Top IMDB Shows Analysis(EDA)

This is an Exploratory Data Analysis of the top IMDB TV shows

import numpy as np import pandas as pd import os for dirname, _, filenames in os.walk('/work/imdb_tvshows.csv'): for filename in filenames: print(os.path.join(dirname, filename))

Reading the data after importing the necessary libraries

df = pd.read_csv("/work/imdb_tvshows.csv")

Data info

df.head(4)

df.tail(4)

This returns a random sample of rows/columns

df.sample(4)

df.rename(columns = {'EpisodeDuration(in Minutes)':'runtime'}, inplace = True)

df.shape

df.isna().sum()

print([col for col in df.columns if df[col].isna().sum()>0])

The features above have missing values, imputation can be done but we aren't building a model. Hence imputing those features would result in misleading insights.

#finding Dulpicates df.duplicated().sum()

df.dropna(inplace=True)

df.describe()

df.info()

Univariate Analysis

import plotly.express as px

df["Title"].value_counts() titles =df["Title"].value_counts().index[:10] title_occurence =df["Title"].value_counts().values[:10] fig = px.bar(x = titles,y = title_occurence,labels={"x":"Show Title","y":"Repeated"},title="Shows With Same Titles",template="ggplot2",color_discrete_sequence =['green']*len(df)) #Top 10 Movies fig.show()

run_t = df["runtime"].value_counts().index rt_count =df["runtime"].value_counts().values fi =px.bar(y=run_t,x=rt_count,labels={"x":"No of Movies","y":"Runtime"},title="Runtime (Minutes) ") fi.update_layout(yaxis=dict(autorange="reversed"),title_x=0.5)

#Top 6 Genres genre = df["Genres"].value_counts() fig = px.pie(values = genre.values[:6],names=genre.index[:6],title="Top 6 Genres") fig.update_layout(title_x=0.432)

!pip install wordcloud

#World CLoud import matplotlib.pyplot as plt from wordcloud import WordCloud genre = genre genre.index=genre.index.map(str) wordcloud = WordCloud(background_color="white").generate_from_frequencies(genre) plt.figure(figsize = (12,8),dpi=50) plt.imshow(wordcloud) plt.axis("off") plt.show()

genre

#Top 6 Genres ratings = df["Rating"].value_counts() ratings.index=ratings.index.map(str) wordcloud = WordCloud().generate_from_frequencies(ratings) plt.imshow(wordcloud) plt.axis("off") plt.show()

#Top 15 Shows top_15 = df.sort_values(["Votes","Rating"],ascending=False)[:15] top_15.loc[:,["Title","Years","Genres","Rating","Votes"]]