"
-      ]
-     },
-     "metadata": {},
-     "execution_count": 22
-    }
-   ],
+   "outputs": [],
    "source": [
     "%%time\n",
     "clf.fit(X, y)"
@@ -182,32 +677,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stderr",
-     "text": [
-      "  6%|▌         | 28/500 [01:01<27:33,  3.50s/it]/Users/49796/miniconda3/envs/py38/lib/python3.8/site-packages/sklearn/svm/_base.py:976: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.\n",
-      "  warnings.warn(\"Liblinear failed to converge, increase \"\n",
-      " 31%|███       | 156/500 [06:18<13:54,  2.43s/it]\n"
-     ]
-    },
-    {
-     "output_type": "error",
-     "ename": "KeyboardInterrupt",
-     "evalue": "",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-14-1fef5b7ccf45>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     39\u001b[0m     \u001b[0;31m# fit\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     40\u001b[0m     \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 41\u001b[0;31m         \u001b[0mclf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mselection\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mselection\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     42\u001b[0m     \u001b[0;32mexcept\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     43\u001b[0m         \u001b[0;32mcontinue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m~/miniconda3/envs/py38/lib/python3.8/site-packages/sklearn/linear_model/_logistic.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[1;32m   1354\u001b[0m                               \u001b[0;34m\" 'solver' is set to 'liblinear'. Got 'n_jobs'\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1355\u001b[0m                               \" = {}.\".format(effective_n_jobs(self.n_jobs)))\n\u001b[0;32m-> 1356\u001b[0;31m             self.coef_, self.intercept_, n_iter_ = _fit_liblinear(\n\u001b[0m\u001b[1;32m   1357\u001b[0m                 \u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mC\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit_intercept\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mintercept_scaling\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1358\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclass_weight\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpenalty\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdual\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mverbose\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m~/miniconda3/envs/py38/lib/python3.8/site-packages/sklearn/svm/_base.py\u001b[0m in \u001b[0;36m_fit_liblinear\u001b[0;34m(X, y, C, fit_intercept, intercept_scaling, class_weight, penalty, dual, verbose, max_iter, tol, random_state, multi_class, loss, epsilon, sample_weight)\u001b[0m\n\u001b[1;32m    964\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    965\u001b[0m     \u001b[0msolver_type\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_get_liblinear_solver_type\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmulti_class\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpenalty\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mloss\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdual\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 966\u001b[0;31m     raw_coef_, n_iter_ = liblinear.train_wrap(\n\u001b[0m\u001b[1;32m    967\u001b[0m         \u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_ind\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misspmatrix\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msolver_type\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtol\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbias\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mC\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    968\u001b[0m         \u001b[0mclass_weight_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmax_iter\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrnd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrandint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0miinfo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'i'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmax\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "n_instances, n_features = X.shape\n",
     "n_classes = len(y_names)\n",
@@ -293,5 +765,30 @@
    "outputs": [],
    "source": []
   }
- ]
-}
+ ],
+ "metadata": {
+  "interpreter": {
+   "hash": "aa7efd0b3ada76bb0689aa8ed0b61d7de788847e3d11d2d142fc5800c765982f"
+  },
+  "kernelspec": {
+   "display_name": "Python 3.8.3 64-bit ('py38': conda)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.11"
+  },
+  "orig_nbformat": 2
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

