Skip to content
import pandas as pd 
import matplotlib.pyplot as plt

#Read DataFrame netflix_data.csv
df_netflix = pd.read_csv("netflix_data.csv")

#Subset a DataFrame to select the type of movie
subset_netflix = df_netflix[df_netflix["type"] == "Movie"]

#Filter values
movies_90s = subset_netflix[(subset_netflix["release_year"] >= 1990) & (subset_netflix["release_year"] < 2000)]

#Visualizing a distribution
plt.hist(movies_90s["duration"])
plt.title('Distribution of Movie Durations in the 1990s')
plt.xlabel('Duration (minutes)')
plt.ylabel('Number of Movies')
plt.show()

duration = 100

#Subsetting by genre
action_movies_90s = movies_90s[movies_90s["genre"] == "Action"]

short_movie_count = 0

for lab, row in action_movies_90s.iterrows():
    if row["duration"] < 90: 
        short_movie_count = short_movie_count + 1

    else:
        short_movie_count = short_movie_count
        
print(short_movie_count)