Update app.py

app.py

@@ -2,12 +2,8 @@ import requests
 import streamlit as st
 import PyPDF2
 import torch
-import joblib
-import tensorflow as tf
 from transformers import AutoTokenizer, LEDForConditionalGeneration
-from tensorflow.keras.models import load_model
-from transformers import TFBertForSequenceClassification, BertTokenizer
-st.set_page_config(page_title="Summarization&tweet_analysis", page_icon="📈",layout="wide")
+st.set_page_config(page_title="Summarization", page_icon="📈",layout="wide")
 hide_streamlit_style = """
             <style>
             #MainMenu {visibility: hidden;}
@@ -63,7 +59,7 @@ def add_bg_from_local(image_file):
 #add_bg_from_local(background_image)  
 
 #@st.cache
-st.header('Summarization & tweet_analysis')
+st.header('Summarization')
 def convert_df(df):
                 # IMPORTANT: Cache the conversion to prevent computation on every rerun
                 return df.to_csv(index=False).encode('utf-8')  
@@ -73,9 +69,9 @@ result_csv_batch_sql = result_csv_batch_fail=result_csv_batch=result_csv4=result
 with col1:
     models = st.selectbox(
     'Select the option',
-    ('summarization_model1','tweet_analysis' ))
+    ('model1', ))
     #try: 
-    if models == 'summarization_model1':   
+    if models == 'model1':   
         st.markdown("")
     else:
          st.markdown("")
@@ -92,92 +88,26 @@ with col1:
         st.markdown(hide_label, unsafe_allow_html=True)            
         submitted = st.form_submit_button("Submit")
         if submitted:
-            if models == 'summarization_model1': 
-                #torch.cuda.set_device(2)
-                tokenizer = AutoTokenizer.from_pretrained('allenai/PRIMERA-multinews')
-                model = LEDForConditionalGeneration.from_pretrained('allenai/PRIMERA-multinews')
-                #device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # get the device
-                device = "cpu"
-                model.to(device) # move the model to the device  
-                documents = text_data
-    
-                # Tokenize and encode the documents
-                inputs = tokenizer(documents, return_tensors='pt', padding=True, truncation=True,max_length=1000000)
-    
-                # Move the inputs to the device
-                inputs = inputs.to(device)
-    
-                # Generate summaries
-                outputs = model.generate(**inputs,max_length=1000000)
-    
-                # Decode the summaries
-                st.write(tokenizer.batch_decode(outputs, skip_special_tokens=True))                          
-                st.success('Prediction done successfully!', icon="✅")  
-            else:
-                    # Define the custom objects (custom layers) needed for loading the model
-                    custom_objects = {"TFBertForSequenceClassification": TFBertForSequenceClassification}
-                    
-                    # Load the best model checkpoint
-                    best_model = load_model('best_model_checkpoint_val_acc_0.8697_epoch_03.h5', custom_objects=custom_objects)
+            #torch.cuda.set_device(2)
+            tokenizer = AutoTokenizer.from_pretrained('allenai/PRIMERA-multinews')
+            model = LEDForConditionalGeneration.from_pretrained('allenai/PRIMERA-multinews')
+            #device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # get the device
+            device = "cpu"
+            model.to(device) # move the model to the device  
+            documents = text_data
 
-                    # Assuming you already have the test set DataFrame (df_test) and tokenizer
-                    tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-                    test_encodings = tokenizer(text_data, padding=True, truncation=True, return_tensors='tf')
-                    test_dataset = tf.data.Dataset.from_tensor_slices((dict(test_encodings)))
+            # Tokenize and encode the documents
+            inputs = tokenizer(documents, return_tensors='pt', padding=True, truncation=True,max_length=1000000)
 
-                    # Make predictions on the test set using the loaded model
-                    predictions_probabilities = best_model.predict(test_dataset.batch(8))
+            # Move the inputs to the device
+            inputs = inputs.to(device)
 
-                    # Convert probabilities to one-hot encoded predictions
-                    predictions_onehot = np.eye(9)[np.argmax(predictions_probabilities, axis=1)]
+            # Generate summaries
+            outputs = model.generate(**inputs,max_length=1000000)
 
-                    # Display or save the DataFrame with predicted labels
-                    index_arg = np.argmax(predictions_probabilities, axis=1)
-                    # Later, you can load the LabelEncoder
-                    label_encoder = joblib.load('label_encoder.joblib')
-                    result_label = label_encoder.inverse_transform(index_arg)
-
-                    # Display or save the DataFrame with predicted labels
-                    st.write("Item name: ", result_label[0])
-                    
-                    from transformers import AutoTokenizer, AutoConfig, AutoModelForSequenceClassification
-                    from scipy.special import softmax
-
-                    MODEL = f"cardiffnlp/twitter-roberta-base-sentiment-latest"
-                    tokenizer = AutoTokenizer.from_pretrained(MODEL)
-                    config = AutoConfig.from_pretrained(MODEL)
-                    # PT
-                    model = AutoModelForSequenceClassification.from_pretrained(MODEL)
-                    #model.save_pretrained(MODEL)
-                    #text = "Covid cases are increasing fast!"
-                    pred_label = []
-                    pred_scor = []
-                    def preprocess(text):
-                        new_text = []
-                        for t in text.split(" "):
-                            t = '@user' if t.startswith('@') and len(t) > 1 else t
-                            t = 'http' if t.startswith('http') else t
-                            new_text.append(t)
-                        return " ".join(new_text)
-                    def predict_pret(text):
-                        #print(text)
-                        text = preprocess(text)
-                        encoded_input = tokenizer(text, return_tensors='pt')
-                        output = model(**encoded_input)
-                        scores = output[0][0].detach().numpy()
-                        scores = softmax(scores)
-
-                        ranking = np.argsort(scores)
-                        ranking = ranking[::-1]
-                        l = config.id2label[ranking[0]]
-                        s = scores[ranking[0]]
-                        return l,s
-
-                    l,s = predict_pret(text_data)
-
-                    st.write("Sentiment is: ", l)
-
-                    st.success('Prediction done successfully!', icon="✅")                 
+            # Decode the summaries
+            st.write(tokenizer.batch_decode(outputs, skip_special_tokens=True))                          
+            st.success('Prediction done successfully!', icon="✅")  
         _='''
         except Exception as e:
             if 'NoneType' or 'not defined' in str(e):