深度学习|泰坦尼克号生还数据处理

import numpy as np
import pandas as pd

data = pd.read_csv('titanic.csv')
data.head()

data.isnull().sum()

age_mean = data['Age'].mean()
data['Age'] = data['Age'].fillna(age_mean)
data['Embarked'] = data['Embarked'].fillna('S')

data['Sex']= data['Sex'].map({'female':0, 'male': 1}).astype(int)

data = pd.get_dummies(data=data,columns=['Embarked'])

X = data.iloc[:,1:]
Y = data.iloc[:,0]
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.2, random_state=33)

from sklearn import preprocessing
scale = preprocessing.MinMaxScaler()
X_train = scale.fit_transform(X_train)
X_test = scale.transform(X_test)