10. 랜덤 포레스트 (random forest) 02

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets, metrics
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
# 정확도, 혼돈행렬, 리포트
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
# 표준화 lib
from sklearn.preprocessing import StandardScaler

wine = datasets.load_wine();
X = wine.data
y = wine.target

X_train, X_test , y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=123)

sc =  StandardScaler()  

X_train_sc = sc.fit_transform(X_train)
X_test_sc = sc.transform(X_test) # fit을 쓰지 않는 다 fit을 적용시 X_test로 재 학습을 한다

model = RandomForestClassifier(max_depth=2, random_state=124)
model.fit(X_train_sc, y_train)
y_pred = model.predict(X_test_sc)

accuracy_score(y_test, y_pred)
confusion_matrix(y_test, y_pred)
print(classification_report(y_test, y_pred))

              precision    recall  f1-score   support

           0       1.00      1.00      1.00        14
           1       0.86      1.00      0.92        18
           2       1.00      0.86      0.93        22

    accuracy                           0.94        54
   macro avg       0.95      0.95      0.95        54
weighted avg       0.95      0.94      0.94        54