Update app.py

app.py

@@ -6,6 +6,7 @@ import streamlit as st
 from wordcloud import WordCloud
 import matplotlib.pyplot as plt
 from collections import Counter
+import numpy as np
 
 # Function to load data from SQLite database
 def load_data(db_file):
@@ -145,8 +146,8 @@ def plot_movie_release_years(df_release_years):
 
 # Function to plot global map of total films per region using Plotly Express
 def plot_global_map():
-    # Country code to name mapping
     df = pd.read_csv('movie_region.csv')
+    # Country code to name mapping
     country_mapping = {
         'AF': 'Afghanistan', 'AX': 'Åland Islands', 'AL': 'Albania', 'DZ': 'Algeria', 'AS': 'American Samoa',
         'AD': 'Andorra', 'AO': 'Angola', 'AI': 'Anguilla', 'AQ': 'Antarctica', 'AG': 'Antigua and Barbuda',
@@ -164,42 +165,49 @@ def plot_global_map():
         'FR': 'France', 'GA': 'Gabon', 'GM': 'Gambia', 'GE': 'Georgia', 'DE': 'Germany',
         'GH': 'Ghana', 'GR': 'Greece', 'GD': 'Grenada', 'GT': 'Guatemala', 'GN': 'Guinea',
         'GW': 'Guinea-Bissau', 'GY': 'Guyana', 'HT': 'Haiti', 'HN': 'Honduras', 'HK': 'Hong Kong',
-        'HU': 'Hungary', 'IS': 'Iceland', 'IN': 'India', 'ID': 'Indonesia', 'IR': 'Iran',
-        'IQ': 'Iraq', 'IE': 'Ireland', 'IM': 'Isle of Man', 'IL': 'Israel', 'IT': 'Italy',
-        'CI': 'Ivory Coast', 'JM': 'Jamaica', 'JP': 'Japan', 'JO': 'Jordan', 'KZ': 'Kazakhstan',
-        'KE': 'Kenya', 'KI': 'Kiribati', 'KW': 'Kuwait', 'KG': 'Kyrgyzstan', 'LA': 'Laos',
+        'HU': 'Hungary', 'IS': 'Iceland', 'IN': 'India', 'ID': 'Indonesia', 'IR': 'Iran, Islamic Republic of',
+        'IQ': 'Iraq', 'IE': 'Ireland', 'IL': 'Israel', 'IT': 'Italy', 'JM': 'Jamaica',
+        'JP': 'Japan', 'JO': 'Jordan', 'KZ': 'Kazakhstan', 'KE': 'Kenya', 'KP': 'Korea, Democratic People\'s Republic of',
+        'KR': 'Korea, Republic of', 'KW': 'Kuwait', 'KG': 'Kyrgyzstan', 'LA': 'Lao People\'s Democratic Republic',
         'LV': 'Latvia', 'LB': 'Lebanon', 'LS': 'Lesotho', 'LR': 'Liberia', 'LY': 'Libya',
-        'LI': 'Liechtenstein', 'LT': 'Lithuania', 'LU': 'Luxembourg', 'MO': 'Macao', 'MK': 'Macedonia',
+        'LT': 'Lithuania', 'LU': 'Luxembourg', 'MO': 'Macao', 'MK': 'Macedonia, the Former Yugoslav Republic of',
         'MG': 'Madagascar', 'MW': 'Malawi', 'MY': 'Malaysia', 'MV': 'Maldives', 'ML': 'Mali',
-        'MT': 'Malta', 'MH': 'Marshall Islands', 'MR': 'Mauritania', 'MU': 'Mauritius', 'MX': 'Mexico',
-        'FM': 'Micronesia', 'MD': 'Moldova', 'MC': 'Monaco', 'MN': 'Mongolia', 'ME': 'Montenegro',
-        'MS': 'Montserrat', 'MA': 'Morocco', 'MZ': 'Mozambique', 'MM': 'Myanmar', 'NA': 'Namibia',
-        'NR': 'Nauru', 'NP': 'Nepal', 'NL': 'Netherlands', 'NZ': 'New Zealand', 'NI': 'Nicaragua',
-        'NE': 'Niger', 'NG': 'Nigeria', 'NU': 'Niue', 'KP': 'North Korea', 'MP': 'Northern Mariana Islands',
-        'NO': 'Norway', 'OM': 'Oman', 'PK': 'Pakistan', 'PW': 'Palau', 'PS': 'Palestine',
-        'PA': 'Panama', 'PG': 'Papua New Guinea', 'PY': 'Paraguay', 'PE': 'Peru', 'PH': 'Philippines',
-        'PL': 'Poland', 'PT': 'Portugal', 'PR': 'Puerto Rico', 'QA': 'Qatar', 'RO': 'Romania',
-        'RU': 'Russia', 'RW': 'Rwanda', 'KN': 'Saint Kitts and Nevis', 'LC': 'Saint Lucia', 'VC': 'Saint Vincent and the Grenadines',
-        'WS': 'Samoa', 'SM': 'San Marino', 'ST': 'Sao Tome and Principe', 'SA': 'Saudi Arabia', 'SN': 'Senegal',
-        'RS': 'Serbia', 'SC': 'Seychelles', 'SL': 'Sierra Leone', 'SG': 'Singapore', 'SK': 'Slovakia',
-        'SI': 'Slovenia', 'SB': 'Solomon Islands', 'SO': 'Somalia', 'ZA': 'South Africa', 'KR': 'South Korea',
