Decision Tree를 이용한 와인데이터 분석

1. 데이터 불러오기 & 탐색

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.head()

white_wine.head()

# red, white 두 데이터 합치기 
red_wine['color']= 1.
white_wine['color'] = 0.

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

wine['quality'].unique()

array([5, 6, 7, 4, 8, 3, 9], dtype=int64)

wine['quality'].value_counts()

6    2836
5    2138
7    1079
4     216
8     193
3      30
9       5
Name: quality, dtype: int64

import plotly.express as px

fig = px.histogram(wine, x='quality')
fig.show()

fig = px.histogram(wine, x='quality',color = 'color')
fig.show()

2. 데이터 분리, 모델 생성 및 학습

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

# 훈련용, 테스트용 나누기 
from sklearn.model_selection import train_test_split
import numpy as np

X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2, random_state=13)
np.unique(y_train, return_counts=True)

(array([0., 1.]), array([3913, 1284], dtype=int64))

# 훈련용과 테스트용이 레드/화이트에 따라 어느정도 구분이 되는지 확인
import plotly.graph_objects as go

fig = go.Figure()
fig.add_trace(go.Histogram(x=X_train['quality'], name='Train'))
fig.add_trace(go.Histogram(x=X_test['quality'], name='Test'))

fig.update_layout(barmode='overlay')
fig.update_traces(opacity=0.75)
fig.show()

# Decision Tree 훈련
from sklearn.tree import DecisionTreeClassifier

wine_tree = DecisionTreeClassifier(max_depth=2, random_state=13)
wine_tree.fit(X_train,y_train)

# 학습결과
from sklearn.metrics import accuracy_score

y_pred_tr = wine_tree.predict(X_train)
y_pred_test = wine_tree.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 :  0.9553588608812776
test Acc :  0.9569230769230769

와인데이터 몇개 항목의 boxplot 그려보기 데이터

fig = go.Figure()
fig.add_trace(go.Box(y=X['fixed acidity'], name='fixed acidity'))
fig.add_trace(go.Box(y=X['chlorides'], name='chlorides'))
fig.add_trace(go.Box(y=X['quality'], name='quality'))

from sklearn.preprocessing import MinMaxScaler, StandardScaler

ss = StandardScaler()
mms = MinMaxScaler()

ss.fit(X)
mms.fit(X)

X_ss = ss.transform(X)
X_mms = mms.transform(X)

X_ss_pd = pd.DataFrame(X_ss,columns=X.columns)
X_mms_pd = pd.DataFrame(X_mms,columns=X.columns)

# MinMaxScaler
fig = go.Figure()
fig.add_trace(go.Box(y=X_mms_pd['fixed acidity'], name='fixed acidity'))
fig.add_trace(go.Box(y=X_mms_pd['chlorides'], name='chlorides'))
fig.add_trace(go.Box(y=X_mms_pd['quality'], name='quality'))
fig.show()

# StandardScaler  : 평균을 0. 표준편차를 1에 맞추기 
fig.add_trace(go.Box(y=X_ss_pd['fixed acidity'], name='fixed acidity'))
fig.add_trace(go.Box(y=X_ss_pd['chlorides'], name='chlorides'))
fig.add_trace(go.Box(y=X_ss_pd['quality'], name='quality'))
fig.show()

# MinMax 확인 
X_train,X_test,y_train,y_test = train_test_split(X_mms_pd, y, test_size=0.2, random_state=13)

wine_tree = DecisionTreeClassifier(max_depth=2, random_state=13)
wine_tree.fit(X_train,y_train)

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

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

Train Acc :  0.9553588608812776
Test Acc :  0.9569230769230769

# StandardScaler 확인 
X_train,X_test,y_train,y_test = train_test_split(X_ss_pd, y, test_size=0.2, random_state=13)

wine_tree = DecisionTreeClassifier(max_depth=2, random_state=13)
wine_tree.fit(X_train,y_train)

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

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

Train Acc :  0.9553588608812776
Test Acc :  0.9569230769230769

결정나무는 화이트/레드 와인 구분을 어떻게 하는가?

import graphviz
from graphviz import Source
from sklearn.tree import export_graphviz

Source(export_graphviz(wine_tree, feature_names=X_train.columns,
                      class_names=['W','R'],
                      rounded=True, filled=True))    

# 레드와인과 화이트와인 구분하는 중요한 특성
dict(zip(X_train.columns, wine_tree.feature_importances_))
# max_depth를 높이면 위의 수치도 변함

{'fixed acidity': 0.0,
 'volatile acidity': 0.0,
 'citric acid': 0.0,
 'residual sugar': 0.0,
 'chlorides': 0.24230360549660776,
 'free sulfur dioxide': 0.0,
 'total sulfur dioxide': 0.7576963945033922,
 'density': 0.0,
 'pH': 0.0,
 'sulphates': 0.0,
 'alcohol': 0.0,
 'quality': 0.0}

✔ 이진분류

quality컬럼 이진화

wine['taste'] = [1. if grade > 5 else 0. for grade in wine['quality']]
wine.head()

# 레드/화이트 분류와 동일 과정을 거치기 
X = wine.drop(['taste'],axis=1)
y = wine['taste']

X_train,X_test, y_train, y_test = train_test_split(X,y,test_size=0.2, random_state=13)

wine_tree = DecisionTreeClassifier(max_depth=2, random_state=13)
wine_tree.fit(X_train,y_train)

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

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

Train Acc :  1.0
Test Acc :  1.0

import matplotlib.pyplot as plt
import sklearn.tree as tree

plt.figure(figsize=(12,8))
tree.plot_tree(wine_tree, feature_names=X.columns);

# taste 와 함께 quality컬럼도 같이 제거해주어야 함.
X = wine.drop(['taste','quality'],axis=1)
y = wine['taste']

X_train,X_test, y_train, y_test = train_test_split(X,y,test_size=0.2, random_state=13)

wine_tree = DecisionTreeClassifier(max_depth=2, random_state=13)
wine_tree.fit(X_train,y_train)

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

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

Train Acc :  0.7294593034442948
Test Acc :  0.7161538461538461

plt.figure(figsize=(12,8))
tree.plot_tree(wine_tree, feature_names=X.columns,
            rounded=True,
            filled=True)
            
plt.show()