Update app.py

app.py

@@ -8,100 +8,59 @@ import torch
 tokenizer = T5Tokenizer.from_pretrained("UBC-NLP/araT5-base")
 model = T5ForConditionalGeneration.from_pretrained("UBC-NLP/araT5-base")
 
-# Emotion classification pipeline (updated model for Arabic emotion classification)
+# Emotion classification pipeline
 emotion_classifier = pipeline("text-classification", model="aubmindlab/bert-base-arabertv2")
 
 # Function to get embeddings from ARAT5 for topic modeling
 def generate_embeddings(texts):
-    # Tokenize the Arabic text for ARAT5
     inputs = tokenizer(texts, return_tensors="pt", padding=True, truncation=True, max_length=512)
     with torch.no_grad():
-        # Use ARAT5 to generate embeddings
         outputs = model.encoder(input_ids=inputs['input_ids'])
-    # Extract the embeddings (mean of hidden states for simplicity)
-    return outputs.last_hidden_state.mean(dim=1).numpy()
+    embeddings = outputs[0].mean(dim=1).numpy()
+    return embeddings
 
-# Function to process the CSV file and return emotion and topic model
+# Function to process the CSV or Excel file
 def process_file(uploaded_file):
-    # Load CSV
-    df = pd.read_csv(uploaded_file)
-    
-    # Display basic info about the CSV
-    st.write("CSV Loaded Successfully!")
-    st.write(f"Data Preview: {df.head()}")
+    # Determine the file type
+    if uploaded_file.name.endswith(".csv"):
+        df = pd.read_csv(uploaded_file)
+    elif uploaded_file.name.endswith(".xlsx"):
+        df = pd.read_excel(uploaded_file)
+    else:
+        st.error("Unsupported file format.")
+        return None
+
+    # Validate required columns
+    required_columns = ['date', 'poem']
+    missing_columns = [col for col in required_columns if col not in df.columns]
+    if missing_columns:
+        st.error(f"Missing columns: {', '.join(missing_columns)}")
+        return None
     
-    # Ensure 'date' column is in datetime format and extract the year
-    df['date'] = pd.to_datetime(df['date'], errors='coerce')  # Replace 'date' with your actual column name
+    # Process the file
+    df['date'] = pd.to_datetime(df['date'], errors='coerce')
+    df = df.dropna(subset=['date'])
     df['year'] = df['date'].dt.year
     
-    # Modify this to use the 'poem' column that contains the Arabic poems
-    texts = df['poem'].dropna().tolist()  # Replace 'poem' with your actual column name
-    
-    # Emotion Classification: Classify emotions for each poem (Arabic)
+    texts = df['poem'].dropna().tolist()
     emotions = [emotion_classifier(text)[0]['label'] for text in texts]
     df['emotion'] = emotions
     
-    # Topic Modeling using ARAT5 embeddings
     embeddings = generate_embeddings(texts)
     topic_model = BERTopic()
     topics, _ = topic_model.fit_transform(embeddings)
     df['topic'] = topics
-    
-    # Return the processed dataframe
     return df
 
 # Streamlit App
-st.title("Arabic Poem Topic Modeling & Emotion Classification with ARAT5")
-st.write("Upload a CSV file to perform topic modeling and emotion classification on Arabic poems.")
-
-# File upload widget
-uploaded_file = st.file_uploader("Choose a CSV file", type=["csv"])
+st.title("Arabic Poem Topic Modeling & Emotion Classification")
+uploaded_file = st.file_uploader("Choose a file", type=["csv", "xlsx"])
 
-# If file is uploaded, process and display results
 if uploaded_file is not None:
-    result_df = process_file(uploaded_file)
-
-    # Show date selection widgets
-    st.write("### Filter by Date Range")
-    start_date = st.date_input("Start Date", value=pd.to_datetime(result_df['date'].min()))
-    end_date = st.date_input("End Date", value=pd.to_datetime(result_df['date'].max()))
-    
-    # Filter data based on selected date range
-    filtered_df = result_df[(result_df['date'] >= start_date) & (result_df['date'] <= end_date)]
-    
-    # Display filtered data
-    st.write(f"Filtered Data (Poems from {start_date} to {end_date}):")
-    st.write(filtered_df[['poet_name', 'era', 'poem', 'emotion', 'topic', 'date']])
-
-    # Create buttons to show different summaries
-    summary_type = st.radio("Select Summary Type:", 
-                            ("Emotion and Topic Summary by Date Range", 
-                             "Global Emotion and Topic Summary"))
-
-    # Display the selected summary
-    if summary_type == "Emotion and Topic Summary by Date Range":
-        st.write("Emotion and Topic Summary for Selected Date Range:")
-        
-        # Emotion Distribution in Date Range
-        emotion_counts = filtered_df['emotion'].value_counts()
-        st.write("Emotion Counts in Date Range:")
-        st.write(emotion_counts)
-        
-        # Topic Distribution in Date Range
-        topic_counts = filtered_df['topic'].value_counts()
-        st.write("Topic Counts in Date Range:")
-        st.write(topic_counts)
-        
-        # Visualize emotion distribution over the selected range (optional)
-        st.bar_chart(emotion_counts, use_container_width=True)
-        
-        # Visualize topic distribution over the selected range (optional)
-        st.bar_chart(topic_counts, use_container_width=True)
-
-    elif summary_type == "Global Emotion and Topic Summary":
-        st.write("Global Emotion and Topic Summary (All Poems):")
-        global_emotion_count = result_df['emotion'].value_counts().to_dict()
-        global_topic_count = result_df['topic'].value_counts().to_dict()
-        
-        st.write(f"Emotion Distribution: {global_emotion_count}")
-        st.write(f"Topic Distribution: {global_topic_count}")
+    try:
+        result_df = process_file(uploaded_file)
+        if result_df is not None:
+            st.write("Data successfully processed!")
+            st.write(result_df.head())
+    except Exception as e:
+        st.error(f"Error: {e}")