Update app.py

app.py

@@ -57,23 +57,16 @@ def display_sentiment_analysis(vader_score, bert_result):
     sentiment_data = {'Positive': max(0, vader_score), 'Negative': min(0, vader_score), 'Neutral': 1 - abs(vader_score)}
     sentiment_df = pd.DataFrame(list(sentiment_data.items()), columns=["Sentiment", "Score"])
     
-    # Color graphs based on sentiment (if negative, turn red)
-    bar_colors = ['green' if sentiment == 'Positive' else 'red' for sentiment in sentiment_df['Sentiment']]
+    # Set color dynamically based on sentiment
+    bar_colors = ['green' if sentiment == 'Positive' else 'red' if sentiment == 'Negative' else 'gray' for sentiment in sentiment_df['Sentiment']]
     
+    # Display the bar chart
     st.bar_chart(sentiment_df.set_index("Sentiment"), color=bar_colors)
 
     # Generate and display the word cloud
     wordcloud_img = f'data:image/png;base64,{generate_wordcloud(user_input)}'
     st.image(wordcloud_img, use_column_width=True)
 
-    # Explanation of Sentiment Analysis
-    st.write("""
-        - **VADER Sentiment Score**: This is a numerical value that indicates the overall sentiment of the text. 
-        Positive values indicate positive sentiment, negative values indicate negative sentiment, and values close to zero indicate neutral sentiment.
-        - **BERT Sentiment**: This is another model's analysis, where it categorizes the text as 'Positive', 'Negative', or 'Neutral' with a confidence score.
-        - The bar chart visually shows the balance between positive, negative, and neutral sentiments in your text.
-    """)
-
 # Analyze sentiment on button click
 if st.sidebar.button('Analyze Sentiment'):
     if user_input:
@@ -92,26 +85,22 @@ if st.sidebar.button('Analyze Sentiment'):
 # Section for past sentiment trends
 st.subheader("Past Sentiment Trends (Last 14 Days)")
 fig1 = px.line(df, x='Date', y='Sentiment Score', title='Past Sentiment Trends', markers=True, line_shape='spline')
-fig1.update_traces(line_color='red' if df['Sentiment Score'].mean() < 0 else 'green')
 st.plotly_chart(fig1)
 
 # Section for future sentiment predictions
 st.subheader("Sentiment Prediction for Next 7 Days")
 fig2 = px.line(future_df, x='Date', y='Predicted Sentiment', title='Sentiment Prediction for Next 7 Days', markers=True, line_shape='spline')
-fig2.update_traces(line_color='red' if future_df['Predicted Sentiment'].mean() < 0 else 'green')
 st.plotly_chart(fig2)
 
 # Sentiment Distribution Pie Chart
 st.subheader("Sentiment Distribution")
 fig3 = px.pie(values=[sum(df['Sentiment Score'] > 0), sum(df['Sentiment Score'] <= 0)], 
               names=['Positive', 'Negative'], title='Sentiment Distribution', hole=0.3)
-fig3.update_traces(marker=dict(colors=['green', 'red']))
 st.plotly_chart(fig3)
 
 # Histogram of Sentiment Scores (Distribution)
 st.subheader("Sentiment Score Distribution (Past 14 Days)")
 fig4 = px.histogram(df, x='Sentiment Score', nbins=20, title="Sentiment Score Distribution")
-fig4.update_traces(marker_color='red' if df['Sentiment Score'].mean() < 0 else 'green')
 st.plotly_chart(fig4)
 
 # Time-Series Heatmap for Sentiment Over Time
@@ -120,34 +109,19 @@ df['Day'] = df['Date'].dt.dayofweek
 df['Hour'] = df['Date'].dt.hour
 heatmap_data = df.pivot('Day', 'Hour', 'Sentiment Score')
 fig5 = px.imshow(heatmap_data, title="Heatmap of Sentiment Over Time", labels={'x': 'Hour of Day', 'y': 'Day of Week'})
-fig5.update_traces(colorscale='reds' if df['Sentiment Score'].mean() < 0 else 'greens')
 st.plotly_chart(fig5)
 
 # Scatter plot of Sentiment over Time
 st.subheader("Sentiment Scatter Plot (Past 14 Days)")
 fig6 = px.scatter(df, x='Date', y='Sentiment Score', title='Sentiment Over Time')
-fig6.update_traces(marker=dict(color='red' if df['Sentiment Score'].mean() < 0 else 'green'))
 st.plotly_chart(fig6)
 
 # Rolling average of Sentiment (7-day window)
 st.subheader("Rolling Average of Sentiment (7-Day Window)")
 df['Rolling Avg Sentiment'] = df['Sentiment Score'].rolling(window=7).mean()
 fig7 = px.line(df, x='Date', y='Rolling Avg Sentiment', title="Rolling Average of Sentiment (7-Day Window)")
-fig7.update_traces(line_color='red' if df['Rolling Avg Sentiment'].mean() < 0 else 'green')
 st.plotly_chart(fig7)
 
-# Display top comments and posts (Mock Data)
-st.subheader("Top Comments and Posts")
-top_comments = [
-    "I love this! So uplifting!",
-    "This is terrible, I can't believe this happened.",
-    "I'm not sure how I feel about this, it's mixed.",
-    "What a great day, everything is going well!",
-    "This is so frustrating, why does this always happen?"
-]
-for comment in top_comments:
-    st.write(f"- {comment}")
-
 # Reset button to clear inputs and visualizations
 if st.sidebar.button('Reset Analysis'):
     st.experimental_rerun()