EDA TED Talks

import pandas as pd import seaborn as sns import matplotlib.pyplot as plt

df = pd.read_csv('data.csv')

df.head()

df.shape

df.info()

df.isnull().sum()

df.nunique()

# Date df.sort_values('date', ascending=False)[['title', 'date']]

df.sort_values('date', ascending=True)[['title', 'date']]

# Views df.sort_values('views', ascending=False)[['title', 'views']]

# Views df.sort_values('views', ascending=True)[['title', 'views']]

#Likes df.sort_values('likes', ascending=False)[['title', 'likes']]

#Likes df.sort_values('likes', ascending=True)[['title', 'likes']]

df.nunique()

df.sort_values('likes', ascending=False)[['author', 'likes']]

df.groupby('author')['likes'].mean().sort_values(ascending=False)

df.groupby('author')['views'].sum().sort_values(ascending=False)

The authors below are the viewest in all TED Talks

df['author'].value_counts()

df.nunique()

df['date'].hist() plt.xticks(rotation=90) plt.show()

df.describe()

df.plot(kind='box', vert=False)

df.corr()

sns.pairplot(df)