File size: 382 Bytes
8b2b7fb | 1 2 3 4 5 6 7 8 9 10 11 12 | import pandas as pd
def preprocess(df,region_df):
# filtering for summer olympics
df = df[df['Season'] == 'Summer']
# merge with region_df
df = df.merge(region_df, on='NOC', how='left')
# dropping duplicates
df.drop_duplicates(inplace=True)
# one hot encoding medals
df = pd.concat([df, pd.get_dummies(df['Medal'])], axis=1)
return df |