Update app.py

app.py

@@ -36,7 +36,7 @@ df = load_and_clean_data()
 
 
 # Page navigation setup
-page_names = ["Overview", "Sentiment Analysis", "Discrimination Analysis", "Channel Analysis"]
+page_names = [" GESI Overview", "Sentiment Analysis", "Discrimination Analysis", "Channel Analysis"]
 page = st.sidebar.selectbox("Choose a page", page_names)
 
 # Sidebar Filters
@@ -63,7 +63,7 @@ color_palette = px.colors.sequential.Viridis
 # 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=10, r=10, t=20, b=10), legend=dict(x=0.1, y=1), font=dict(size=10))
+    fig.update_layout(margin=dict(l=6, r=6, t=12, b=6), legend=dict(x=0.1, y=1), font=dict(size=7)
     fig.update_traces(marker=dict(colors=color_palette))
     return fig
 
@@ -71,7 +71,7 @@ def create_pie_chart(df, column, title):
 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=10, r=10, t=20, b=10), legend=dict(x=0.1, y=1), font=dict(size=10))
+    fig.update_layout(margin=dict(l=6, r=6, t=12, b=6), legend=dict(x=0.1, y=1), font=dict(size=7)
     return fig
 
 # Visualization for Sentiment Distribution Across Domains
@@ -79,7 +79,7 @@ def create_sentiment_distribution_chart(df):
     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=10, r=10, t=20, b=10), xaxis_title="Domain", yaxis_title="Counts", font=dict(size=10))
+    fig.update_layout(margin=dict(l=6, r=6, t=12, b=6), xaxis_title="Domain", yaxis_title="Counts", font=dict(size=7))
     return fig
 
 # Visualization for Correlation between Sentiment and Discrimination
@@ -96,7 +96,7 @@ def create_sentiment_discrimination_grouped_chart(df):
     # Proceeding to plot only if we have data to plot
     if not melted_df.empty:
         fig = px.bar(melted_df, x='Sentiment', y='Count', color='Discrimination', barmode='group', title="Sentiment vs. Discrimination")
-        fig.update_layout(margin=dict(l=10, r=10, t=20, b=10), xaxis_title="Sentiment", yaxis_title="Count", font=dict(size=10))
+        fig.update_layout(margin=dict(l=6, r=6, t=12, b=6), xaxis_title="Sentiment", yaxis_title="Count", font=dict(size=7))
         return fig
     else:
         return "No data to display for the selected filters."
@@ -111,7 +111,7 @@ 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=10, r=10, t=20, b=10), xaxis_title="Negative sentiment content Count", yaxis_title="Domain")
+    fig.update_layout(margin=dict(l=6, r=6, t=12, b=6), xaxis_title="Negative sentiment content Count", yaxis_title="Domain", font=dict(size=7))
     return fig
 
 # Function for Key Phrases in Negative Sentiment Content Chart
@@ -122,15 +122,26 @@ def create_key_phrases_negative_sentiment_chart(df):
     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.update_layout(margin=dict(l=10, r=10, t=20, b=10), xaxis_title="Frequency", yaxis_title="Trigram")
+    fig.update_layout(margin=dict(l=6, r=6, t=12, b=6), xaxis_title="Frequency", yaxis_title="Trigram", font=dict(size=7))
     return fig
 
+# Function for Key Phrases in Positive Sentiment Content Chart
+def create_key_phrases_positive_sentiment_chart(df):
+    cv = CountVectorizer(ngram_range=(3, 3), stop_words='english')
+    trigrams = cv.fit_transform(df['Content'][df['Sentiment'] == 'Positive'])
+    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 Positive Sentiment Content')
+    fig.update_layout(margin=dict(l=6, r=6, t=12, b=6), xaxis_title="Frequency", yaxis_title="Trigram", font=dict(size=7))
+    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)
     fig = px.bar(domain_counts, x=domain_counts.index, y=['Discriminative', 'Non-Discriminative'], barmode='group',
                  title='Prevalence of Discriminatory Content')
-    fig.update_layout(margin=dict(l=20, r=20, t=40, b=20), xaxis_title="Domain", yaxis_title="Count")
+    fig.update_layout(margin=dict(l=6, r=6, t=12, b=6), xaxis_title="Domain", yaxis_title="Count", font=dict(size=7))
     return fig
 
 # Function for Top Domains with Discriminatory Content Chart
@@ -141,27 +152,27 @@ def create_top_discriminatory_domains_chart(df):
     domain_counts_subset = domain_counts_subset.rename(columns={'Discriminative': 'Count'})
     fig = px.bar(domain_counts_subset, x='Count', y=domain_counts_subset.index, orientation='h',
                  title='Top Domains with Discriminatory Content')
-    fig.update_layout(margin=dict(l=10, r=10, t=20, b=10), xaxis_title="Discriminatory Content Count", yaxis_title="Domain")
+    fig.update_layout(margin=dict((l=6, r=6, t=12, b=6), xaxis_title="Discriminatory Content Count", yaxis_title="Domain", font=dict(size=7))
     return fig
 
 # Function for Channel-wise Sentiment Over Time Chart
 def create_sentiment_distribution_by_channel_chart(df):
     sentiment_by_channel = df.groupby(['Channel', 'Sentiment']).size().reset_index(name='counts')
     fig = px.bar(sentiment_by_channel, x='Channel', y='counts', color='Sentiment', title="Sentiment Distribution by Channel", barmode='group')
-    fig.update_layout(margin=dict(l=10, r=10, t=20, b=10), xaxis_title="Channel", yaxis_title="Counts", font=dict(size=10))
+    fig.update_layout(margin=dict(l=6, r=6, t=12, b=6), xaxis_title="Channel", yaxis_title="Counts", font=dict(size=7))
     return fig
 
 # Function for Channel-wise Distribution of Discriminative Content Chart
 def create_channel_discrimination_chart(df):
     channel_discrimination = df.groupby(['Channel', 'Discrimination']).size().unstack(fill_value=0)
     fig = px.bar(channel_discrimination, x=channel_discrimination.index, y=['Discriminative', 'Non-Discriminative'], barmode='group')
-    fig.update_layout(title='Channel-wise Distribution of Discriminative Content', margin=dict(l=10, r=10, t=20, b=10))
+    fig.update_layout(title='Channel-wise Distribution of Discriminative Content', margin=dict(l=6, r=6, t=12, b=6), font=dict(size=7))
     return fig
 
 # Function for rendering dashboard
 def render_dashboard(page, df_filtered):
-    if page == "Overview":
-        st.title("Overview Dashboard")
+    if page == " GESI Overview":
+        st.title(" GESI Overview Dashboard")
         col1, col2 = st.columns(2)
         with col1:
             st.plotly_chart(create_pie_chart(df_filtered, 'Domain', 'Distribution of Domains'))
@@ -189,6 +200,8 @@ def render_dashboard(page, df_filtered):
         col3, col4 = st.columns(2)
         with col3:
             st.plotly_chart(create_key_phrases_negative_sentiment_chart(df_filtered))
+        with col4:
+            st.plotly_chart(create_key_phrases_positive_sentiment_chart(df_filtered)
 
     elif page == "Discrimination Analysis":
         st.title("Discrimination Analysis Dashboard")