app.py

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'
    elif count <= 50:
        return '10-50'
    elif count <= 100:
        return '50-100'
    elif count <= 500:
        return '100-500'
    elif count <= 1000:
        return '500-1000'
    else:
        return '>1000'

# Country mapping dictionary
country_mapping = {
    'United States': 'USA',
    'United Kingdom': 'GBR',
    'France': 'FRA',
    'Canada': 'CAN',
    'Germany': 'DEU',
    'Japan': 'JPN',
    'India': 'IND',
    'Australia': 'AUS',
    'China': 'CHN',
    'Italy': 'ITA',
    'Spain': 'ESP',
    'Mexico': 'MEX',
    'Hong Kong': 'HKG',
    'Sweden': 'SWE',
    'Denmark': 'DNK',
    'New Zealand': 'NZL',
    'Belgium': 'BEL',
    'South Korea': 'KOR',
    'Ireland': 'IRL',
    'Czech Republic': 'CZE',
    'Switzerland': 'CHE',
    'Hungary': 'HUN',
    'Norway': 'NOR',
    'United Arab Emirates': 'ARE',
    'Netherlands': 'NLD',
    'South Africa': 'ZAF',
    'Poland': 'POL',
    'Austria': 'AUT',
    'Turkey': 'TUR',
    'Brazil': 'BRA',
    'Russia': 'RUS',
    'Argentina': 'ARG',
    'Singapore': 'SGP',
    'Thailand': 'THA',
    'Portugal': 'PRT',
    'Greece': 'GRC',
    'Egypt': 'EGY',
    'Vietnam': 'VNM',
    'Malaysia': 'MYS',
    'Philippines': 'PHL',
    'Taiwan': 'TWN',
    'Israel': 'ISR',
    'Saudi Arabia': 'SAU',
    'Indonesia': 'IDN',
    'Pakistan': 'PAK',
    'Iran': 'IRN',
    'Iraq': 'IRQ',
    'Syria': 'SYR',
    'Lebanon': 'LBN',
    'Jordan': 'JOR',
    'Qatar': 'QAT',
    'Oman': 'OMN',
    'Kuwait': 'KWT',
    'Bahrain': 'BHR',
    'Yemen': 'YEM',
    'Morocco': 'MAR',
    'Tunisia': 'TUN',
    'Algeria': 'DZA',
    'Libya': 'LBY',
    'Sudan': 'SDN',
    'Kenya': 'KEN',
    'Nigeria': 'NGA',
    'Ghana': 'GHA',
    'Ethiopia': 'ETH',
    'Botswana': 'BWA',
    'Namibia': 'NAM',
    'Zimbabwe': 'ZWE',
    'Zambia': 'ZMB',
    'Uganda': 'UGA',
    'Rwanda': 'RWA',
    'Burundi': 'BDI',
    'Tanzania': 'TZA',
    'Angola': 'AGO',
    'Mozambique': 'MOZ',
    'Madagascar': 'MDG',
    'Mauritius': 'MUS',
    'Somalia': 'SOM',
    'Somaliland': 'SOM',
    'Senegal': 'SEN',
    'Ivory Coast': 'CIV',
    'Cameroon': 'CMR',
    'Benin': 'BEN',
    'Togo': 'TGO',
    'Gambia': 'GMB',
    'Guinea': 'GIN',
    'Guinea-Bissau': 'GNB',
    'Equatorial Guinea': 'GNQ',
    'Gabon': 'GAB',
    'Congo': 'COG',
    'Democratic Republic of the Congo': 'COD',
    'Central African Republic': 'CAF',
    'Chad': 'TCD',
    'Niger': 'NER',
    'Mali': 'MLI',
    'Burkina Faso': 'BFA',
    'Mauritania': 'MRT',
    'Western Sahara': 'ESH',
    'Sierra Leone': 'SLE',
    'Liberia': 'LBR',
    'Cape Verde': 'CPV',
    'Seychelles': 'SYC',
    'Comoros': 'COM',
    'Maldives': 'MDV'
}

# Load your dataframes
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 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):
    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)  # 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):
    df_exploded = df.explode('country')
    country_counts = df_exploded['country'].value_counts().reset_index()
    country_counts.columns = ['country', 'count']
    
    # Map country names to ISO codes
    country_counts['country'] = country_counts['country'].map(country_mapping)
    
    # Assign color based on count
    country_counts['color'] = country_counts['count'].apply(assign_color)
    
    fig = px.choropleth(country_counts, 
                        locations="country",
                        color="color",
                        hover_name="country",
                        title=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 Analysis')

# Split into two columns for buttons
col1, col2 = st.columns(2)

# Default selection
selection = 'Movies'

# Buttons for Movies and TV Series
with col1:
    if st.button('Movies'):
        selection = 'Movies'

with col2:
    if st.button('TV Series'):
        selection = 'TV Series'

# 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)
    st.plotly_chart(create_country_map(df_movies, 'Global Distribution of Movies'), use_container_width=True)
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)