Update app.py

app.py

@@ -36,7 +36,6 @@ def load_and_clean_data():
 
 df = load_and_clean_data()
 
-
 # Page navigation setup
 page_names = ["Dashboard for GESI Conversation in Sri Lanka", "GESI Overview", "Sentiment Analysis", "Discrimination Analysis", "Channel Analysis"]
 page = st.sidebar.selectbox("Choose a page", page_names)
@@ -63,49 +62,49 @@ color_palette = px.colors.sequential.Viridis
 
 # Function to render the model prediction visualization page
 def render_prediction_page():
-  st.title("Dashboard for GESI Conversations in Sri Lanka")
-  st.write("""
-  Instant Analysis: Enter any text snippet and get immediate predictions from out model train on English, Sinhala and Tamil based languages \n\n
-  Domain Identification: Discover the subject matter of your text with a quantifiable domain score. """)
-  
-  # User input text area
-  user_input = st.text_are("Enter Text/Content here to analyze", height=150)
-  
-  if st.button("Perfrom contextual Analysis"):
-    # Use run_pipeline to get predictions
-    predictions = run_pipeline(user_input)
-    
-    # Extract prediction details
-    domain_label = prediction.get("domain_label", "Unknown")
-    domain_score = prediction.get("domain_socre", 0)
-    discrimination_label = prediction.get("discrimination_label", "Unknown")
-    discrimination_score = prediction.get("discrimination_score", 0)
+    st.title("Dashboard for GESI Conversations in Sri Lanka")
+    st.write("""
+    Instant Analysis: Enter any text snippet and get immediate predictions from our model trained on English, Sinhala, and Tamil languages.\n\n
+    Domain Identification: Discover the subject matter of your text with a quantifiable domain score.
+    """)
     
-    # Visualization layout
-    col1, col2 = st.columns(2)
+    # User input text area
+    user_input = st.text_area("Enter Text/Content here to analyze", height=150)
     
-    with col1:
-      st.markdown("#### Domain Label")
-      st.markdown(f"## {domain_label}")
-      st.progress(domain_score)
-      
-    with col2:
-      st.makrdown("#### Discrimination Label")
-      st.markdown(f"## {discrimination_label}")
-      st.progress(domain_score)
-      
-    col3, col4 = st.columns(2)
-    
-    with col3:
-      # Display Domain Score in Bold
-      st.markdown(f'**Domain Score: {domain_score:.2f}**', unsafe_allow_html=True)
-      
-    with col4:
-      # Display Discrimination Score in Bold
-      st.markdown(f'**Discrimination Score: {discrimination_score:.2f}**', unsafe_allow_html=True)
-      
-      
-# Visualisation for Domain Distribution
+    if st.button("Perform Contextual Analysis"):
+        # Use run_pipeline to get predictions
+        predictions = run_pipeline(user_input)
+        
+        # Extract prediction details
+        domain_label = predictions.get("domain_label", "Unknown")
+        domain_score = predictions.get("domain_score", 0)
+        discrimination_label = predictions.get("discrimination_label", "Unknown")
+        discrimination_score = predictions.get("discrimination_score", 0)
+        
+        # Visualization layout
+        col1, col2 = st.columns(2)
+        
+        with col1:
+            st.markdown("#### Domain Label")
+            st.markdown(f"## {domain_label}")
+            st.progress(domain_score)
+            
+        with col2:
+            st.markdown("#### Discrimination Label")
+            st.markdown(f"## {discrimination_label}")
+            st.progress(discrimination_score)
+            
+        col3, col4 = st.columns(2)
+        
+        with col3:
+            # Display Domain Score in Bold
+            st.markdown(f'**Domain Score: {domain_score:.2f}**', unsafe_allow_html=True)
+            
+        with col4:
+            # Display Discrimination Score in Bold
+            st.markdown(f'**Discrimination Score: {discrimination_score:.2f}**', unsafe_allow_html=True)
+
+# Visualization for Domain Distribution
 def create_pie_chart(df, column, title):
     fig = px.pie(df, names=column, title=title, hole=0.35)
     fig.update_layout(margin=dict(l=20, r=20, t=30, b=20), legend=dict(x=0.1, y=1), font=dict(size=12))
@@ -132,16 +131,15 @@ def create_sentiment_distribution_chart(df):
     fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Domain", yaxis_title="Counts", font=dict(size=10))
     return fig
 
-
 # Visualization for Correlation between Sentiment and Discrimination
 def create_sentiment_discrimination_grouped_chart(df):
     # Creating a crosstab of 'Sentiment' and 'Discrimination'
     crosstab_df = pd.crosstab(df['Sentiment'], df['Discrimination'])
 
-    # Check if 'Yes' and 'No' are in the columns after the crosstab operation
+    # Check if 'Discriminative' and 'Non Discriminative' are in the columns after the crosstab operation
     value_vars = crosstab_df.columns.intersection(['Discriminative', 'Non Discriminative']).tolist()
 
-    # If 'No' is not in columns, it will not be included in melting
+    # If 'Non Discriminative' is not in columns, it will not be included in melting
     melted_df = pd.melt(crosstab_df.reset_index(), id_vars='Sentiment', value_vars=value_vars, var_name='Discrimination', value_name='Count')
 
     # Proceeding to plot only if we have data to plot
@@ -152,8 +150,6 @@ def create_sentiment_discrimination_grouped_chart(df):
     else:
         return "No data to display for the selected filters."
 
