Update app.py

app.py

@@ -42,56 +42,48 @@ def sentiment_analysis(sentence, model_name):
     translated_tokens = model.generate(
          **tokenizer(sentences, return_tensors="pt", padding=True)
     )
-    # for t in translated:
-    # print( tokenizer.decode(t, skip_special_tokens=True) )
-   
-    # output = [sentence ['translation_text'] for sentence in tokenizer.decode(translated_tokens, skip_special_tokens=True)]
-    output = []
+    sentences_list = []
     for t in translated_tokens:
-        output.append(tokenizer.decode(t, skip_special_tokens=True))
+        sentences_list.append(tokenizer.decode(t, skip_special_tokens=True))
 
-        
-    
-    # testdata = []
-    # for i,sentence in enumerate(sentences):
-    #     testdata.append(InputExample(guid=i,text_a=sentence,label=0))
+    testdata = []
+    for i,sentence in enumerate(sentences_list):
+        testdata.append(InputExample(guid=i,text_a=sentence,label=0))
 
-    # plm, tokenizer, model_config, WrapperClass = load_plm(type_dic[model_name], model_name)
+    plm, tokenizer, model_config, WrapperClass = load_plm(type_dic[model_name], model_name)
 
-    # promptTemplate = ManualTemplate(
-    #     text = template,
-    #     tokenizer = tokenizer,
-    # )
-    # promptVerbalizer = ManualVerbalizer(
-    #     classes = classes,
-    #     label_words = label_words,
-    #     tokenizer = tokenizer,
-    # )
-    # test_dataloader = PromptDataLoader(
-    #     dataset = testdata,
-    #     tokenizer = tokenizer, 
-    #     template = promptTemplate, 
-    #     tokenizer_wrapper_class = WrapperClass,
-    #     batch_size = 4,
-    #     max_seq_length = 512,
-    # )
-    # prompt_model = PromptForClassification(
-    #     plm=plm,
-    #     template=promptTemplate, 
-    #     verbalizer=promptVerbalizer, 
-    #     freeze_plm=True
-    # )
-    # result = []
-    # for step, inputs in enumerate(test_dataloader):
-    #     logits = prompt_model(inputs)
-    #     result.extend(torch.argmax(logits, dim=-1))
-    # output = '\n'.join([classes[i] for i in result])
+    promptTemplate = ManualTemplate(
+        text = template,
+        tokenizer = tokenizer,
+    )
+    promptVerbalizer = ManualVerbalizer(
+        classes = classes,
+        label_words = label_words,
+        tokenizer = tokenizer,
+    )
+    test_dataloader = PromptDataLoader(
+        dataset = testdata,
+        tokenizer = tokenizer, 
+        template = promptTemplate, 
+        tokenizer_wrapper_class = WrapperClass,
+        batch_size = 4,
+        max_seq_length = 512,
+    )
+    prompt_model = PromptForClassification(
+        plm=plm,
+        template=promptTemplate, 
+        verbalizer=promptVerbalizer, 
+        freeze_plm=True
+    )
+    result = []
+    for step, inputs in enumerate(test_dataloader):
+        logits = prompt_model(inputs)
+        result.extend(torch.argmax(logits, dim=-1))
+    output = '\n'.join([classes[i] for i in result])
     return str(output)
 
 
 
-
-
 demo = gr.Interface(fn=sentiment_analysis,
                     inputs = [gr.Textbox(placeholder="Enter sentence here. If you have multiple sentences, separate them with '\\n'.",label="Sentence",lines=5),
                             gr.Radio(choices=["RoBERTa_Chinese_AnnualReport_tuned","RoBERTa_Chinese_Financial_News_tuned","RoBERTa_English_AnnualReport_tuned",