Update app.py

app.py

@@ -1,9 +1,65 @@
 import numpy as np
 import gradio as gr
+from huggingface_hub import login
+login(token="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")
+
+dict_ = {
+    0: "negative",
+    1: "positive",
+    2: "neutral"}
+path_sent = "/content/drive/MyDrive/company-review-analysis-model/sentiment_checkpoint"
+tokenizer_sent = AutoTokenizer.from_pretrained(path_sent, use_fast=False)
+model_sent = AutoModelForSequenceClassification.from_pretrained(path_sent, num_labels=3).to(device)
+def cvt2cls(data):
+    data = list(set(data))
+    try: 
+        data.remove(20)
+    except:
+        pass
+    for i, num in enumerate(data):
+        if num == 20:
+            continue
+        if num>=10:
+            data[i] -= 10
+    return data
+ner_tags = {0: 'B-chỗ để xe', 1: 'B-con người', 2: 'B-công việc', 3: 'B-cơ sở vật chất', 4: 'B-dự án', 5: 'B-lương', 6: 'B-môi trường làm việc', 7: 'B-ot/thời gian', 8: 'B-văn phòng', 9: 'B-đãi ngộ', 10: 'I-chỗ để xe', 11: 'I-con người', 12: 'I-công việc', 13: 'I-cơ sở vật chất', 14: 'I-dự án', 15: 'I-lương', 16: 'I-môi trường làm việc', 17: 'I-ot/thời gian', 18: 'I-văn phòng', 19: 'I-đãi ngộ', 20: 'O'}
+topic_tags = {0: 'chỗ để xe', 1: 'con người', 2: 'công việc', 3: 'cơ sở vật chất', 4: 'dự án', 5: 'lương', 6: 'môi trường làm việc', 7: 'ot/thời gian', 8: 'văn phòng', 9: 'đãi ngộ'}
+path_topic = "/content/drive/MyDrive/company-review-analysis-model/topic_checkpoint"
+num_labels = 20
+config = RobertaConfig.from_pretrained(path_topic, num_labels=num_labels)
+tokenizer_topic = AutoTokenizer.from_pretrained(path_topic, use_fast=False) 
+model_topic = PhoBertLstmCrf.from_pretrained(path_topic, config=config, from_tf=False).to(device)
+model_topic.resize_token_embeddings(len(tokenizer_topic)) 
+
+
+def review_company(sent: str):
+    try:
+        sent = normalize(text=sent) # segment input sentence, maybe raise ConnectionError: HTTPConnectionPool())
+    except:
+        pass
+    input_sent = torch.tensor([tokenizer_sent.encode(sent)]).to(device)
+    with torch.no_grad():
+        out_sent = model_sent(input_sent)
+        logits_sent = out_sent.logits.softmax(dim=-1).tolist()[0]
+        pred_sent = dict_[np.argmax(logits_sent)]
+
+    try:
+        sent = replace_all(text=sent) # segment input sentence, maybe raise ConnectionError: HTTPConnectionPool())
+    except:
+        pass
+    sent_segment = rdrsegmenter.tokenize(sent)
+    dump = [[i, 'O'] for s in sent_segment for i in s]
+    dump_set = NerDataset(feature_for_phobert([dump], tokenizer=tokenizer_topic, use_crf=True))    
+    dump_iter = DataLoader(dump_set, batch_size=1)
+    with torch.no_grad():
+        for idx, batch in enumerate(dump_iter):
+            batch = { k:v.to(device) for k, v in batch.items() }        
+            outputs = model_topic(**batch)
+    return list(set([topic_tags[i] for i in cvt2cls(outputs["tags"][0])]))
+
+    return pred_sent
 
 
-def flip_text(x):
-    return x[::-1]
 
 
 def flip_image(x):
@@ -11,8 +67,8 @@ def flip_image(x):
 
 
 with gr.Blocks() as demo:
-    gr.Markdown("Flip text or image files using this demo.")
-    with gr.Tab("Flip Text"):
+    gr.Markdown("Demo projects Review Company and Resume parser phase 1.")
+    with gr.Tab("Review Company"):
         text_input = gr.Textbox()
         text_output = gr.Textbox()
         text_button = gr.Button("Flip")