src/components.py

@@ -0,0 +1,252 @@
+import streamlit as st
+
+from src.configs import Languages, PreprocessingConfigs, SupportedFiles
+from src.preprocessing import PreprocessingPipeline
+from src.wordifier import input_transform, output_transform, wordifier
+
+
+def form(df):
+    with st.form("my_form"):
+        col1, col2 = st.columns([1, 2])
+        with col1:
+
+            cols = [""] + df.columns.tolist()
+            label_column = st.selectbox(
+                "Select label column",
+                cols,
+                index=0,
+                help="Select the column containing the labels",
+            )
+            text_column = st.selectbox(
+                "Select text column",
+                cols,
+                index=0,
+                help="Select the column containing the text",
+            )
+            language = st.selectbox(
+                "Select language",
+                [i.name for i in Languages],
+                help="""
+                    Select the language of your texts amongst the supported one. If we currently do
+                    not support it, feel free to open an issue
+                """,
+            )
+
+        with col2:
+            steps_options = list(PreprocessingPipeline.pipeline_components().keys())
+            pre_steps = st.multiselect(
+                "Select pre-lemmatization processing steps (ordered)",
+                options=steps_options,
+                default=[
+                    steps_options[i] for i in PreprocessingConfigs.DEFAULT_PRE.value
+                ],
+                format_func=lambda x: x.replace("_", " ").title(),
+                help="Select the processing steps to apply before the text is lemmatized",
+            )
+
+            lammatization_options = list(
+                PreprocessingPipeline.lemmatization_component().keys()
+            )
+            lemmatization_step = st.selectbox(
+                "Select lemmatization",
+                options=lammatization_options,
+                index=PreprocessingConfigs.DEFAULT_LEMMA.value,
+                help="Select lemmatization procedure",
+            )
+
+            post_steps = st.multiselect(
+                "Select post-lemmatization processing steps (ordered)",
+                options=steps_options,
+                default=[
+                    steps_options[i] for i in PreprocessingConfigs.DEFAULT_POST.value
+                ],
+                format_func=lambda x: x.replace("_", " ").title(),
+                help="Select the processing steps to apply after the text is lemmatized",
+            )
+
+        # Every form must have a submit button.
+        submitted = st.form_submit_button("Submit")
+        if submitted:
+
+            # preprocess
+            with st.spinner("Step 1/4: Preprocessing text"):
+                pipe = PreprocessingPipeline(
+                    language, pre_steps, lemmatization_step, post_steps
+                )
+                df = pipe.vaex_process(df, text_column)
+
+            # prepare input
+            with st.spinner("Step 2/4: Preparing inputs"):
+                input_dict = input_transform(df[text_column], df[label_column])
+
+            # wordify
+            with st.spinner("Step 3/4: Wordifying"):
+                pos, neg = wordifier(**input_dict)
+
+            # prepare output
+            with st.spinner("Step 4/4: Preparing outputs"):
+                new_df = output_transform(pos, neg)
+
+            # col1, col2, col3 = st.columns(3)
+            # with col1:
+            #     st.metric("Total number of words processed", 3, delta_color="normal")
+            # with col2:
+            #     st.metric("Texts processed", 3, delta_color="normal")
+            # with col3:
+            #     st.metric("Texts processed", 3, delta_color="normal")
+
+            return new_df
+
+
+def faq():
+    st.subheader("Frequently Asked Questions")
+    with st.expander("What is Wordify?"):
+        st.markdown(
+            """
+            __Wordify__ is a way to find out which n-grams (i.e., words and concatenations of words) are most indicative for each of your dependent
+            variable values.
+            """
+        )
+
+    with st.expander("What happens to my data?"):
+        st.markdown(
+            """
+            Nothing. We never store the data you upload on disk: it is only kept in memory for the
+            duration of the modeling, and then deleted. We do not retain any copies or traces of
+            your data.
+            """
+        )
+
+    with st.expander("What input formats do you support?"):
+        st.markdown(
+            f"""
+            We currently support {", ".join([i.name for i in SupportedFiles])}.
+            """
+        )
+
+    with st.expander("What languages are supported?"):
+        st.markdown(
+            f"""
+            Currently we support: {", ".join([i.name for i in Languages])}.
+            """
+        )
+
+    with st.expander("How does it work?"):
+        st.markdown(
+            """
+            It uses a variant of the Stability Selection algorithm
+            [(Meinshausen and Bühlmann, 2010)](https://rss.onlinelibrary.wiley.com/doi/full/10.1111/j.1467-9868.2010.00740.x)
+            to fit hundreds of logistic regression models on random subsets of the data, using
+            different L1 penalties to drive as many of the term coefficients to 0. Any terms that
+            receive a non-zero coefficient in at least 30% of all model runs can be seen as stable
+            indicators.
+            """
+        )
+
+    with st.expander("What libraries do you use?"):
+        st.markdown(
+            """
+            We leverage the power of many great libraries in the Python ecosystem:
+            - `Streamlit`
+            - `Pandas`
+            - `Numpy`
+            - `Spacy`
+            - `Scikit-learn`
+            - `Vaex`
+            """
+        )
+
+    with st.expander("How much data do I need?"):
+        st.markdown(
+            """
+            We recommend at least 2000 instances, the more, the better. With fewer instances, the
+            results are less replicable and reliable.
+            """
+        )
+
+    with st.expander("Is there a paper I can cite?"):
+        st.markdown(
+            """
+            Yes, please! Cite [Wordify: A Tool for Discovering and Differentiating Consumer Vocabularies](https://academic.oup.com/jcr/article/48/3/394/6199426)
+            ```
+            @article{10.1093/jcr/ucab018,
+                author = {Hovy, Dirk and Melumad, Shiri and Inman, J Jeffrey},
+                title = "{Wordify: A Tool for Discovering and Differentiating Consumer Vocabularies}",
+                journal = {Journal of Consumer Research},
+                volume = {48},
+                number = {3},
+                pages = {394-414},
+                year = {2021},
+                month = {03},
+                abstract = "{This work describes and illustrates a free and easy-to-use online text-analysis tool for understanding how consumer word use varies across contexts. The tool, Wordify, uses randomized logistic regression (RLR) to identify the words that best discriminate texts drawn from different pre-classified corpora, such as posts written by men versus women, or texts containing mostly negative versus positive valence. We present illustrative examples to show how the tool can be used for such diverse purposes as (1) uncovering the distinctive vocabularies that consumers use when writing reviews on smartphones versus PCs, (2) discovering how the words used in Tweets differ between presumed supporters and opponents of a controversial ad, and (3) expanding the dictionaries of dictionary-based sentiment-measurement tools. We show empirically that Wordify’s RLR algorithm performs better at discriminating vocabularies than support vector machines and chi-square selectors, while offering significant advantages in computing time. A discussion is also provided on the use of Wordify in conjunction with other text-analysis tools, such as probabilistic topic modeling and sentiment analysis, to gain more profound knowledge of the role of language in consumer behavior.}",
+                issn = {0093-5301},
+                doi = {10.1093/jcr/ucab018},
+                url = {https://doi.org/10.1093/jcr/ucab018},
+                eprint = {https://academic.oup.com/jcr/article-pdf/48/3/394/40853499/ucab018.pdf},
+            }
+            ```
+            """
+        )
+
+    with st.expander("How can I reach out to the Wordify team?"):
+        st.markdown(contacts(), unsafe_allow_html=True)
+
+
+def presentation():
+    st.markdown(
+        """
+        Wordify makes it easy to identify words that discriminate categories in textual data.
+        
+        :point_left: Start by uploading a file. *Once you upload the file, __Wordify__ will
+        show an interactive UI*.
+        """
+    )
+
+    st.subheader("Input format")
+    st.markdown(
+        """
+        Please note that your file must have a column with the texts and a column with the labels,
+        for example
+        """
+    )
+    st.table(
+        {
+            "text": ["A review", "Another review", "Yet another one", "etc"],
+            "label": ["Good", "Bad", "Good", "etc"],
+        }
+    )
+
+    st.subheader("Output format")
+    st.markdown(
+        """
+        As a result of the process, you will get a file containing 4 columns:
+        - `Word`: the n-gram (i.e., a word or a concatenation of words) considered
+        - `Score`: the wordify score, between 0 and 1, of how important is `Word` to discrimitate `Label`
+        - `Label`: the label that `Word` is discriminating
+        - `Correlation`: how `Word` is correlated with `Label` (e.g., "negative" means that if `Word` is present in the text then the label is less likely to be `Label`)
+        """
+    )
+
+
+def footer():
+    st.sidebar.markdown(
+        """
+        <span style="font-size: 0.75em">Built with &hearts; by [`Pietro Lesci`](https://pietrolesci.github.io/) and [`MilaNLP`](https://twitter.com/MilaNLProc?ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5Eauthor).</span>
+        """,
+        unsafe_allow_html=True,
+    )
+
+
+def contacts():
+    return """
+    You can reach out to us via email, phone, or via mail
+    
+    - :email: wordify@unibocconi.it
+    
+    - :telephone_receiver: +39 02 5836 2604
+    
+    - :postbox: Via Röntgen n. 1, Milan 20136 (ITALY)
+
+
+    <iframe src="https://www.google.com/maps/embed?pb=!1m18!1m12!1m3!1d2798.949796165441!2d9.185730115812493!3d45.450667779100726!2m3!1f0!2f0!3f0!3m2!1i1024!2i768!4f13.1!3m3!1m2!1s0x4786c405ae6543c9%3A0xf2bb2313b36af88c!2sVia%20Guglielmo%20R%C3%B6ntgen%2C%201%2C%2020136%20Milano%20MI!5e0!3m2!1sit!2sit!4v1569325279433!5m2!1sit!2sit" frameborder="0" style="border:0; width: 100%; height: 312px;" allowfullscreen></iframe>
+    """

