code

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

# Load the data
netflix_df = pd.read_csv("netflix_data.csv")
netflix_df.head()

# Filter out TV shows from the type
netflix_subset = netflix_df[netflix_df["type"] != "TV Show"]
print(netflix_subset)

# Subseting my dataframe to keep a few necessary columns 

netflix_movies_subset = ["title", "country", "genre", "release_year", "duration"]
netflix_movies = netflix_subset[netflix_movies_subset]
netflix_movies.head()

# Inspect short movies by duration less than 60 mins and perform statistics
short_movies = netflix_movies[netflix_movies["duration"] < 60]
short_movies.head()
statistics = short_movies.describe()
print(statistics)

# Determine average duration for release year
average_duration = netflix_movies.groupby("release_year")["duration"].mean()
# Assign colors to the genre groups
colors = []
for index, row in netflix_movies.iterrows():
    if row["genre"] == "Children":
        colors.append("blue")
    elif row["genre"] == "Documentaries":
        colors.append("red")
    elif row["genre"] == "Stand-Up":
        colors.append("yellow")
    else:
        colors.append("black")
        
# Create a scatter plot for movie duration by release year
fig, ax = plt.subplots(figsize = (12, 6))
ax.scatter(netflix_movies["release_year"], netflix_movies["duration"], 
           c = colors)
ax.plot(average_duration.index, average_duration.values, color = "green",
       linestyle = "-", marker = "o", label = "Average Duration")
ax.set_title("Movie Duration by Year of Release")
ax.set_xlabel("Release year")
ax.set_ylabel("Duration (min)")

ax.legend()
plt.show()

answer = "no"