[파이썬] DecisionTree (winequality-white)

 

 

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.metrics import classification_report
from sklearn.tree import DecisionTreeClassifier
import os
import pydotplus
from sklearn.tree import export_graphviz
from IPython.display import Image

wine_data = pd.read_csv('winequality-white.csv',delimiter=';',dtype=float)
wine_data.head(10)

x_data = wine_data.iloc[:,0:-1]
y_data = wine_data.iloc[:,-1]

# Score 값이 7보다 작으면 0,  7보다 크거나 같으면 1로 값 변경.
y_data = np.array([1 if i>=7 else 0 for i in y_data])
x_data.head(5)


train_x, test_x, train_y, test_y = train_test_split(x_data, y_data, test_size = 0.3,random_state=42)


wine_tree = DecisionTreeClassifier(criterion='gini', max_depth=5,splitter='random')
wine_tree.fit(train_x, train_y)

y_pred_train = wine_tree.predict(train_x)
y_pred_test = wine_tree.predict(test_x)

print("Train Data:", accuracy_score(train_y, y_pred_train))
print("Test Data" , accuracy_score(test_y, y_pred_test))


y_true, y_pred = test_y, wine_tree.predict(test_x)
print(classification_report(y_true, y_pred))

# path 설정 -  자신의 설치한 경로.
# Graphviz설치 : https://graphviz.org/download/   (설치시 path 추가)
os.environ["PATH"] += os.pathsep + r'C:/Program Files/Graphviz/bin'

dot_data = export_graphviz(wine_tree, out_file=None,feature_names=x_data.columns,
                               class_names='Qual', filled=True, rounded=True, special_characters=True)

graph = pydotplus.graph_from_dot_data(dot_data)


# 이미지의 depth 는 모델 학습의 depth의 영향을 받음.
# 현재 이미지는 depth = 5 
# error : Graphviz's executables not found   (Graphviz's설치로 해결)
Image(graph.create_png())

 

다운로드 (2).png

0.50MB

 

 

 

 

 

- Data download

https://question99.tistory.com/191

[파이썬] data (winequality-white)