preprocessing.py

import pandas as pd 
from sys import exit
import numpy as np 

data = pd.read_csv('../../train.csv')
data = data[['Survived', 'Pclass', 'Sex', 'SibSp', 'Parch', 'Embarked']].dropna()

# male = 0
# female = 1
# S = 0
# C = 1
# Q = 2
for index, row in data.iterrows():
	if data.loc[index, "Sex"] == 'male':
		data.loc[index, "Sex"] = 0
	if data.loc[index, "Sex"] == 'female':
		data.loc[index, "Sex"] = 1
	if data.loc[index, "Embarked"] == 'S':
		data.loc[index, "Embarked"] = 0
	if data.loc[index, "Embarked"] == 'C':
		data.loc[index, "Embarked"] = 1
	if data.loc[index, "Embarked"] == 'Q':
		data.loc[index, "Embarked"] = 2
		
data.to_csv('../train1.csv', sep=',')