Update app.py

app.py

@@ -10,20 +10,16 @@ import plotly.graph_objects as go
 # Set page configuration
 st.set_page_config(layout="wide")
 
+# Function to load and clean data
 def load_and_clean_data():
-    # Load data
     df1 = pd.read_csv("data/reviewed_social_media_english.csv")
     df2 = pd.read_csv("data/reviewed_news_english.csv")
     df3 = pd.read_csv("data/tamil_social_media.csv")  
     df4 = pd.read_csv("data/tamil_news.csv")       
 
-    # Concatenate dataframes
+    # Concatenate dataframes and clean data
     df_combined = pd.concat([df1, df2, df3, df4])
-
-    # Normalize Text
     df_combined['Domain'] = df_combined['Domain'].replace("MUSLIM", "Muslim")
-
-    # Drop irrelevant data
     df_combined = df_combined[df_combined['Domain'] != 'Not relevant']
     df_combined = df_combined[df_combined['Domain'] != 'None']
     df_combined = df_combined[df_combined['Discrimination'] != 'None']
@@ -31,12 +27,8 @@ def load_and_clean_data():
 
     return df_combined
 
-# Load and clean data
 df = load_and_clean_data()
 
-# Page navigation
-page = st.sidebar.selectbox("Choose a page", ["Overview", "Sentiment Analysis", "Discrimination Analysis", "Channel Analysis"])
-
 # Define Sidebar Filters
 domain_options = df['Domain'].unique()
 channel_options = df['Channel'].unique()
@@ -48,53 +40,47 @@ channel_filter = st.sidebar.multiselect('Select Channel', options=channel_option
 sentiment_filter = st.sidebar.multiselect('Select Sentiment', options=sentiment_options, default=sentiment_options)
 discrimination_filter = st.sidebar.multiselect('Select Discrimination', options=discrimination_options, default=discrimination_options)
 
-# Apply the filters to the dataframe
+# Apply filters
 df_filtered = df[(df['Domain'].isin(domain_filter)) & 
                  (df['Channel'].isin(channel_filter)) & 
                  (df['Sentiment'].isin(sentiment_filter)) & 
                  (df['Discrimination'].isin(discrimination_filter))]
 
-
 # Define a color palette for consistent visualization styles
 color_palette = px.colors.sequential.Viridis
 
-# Visualization function
-def create_visualizations(df):
-    # [Existing visualization code]
-    pass
-
 # Page navigation
 page = st.sidebar.selectbox("Choose a page", ["Overview", "Sentiment Analysis", "Discrimination Analysis", "Channel Analysis"])
 
-if page == "Overview":
-    create_visualizations(df)  # Placeholder for overview visualizations
-elif page == "Sentiment Analysis":
-    create_visualizations(df)  # Placeholder for sentiment analysis visualizations
-elif page == "Discrimination Analysis":
-    create_visualizations(df)  # Placeholder for discrimination analysis visualizations
-elif page == "Channel Analysis":
-    create_visualizations(df)  # Placeholder for channel analysis visualizations
-
-# [Place the rest of the code for the visualizations here]
-
-
-# Define a color palette for consistent visualization styles
-color_palette = px.colors.sequential.Viridis
-
-# Function for Domain Distribution Chart
-def create_domain_distribution_chart(df):
-    fig = px.pie(df, names='Domain', title='Distribution of Domains', hole=0.35)
-    fig.update_layout(title_x=0.5, margin=dict(l=20, r=20, t=30, b=20), legend=dict(x=0.1, y=1))
+# Visualisation 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))
     fig.update_traces(marker=dict(colors=color_palette))
     return fig
 
