Update app.py

app.py

@@ -2,6 +2,7 @@ import streamlit as st
 import pandas as pd
 import plotly.express as px
 
+# Function to assign color based on count
 def assign_color(count):
     if count <= 10:
         return '1-10'
@@ -16,6 +17,7 @@ def assign_color(count):
     else:
         return '>1000'
 
+# Country mapping dictionary
 country_mapping = {
     'United States': 'USA',
     'United Kingdom': 'GBR',
@@ -81,7 +83,6 @@ country_mapping = {
     'Nigeria': 'NGA',
     'Ghana': 'GHA',
     'Ethiopia': 'ETH',
-    'South Africa': 'ZAF',
     'Botswana': 'BWA',
     'Namibia': 'NAM',
     'Zimbabwe': 'ZWE',
@@ -120,36 +121,35 @@ country_mapping = {
     'Cape Verde': 'CPV',
     'Seychelles': 'SYC',
     'Comoros': 'COM',
-    'Mauritius': 'MUS',
     'Maldives': 'MDV'
 }
 
-
 # Load your dataframes
-df_tv_series= pd.read_csv('series_after_cleaning.csv')
-df_movies= pd.read_csv('movie_after_cleaning.csv')
+df_movies = pd.read_csv('movies.csv')
+df_tv_series = pd.read_csv('tv_series.csv')
 
+# Splitting genres and countries
 df_movies['genre'] = df_movies['genre'].str.split(',')
 df_tv_series['genre'] = df_tv_series['genre'].str.split(',')
 df_movies['country'] = df_movies['country'].str.split(',')
 df_tv_series['country'] = df_tv_series['country'].str.split(',')
 
-# Function to generate treemap
+# Function to create treemap
 def create_treemap(df, title):
     fig = px.treemap(df, path=['parentalguide'], title=title)
     return fig
-    
+
+# Function to create genre bar chart
 def create_genre_bar_chart(df, title):
-    # Explode the genre column to count each genre separately
     df_exploded = df.explode('genre')
     genre_counts = df_exploded['genre'].value_counts().reset_index()
     genre_counts.columns = ['genre', 'count']
-    genre_counts = genre_counts.head(10)  # Get top 10 genres
+    genre_counts = genre_counts.head(10)  # Top 10 genres
     fig = px.bar(genre_counts, x='count', y='genre', orientation='h', title=title)
     return fig
-    
+
+# Function to create choropleth map
 def create_country_map(df, title):
-    # Explode the country column to count each country separately
     df_exploded = df.explode('country')
     country_counts = df_exploded['country'].value_counts().reset_index()
     country_counts.columns = ['country', 'count']
@@ -157,7 +157,7 @@ def create_country_map(df, title):
     # Map country names to ISO codes
     country_counts['country'] = country_counts['country'].map(country_mapping)
     
-    # Assign color ranges based on counts
+    # Assign color based on count
     country_counts['color'] = country_counts['count'].apply(assign_color)
     
     fig = px.choropleth(country_counts, 
@@ -168,18 +168,19 @@ def create_country_map(df, title):
                         projection="natural earth",
                         color_discrete_sequence=['#7FFF00', '#FFD700', '#FFA500', '#FF4500', '#DC143C', '#8B0000'],
                         category_orders={"color": ['1-10', '10-50', '50-100', '100-500', '500-1000', '>1000']})
+    
     return fig
 
 # Streamlit app
-st.title('Parental Guide Treemaps')
+st.title('Parental Guide Analysis')
 
-# Split into two columns
+# Split into two columns for buttons
 col1, col2 = st.columns(2)
 
-# Initialize variable for selection
+# Default selection
 selection = 'Movies'
 
-# Add buttons in each column
+# Buttons for Movies and TV Series
 with col1:
     if st.button('Movies'):
         selection = 'Movies'
@@ -188,7 +189,7 @@ with col2:
     if st.button('TV Series'):
         selection = 'TV Series'
 
-# Display the corresponding treemap in the center
+# Display treemap, genre bar chart, and choropleth map based on selection
 if selection == 'Movies':
     st.plotly_chart(create_treemap(df_movies, 'Parental Guide - Movies'), use_container_width=True)
     st.plotly_chart(create_genre_bar_chart(df_movies, 'Top 10 Genres - Movies'), use_container_width=True)
@@ -196,5 +197,4 @@ if selection == 'Movies':
 elif selection == 'TV Series':
     st.plotly_chart(create_treemap(df_tv_series, 'Parental Guide - TV Series'), use_container_width=True)
     st.plotly_chart(create_genre_bar_chart(df_tv_series, 'Top 10 Genres - TV Series'), use_container_width=True)
-    st.plotly_chart(create_country_map(df_tv_series, 'Global Distribution of TV Series'), use_container_width=True)
-    
+    st.plotly_chart(create_country_map(df_tv_series, 'Global Distribution of TV Series'), use_container_width=True)