src/configs.py

@@ -1,4 +1,5 @@
 from enum import Enum
+
 import pandas as pd
 
 
@@ -10,6 +11,19 @@ class ModelConfigs(Enum):
     MIN_SELECTION = 10_000
 
 
+class InputTransformConfigs(Enum):
+    NGRAM_RANGE = (1, 3)
+    MIN_DF = 0.001
+    MAX_DF = 0.75
+    SUBLINEAR = True
+
+
+class PreprocessingConfigs(Enum):
+    DEFAULT_PRE = [1, 3, 5, 15, 21, 22, 18, 19, 0, 20, -1]
+    DEFAULT_LEMMA = 1
+    DEFAULT_POST = [20, -1]
+
+
 class Languages(Enum):
     English = "en_core_web_sm"
     Italian = "it_core_news_sm"

src/pages/about.py

@@ -1,34 +0,0 @@
-import streamlit as st
-
-
-def write(*args):
-    # ==== Contacts ==== #
-    with st.beta_container():
-        st.markdown("")
-        st.markdown("")
-        st.header(":rocket:About us")
-
-        st.markdown(
-            """
-            You can reach out to us via email, phone, or - if you are old-fashioned - via mail
-            """
-        )
-        with st.beta_expander("Contacts"):
-
-            _, col2 = st.beta_columns([0.5, 3])
-            col2.markdown(
-                """
-                :email: wordify@unibocconi.it
-
-                :telephone_receiver: +39 02 5836 2604
-
-                :postbox: Via Röntgen n. 1, Milan 20136 (ITALY)
-                """
-            )
-
-        st.write(
-            """
-            <iframe src="https://www.google.com/maps/embed?pb=!1m18!1m12!1m3!1d2798.949796165441!2d9.185730115812493!3d45.450667779100726!2m3!1f0!2f0!3f0!3m2!1i1024!2i768!4f13.1!3m3!1m2!1s0x4786c405ae6543c9%3A0xf2bb2313b36af88c!2sVia%20Guglielmo%20R%C3%B6ntgen%2C%201%2C%2020136%20Milano%20MI!5e0!3m2!1sit!2sit!4v1569325279433!5m2!1sit!2sit" frameborder="0" style="border:0; width: 100%; height: 312px;" allowfullscreen></iframe>
-            """,
-            unsafe_allow_html=True,
-        )

src/pages/faq.py

@@ -1,126 +0,0 @@
-import streamlit as st
-from src.configs import Languages
-
-
-def write(*args):
-
-    # ==== HOW IT WORKS ==== #
-    with st.beta_container():
-        st.markdown("")
-        st.markdown("")
-        st.markdown(
-            """
-            Wordify makes it easy to identify words that discriminate categories in textual data.
-
-            Let's explain Wordify with an example. Imagine you are thinking about having a glass
-            of wine :wine_glass: with your friends :man-man-girl-girl: and you have to buy a bottle.
-            You know you like `bold`, `woody` wine but are unsure which one to choose.
-            You wonder whether there are some words that describe each type of wine.
-            Since you are a researcher :female-scientist: :male-scientist:, you decide to approach
-            the problem scientifically :microscope:. That's where Wordify comes to the rescue!
-            """
-        )
-        st.markdown("")
-        st.markdown("")
-        st.header("Steps")
-        st.subheader("Step 1 - Prepare your data")
-        st.markdown(
-            """
-            Create an Excel or CSV file with two columns for each row:
-
-            - a column with the name or the label identifying a specific object or class (e.g., in our
-            wine example above it would be the type of wine or the name of a specific brand). It is
-            common practice naming this column `label`
-
-            - a column with the text describing that specific object or class (e.g., in the wine example
-            above it could be the description that you find on the rear of the bottle label). It is
-            common practice naming this column `text`
-
-            To have reliable results, we suggest providing at least 2000 labelled texts. If you provide
-            less we will still wordify your file, but the results should then be taken with a grain of
-            salt.
-
-            Consider that we also support multi-language texts, therefore you'll be able to
-            automatically discriminate between international wines, even if your preferred Italian
-            producer does not provide you with a description written in English!
-            """
-        )
-
-        st.subheader("Step 2 - Upload your file and Wordify!")
-        st.markdown(
-            """
-            Once you have prepared your Excel or CSV file, click the "Browse File" button.
-            Browse for your file.
-            Choose the language of your texts (select multi-language if your file contains text in
-            different languages).
-            Push the "Wordify|" button, set back, and wait for wordify to do its tricks.
-
-            Depending on the size of your data, the process can take from 1 minute to 5 minutes
-            """
-        )
-
-    # ==== FAQ ==== #
-    with st.beta_container():
-        st.markdown("")
-        st.markdown("")
-        st.header(":question:Frequently Asked Questions")
-        with st.beta_expander("What is Wordify?"):
-            st.markdown(
-                """
-                Wordify is a way to find out which terms are most indicative for each of your dependent
-                variable values.
-                """
-            )
-
-        with st.beta_expander("What happens to my data?"):
-            st.markdown(
-                """
-                Nothing. We never store the data you upload on disk: it is only kept in memory for the
-                duration of the modeling, and then deleted. We do not retain any copies or traces of
-                your data.
-                """
-            )
-
-        with st.beta_expander("What input formats do you support?"):
-            st.markdown(
-                """
-                The file you upload should be .xlsx, with two columns: the first should be labeled
-                'text' and contain all your documents (e.g., tweets, reviews, patents, etc.), one per
-                line. The second column should be labeled 'label', and contain the dependent variable
-                label associated with each text (e.g., rating, author gender, company, etc.).
-                """
-            )
-
-        with st.beta_expander("How does it work?"):
-            st.markdown(
-                """
-                It uses a variant of the Stability Selection algorithm
-                [(Meinshausen and Bühlmann, 2010)](https://rss.onlinelibrary.wiley.com/doi/full/10.1111/j.1467-9868.2010.00740.x)
-                to fit hundreds of logistic regression models on random subsets of the data, using
-                different L1 penalties to drive as many of the term coefficients to 0. Any terms that
-                receive a non-zero coefficient in at least 30% of all model runs can be seen as stable
-                indicators.
-                """
-            )
-
-        with st.beta_expander("How much data do I need?"):
-            st.markdown(
-                """
-                We recommend at least 2000 instances, the more, the better. With fewer instances, the
-                results are less replicable and reliable.
-                """
-            )
-
-        with st.beta_expander("Is there a paper I can cite?"):
-            st.markdown(
-                """
-                Yes please! Reference coming soon...
-                """
-            )
-
-        with st.beta_expander("What languages are supported?"):
-            st.markdown(
-                f"""
-                Currently we support: {", ".join([i.name for i in Languages])}.
-                """
-            )