-        'SS': 'South Sudan', 'ES': 'Spain', 'LK': 'Sri Lanka', 'SD': 'Sudan', 'SR': 'Suriname',
-        'SZ': 'Swaziland', 'SE': 'Sweden', 'CH': 'Switzerland', 'SY': 'Syria', 'TW': 'Taiwan',
-        'TJ': 'Tajikistan', 'TZ': 'Tanzania', 'TH': 'Thailand', 'TL': 'Timor-Leste', 'TG': 'Togo',
-        'TK': 'Tokelau', 'TO': 'Tonga', 'TT': 'Trinidad and Tobago', 'TN': 'Tunisia', 'TR': 'Turkey',
-        'TM': 'Turkmenistan', 'TV': 'Tuvalu', 'UG': 'Uganda', 'UA': 'Ukraine', 'AE': 'United Arab Emirates',
+        'MT': 'Malta', 'MR': 'Mauritania', 'MU': 'Mauritius', 'MX': 'Mexico', 'MD': 'Moldova, Republic of',
+        'MN': 'Mongolia', 'ME': 'Montenegro', 'MA': 'Morocco', 'MZ': 'Mozambique', 'MM': 'Myanmar',
+        'NA': 'Namibia', 'NP': 'Nepal', 'NL': 'Netherlands', 'NZ': 'New Zealand', 'NI': 'Nicaragua',
+        'NE': 'Niger', 'NG': 'Nigeria', 'NO': 'Norway', 'OM': 'Oman', 'PK': 'Pakistan',
+        'PW': 'Palau', 'PA': 'Panama', 'PG': 'Papua New Guinea', 'PY': 'Paraguay', 'PE': 'Peru',
+        'PH': 'Philippines', 'PL': 'Poland', 'PT': 'Portugal', 'QA': 'Qatar', 'RO': 'Romania',
+        'RU': 'Russian Federation', 'RW': 'Rwanda', 'WS': 'Samoa', 'SA': 'Saudi Arabia', 'SN': 'Senegal',
+        'RS': 'Serbia', 'SL': 'Sierra Leone', 'SG': 'Singapore', 'SK': 'Slovakia', 'SI': 'Slovenia',
+        'SB': 'Solomon Islands', 'ZA': 'South Africa', 'ES': 'Spain', 'LK': 'Sri Lanka', 'SD': 'Sudan',
+        'SR': 'Suriname', 'SZ': 'Swaziland', 'SE': 'Sweden', 'CH': 'Switzerland', 'SY': 'Syrian Arab Republic',
+        'TW': 'Taiwan, Province of China', 'TJ': 'Tajikistan', 'TZ': 'Tanzania, United Republic of', 'TH': 'Thailand',
+        'TL': 'Timor-Leste', 'TG': 'Togo', 'TO': 'Tonga', 'TT': 'Trinidad and Tobago', 'TN': 'Tunisia',
+        'TR': 'Turkey', 'TM': 'Turkmenistan', 'UG': 'Uganda', 'UA': 'Ukraine', 'AE': 'United Arab Emirates',
         'GB': 'United Kingdom', 'US': 'United States', 'UY': 'Uruguay', 'UZ': 'Uzbekistan', 'VU': 'Vanuatu',
-        'VA': 'Vatican City', 'VE': 'Venezuela', 'VN': 'Vietnam', 'YE': 'Yemen', 'ZM': 'Zambia', 'ZW': 'Zimbabwe'
+        'VE': 'Venezuela, Bolivarian Republic of', 'VN': 'Viet Nam', 'ZM': 'Zambia', 'ZW': 'Zimbabwe'
     }
 
-    # Apply country code mapping
+    # Map country codes to country names
     df['region'] = df['region'].map(country_mapping)
 
-    # Plot the global map
-    fig = px.choropleth(df, locations='region', locationmode='country names',
-                        color='count', hover_name='region',
-                        title='Global Movie Productions by Country',
-                        color_continuous_scale=px.colors.sequential.Plasma)
+    # Group by country and count the number of films
+    df_grouped = df.groupby('region').size().reset_index(name='total_films')
+
+    # Apply log transformation to handle outliers
+    df_grouped['log_total_films'] = np.log1p(df_grouped['total_films'])
+
+    # Create a choropleth map with the log-transformed data
+    fig = px.choropleth(df_grouped, locations='region', locationmode='country names',
+                        color='log_total_films', hover_name='region',
+                        color_continuous_scale='Plasma',  # Change the color scheme here
+                        labels={'log_total_films': 'Total Films (log scale)'})
+
+    # Update layout of the map
+    fig.update_layout(title='Total Films by Country (Log Scale)',
+                      geo=dict(showframe=False, showcoastlines=False,
+                               projection_type='equirectangular'))
 
     return fig