파이썬 테스트 데이터 분리 실습

과적합 해결: 테스트 데이터 분리 실습¶

• x변수: Fare, Sex
• y변수: Survived

In [ ]:

import seaborn as sns
import matplotlib.pyplot as plt 
import pandas as pd
import numpy as np
import sklearn 

In [ ]:

# 타이타닉 데이터
titanic = pd.read_csv('C:/Users/LOVE/Downloads/vscode/ML/titanic/train.csv')

titanic.head(3)

Out[ ]:

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S

In [ ]:

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(titanic[['Fare', 'Sex']], titanic[['Survived']],
                                                    test_size = 0.3, shuffle = True, random_state = 42,
                                                    stratify = titanic[['Survived']])

In [ ]:

print(X_train.shape, X_test.shape, y_train.shape, y_test.shape)

(623, 2) (268, 2) (623, 1) (268, 1)

In [ ]:

# 원본 데이터에 대한 Y 값의 분포
sns.countplot(titanic, x = 'Survived')

Out[ ]:

<Axes: xlabel='Survived', ylabel='count'>

In [ ]:

sns.countplot(y_train, x = 'Survived')

Out[ ]:

<Axes: xlabel='Survived', ylabel='count'>

In [ ]:

sns.countplot(y_test, x = 'Survived')

Out[ ]:

<Axes: xlabel='Survived', ylabel='count'>