Update app.py

app.py

@@ -10,44 +10,52 @@ import plotly.graph_objects as go
 # Set page configuration
 st.set_page_config(layout="wide")
 
-
 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")       
 
-    # Normalize Text and Drop irrelevant data
-    frames = [df1, df2, df3, df4]
-    for frame in frames:
-        frame['Domain'].replace("MUSLIM", "Muslim", inplace=True)
-        frame.drop(frame[frame['Domain'] == 'Not relevant'].index, inplace=True)
-        frame.drop(frame[frame['Domain'] == 'None'].index, inplace=True)
-        frame.drop(frame[frame['Discrimination'] == 'None'].index, inplace=True)
-        frame.drop(frame[frame['Sentiment'] == 'None'].index, inplace=True)
-
-    # Concatenate/merge dataframes
-    df_combined = pd.concat(frames)
+    # Concatenate dataframes
+    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']
+    df_combined = df_combined[df_combined['Sentiment'] != 'None']
+
     return df_combined
 
+# Load and clean data
 df = load_and_clean_data()
 
-# Normalize Text
-df1['Domain'].replace("MUSLIM", "Muslim", inplace=True)
-df2['Domain'].replace("MUSLIM", "Muslim", inplace=True)
-df3['Domain'].replace("MUSLIM", "Muslim", inplace=True)
-df4['Domain'].replace("MUSLIM", "Muslim", inplace=True)
+# Define Sidebar Filters
+domain_options = df['Domain'].unique()
+channel_options = df['Channel'].unique()
+sentiment_options = df['Sentiment'].unique()
+discrimination_options = df['Discrimination'].unique()
+
+domain_filter = st.sidebar.multiselect('Select Domain', options=domain_options, default=domain_options)
+channel_filter = st.sidebar.multiselect('Select Channel', options=channel_options, default=channel_options)
+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
+df_filtered = df[(df['Domain'].isin(domain_filter)) & 
+                 (df['Channel'].isin(channel_filter)) & 
+                 (df['Sentiment'].isin(sentiment_filter)) & 
+                 (df['Discrimination'].isin(discrimination_filter))]
 
-# Drop irrelevant data
-frames = [df1, df2, df3, df4]
-for df in frames:
-    df = df[df['Domain'] != 'Not relevant']
-    df = df[df['Domain'] != 'None']
-    df = df[df['Discrimination'] != 'None']
-    df = df[df['Sentiment'] != 'None']
+# Page navigation
+page = st.sidebar.selectbox("Choose a page", ["Overview", "Sentiment Analysis", "Discrimination Analysis", "Channel Analysis"])
 
-# Concatenate/merge dataframes
-df = pd.concat(frames)
+# Define a color palette for consistent visualization styles
+color_palette = px.colors.sequential.Viridis
 
 # Visualization function
 def create_visualizations(df):
@@ -116,22 +124,6 @@ def render_dashboard():
 
     # ... [Other pages]
 
-# Define Sidebar Filters
-domain_options = df['Domain'].unique()
-channel_options = df['Channel'].unique()
-sentiment_options = df['Sentiment'].unique()
-discrimination_options = df['Discrimination'].unique()
-
-domain_filter = st.sidebar.multiselect('Select Domain', options=domain_options, default=domain_options)
-channel_filter = st.sidebar.multiselect('Select Channel', options=channel_options, default=channel_options)
-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
-df_filtered = df[(df['Domain'].isin(domain_filter)) & 
-                 (df['Channel'].isin(channel_filter)) & 
-                 (df['Sentiment'].isin(sentiment_filter)) & 
-                 (df['Discrimination'].isin(discrimination_filter))]
 
 # Render the dashboard with filtered data
 render_dashboard(df_filtered)