Add application file

app.py

@@ -0,0 +1,84 @@
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+# import torch
+# device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
+# device
+
+
+
+download = False
+save_model_locally= False
+if download:
+    tokenizer = AutoTokenizer.from_pretrained("MilaNLProc/feel-it-italian-sentiment", cache_dir="data/")
+    model = AutoModelForSequenceClassification.from_pretrained("MilaNLProc/feel-it-italian-sentiment", cache_dir="data/")
+    model.eval()
+    tokenizer_emo = AutoTokenizer.from_pretrained("MilaNLProc/feel-it-italian-emotion", cache_dir="data/")
+    model_emo = AutoModelForSequenceClassification.from_pretrained("MilaNLProc/feel-it-italian-emotion", cache_dir="data/")
+    model_emo.eval()
+    if save_model_locally:
+        model.save_pretrained('./local_models/sentiment_ITA')
+        tokenizer.save_pretrained('./local_models/sentiment_ITA')
+        model_emo.save_pretrained('./local_models/emotion_ITA')
+        tokenizer_emo.save_pretrained('./local_models/emotion_ITA')
+else:
+    tokenizer = AutoTokenizer.from_pretrained("./local_models/sentiment_ITA/")
+    model = AutoModelForSequenceClassification.from_pretrained("./local_models/sentiment_ITA/", num_labels=2)
+    model.eval()
+
+    tokenizer_emo = AutoTokenizer.from_pretrained("./local_models/emotion_ITA/")
+    model_emo = AutoModelForSequenceClassification.from_pretrained("./local_models/emotion_ITA/", num_labels=4)
+    model_emo.eval()
+
+
+#%%
+
+from transformers import pipeline
+import re
+
+generator = pipeline(task="text-classification", model=model, tokenizer=tokenizer, return_all_scores =True)
+generator_emo = pipeline(task="text-classification", model=model_emo, tokenizer=tokenizer_emo, return_all_scores =True)
+
+def sentiment_emoji(input_abs):
+
+    if(input_abs ==""):
+        return "🤷‍♂️"
+        
+    res = generator(input_abs)[0]
+    res = {res[x]["label"]: res[x]["score"] for x in range(len(res))}
+    res["🙂 positive"] = res.pop("positive")
+    res["🙁 negative"] = res.pop("negative")
+    return res
+
+
+def emotion_emoji(input_abs):
+    if(input_abs ==""):
+        return "🤷‍♂️"
+
+    res = generator_emo(input_abs)[0]
+    res = {res[x]["label"]: res[x]["score"] for x in range(len(res))}
+    res["😃 joy"] = res.pop("joy")
+    res["😡 anger"] = res.pop("anger")
+    res["😨 fear"] = res.pop("fear")
+    res["😟 sadness"] = res.pop("sadness")
+   
+    return res
+#%%
+
+import gradio as gr
+demo = gr.Blocks()
+with demo:
+   gr.Markdown("# Analisi sentimento/emozioni del testo italiano")
+   with gr.Row():
+      with gr.Column():
+         text_input = gr.Textbox(placeholder="Scrivi qui")
+         button_1 = gr.Button("Invia")
+      with gr.Column():
+         label_sem = gr.Label()
+         label_emo = gr.Label()
+      #   gr.Interface(fn=emotion_emoji, inputs=text_input, outputs="label")
+   button_1.click(sentiment_emoji, inputs=text_input, outputs=label_sem, api_name="sentiment")
+   button_1.click(emotion_emoji, inputs=text_input, outputs=label_emo, api_name="emotion")
+            
+
+demo.launch(share=True)
+print("Running is terminated")

local_models/emotion_ITA/config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "MilaNLProc/feel-it-italian-emotion",
+  "architectures": [
+    "CamembertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "anger",
+    "1": "fear",
+    "2": "joy",
+    "3": "sadness"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anger": 0,
+    "fear": 1,
+    "joy": 2,
+    "sadness": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

local_models/emotion_ITA/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b685808afcf75d3a459b98c0a19da2d468633a0960a171f4f6ba5652f097ce8
+size 442570677

local_models/emotion_ITA/special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

local_models/emotion_ITA/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

local_models/sentiment_ITA/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "MilaNLProc/feel-it-italian-sentiment",
+  "architectures": [
+    "CamembertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

local_models/sentiment_ITA/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c0f2cec262c7b31b727b242e786d4743bc09fb26652324e0b7f84e5f520bfc2
+size 442564533

local_models/sentiment_ITA/special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

local_models/sentiment_ITA/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}