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")

#1.Inspect the data
# Display the first few rows of the dataset to understand its structure
print(netflix_df.head())

# Check the data types and missing values
print(netflix_df.info())

# Check for unique values in relevant columns
print(netflix_df['type'].unique())  # Movies or TV Shows?
print(netflix_df['release_year'].unique())  # Year of release

#2. Filter the movies from the 1990s
# Filter for movies only
movies_df = netflix_df[netflix_df['type'] == 'Movie']

# Filter further for movies released in the 1990s
movies_1990s = movies_df[(movies_df['release_year'] >= 1990) & (movies_df['release_year'] <= 1999)]

# Display the first few rows of the filtered DataFrame
print(movies_1990s.head())

# Check the number of movies from the 1990s
print(f"Number of movies from the 1990s: {len(movies_1990s)}")

#3. Movies released each year
# Count the number of movies released each year
movies_by_year = movies_1990s['release_year'].value_counts().sort_index()

# Plot the distribution
plt.figure(figsize=(10, 6))
movies_by_year.plot(kind='bar', color='skyblue')
plt.title('Number of Movies Released Each Year (1990s)', fontsize=16)
plt.xlabel('Release Year', fontsize=14)
plt.ylabel('Number of Movies', fontsize=14)
plt.xticks(rotation=45)
plt.show()

#4. Explore genres
# Check unique genres
print(movies_1990s['genre'].unique())

# Count the number of movies per genre
genre_counts = movies_1990s['genre'].value_counts()

# Plot the genre distribution
plt.figure(figsize=(12, 6))
genre_counts.plot(kind='bar', color='orange')
plt.title('Popular Genres of Movies (1990s)', fontsize=16)
plt.xlabel('Genre', fontsize=14)
plt.ylabel('Number of Movies', fontsize=14)
plt.xticks(rotation=45)
plt.show()

#5. Explore runtime
# Check for missing runtime values
print(movies_1990s['duration'].isnull().sum())

# Plot a histogram of runtimes
plt.figure(figsize=(10, 6))
movies_1990s['duration'].plot(kind='hist', bins=20, color='purple', alpha=0.7)
plt.title('Distribution of Movie Runtimes (1990s)', fontsize=16)
plt.xlabel('Runtime (minutes)', fontsize=14)
plt.ylabel('Frequency', fontsize=14)
plt.show()

#6. Full Analysis
# Importing libraries
import pandas as pd
import matplotlib.pyplot as plt

# Read the Netflix dataset
netflix_df = pd.read_csv("netflix_data.csv")

# Inspect the dataset
print(netflix_df.head())
print(netflix_df.info())

# Filter for movies from the 1990s
movies_df = netflix_df[netflix_df['type'] == 'Movie']
movies_1990s = movies_df[(movies_df['release_year'] >= 1990) & (movies_df['release_year'] <= 1999)]

# Number of movies from the 1990s
print(f"Number of movies from the 1990s: {len(movies_1990s)}")

# Movies released each year
movies_by_year = movies_1990s['release_year'].value_counts().sort_index()
plt.figure(figsize=(10, 6))
movies_by_year.plot(kind='bar', color='skyblue')
plt.title('Number of Movies Released Each Year (1990s)', fontsize=16)
plt.xlabel('Release Year', fontsize=14)
plt.ylabel('Number of Movies', fontsize=14)
plt.xticks(rotation=45)
plt.show()

# Popular genres
if 'genre' in movies_1990s.columns:
    genre_counts = movies_1990s['genre'].value_counts()
    plt.figure(figsize=(12, 6))
    genre_counts.plot(kind='bar', color='orange')
    plt.title('Popular Genres of Movies (1990s)', fontsize=16)
    plt.xlabel('Genre', fontsize=14)
    plt.ylabel('Number of Movies', fontsize=14)
    plt.xticks(rotation=45)
    plt.show()