src/pages/home.py

@@ -1,240 +0,0 @@
-from src.configs import Languages
-from src.utils import read_file, download_button
-from src.plotting import plot_labels_prop, plot_nchars, plot_score
-from src.preprocessing import Lemmatizer, PreprocessingPipeline, encode
-from src.wordifier import wordifier
-import streamlit as st
-
-
-def write(session, uploaded_file):
-
-    if not uploaded_file:
-        st.markdown(
-            """
-            Hi, welcome to __Wordify__! :rocket:
-
-            Start by uploading a file - CSV, XLSX (avoid Strict Open XML Spreadsheet format [here](https://stackoverflow.com/questions/62800822/openpyxl-cannot-read-strict-open-xml-spreadsheet-format-userwarning-file-conta)),
-            or PARQUET are currently supported.
-
-            Once you have uploaded the file, __Wordify__ will show an interactive UI through which
-            you'll be able to interactively decide the text preprocessing steps, their order, and
-            proceed to Wordify your text.
-
-            If you're ready, let's jump in:
-
-            :point_left: upload a file via the upload widget in the sidebar!
-
-            NOTE: whenever you want to reset everything, simply refresh the page.
-            """
-        )
-
-    elif uploaded_file:
-
-        # ==== 1. READ FILE ==== #
-        with st.spinner("Reading file"):
-            # TODO: write parser function that automatically understands format
-            data = read_file(uploaded_file)
-
-        # 2. CREATE UI TO SELECT COLUMNS
-        col1, col2, col3 = st.beta_columns(3)
-        with col1:
-            language = st.selectbox("Select language", [i.name for i in Languages])
-            with st.beta_expander("Description"):
-                st.markdown(
-                    f"Select a language amongst those supported: {', '.join([f'`{i.name}`' for i in Languages])}. This will be used to lemmatize and remove stopwords."
-                )
-        with col2:
-            cols_options = [""] + data.columns.tolist()
-            label_column = st.selectbox(
-                "Select label column name", cols_options, index=0
-            )
-            with st.beta_expander("Description"):
-                st.markdown("Select the column containing the labels.")
-
-            if label_column:
-                plot = plot_labels_prop(data, label_column)
-                if plot:
-                    st.altair_chart(plot, use_container_width=True)
-
-        with col3:
-            text_column = st.selectbox("Select text column name", cols_options, index=0)
-            with st.beta_expander("Description"):
-                st.markdown("Select the column containing the texts.")
-
-            if text_column:
-                st.altair_chart(
-                    plot_nchars(data, text_column), use_container_width=True
-                )
-
-        # ==== 2.1 CREATE UI FOR ADVANCED OPTIONS ==== #
-        with st.beta_expander("Advanced options"):
-
-            steps_options = list(PreprocessingPipeline.pipeline_components().keys())
-
-            # stopwords option and
-            col1, col2 = st.beta_columns([1, 3])
-            with col1:
-                st.markdown("Remove stopwords (uses Spacy vocabulary)")
-            with col2:
-                remove_stopwords_elem = st.empty()
-
-            # lemmatization option
-            col1, col2 = st.beta_columns([1, 3])
-            with col1:
-                st.markdown("Lemmatizes text (uses Spacy)")
-            with col2:
-                lemmatization_elem = st.empty()
-
-            # pre-lemmatization cleaning steps and
-            # post-lemmatization cleaning steps
-            col1, col2 = st.beta_columns([1, 3])
-            with col1:
-                st.markdown(
-                    f"""
-                    Define a pipeline of cleaning steps that is applied before and/or after lemmatization.
-                    The available cleaning steps are:\n
-                    {", ".join([f"`{x.replace('_', ' ').title()}`" for x in steps_options])}
-                    """
-                )
-            with col2:
-                pre_steps_elem = st.empty()
-                post_steps_elem = st.empty()
-                reset_button = st.empty()
-
-            # implement reset logic
-            if reset_button.button("Reset steps"):
-                session.run_id += 1
-
-            pre_steps = pre_steps_elem.multiselect(
-                "Select pre-lemmatization preprocessing steps (ordered)",
-                options=steps_options,
-                default=steps_options,
-                format_func=lambda x: x.replace("_", " ").title(),
-                key=session.run_id,
-            )
-            post_steps = post_steps_elem.multiselect(
-                "Select post-lemmatization processing steps (ordered)",
-                options=steps_options,
-                default=steps_options[-4:],
-                format_func=lambda x: x.replace("_", " ").title(),
-                key=session.run_id,
-            )
-            remove_stopwords = remove_stopwords_elem.checkbox(
-                "Remove stopwords",
-                value=True,
-                key=session.run_id,
-            )
-            lemmatization = lemmatization_elem.checkbox(
-                "Lemmatize text",
-                value=True,
-                key=session.run_id,
-            )
-
-        # show sample checkbox
-        col1, col2 = st.beta_columns([1, 2])
-        with col1:
-            show_sample = st.checkbox("Show sample of preprocessed text")
-
-        # initialize text preprocessor
-        preprocessing_pipeline = PreprocessingPipeline(
-            pre_steps=pre_steps,
-            lemmatizer=Lemmatizer(
-                language=language,
-                remove_stop=remove_stopwords,
-                lemmatization=lemmatization,
-            ),
-            post_steps=post_steps,
-        )
-
-        print(preprocessing_pipeline.pre_steps)
-
-        # ==== 3. PROVIDE FEEDBACK ON OPTIONS ==== #
-        if show_sample and not (label_column and text_column):
-            st.warning("Please select `label` and `text` columns")
-
-        elif show_sample and (label_column and text_column):
-            sample_data = data.sample(5)
-            sample_data[f"preprocessed_{text_column}"] = preprocessing_pipeline(
-                sample_data[text_column]
-            ).values
-
-            print(sample_data)
-            st.table(
-                sample_data.loc[
-                    :, [label_column, text_column, f"preprocessed_{text_column}"]
-                ]
-            )
-
-        # ==== 4. RUN ==== #
-        run_button = st.button("Wordify!")
-        if run_button and not (label_column and text_column):
-            st.warning("Please select `label` and `text` columns")
-
-        elif run_button and (label_column and text_column) and not session.process:
-
-            with st.spinner("Process started"):
-                # data = data.head()
-                data[f"preprocessed_{text_column}"] = preprocessing_pipeline(
-                    data[text_column]
-                ).values
-
-                print(data.head())
-
-                inputs = encode(data[f"preprocessed_{text_column}"], data[label_column])
-                session.posdf, session.negdf = wordifier(**inputs)
-            st.success("Wordified!")
-
-            # session.posdf, session.negdf = process(data, text_column, label_column)
-            session.process = True
-
-        # ==== 5. RESULTS ==== #
-        if session.process and (label_column and text_column):
-            st.markdown("")
-            st.markdown("")
-            st.header("Results")
-
-            # col1, col2, _ = st.beta_columns(3)
-            col1, col2, col3 = st.beta_columns([2, 3, 3])
-
-            with col1:
-                label = st.selectbox(
-                    "Select label", data[label_column].unique().tolist()
-                )
-                # # with col2:
-                # thres = st.slider(
-                #     "Select threshold",
-                #     min_value=0,
-                #     max_value=100,
-                #     step=1,
-                #     format="%f",
-                #     value=30,
-                # )
-                show_plots = st.checkbox("Show plots of top 100")
-
-            with col2:
-                st.subheader(f"Words __positively__ identifying label `{label}`")
-                st.write(
-                    session.posdf[session.posdf[label_column] == label].sort_values(
-                        "score", ascending=False
-                    )
-                )
-                download_button(session.posdf, "positive_data")
-                if show_plots:
-                    st.altair_chart(
-                        plot_score(session.posdf, label_column, label),
-                        use_container_width=True,
-                    )
-
-            with col3:
-                st.subheader(f"Words __negatively__ identifying label `{label}`")
-                st.write(
-                    session.negdf[session.negdf[label_column] == label].sort_values(
-                        "score", ascending=False
-                    )
-                )
-                download_button(session.negdf, "negative_data")
-                if show_plots:
-                    st.altair_chart(
-                        plot_score(session.negdf, label_column, label),
-                        use_container_width=True,
-                    )

