21 lines
630 B
Python
21 lines
630 B
Python
|
import pandas as pd
|
||
|
|
from sklearn.preprocessing import MinMaxScaler
|
||
|
|
|
||
|
|
def prepare_data(file_path):
|
||
|
|
data = pd.read_csv(file_path, sep=';')
|
||
|
|
|
||
|
|
data = pd.get_dummies(data, columns=['Sex', 'Medal'])
|
||
|
|
data = data.drop(columns=['Name', 'Team', 'NOC', 'Games', 'Year', 'Season', 'City', 'Sport', 'Event'])
|
||
|
|
|
||
|
|
data = data.fillna(0)
|
||
|
|
scaler = MinMaxScaler()
|
||
|
|
data = pd.DataFrame(scaler.fit_transform(data), columns=data.columns)
|
||
|
|
|
||
|
|
return data
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
file_path = 'olympics-124-years-datasettill-2020/Data.csv'
|
||
|
|
data = prepare_data(file_path)
|
||
|
|
|
||
|
|
data.to_csv('processed_data.csv', index=False)
|