Netflix Movie Data

# Load packages
import pandas as pd
import numpy as np 
import matplotlib.pyplot as plt

#Load data
Netflix_data = pd.read_csv("netflix_dataset.csv", index_col=0)
Netflix_data.head()

# Explore: 
# How much variety exists in Netflix's offering? Base this on three variables: type, country, and listed_in.
distinct_count_type = Netflix_data['type'].nunique()
distinct_countries = Netflix_data['country'].str.split(',').explode().str.strip().nunique()
distinct_listed_in = Netflix_data['listed_in'].str.split(',').explode().str.strip().nunique()

print('Distinct count of type:', distinct_count_type)
print('Distinct count of countries:', distinct_countries)
print('Distinct count of listed_in:', distinct_listed_in)

#pull type, country, listed in                          
type_nf = Netflix_data["type"].unique()
print(type_nf)

unique_countries = Netflix_data['country'].str.split(',').explode().str.strip().unique()
unique_countries_nf = unique_countries
distinct_countries_nf = list(set(unique_countries_nf))
print(distinct_countries_nf)

distinct_listed_in_nf = list(set(Netflix_data['listed_in'].str.split(',').explode().str.strip().unique()))
print(distinct_listed_in_nf)

# Import the necessary libraries for WORDCLOUD
import pandas as pd
from wordcloud import WordCloud
import matplotlib.pyplot as plt

# Concatenate all the descriptions into a single string
descriptions = ' '.join(Netflix_data['description'].dropna())

# Create a word cloud
wordcloud = WordCloud(width=800, height=400, background_color='white').generate(descriptions)

# Display the word cloud
plt.figure(figsize=(10, 5))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.show()

#Variables
import pandas as pd

variables = pd.DataFrame(columns=['Variable','Number of unique values','Values'])

for i, var in enumerate(Netflix_data.columns):
    variables.loc[i] = [var, Netflix_data[var].nunique(), Netflix_data[var].unique().tolist()]
    
print(variables)

#Checking data type and missing values
Netflix_data.info()

nf_movies = Netflix_data[Netflix_data['type'] == 'Movie']
print('Number of movies in the dataset : ', nf_movies.shape[0])

nf_tv = Netflix_data[Netflix_data['type'] == 'TV Show']
print('Number of TV Shows in the dataset : ', nf_tv.shape[0])

nf_movies['duration'] = nf_movies['duration'].str.replace(' min', '')
duration = nf_movies['duration'].astype('float64')
duration.describe()

# Plotting the distribution of movie durations
import matplotlib.pyplot as plt

# Extracting the duration column from nf_movies dataframe
duration = nf_movies['duration'].str.replace(' min', '').astype('float64')

# Creating a histogram
plt.hist(duration, bins=100, edgecolor='black')
plt.xlabel('Duration (minutes)')
plt.ylabel('Frequency')
plt.title('Distribution of Movie Durations')
plt.show()

nf_tv['duration'] = nf_tv['duration'].str.replace(' Season', '')
nf_tv['duration'] = nf_tv['duration'].str.replace('s', '')
seasons = nf_tv['duration'].astype('float64')
seasons.describe()

# Plotting the distribution of number of seasons
# Extract the number of seasons
seasons = nf_tv['duration'].astype('float64')

# Plot the histogram
plt.hist(seasons, bins=30, edgecolor='black', color = 'red')
plt.xlabel('Number of Seasons')
plt.ylabel('Frequency')
plt.title('Distribution of TV Shows on Netflix')
plt.show()