src/plotting.py

@@ -1,84 +0,0 @@
-import altair as alt
-import pandas as pd
-import streamlit as st
-from stqdm import stqdm
-
-stqdm.pandas()
-
-
-def plot_labels_prop(data: pd.DataFrame, label_column: str):
-
-    unique_value_limit = 100
-
-    if data[label_column].nunique() > unique_value_limit:
-
-        st.warning(
-            f"""
-            The column you selected has more than {unique_value_limit}.
-            Are you sure it's the right column? If it is, please note that
-            this will impact __Wordify__ performance.
-            """
-        )
-
-        return
-
-    source = (
-        data[label_column]
-        .value_counts()
-        .reset_index()
-        .rename(columns={"index": "Labels", label_column: "Counts"})
-    )
-    source["Props"] = source["Counts"] / source["Counts"].sum()
-    source["Proportions"] = (source["Props"].round(3) * 100).map("{:,.2f}".format) + "%"
-
-    bars = (
-        alt.Chart(source)
-        .mark_bar()
-        .encode(
-            x=alt.X("Labels:O", sort="-y"),
-            y="Counts:Q",
-        )
-    )
-
-    text = bars.mark_text(align="center", baseline="middle", dy=15).encode(
-        text="Proportions:O"
-    )
-
-    return (bars + text).properties(height=300)
-
-
-def plot_nchars(data: pd.DataFrame, text_column: str):
-    source = data[text_column].str.len().to_frame()
-
-    plot = (
-        alt.Chart(source)
-        .mark_bar()
-        .encode(
-            alt.X(
-                f"{text_column}:Q", bin=True, axis=alt.Axis(title="# chars per text")
-            ),
-            alt.Y("count()", axis=alt.Axis(title="")),
-        )
-    )
-
-    return plot.properties(height=300)
-
-
-def plot_score(data: pd.DataFrame, label_col: str, label: str):
-
-    source = (
-        data.loc[data[label_col] == label]
-        .sort_values("score", ascending=False)
-        .head(100)
-    )
-
-    plot = (
-        alt.Chart(source)
-        .mark_bar()
-        .encode(
-            y=alt.Y("word:O", sort="-x"),
-            x="score:Q",
-        )
-    )
-
-    return plot.properties(height=max(30 * source.shape[0], 50))

src/preprocessing.py

@@ -1,56 +1,20 @@
+import multiprocessing as mp
+import os
 import re
 import string
 from collections import OrderedDict
-from typing import Callable, List, Optional, Tuple
+from typing import Callable, List, Optional
 
-import numpy as np
 import pandas as pd
 import spacy
 import streamlit as st
+import vaex
+from pandas.core.frame import DataFrame
 from pandas.core.series import Series
-from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.preprocessing import LabelEncoder
-from stqdm import stqdm
 from textacy.preprocessing import make_pipeline, normalize, remove, replace
 
 from .configs import Languages
 
-stqdm.pandas()
-
-
-def encode(text: pd.Series, labels: pd.Series):
-    """
-    Encodes text in mathematical object ameanable to training algorithm
-    """
-    tfidf_vectorizer = TfidfVectorizer(
-        input="content",  # default: file already in memory
-        encoding="utf-8",  # default
-        decode_error="strict",  # default
-        strip_accents=None,  # do nothing
-        lowercase=False,  # do nothing
-        preprocessor=None,  # do nothing - default
-        tokenizer=None,  # default
-        stop_words=None,  # do nothing
-        analyzer="word",
-        ngram_range=(1, 3),  # maximum 3-ngrams
-        min_df=0.001,
-        max_df=0.75,
-        sublinear_tf=True,
-    )
-    label_encoder = LabelEncoder()
-
-    with st.spinner("Encoding text using TF-IDF and Encoding labels"):
-        X = tfidf_vectorizer.fit_transform(text.values)
-        y = label_encoder.fit_transform(labels.values)
-
-    return {
-        "X": X,
-        "y": y,
-        "X_names": np.array(tfidf_vectorizer.get_feature_names()),
-        "y_names": label_encoder.classes_,
-    }
-
-
 # more [here](https://github.com/fastai/fastai/blob/master/fastai/text/core.py#L42)
 # and [here](https://textacy.readthedocs.io/en/latest/api_reference/preprocessing.html)
 # fmt: off
@@ -87,118 +51,105 @@ def normalize_repeating_words(t):
     return _re_wrep.sub(_replace_wrep, t)
 
 
-# fmt: on
-class Lemmatizer:
-    """Creates lemmatizer based on spacy"""
+def lowercase(t: str) -> str:
+    return t.lower()
 