-
-
 # Function for Top Domains with Negative Sentiment Chart
 def create_top_negative_sentiment_domains_chart(df):
     domain_counts = df.groupby(['Domain', 'Sentiment']).size().unstack(fill_value=0)
@@ -164,7 +160,7 @@ def create_top_negative_sentiment_domains_chart(df):
     colors = ['limegreen', 'crimson', 'darkcyan']
     fig = px.bar(domain_counts_subset, x='Count', y='Domain', title='Top Domains with Negative Sentiment', color='Domain',
                  orientation='h', color_discrete_sequence=colors)
-    fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Negative sentiment content Count", yaxis_title="Domain", font=dict(size=10))
+    fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Negative Sentiment Content Count", yaxis_title="Domain", font=dict(size=10))
     return fig
 
 # Function for Key Phrases in Negative Sentiment Content Chart
@@ -174,7 +170,7 @@ def create_key_phrases_negative_sentiment_chart(df):
     count_values = trigrams.toarray().sum(axis=0)
     ngram_freq = pd.DataFrame(sorted([(count_values[i], k) for k, i in cv.vocabulary_.items()], reverse=True))
     ngram_freq.columns = ['frequency', 'ngram']
-    fig = px.bar(ngram_freq.head(10), x='frequency', y='ngram', orientation='h', title='Key phrases in Negative Sentiment Content')
+    fig = px.bar(ngram_freq.head(10), x='frequency', y='ngram', orientation='h', title='Key Phrases in Negative Sentiment Content')
     fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Frequency", yaxis_title="Trigram", font=dict(size=10))
     return fig
 
@@ -195,14 +191,13 @@ def create_key_phrases_positive_sentiment_chart(df):
     ngram_freq.columns = ['frequency', 'ngram']
 
     # Create the bar chart
-    fig = px.bar(ngram_freq.head(10), x='frequency', y='ngram', orientation='h', title='Key phrases in Positive Sentiment Content')
+    fig = px.bar(ngram_freq.head(10), x='frequency', y='ngram', orientation='h', title='Key Phrases in Positive Sentiment Content')
 
     # Update layout settings
     fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Frequency", yaxis_title="Trigram", font=dict(size=10))
 
     return fig
 
-
 # Function for Prevalence of Discriminatory Content Chart
 def create_prevalence_discriminatory_content_chart(df):
     domain_counts = df.groupby(['Domain', 'Discrimination']).size().unstack(fill_value=0)
@@ -226,7 +221,7 @@ def create_top_discriminatory_domains_chart(df):
 def create_sentiment_distribution_by_channel_chart(df):
     sentiment_by_channel = df.groupby(['Channel', 'Sentiment']).size().reset_index(name='counts')
     color_map = {'Positive': 'blue', 'Neutral': 'lightblue', 'Negative': 'red'}
-    fig = px.bar(sentiment_by_channel, x='Channel', y='counts', color='Sentiment', title="Sentiment Distribution by Channel", barmode='group', color_discret>
+    fig = px.bar(sentiment_by_channel, x='Channel', y='counts', color='Sentiment', title="Sentiment Distribution by Channel", barmode='group', color_discrete_map=color_map)
     fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Channel", yaxis_title="Counts", font=dict(size=10), title_x=0.5)
     return fig
 
@@ -237,13 +232,12 @@ def create_channel_discrimination_chart(df):
     fig.update_layout(title='Channel-wise Distribution of Discriminative Content', margin=dict(l=20, r=20, t=50, b=20), font=dict(size=10), title_x=0.5)
     return fig
 
-
 # Function for rendering dashboard
 def render_dashboard(page, df_filtered):
     if page == "Dashboard for GESI Conversations in Sri Lanka":
         render_prediction_page()
     elif page == "GESI Overview":
-        st.title(" GESI Overview Dashboard")
+        st.title("GESI Overview Dashboard")
         col1, col2 = st.columns(2)
         with col1:
             st.plotly_chart(create_pie_chart(df_filtered, 'Domain', 'Distribution of Domains'))
@@ -290,6 +284,5 @@ def render_dashboard(page, df_filtered):
         with col2:
             st.plotly_chart(create_channel_discrimination_chart(df_filtered))
 
-
 # Render the selected dashboard page
 render_dashboard(page, df_filtered)