Olympics Data Analysis

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

df=pd.read_csv('athlete_events.csv')
region_df=pd.read_csv('noc_regions.csv')

df.tail()

df=df[df['Season']=='Summer']

df.shape

df.tail()

region_df.tail()

df=df.merge(region_df,on='NOC',how='left')

df.head()

df['region'].unique()

df.isnull().sum()

df.duplicated().sum()

df.drop_duplicates(inplace=True)