Slicing Big Data of Movie Streaming with px.choropleth of Seaborn in Python coding

 

 Slicing the movie streaming data into genres to visualise their rating in each country

Data: https://uranaisearchastrology.wordpress.com/wp-content/uploads/2025/08/streaming_movies.xlsx * Please change it to the .CSV file format after downloading it! *

Please click "Read more »" below: 

 

# Importing necessary liberaries

import pycountry

import math

import matplotlib.pyplot as plt

import numpy as np

%matplotlib inline

import seaborn as sns

import pandas as pd

import plotly.express as px

print('Original Source: https://www.kaggle.com/datasets/ruchi798/movies-on-netflix-prime-video-hulu-and-disney')

# # Importing csv data (in Anaconda)

# movie=pd.read_csv('streaming_movies.csv')

# # Importing csv data (in Google Collab) at the first time

# from google.colab import files

# uploaded = files.upload()  # this will prompt you to select a file

# import io

# import pandas as pd

# movie = pd.read_csv(io.BytesIO(uploaded['streaming_movies.csv']))

# Importing csv data (in Google Collab) from the second time onward

filename = list(uploaded.keys())[0]  # picks the first uploaded file

movie = pd.read_csv(io.BytesIO(uploaded[filename]))

display(movie.tail()) # Display the last 5 rows of data

# Normalise IMDb and Rotten Tomatoes scores

movie['IMDb'] = movie['IMDb']/10

movie['Rotten Tomatoes']= movie[r'Rotten Tomatoes'].str.rstrip('%').astype(float)/100

# Making average of these two rating systems

movie['Rating'] = movie[['IMDb', 'Rotten Tomatoes']].mean(axis=1)

Rating=movie['Rating']

movie.drop(labels=['Rating'], axis=1,inplace = True)

movie.drop(labels=['IMDb'], axis=1,inplace = True)

movie.drop(labels=['Rotten Tomatoes'], axis=1,inplace = True)

movie.insert(5, 'Rating', Rating)  

# Display the last 5 rows of data

display(movie.tail())

# Separating multiple Genres in different columns

Genres=movie['Genres'].str.split(",",expand=True,)

G_list=[];

for i in range(len(Genres.columns)):

    Ind="".join(("G",str(i+1)));G_list.append(Ind)

    movie[Ind]=Genres.iloc[:, i]

   

# Separating multiple countries in different columns

Countries=movie['Country'].str.split(",",expand=True,)

C_list=[];

NoC=(len(Countries.columns))

# Find the country names and their Alpha3 codes

countries = {}

for country in pycountry.countries:

    countries[country.name] = country.alpha_3

# Get countries alpha3

for i in range(NoC):

    Ind="".join(("C",str(i+1))); C_list.append(Ind)

    movie[Ind]=Countries.iloc[:, i]

    movie[Ind]=[countries.get(country, '') for country in movie[Ind]]

   

# Creating a function for the output map

def MapOutPut(Data,GenreSelected,C_list,YearStart,YearEnd):

    # Reshape location columns into one

    Data_locs = Data.melt(

        id_vars=['Year', 'Rating'],

        value_vars=C_list,

        var_name='LocType',

        value_name='Location'

    )

   

    # Drop missing locations

    Data_locs = Data_locs.dropna(subset=['Location'])

    Data_locs_Years = Data_locs[Data_locs['Year'].between(YearStart,YearEnd)]

   

#     # Take average instead of the aggregate

#     Data_locs_Years = Data_locs_Years.groupby('Location', as_index=False)['Rating'].mean()

   

    fig = px.choropleth(

        Data_locs_Years,

        locations='Location',

        color='Rating',

        title=(f"{GS} Movie Rating by Country ({YearStart}–{YearEnd})")

    )

    fig.show()

GS='Animation' #GenreSelection

movie_GenreSelected=movie[movie[G_list].eq(GS).any(axis=1)]

# Iteration to compare graphs in different decade groups

MinYear=min(movie_GenreSelected['Year'])

MaxYear=max(movie_GenreSelected['Year'])

Step=5;Interval=10;

for i in range(math.ceil((MaxYear-MinYear)/Step)):

    YearEd=MaxYear-Step*i

    YearSt=(max(MinYear,YearEd-Interval))

    MapOutPut(movie_GenreSelected,GS,C_list,YearSt,YearEd)