-    def __init__(
-        self, language: str, remove_stop: bool = True, lemmatization: bool = True
-    ) -> None:
-        self.language = language
-        self.nlp = spacy.load(
-            Languages[language].value, exclude=["parser", "ner", "pos", "tok2vec"]
-        )
-        self._lemmatizer_fn = self._get_lemmatization_fn(remove_stop, lemmatization)
-        self.lemmatization = lemmatization
 
-    def _get_lemmatization_fn(
-        self, remove_stop: bool, lemmatization: bool
-    ) -> Optional[Callable]:
-        """Return the correct spacy Doc-level lemmatizer"""
-        if remove_stop and lemmatization:
+def strip(t: str) -> str:
+    return t.strip()
 
-            def lemmatizer_fn(doc: spacy.tokens.doc.Doc) -> str:
-                return " ".join(
-                    [t.lemma_ for t in doc if t.lemma_ != "-PRON-" and not t.is_stop]
-                )
 
-        elif remove_stop and not lemmatization:
+def lemmatize_remove_stopwords(doc: spacy.tokens.doc.Doc) -> str:
+    return " ".join(
+        [t.lemma_ for t in doc if t.lemma_ != "-PRON-" and not t.is_stop]
+    )
 
-            def lemmatizer_fn(doc: spacy.tokens.doc.Doc) -> str:
-                return " ".join([t.text for t in doc if not t.is_stop])
 
-        elif lemmatization and not remove_stop:
+def remove_stopwords(doc: spacy.tokens.doc.Doc) -> str:
+    return " ".join([t.text for t in doc if not t.is_stop])
 
-            def lemmatizer_fn(doc: spacy.tokens.doc.Doc) -> str:
-                return " ".join([t.lemma_ for t in doc if t.lemma_ != "-PRON-"])
 
-        else:
-            self.status = False
-            return
-
-        return lemmatizer_fn
-
-    def __call__(self, series: Series) -> Series:
-        """
-        Apply spacy pipeline to transform string to spacy Doc and applies lemmatization
-        """
-        res = []
-        pbar = stqdm(total=len(series), desc="Lemmatizing")
-        for doc in self.nlp.pipe(series, batch_size=500):
-            res.append(self._lemmatizer_fn(doc))
-            pbar.update(1)
-        pbar.close()
-        return pd.Series(res)
+def lemmatize_keep_stopwords(doc: spacy.tokens.doc.Doc) -> str:
+    return " ".join([t.lemma_ for t in doc if t.lemma_ != "-PRON-"])
 
 
+# fmt: on
 class PreprocessingPipeline:
     def __init__(
-        self, pre_steps: List[str], lemmatizer: Lemmatizer, post_steps: List[str]
+        self,
+        language: str,
+        pre_steps: Optional[List[str]],
+        lemmatization_step: Optional[str],
+        post_steps: Optional[List[str]],
     ):
+        self.language = language
+        self.pre_steps = pre_steps
+        self.lemmatization_step = lemmatization_step
+        self.post_steps = post_steps
+
+        self.nlp = spacy.load(Languages[language].value, disable=["parser", "ner"])
+        self.pre = self.make_pre_post_component(self.pre_steps)
+        self.post = self.make_pre_post_component(self.post_steps)
+        self.lemma = self.lemmatization_component()[self.lemmatization_step]
+
+    def apply_multiproc(fn, series):
+        with mp.Pool(mp.cpu_count()) as pool:
+            new_series = pool.map(fn, series)
+
+        return new_series
 
-        # build pipeline
-        self.pre_pipeline, self.lemmatizer, self.post_pipeline = self.make_pipeline(
-            pre_steps, lemmatizer, post_steps
+    def vaex_process(self, df: DataFrame, text_column: str) -> DataFrame:
+        def fn(t):
+            return self.post(self.lemma(self.nlp(self.pre(t))))
+
+        vdf = vaex.from_pandas(df)
+        vdf["processed_text"] = vdf.apply(
+            fn, arguments=[vdf[text_column]], vectorize=False
         )
 
-    def __call__(self, series: Series) -> Series:
-        with st.spinner("Pre-lemmatization cleaning"):
-            res = series.progress_map(self.pre_pipeline)
+        return vdf.to_pandas_df()
 
-        with st.spinner("Lemmatizing"):
-            res = self.lemmatizer(series)
+    def __call__(self, series: Series) -> Series:
+        if self.pre:
+            series = series.map(self.pre)
 
-        with st.spinner("Post-lemmatization cleaning"):
-            res = series.progress_map(self.post_pipeline)
+        if self.lemma:
+            total_steps = len(series) // 100
+            res = []
+            pbar = st.progress(0)
+            for i, doc in enumerate(
+                self.nlp.pipe(series, batch_size=500, n_process=os.cpu_count())
+            ):
+                res.append(self.lemma(doc))
 
-        return res
+                if i % total_steps == 0:
+                    pbar.progress(1)
 
-    def make_pipeline(
-        self, pre_steps: List[str], lemmatizer: Lemmatizer, post_steps: List[str]
-    ) -> Tuple[Callable]:
+            series = pd.Series(res)
 
-        # pre-lemmatization steps
-        pre_steps = [
-            self.pipeline_components()[step]
-            for step in pre_steps
-            if step in self.pipeline_components()
-        ]
-        pre_steps = make_pipeline(*pre_steps) if pre_steps else lambda x: x
+        if self.post:
+            series = series.map(self.post)
 
-        # lemmatization
-        lemmatizer = lemmatizer if lemmatizer.lemmatization else lambda x: x
+        return series
 
-        # post lemmatization steps
-        post_steps = [
-            self.pipeline_components()[step]
-            for step in post_steps
-            if step in self.pipeline_components()
-        ]
-        post_steps = make_pipeline(*post_steps) if post_steps else lambda x: x
+    def make_pre_post_component(self, steps: Optional[List[str]]) -> Optional[Callable]:
+        if not steps:
+            return
+        components = [self.pipeline_components()[step] for step in steps]
 
-        return pre_steps, lemmatizer, post_steps
+        return make_pipeline(*components)
 
