olympics_analysis_app / preprocessor.py
ritish369's picture
Commit to ad remaining required files
eb0f487
raw
history blame contribute delete
387 Bytes
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