Update app.py

app.py

@@ -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=20, r=20, t=50, b=20), legend=dict(x=0.1, y=1), font=dict(size=10), title_x=0.5)
+    fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), legend=dict(x=0.1, y=1), font=dict(size=10))
     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=20, r=20, t=50, b=20), legend=dict(x=0.1, y=1), font=dict(size=10), title_x=0.5)
+    fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), legend=dict(x=0.1, y=1), font=dict(size=10))
     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=20, r=20, t=50, b=20), xaxis_title="Domain", yaxis_title="Counts", font=dict(size=10), title_x=0.5)
+    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
@@ -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=20, r=20, t=50, b=20), xaxis_title="Sentiment", yaxis_title="Count", font=dict(size=10), title_x=0.5)
+        fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Sentiment", yaxis_title="Count", font=dict(size=10))
         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=20, r=20, t=50, b=20), xaxis_title="Negative sentiment content Count", yaxis_title="Domain", font=dict(size=10), title_x=0.5)
+    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
@@ -122,26 +122,37 @@ 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=20, r=20, t=50, b=20), xaxis_title="Frequency", yaxis_title="Trigram", font=dict(size=10), title_x=0.5)
+    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 Key Phrases in Positive Sentiment Content Chart
 def create_key_phrases_positive_sentiment_chart(df):
+    # Filter the DataFrame for positive sentiments and drop any rows with NaN in 'Content'
+    positive_df = df[df['Sentiment'] == 'Positive'].dropna(subset=['Content'])
+    
+    # Create a CountVectorizer instance
     cv = CountVectorizer(ngram_range=(3, 3), stop_words='english')
-    trigrams = cv.fit_transform(df['Content'][df['Sentiment'] == 'Positive'])
+    
+    # Apply CountVectorizer only on non-null content
+    trigrams = cv.fit_transform(positive_df['Content'])
+    
+    # Sum the frequency of each n-gram and create a DataFrame
     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']
+    
+    # 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.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Frequency", yaxis_title="Trigram", font=dict(size=10), title_x=0.5)
-    return fig
+    
+    # Update layout settings to fit and look better
+    fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Frequency", yaxis_title="Trigram", font=dict(size=10))
     
 # 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=50, b=20), xaxis_title="Domain", yaxis_title="Count", font=dict(size=10), title_x=0.5)
+    fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Domain", yaxis_title="Count", font=dict(size=10))
     return fig
 
 # Function for Top Domains with Discriminatory Content Chart
@@ -152,7 +163,7 @@ 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=20, r=20, t=50, b=20), xaxis_title="Discriminatory Content Count", yaxis_title="Domain", font=dict(size=10), title_x=0.5)
+    fig.update_layout(margin=dict(l=20, r=20, t=50, b=20), xaxis_title="Discriminatory Content Count", yaxis_title="Domain", font=dict(size=10))
     return fig
 
 # Function for Channel-wise Sentiment Over Time Chart