ML - Pipeline

⏹ Pipeline

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']

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

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

pipe = Pipeline(estimators)

# 어떤 step으로 움직이는지 
pipe.steps

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

pipe.steps[0]

('scaler', StandardScaler())

pipe['scaler']

StandardScaler()

set parameter

# step이름 + 언더바 2개 '__' + 속성이름
pipe.set_params(clf__max_depth=2)
pipe.set_params(clf__random_state=13)

pipeline을 이용한 분류기 생성

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)

X_train

scaler, 분류기 학습 따로하지 않고 pipe를 이용해서 한번에 실행

pipe.fit(X_train, y_train)

from sklearn.metrics import accuracy_score

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

print('Train Accuracy : ', accuracy_score(y_train, y_pred_train))
print('Test Accuracy : ', accuracy_score(y_test, y_pred_test))

Train Accuracy :  0.9657494708485664
Test Accuracy :  0.9576923076923077