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")

# --- Step 1: Import your 'toolbox' ---
# We import the pandas library, which is the main tool for data analysis.
# We give it the nickname 'pd' to save time, which is the standard practice.
import pandas as pd

# --- Step 2: Load the data ---
# We use the pandas 'read_csv' tool to read our 'netflix_data.csv' file.
# We save this entire table in a variable called 'df' (which stands for DataFrame).
# This 'df' variable is now our main "filing cabinet" or spreadsheet.
df = pd.read_csv("netflix_data.csv")


# --- Step 3: Solve Task 1 (Find the most frequent 1990s movie duration) ---

# First, we create a new, smaller table called 'movies_1990s'.
# This is our "filter" pattern. We are selecting rows from 'df'
# that match our rules.
movies_1990s = df[
    
    # Rule 1: The 'release_year' column must be greater than or equal to 1990
    (df['release_year'] >= 1990) & 
    
    # We use '&' (AND) to connect our rules.
    
    # Rule 2: The 'release_year' column must be less than or equal to 1999
    (df['release_year'] <= 1999)
]

# Now, we work with our NEW 'movies_1990s' table.
# 1. We select *only* the 'duration' column.
# 2. We use the '.mode()' function to find the most common value.
# 3. .mode() gives us a list (in case of a tie), so we use [0] to get the first item.
# 4. We save this single number into the 'duration' variable.
duration = movies_1990s['duration'].mode()[0]


# --- Step 4: Solve Task 2 (Count short 1990s action movies) ---

# We create another new, filtered table.
# This time, we are filtering the main 'df' table with FOUR rules.
short_action_movies_1990s = df[
    
    # Rule 1: The 'genre' column must be exactly 'Action'.
    # We use '==' (double equals) to check if two things are equal.
    (df['genre'] == 'Action') &
    
    # Rule 2: The 'duration' column must be less than 90.
    (df['duration'] < 90) &
    
    # Rule 3: The 'release_year' must be 1990 or newer.
    (df['release_year'] >= 1990) &
    
    # Rule 4: The 'release_year' must be 1999 or older.
    (df['release_year'] <= 1999)
]

# Finally, we use the built-in Python 'len()' function.
# 'len()' gets the length (or the total number of rows) of our new table.
# We save this count (which is an integer) into the 'short_movie_count' variable.
short_movie_count = len(short_action_movies_1990s)


# --- End of Project ---
# The DataCamp project will automatically check the final values stored in
# your 'duration' and 'short_movie_count' variables to pass the project.

# --- Displaying the Answers ---
# Now, we use the "loud" print() function to see what's in our variables
print("The most frequent 90s duration is:")
print(duration)

print("The number of short action movies from the 90s is:")
print(short_movie_count)

# --- Imports needed for plotting ---
import matplotlib.pyplot as plt

# --- Visualization for Task 1 ---
print(f"The most frequent duration is: {duration} minutes")

# Create a figure (drawing canvas) and set its size
plt.figure(figsize=(10, 6)) 

# Plot a histogram of the 'duration' column from your 1990s data
plt.hist(movies_1990s['duration'], bins=20, edgecolor='black') 

# Add a title (using an f-string to include your 'duration' variable)
plt.title(f'Distribution of Movie Durations in the 1990s (Mode: {duration} mins)') 

# Label the x-axis and y-axis
plt.xlabel('Movie Duration (minutes)') 
plt.ylabel('Number of Movies') 

# Add a light grid for readability
plt.grid(axis='y', alpha=0.75) 

# Display the plot
plt.show()

# --- Imports needed for plotting ---
import matplotlib.pyplot as plt

# --- Visualization for Task 2 ---
# This part recalculates the genre counts, just to be safe
genre_counts_1990s = movies_1990s['genre'].value_counts().head(10)

print(f"The number of short action movies is: {short_movie_count}")

# Create a figure and set its size
plt.figure(figsize=(12, 7)) 

# Plot a bar chart of the top 10 genres
genre_counts_1990s.plot(kind='bar', color='skyblue', edgecolor='black')

# Add a title that includes your 'short_movie_count' variable
plt.title(f'Top 10 Movie Genres in the 1990s (Short Action Count: {short_movie_count})')

# Label the axes
plt.xlabel('Genre')
plt.ylabel('Number of Movies')

# Rotate the x-axis labels so they are readable
plt.xticks(rotation=45, ha='right') 

# Adjust layout to prevent labels from being cut off
plt.tight_layout() 

# Display the plot
plt.show()