# Runtime distribution
if 'duration' in movies_1990s.columns:
    plt.figure(figsize=(10, 6))
    movies_1990s['duration'].plot(kind='hist', bins=20, color='purple', alpha=0.7)
    plt.title('Distribution of Movie Runtimes (1990s)', fontsize=16)
    plt.xlabel('Runtime (minutes)', fontsize=14)
    plt.ylabel('Frequency', fontsize=14)
    plt.show()

#7. Inspect columns for further analysis
# List all the columns in the dataset
print(netflix_df.columns)

#8. Group by time period.
# Convert 'date_added' to datetime format
netflix_df['date_added'] = pd.to_datetime(netflix_df['date_added'])

# Extract the year from 'date_added' for analysis
netflix_df['year_added'] = netflix_df['date_added'].dt.year

# Group data into time periods (e.g., pre-2000s, 2000s, 2010s, and 2020s)
def assign_time_period(year):
    if pd.isna(year):
        return 'Unknown'
    elif year < 2000:
        return 'Before 2000'
    elif 2000 <= year < 2010:
        return '2000-2009'
    elif 2010 <= year < 2020:
        return '2010-2019'
    else:
        return '2020+'

netflix_df['time_period'] = netflix_df['year_added'].apply(assign_time_period)

# Inspect the time periods
print(netflix_df['time_period'].value_counts())

#9.Growth overtime
# Count the number of movies and TV shows added each year
content_growth = netflix_df.groupby(['year_added', 'type']).size().unstack()

# Plot the content growth over time
plt.figure(figsize=(12, 6))
content_growth.plot(kind='line', marker='o', linewidth=2)
plt.title('Netflix Content Growth Over Time', fontsize=16)
plt.xlabel('Year Added to Netflix', fontsize=14)
plt.ylabel('Number of Titles', fontsize=14)
plt.legend(title='Content Type', labels=['Movies', 'TV Shows'])
plt.grid(alpha=0.3)
plt.show()

#10. # Group movies by release decade
movies_df = netflix_df[netflix_df['type'] == 'Movie']
movies_df['release_decade'] = (movies_df['release_year'] // 10) * 10

# Count the number of movies per decade
movies_by_decade = movies_df['release_decade'].value_counts().sort_index()

# Plot the distribution of movies by release decade
plt.figure(figsize=(12, 6))
movies_by_decade.plot(kind='bar', color='skyblue')
plt.title('Number of Movies by Release Decade', fontsize=16)
plt.xlabel('Decade of Release', fontsize=14)
plt.ylabel('Number of Movies', fontsize=14)
plt.xticks(rotation=45)
plt.show()

#11. Analyze the boom
# Count movies by release year
movies_by_release_year = movies_df['release_year'].value_counts().sort_index()

# Count movies added to Netflix by year
movies_added_by_year = movies_df['year_added'].value_counts().sort_index()

# Plot comparison
plt.figure(figsize=(12, 6))
plt.plot(movies_by_release_year.index, movies_by_release_year.values, label='Movies by Release Year', color='orange', marker='o')
plt.plot(movies_added_by_year.index, movies_added_by_year.values, label='Movies Added to Netflix', color='blue', marker='o')
plt.title('Movies by Release Year vs. Movies Added to Netflix', fontsize=16)
plt.xlabel('Year', fontsize=14)
plt.ylabel('Number of Movies', fontsize=14)
plt.legend()
plt.grid(alpha=0.3)
plt.show()

#12.Genre trends over time
# Group by genre and year added
if 'genre' in netflix_df.columns:
    genre_trends = netflix_df.groupby(['year_added', 'genre']).size().unstack(fill_value=0)

    # Plot trends for the top 5 genres
    top_5_genres = genre_trends.sum().sort_values(ascending=False).head(5).index
    genre_trends[top_5_genres].plot(figsize=(12, 6), linewidth=2)
    plt.title('Top 5 Genres Added to Netflix Over Time', fontsize=16)
    plt.xlabel('Year Added', fontsize=14)
    plt.ylabel('Number of Titles', fontsize=14)
    plt.legend(title='Genre')
    plt.grid(alpha=0.3)
    plt.show()