[ML] Pipeline을 이용한 와인데이터 분석

1. 와인데이터 받아오기

import pandas as pd

red_url = 'https://raw.githubusercontent.com/PinkWink/ML_tutorial/master/dataset/winequality-red.csv'
white_url = 'https://raw.githubusercontent.com/PinkWink/ML_tutorial/master/dataset/winequality-white.csv'

red_wine = pd.read_csv(red_url, sep= ';')
white_wine = pd.read_csv(white_url, sep= ';')

red_wine['color'] = 1.
white_wine['color'] = 0.

wine = pd.concat([red_wine, white_wine])

X = wine.drop(['color'], axis=1)
y = wine['color']

2. 레드/화이트 와인 분류기의 동작 Process

- 여기서 test_train_split은 Pipeline 내부가 아니다.

3. 위 그림을 Pipeline을 코드로 구현

from sklearn.pipeline import Pipeline
from sklearn.tree import DecisionTreeClassifier
from sklearn.preprocessing import StandardScaler

estimators = [
        ('scaler', StandardScaler()),
        ('clf', DecisionTreeClassifier())
    ]

pipe = Pipeline(estimators)

pipe.steps

# [('scaler', StandardScaler()), ('clf', DecisionTreeClassifier())]

4. set_params

pipe.set_params(clf__max_depth = 2)
pipe.set_params(clf__random_state=13)

# Pipeline(steps=[
			('scaler', StandardScaler()), 
	        ('clf', DecisionTreeClassifier(max_depth=2, random_state=13))
            ])

5. Pipeline을 이용한 분류기 구성

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=13, stratify=y)

pipe.fit(X_train, y_train)

# 성능 확인 
from sklearn.metrics import accuracy_score

y_pred_tr = pipe.predict(X_train)
y_pred_test = pipe.predict(X_test)

print('train Acc : ',accuracy_score(y_train, y_pred_tr))
print('test Acc : ',accuracy_score(y_test, y_pred_test))

# train Acc :  0.9657494708485664
# test Acc :  0.9576923076923077