     @staticmethod
     def pipeline_components() -> "OrderedDict[str, Callable]":
         """Returns available cleaning steps in order"""
         return OrderedDict(
             [
-                ("lower", lambda x: x.lower()),
+                ("lowercase", lowercase),
                 ("normalize_unicode", normalize.unicode),
                 ("normalize_bullet_points", normalize.bullet_points),
                 ("normalize_hyphenated_words", normalize.hyphenated_words),
                 ("normalize_quotation_marks", normalize.quotation_marks),
-                ("normalize_whitespace", normalize.whitespace),
+                ("normalize_whitespaces", normalize.whitespace),
                 ("replace_urls", replace.urls),
                 ("replace_currency_symbols", replace.currency_symbols),
                 ("replace_emails", replace.emails),
@@ -216,6 +167,17 @@ class PreprocessingPipeline:
                 ("normalize_useless_spaces", normalize_useless_spaces),
                 ("normalize_repeating_chars", normalize_repeating_chars),
                 ("normalize_repeating_words", normalize_repeating_words),
-                ("strip", lambda x: x.strip()),
+                ("strip", strip),
+            ]
+        )
+
+    @staticmethod
+    def lemmatization_component() -> "OrderedDict[str, Optional[Callable]]":
+        return OrderedDict(
+            [
+                ("Spacy lemmatizer (keep stopwords)", lemmatize_keep_stopwords),
+                ("Spacy lemmatizer (no stopwords)", lemmatize_remove_stopwords),
+                ("Disable lemmatizer", None),
+                ("Remove stopwords", remove_stopwords),
             ]
         )

src/session_state.py

@@ -1,121 +0,0 @@
-"""Hack to add per-session state to Streamlit.
-
-Usage
------
-
->>> import SessionState
->>>
->>> session_state = SessionState.get(user_name='', favorite_color='black')
->>> session_state.user_name
-''
->>> session_state.user_name = 'Mary'
->>> session_state.favorite_color
-'black'
-
-Since you set user_name above, next time your script runs this will be the
-result:
->>> session_state = get(user_name='', favorite_color='black')
->>> session_state.user_name
-'Mary'
-
-"""
-try:
-    import streamlit.ReportThread as ReportThread
-    from streamlit.server.Server import Server
-except Exception:
-    # Streamlit >= 0.65.0
-    import streamlit.report_thread as ReportThread
-    from streamlit.server.server import Server
-
-
-class SessionState(object):
-    def __init__(self, **kwargs):
-        """A new SessionState object.
-
-        Parameters
-        ----------
-        **kwargs : any
-            Default values for the session state.
-
-        Example
-        -------
-        >>> session_state = SessionState(user_name='', favorite_color='black')
-        >>> session_state.user_name = 'Mary'
-        ''
-        >>> session_state.favorite_color
-        'black'
-
-        """
-        for key, val in kwargs.items():
-            setattr(self, key, val)
-
-
-def get(**kwargs):
-    """Gets a SessionState object for the current session.
-
-    Creates a new object if necessary.
-
-    Parameters
-    ----------
-    **kwargs : any
-        Default values you want to add to the session state, if we're creating a
-        new one.
-
-    Example
-    -------
-    >>> session_state = get(user_name='', favorite_color='black')
-    >>> session_state.user_name
-    ''
-    >>> session_state.user_name = 'Mary'
-    >>> session_state.favorite_color
-    'black'
-
-    Since you set user_name above, next time your script runs this will be the
-    result:
-    >>> session_state = get(user_name='', favorite_color='black')
-    >>> session_state.user_name
-    'Mary'
-
-    """
-    # Hack to get the session object from Streamlit.
-
-    ctx = ReportThread.get_report_ctx()
-
-    this_session = None
-
-    current_server = Server.get_current()
-    if hasattr(current_server, "_session_infos"):
-        # Streamlit < 0.56
-        session_infos = Server.get_current()._session_infos.values()
-    else:
-        session_infos = Server.get_current()._session_info_by_id.values()
-
-    for session_info in session_infos:
-        s = session_info.session
-        if (
-            # Streamlit < 0.54.0
-            (hasattr(s, "_main_dg") and s._main_dg == ctx.main_dg)
-            or
-            # Streamlit >= 0.54.0
-            (not hasattr(s, "_main_dg") and s.enqueue == ctx.enqueue)
-            or
-            # Streamlit >= 0.65.2
-            (
-                not hasattr(s, "_main_dg")
-                and s._uploaded_file_mgr == ctx.uploaded_file_mgr
-            )
-        ):
-            this_session = s
-
-    if this_session is None:
-        raise RuntimeError(
-            "Oh noes. Couldn't get your Streamlit Session object. "
-            "Are you doing something fancy with threads?"
-        )
-
-    # Got the session object! Now let's attach some state into it.
-
-    if not hasattr(this_session, "_custom_session_state"):
-        this_session._custom_session_state = SessionState(**kwargs)
-
-    return this_session._custom_session_state

src/utils.py

@@ -1,34 +1,31 @@
 import base64
+
 import altair as alt
 import pandas as pd
 import streamlit as st
 from PIL import Image
-from stqdm import stqdm
 
 from .configs import SupportedFiles
 
-stqdm.pandas()
-
 
 @st.cache
 def get_logo(path):
     return Image.open(path)
 
 
-# @st.cache(suppress_st_warning=True)
-@st.cache(allow_output_mutation=True)
+@st.experimental_memo
 def read_file(uploaded_file) -> pd.DataFrame:
-
     file_type = uploaded_file.name.split(".")[-1]
-    if file_type in set(i.name for i in SupportedFiles):
-        read_f = SupportedFiles[file_type].value[0]
-        df = read_f(uploaded_file)
-        # remove any NA
-        df = df.dropna()
-        return df
-
-    else:
-        st.error("File type not supported")
+    read_fn = SupportedFiles[file_type].value[0]
+    df = read_fn(uploaded_file)
+    df = df.dropna()
+    return df
+
+
+@st.cache
+def convert_df(df):
+    # IMPORTANT: Cache the conversion to prevent computation on every rerun
+    return df.to_csv(index=False, sep=";").encode("utf-8")
 
 
 def download_button(dataframe: pd.DataFrame, name: str):

src/wordifier.py

@@ -1,17 +1,58 @@
-from typing import List
+from typing import Dict, List, Tuple
+
 import numpy as np
 import pandas as pd
 import streamlit as st
+from pandas.core.frame import DataFrame
+from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.linear_model import LogisticRegression
+from sklearn.preprocessing import LabelEncoder
 from sklearn.utils import resample
-from stqdm import stqdm
 
