The Evolution of Cinema: IMDb Movie Analysis from 2000 to 2020¶

data.head()

data.info()

# Let's Start with basic question or insights i.e. Number of Movies Released each year.
movies_per_year = data.groupby('year').size() # Group by the 'year' column and count the number of movies per year
movies_per_year.plot(kind='bar', color='skyblue')

data.head()

# Calculate the Most Popular Genres Each Year

# Group by 'year' and 'genre' to count the number of movies per genre each year
genre_counts = data.groupby(['year', 'genre']).size().reset_index(name='count')

# Find the most popular genre per year
most_popular_genres = genre_counts.loc[genre_counts.groupby('year')['count'].idxmax()]

# Display the most popular genres by year
print(most_popular_genres)

# Plot Genre Trends Over Time
# Pivot the data to create a matrix of years (rows) and genres (columns) with movie counts
genre_trends = genre_counts.pivot(index='year', columns='genre', values='count').fillna(0)

# Plot the genre trends
plt.figure(figsize=(12, 8))
sns.lineplot(data=genre_trends)
plt.title("Genre Trends Over Time (2000-2020)")
plt.xlabel("Year")
plt.ylabel("Number of Movies")
plt.legend(title="Genres", bbox_to_anchor=(1.05, 1), loc='upper left')
plt.show()

# Calculate Average Movie Duration by Genre and Year
average_duration = data.groupby(['year', 'genre'])['duration'].mean().reset_index()

# Display the average duration data
print(average_duration.head())

# Plot Average Movie Duration by Genre and Year
# Pivot the data to create a matrix for the heatmap
duration_trends = average_duration.pivot(index='year', columns='genre', values='duration')

# Plot the heatmap
plt.figure(figsize=(12, 8))
sns.heatmap(duration_trends, cmap="YlGnBu", cbar_kws={'label': 'Average Duration (minutes)'})
plt.title("Average Movie Duration by Genre and Year")
plt.xlabel("Genre")
plt.ylabel("Year")
plt.show()

# Plot average duration for a few selected genres over time
selected_genres = ['Animation', 'Biography', 'History', 'Musical']  # Select genres of interest
plt.figure(figsize=(12, 8))
for genre in selected_genres:
    sns.lineplot(data=average_duration[average_duration['genre'] == genre], x='year', y='duration', label=genre)

plt.title("Average Movie Duration by Genre (2000-2020)")
plt.xlabel("Year")
plt.ylabel("Average Duration (minutes)")
plt.legend(title="Genre")
plt.show()

# Identify top-rated movies each year

# Using a new data set because in previous we split the genre to get detailed analysis, which lead to duplicate the same movie.
new_data = pd.read_csv('IMDB Movies 2000 - 2020.csv')

# Find the top-rated movie for each year
# Group by 'year' and select the row with the highest rating for each year
top_rated_each_year = new_data.loc[data.groupby('year')['avg_vote'].idxmax()]

# Select only the desired columns
top_rated_each_year = top_rated_each_year[['year', 'original_title', 'avg_vote', 'genre','country']]

# Display the result
top_rated_each_year

most_popular_language_each_year

# Analyze the 2nd language column 
language_count = new_data.groupby(['year', 'language_2']).size().reset_index(name='count')

most_popular_language_each = language_count.loc[language_count.groupby('year')['count'].idxmax()]

most_popular_language_each = most_popular_language_each[['year', 'language_2', 'count']]

# Display the result
most_popular_language_each

# Split the actors column because each row has many actors.
new_data['actors'] = new_data['actors'].astype(str)
new_data['actors'] = new_data['actors'].str.split(', ')
new_data_exploded = new_data.explode('actors')

# Group by actor and calculate average rating, total votes, and movie count
top_actors = (
    new_data_exploded.groupby('actors')
    .agg(avg_rating=('avg_vote', 'mean'), total_votes=('votes', 'sum'), total_movies=('avg_vote', 'count'))
    .reset_index()
)

# Sort by average total votes. Later we can use rating or movie count
top_actors = top_actors.sort_values(by=['total_votes'], ascending=[False])

top_actors.head(10)

# Getting the top 10 actors
top_actors_sorted = top_actors.sort_values(by='total_votes', ascending=False).head(10)
# Plotting 
plt.figure(figsize=(12, 8))
sns.barplot(x='total_votes', y='actors', data=top_actors_sorted, palette='viridis')
plt.xlabel("Total Votes")
plt.ylabel("Actors")
plt.title("Top 10 Actors by Total Votes")
plt.show()

# Define thresholds for high rating and high votes
high_rating_threshold = 8.0
high_votes_threshold = 50000

# Find actors with an average rating above the high rating threshold
high_rating_actors = top_actors[top_actors['avg_rating'] >= high_rating_threshold]

# Find actors with a total number of votes above the high votes threshold
high_votes_actors = top_actors[top_actors['total_votes'] >= high_votes_threshold]

# Find actors who meet both criteria (high-rated movies and high votes)
high_rating_and_votes_actors = top_actors[
    (top_actors['avg_rating'] >= high_rating_threshold) &
    (top_actors['total_votes'] >= high_votes_threshold)
]

# Display the actors who meet both criteria
print("Actors frequently appearing in high-rated and high-vote movies:")
print(high_rating_and_votes_actors[['actors', 'avg_rating', 'total_votes', 'total_movies']])

plt.figure(figsize=(12, 8))
sns.barplot(x='total_votes', y='actors', data=high, palette='viridis')
plt.xlabel("Total Votes")
plt.ylabel("Actors")
plt.title("Top 10 Actors in high-rated movies")
plt.show()

# Assuming 'year', 'avg_vote' (IMDb rating), and 'votes' columns are in your DataFrame
# Group by year to calculate the average IMDb rating and total votes each year
yearly_stats = new_data.groupby('year').agg(avg_rating=('avg_vote', 'mean'), total_votes=('votes', 'sum')).reset_index()

# Create the plot
fig, ax1 = plt.subplots(figsize=(10, 4))

# Plot average IMDb rating on the primary y-axis
sns.lineplot(data=yearly_stats, x='year', y='avg_rating', marker='o', color='b', ax=ax1)
ax1.set_ylabel('Average IMDb Rating', color='b')
ax1.tick_params(axis='y', labelcolor='b')
ax1.set_title('Average IMDb Rating and Total Votes by Year')

# Create a second y-axis for total votes
ax2 = ax1.twinx()
sns.lineplot(data=yearly_stats, x='year', y='total_votes', marker='o', color='r', ax=ax2)
ax2.set_ylabel('Total Votes', color='r')
ax2.tick_params(axis='y', labelcolor='r')

# Show the plot
plt.show()

from scipy.stats import pearsonr

# Calculate the Pearson correlation coefficient
correlation, p_value = pearsonr(new_data['duration'], new_data['avg_vote'])
print(f"Correlation between duration and IMDb rating: {correlation:.2f}")
print(f"P-value: {p_value:.2f}")

# Scatter plot to visualize the relationship
plt.figure(figsize=(10, 6))
sns.scatterplot(data=new_data, x='duration', y='avg_vote', alpha=0.5)
plt.title("Scatter Plot of Movie Duration vs IMDb Rating")
plt.xlabel("Duration (minutes)")
plt.ylabel("IMDb Rating (avg_vote)")
plt.show()