This commit is contained in:
Jakub Zaręba 2023-05-23 23:24:45 +02:00
parent 7d0cef3a54
commit 1918917126
2 changed files with 48573 additions and 12 deletions

View File

@ -1,20 +1,16 @@
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
def prepare_data(file_path):
data = pd.read_csv(file_path, sep=';')
data_path = 'data.csv'
processed_data_path = 'processed_data.csv'
data = pd.get_dummies(data, columns=['Sex', 'Medal'])
data = data.drop(columns=['Name', 'Team', 'NOC', 'Games', 'Year', 'Season', 'City', 'Sport', 'Event'])
data = pd.read_csv(data_path, sep=';')
data = data.fillna(0)
scaler = MinMaxScaler()
data = pd.DataFrame(scaler.fit_transform(data), columns=data.columns)
data = pd.get_dummies(data, columns=['Sex', 'Medal'])
return data
data = data.drop(columns=['Name', 'Team', 'NOC', 'Games', 'Year', 'Season', 'City', 'Sport', 'Event'])
if __name__ == "__main__":
file_path = 'olympics-124-years-datasettill-2020/Data.csv'
data = prepare_data(file_path)
scaler = MinMaxScaler()
data = pd.DataFrame(scaler.fit_transform(data), columns=data.columns)
data.to_csv('processed_data.csv', index=False)
data.to_csv(processed_data_path, index=False)

48565
processed_data.csv Normal file

File diff suppressed because it is too large Load Diff