-from .configs import ModelConfigs
+from .configs import InputTransformConfigs, ModelConfigs
+
+
+def input_transform(
+    text: pd.Series, labels: pd.Series, configs=InputTransformConfigs
+) -> Dict[str, np.ndarray]:
+    """
+    Encodes text in mathematical object ameanable to training algorithm
+    """
+    tfidf_vectorizer = TfidfVectorizer(
+        input="content",  # default: file already in memory
+        encoding="utf-8",  # default
+        decode_error="strict",  # default
+        strip_accents=None,  # do nothing
+        lowercase=False,  # do nothing
+        preprocessor=None,  # do nothing - default
+        tokenizer=None,  # default
+        stop_words=None,  # do nothing
+        analyzer="word",
+        ngram_range=configs.NGRAM_RANGE.value,  # maximum 3-ngrams
+        min_df=configs.MIN_DF.value,
+        max_df=configs.MAX_DF.value,
+        sublinear_tf=configs.SUBLINEAR.value,
+    )
+    label_encoder = LabelEncoder()
+
+    X = tfidf_vectorizer.fit_transform(text.values)
+    y = label_encoder.fit_transform(labels.values)
 
-stqdm.pandas()
+    return {
+        "X": X,
+        "y": y,
+        "X_names": np.array(tfidf_vectorizer.get_feature_names_out()),
+        "y_names": label_encoder.classes_,
+    }
 
 
-def wordifier(X, y, X_names: List[str], y_names: List[str], configs=ModelConfigs):
+def wordifier(
+    X: np.ndarray,
+    y: np.ndarray,
+    X_names: List[str],
+    y_names: List[str],
+    configs=ModelConfigs,
+) -> List[Tuple[str, float, str]]:
 
     n_instances, n_features = X.shape
     n_classes = len(y_names)
@@ -36,70 +77,80 @@ def wordifier(X, y, X_names: List[str], y_names: List[str], configs=ModelConfigs
     pos_scores = np.zeros((n_classes, n_features), dtype=int)
     neg_scores = np.zeros((n_classes, n_features), dtype=int)
 
-    with st.spinner("Wordifying!"):
-
-        for _ in stqdm(range(configs.NUM_ITERS.value)):
-
-            # run randomized regression
-            clf = LogisticRegression(
-                penalty="l1",
-                C=configs.PENALTIES.value[
-                    np.random.randint(len(configs.PENALTIES.value))
-                ],
-                solver="liblinear",
-                multi_class="auto",
-                max_iter=500,
-                class_weight="balanced",
-            )
-
-            # sample indices to subsample matrix
-            selection = resample(
-                np.arange(n_instances), replace=True, stratify=y, n_samples=sample_size
-            )
-
-            # fit
-            try:
-                clf.fit(X[selection], y[selection])
-            except ValueError:
-                continue
-
-            # record coefficients
-            if n_classes == 2:
-                pos_scores[1] = pos_scores[1] + (clf.coef_ > 0.0)
-                neg_scores[1] = neg_scores[1] + (clf.coef_ < 0.0)
-                pos_scores[0] = pos_scores[0] + (clf.coef_ < 0.0)
-                neg_scores[0] = neg_scores[0] + (clf.coef_ > 0.0)
-            else:
-                pos_scores += clf.coef_ > 0
-                neg_scores += clf.coef_ < 0
-
-        # normalize
-        pos_scores = pos_scores / configs.NUM_ITERS.value
-        neg_scores = neg_scores / configs.NUM_ITERS.value
-
-        # get only active features
-        pos_positions = np.where(
-            pos_scores >= configs.SELECTION_THRESHOLD.value, pos_scores, 0
+    pbar = st.progress(0)
+    for i, _ in enumerate(range(configs.NUM_ITERS.value)):
+
+        # run randomized regression
+        clf = LogisticRegression(
+            penalty="l1",
+            C=configs.PENALTIES.value[np.random.randint(len(configs.PENALTIES.value))],
+            solver="liblinear",
+            multi_class="auto",
+            max_iter=500,
+            class_weight="balanced",
         )
-        neg_positions = np.where(
-            neg_scores >= configs.SELECTION_THRESHOLD.value, neg_scores, 0
+
+        # sample indices to subsample matrix
+        selection = resample(
+            np.arange(n_instances), replace=True, stratify=y, n_samples=sample_size
         )
 
-        # prepare DataFrame
-        pos = [
-            (X_names[i], pos_scores[c, i], y_names[c])
-            for c, i in zip(*pos_positions.nonzero())
-        ]
-        neg = [
-            (X_names[i], neg_scores[c, i], y_names[c])
-            for c, i in zip(*neg_positions.nonzero())
-        ]
+        # fit
+        try:
+            clf.fit(X[selection], y[selection])
+        except ValueError:
+            continue
+
+        # record coefficients
+        if n_classes == 2:
+            pos_scores[1] = pos_scores[1] + (clf.coef_ > 0.0)
+            neg_scores[1] = neg_scores[1] + (clf.coef_ < 0.0)
+            pos_scores[0] = pos_scores[0] + (clf.coef_ < 0.0)
+            neg_scores[0] = neg_scores[0] + (clf.coef_ > 0.0)
+        else:
+            pos_scores += clf.coef_ > 0
+            neg_scores += clf.coef_ < 0
+
+        pbar.progress(round(i / configs.NUM_ITERS.value, 1))
+
+    # normalize
+    pos_scores = pos_scores / configs.NUM_ITERS.value
+    neg_scores = neg_scores / configs.NUM_ITERS.value
+
+    # get only active features
+    pos_positions = np.where(
+        pos_scores >= configs.SELECTION_THRESHOLD.value, pos_scores, 0
+    )
+    neg_positions = np.where(
+        neg_scores >= configs.SELECTION_THRESHOLD.value, neg_scores, 0
+    )
+
+    # prepare DataFrame
+    pos = [
+        (X_names[i], pos_scores[c, i], y_names[c])
+        for c, i in zip(*pos_positions.nonzero())
+    ]
+    neg = [
+        (X_names[i], neg_scores[c, i], y_names[c])
+        for c, i in zip(*neg_positions.nonzero())
+    ]
+
+    return pos, neg
 
+
+def output_transform(
+    pos: List[Tuple[str, float, str]], neg: List[Tuple[str, float, str]]
+) -> DataFrame:
     posdf = pd.DataFrame(pos, columns="word score label".split()).sort_values(
         ["label", "score"], ascending=False
     )
+    posdf["correlation"] = "positive"
     negdf = pd.DataFrame(neg, columns="word score label".split()).sort_values(
         ["label", "score"], ascending=False
     )
+    negdf["correlation"] = "negative"
+
+    output = pd.concat([posdf, negdf], ignore_index=False, axis=0)
+    output.columns = output.columns.str.title()
 
-    return posdf, negdf
+    return output