File size: 387 Bytes
eb0f487
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
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"], dtype="int")], axis=1)
    return df