Update app.py

app.py

@@ -82,6 +82,49 @@ def create_sentiment_discrimination_grouped_chart(df):
     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 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)
+    domain_counts.sort_values(by='Negative', ascending=False, inplace=True)
+    domain_counts_subset = domain_counts.iloc[:3, [0]]
+    domain_counts_subset = domain_counts_subset.rename(columns={domain_counts_subset.columns[0]: 'Count'})
+    domain_counts_subset = domain_counts_subset.reset_index()
+    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=40, b=20), xaxis_title="Negative sentiment content Count", yaxis_title="Domain")
+    return fig
+
+# Function for Key Phrases in Negative Sentiment Content Chart
+def create_key_phrases_negative_sentiment_chart(df):
+    cv = CountVectorizer(ngram_range=(3,3), stop_words='english')
+    trigrams = cv.fit_transform(df['Content'][df['Sentiment'] == 'Negative'])
+    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.update_layout(margin=dict(l=20, r=20, t=40, b=20), xaxis_title="Frequency", yaxis_title="Trigram")
+    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")
+    return fig
+
+# Function for Top Domains with Discriminatory Content Chart
+def create_top_discriminatory_domains_chart(df):
+    domain_counts = df.groupby(['Domain', 'Discrimination']).size().unstack(fill_value=0)
+    domain_counts.sort_values(by='Discriminative', ascending=False, inplace=True)
+    domain_counts_subset = domain_counts.iloc[:3]
+    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=20, r=20, t=40, b=20), xaxis_title="Discriminatory Content Count", yaxis_title="Domain")
+    return fig
+
 # Function for Channel-wise Sentiment Over Time Chart
 def create_channel_sentiment_over_time_chart(df):
     df['Date'] = pd.to_datetime(df['Date'])
@@ -116,11 +159,25 @@ def render_dashboard(page, df_filtered):
 
     elif page == "Sentiment Analysis":
         st.title("Sentiment Analysis Dashboard")
-        # Implement sentiment analysis visualizations here
+        # Create visualizations for the sentiment analysis page
+        col1, col2 = st.beta_columns(2)
+        with col1:
+            st.plotly_chart(create_sentiment_distribution_chart(df_filtered))
+        with col2:
+            st.plotly_chart(create_top_negative_sentiment_domains_chart(df_filtered))
 
+        col3, col4 = st.beta_columns(2)
+        with col3:
+            st.plotly_chart(create_key_phrases_negative_sentiment_chart(df_filtered))
+        
     elif page == "Discrimination Analysis":
         st.title("Discrimination Analysis Dashboard")
-        # Implement discrimination analysis visualizations here
+        # Create visualizations for the discrimination analysis page
+        col1, col2 = st.beta_columns(2)
+        with col1:
+            st.plotly_chart(create_prevalence_discriminatory_content_chart(df_filtered))
+        with col2:
+            st.plotly_chart(create_top_discriminatory_domains_chart(df_filtered))e
 
     elif page == "Channel Analysis":
         st.title("Channel Analysis Dashboard")