[데이터마이닝] Scikit-learn Winedata Lab4-sample

1번

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_wine

wineData = load_wine()
# print(data.data.shape)  # 178 x 13
# print(data.data)    # 데이터 전체
# print(data.target)  # target => 분류해야 하는 데이터(여기서는 178개)
# print(data.target_names)    # class임 => 얘네로 분류해야 하는 것
# print(data.feature_names)   # 열 이름들

def makeScatter():
    n_classes = 3   # 분류되는 class 개수
    plot_colors = 'ryb'     # 점의 색

    X = wineData.data
    y = wineData.target

    for i, color in zip(range(n_classes), plot_colors):
        idx = np.where(y == i)
        plt.scatter(
            X[idx, 0],
            X[idx, 1],
            c=color,
            edgecolors='black'
        )

 

 

문제 2번

from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.metrics import accuracy_score

# 와인 데이터를 불러오고 train 데이터와 test 데이터로 분류
def loadWinedata():
    wineData = load_wine()
    X_train, X_test, y_train, y_test = train_test_split(wineData.data, wineData.target, test_size=0.2, random_state=30)
    return X_train, X_test, y_train, y_test
    
def wineDecisionTree(X_train, X_test, y_train, y_test):
    model = DecisionTreeClassifier(random_state=42)     # 모델 설정(default 값)
    model.fit(X_train, y_train)     # 데이터 학습
    pred = model.predict(X_test)
    print('DecisionTree 정확도: {:.4f}'.format(accuracy_score(y_test, pred)))

def wineRandomForest(X_train, X_test, y_train, y_test):
    model = RandomForestClassifier(n_estimators=5, random_state=0)  # 랜덤포레스트 사용
    model.fit(X_train, y_train)
    pred = model.predict(X_test)
    print('RandomForest 정확도: {:.4f}'.format(accuracy_score(y_test, pred)))

def wineAdaBoost(X_train, X_test, y_train, y_test):
    model = AdaBoostClassifier(n_estimators=10, random_state=10, learning_rate=0.1)  # 모델 설정
    model.fit(X_train, y_train)   # 학습
    pred = model.predict(X_test)
    print('AdaBoost 정확도: {:.4f}'.format(accuracy_score(y_test, pred)))

 

 

결과

def main():
    X_train, X_test, y_train, y_test = loadWinedata()
    
    makeScatter()
    wineDecisionTree(X_train, X_test, y_train, y_test)
    wineRandomForest(X_train, X_test, y_train, y_test)
    wineAdaBoost(X_train, X_test, y_train, y_test)

main()

DecisionTree 정확도: 0.8889 RandomForest 정확도: 0.9722 AdaBoost 정확도: 0.9444