-# Function for Sentiment Distribution Across Domains Chart
+# Visualization for Distribution of Gender versus Ethnicity
+def create_gender_ethnicity_distribution_chart(df):
+    df['GenderOrEthnicity'] = df['Domain'].apply(lambda x: "Gender: Women & LGBTQIA+" if x in ["Women", "LGBTQIA+"] else "Ethnicity")
+    fig = px.pie(df, names='GenderOrEthnicity', title='Distribution of Gender versus Ethnicity', 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))
+    return fig
+
+# Visualization for Sentiment Distribution Across Domains
 def create_sentiment_distribution_chart(df):
-    # ... [Include the existing code for the Sentiment Distribution chart]
-    fig.update_layout(margin=dict(l=20, r=20, t=40, b=20))
+    df['Discrimination'] = df['Discrimination'].replace({"Non Discriminative": "Non-Discriminative"})  # Assuming typo in the original script
+    domain_counts = df.groupby(['Domain', 'Sentiment']).size().reset_index(name='counts')
+    fig = px.bar(domain_counts, x='Domain', y='counts', color='Sentiment', title="Sentiment Distribution Across Domains", barmode='stack')
+    fig.update_layout(margin=dict(l=20, r=20, t=40, b=20), xaxis_title="Domain", yaxis_title="Counts", font=dict(size=12))
     return fig
 
-# ... [Define other chart functions following the same pattern]
+# Visualization for Correlation between Sentiment and Discrimination
+def create_sentiment_discrimination_grouped_chart(df):
+    crosstab_df = pd.crosstab(df['Sentiment'], df['Discrimination']).reset_index()
+    melted_df = pd.melt(crosstab_df, id_vars='Sentiment', value_vars=['Yes', 'No'], var_name='Discrimination', value_name='Count')
+    fig = px.bar(melted_df, x='Sentiment', y='Count', color='Discrimination', barmode='group', title="Sentiment vs. Discrimination")
+    fig.update_layout(margin=dict(l=20, r=20, t=40, b=20), xaxis_title="Sentiment", yaxis_title="Count", font=dict(size=12))
+    return fig
 
 # Function for Channel-wise Sentiment Over Time Chart
 def create_channel_sentiment_over_time_chart(df):
@@ -111,20 +97,40 @@ def create_channel_discrimination_chart(df):
     fig.update_layout(title='Channel-wise Distribution of Discriminative Content', margin=dict(l=20, r=20, t=40, b=20))
     return fig
 
-# Dashboard Layout
-def render_dashboard():
-    # Overview page layout
+def render_dashboard(page, df_filtered):
     if page == "Overview":
-        st.header("Overview of Domains and Sentiments")
+        st.title("Overview Dashboard")
+        # Create 2x2 grid for overview visualizations
         col1, col2 = st.beta_columns(2)
         with col1:
-            st.plotly_chart(create_domain_distribution_chart(df))
+            st.plotly_chart(create_pie_chart(df_filtered, 'Domain', 'Distribution of Domains'))
         with col2:
-            st.plotly_chart(create_sentiment_distribution_chart(df))
-        # ... [Additional overview charts]
-
-    # ... [Other pages]
-
+            st.plotly_chart(create_gender_ethnicity_distribution_chart(df_filtered))
+
+        col3, col4 = st.beta_columns(2)
+        with col3:
+            st.plotly_chart(create_sentiment_distribution_chart(df_filtered))
+        with col4:
+            st.plotly_chart(create_sentiment_discrimination_grouped_chart(df_filtered))
+
+    elif page == "Sentiment Analysis":
+        st.title("Sentiment Analysis Dashboard")
+        # Implementation for the "Sentiment Analysis" page...
+        # Example: st.plotly_chart(create_some_other_chart(df_filtered))
+
+    elif page == "Discrimination Analysis":
+        st.title("Discrimination Analysis Dashboard")
+        # Implementation for the "Discrimination Analysis" page...
+        # Example: st.plotly_chart(create_another_chart(df_filtered))
+
+    elif page == "Channel Analysis":
+        st.title("Channel Analysis Dashboard")
+        # Create visualizations for the channel analysis page
+        col1, col2 = st.columns(2)
+        with col1:
+            st.plotly_chart(create_channel_sentiment_over_time_chart(df_filtered))
+        with col2:
+            st.plotly_chart(create_channel_discrimination_chart(df_filtered))
 
 # Render the dashboard with filtered data
-render_dashboard(df_filtered)
+render_dashboard(page, df_filtered)