Project: Investigating Netflix Movies

# Importing pandas and matplotlib
import pandas as pd
import matplotlib.pyplot as plt

# Read in the Netflix CSV as a DataFrame
netflix_df = pd.read_csv("netflix_data.csv")

# Start coding here! Use as many cells as you like

import numpy as np
import seaborn as sns
import missingno as msno

# Setting up the visual aesthetics
%matplotlib inline
sns.set(style="whitegrid")

netflix_df.head()
netflix_df.info()
# Numerical columns
netflix_df.describe()

# Categorical columns
netflix_df.describe(include=['object'])

# Visual representation
msno.matrix(netflix_df)
plt.show()

# Detailed count
missing_values = netflix_df.isnull().sum()
missing_values[missing_values > 0]

# Convert 'date_added' to datetime
netflix_df['date_added'] = pd.to_datetime(netflix_df['date_added'], errors='coerce')

# Extract year from 'date_added' if needed
netflix_df['year_added'] = netflix_df['date_added'].dt.year

# Convert 'duration' to numeric (assuming duration is in minutes as per description)
netflix_df['duration'] = pd.to_numeric(netflix_df['duration'], errors='coerce')

# Verify changes
netflix_df.info()

duplicates = netflix_df.duplicated().sum()
print(f"Number of duplicate rows: {duplicates}")

# Remove duplicates
netflix_df = netflix_df.drop_duplicates()

plt.figure(figsize=(6,4))
sns.countplot(data=netflix_df, x='type', palette='viridis')
plt.title('Distribution of Show Types')
plt.xlabel('Type')
plt.ylabel('Count')
plt.show()

# Since 'country' may have multiple countries separated by commas, we need to split them
countries = netflix_df['country'].dropna().str.split(', ').explode()

# Create a DataFrame with the counts of the top 10 countries
top_countries = countries.value_counts().head(10).reset_index()
top_countries.columns = ['Country', 'Number of Shows']

plt.figure(figsize=(12,6))
sns.barplot(data=top_countries, x='Country', y='Number of Shows', palette='plasma')
plt.title('Top 10 Countries by Number of Shows')
plt.xlabel('Country')
plt.ylabel('Number of Shows')
plt.xticks(rotation=45)
plt.show()

plt.figure(figsize=(12,6))
sns.histplot(data=netflix_df, x='release_year', bins=30, kde=True, color='teal')
plt.title('Distribution of Release Years')
plt.xlabel('Release Year')
plt.ylabel('Number of Shows')
plt.show()

plt.figure(figsize=(12,6))
sns.histplot(data=netflix_df, x='duration', bins=30, kde=True, color='coral')
plt.title('Distribution of Show Durations')
plt.xlabel('Duration (minutes)')
plt.ylabel('Number of Shows')
plt.show()

# If 'type' is either Movie or TV Show, we can compare durations
plt.figure(figsize=(12,6))
sns.boxplot(data=netflix_df, x='type', y='duration', palette='Set2')
plt.title('Duration by Show Type')
plt.xlabel('Type')
plt.ylabel('Duration (minutes)')
plt.show()

# Assuming 'genre' may have multiple genres separated by commas
genres = netflix_df['genre'].dropna().str.split(', ').explode()

# Create a DataFrame with the counts of the top 15 genres
top_genres = genres.value_counts().head(15).reset_index()
top_genres.columns = ['genre', 'count']

plt.figure(figsize=(12,6))
sns.barplot(data=top_genres, x='genre', y='count', palette='magma')
plt.title('Top 15 Genres')
plt.xlabel('Genre')
plt.ylabel('Number of Shows')
plt.xticks(rotation=45)
plt.show()

# Handle multiple directors if present
directors = netflix_df['director'].dropna().str.split(', ').explode()

# Create a DataFrame with the counts of the top 10 directors
top_directors = directors.value_counts().head(10).reset_index()
top_directors.columns = ['director', 'count']

plt.figure(figsize=(12,6))
sns.barplot(data=top_directors, x='director', y='count', palette='coolwarm')
plt.title('Top 10 Directors by Number of Shows')
plt.xlabel('Director')
plt.ylabel('Number of Shows')
plt.xticks(rotation=45)
plt.show()