logistic regression

데이터 로드

In [20]:

import pandas as pd

wine_url = "https://raw.githubusercontent.com/PinkWink/ML_tutorial/master/dataset/wine.csv"


wine = pd.read_csv(wine_url, index_col=0)
wine.head()

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality	color
0	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5	1
1	7.8	0.88	0.00	2.6	0.098	25.0	67.0	0.9968	3.20	0.68	9.8	5	1
2	7.8	0.76	0.04	2.3	0.092	15.0	54.0	0.9970	3.26	0.65	9.8	5	1
3	11.2	0.28	0.56	1.9	0.075	17.0	60.0	0.9980	3.16	0.58	9.8	6	1
4	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5	1

Plain text view

   fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \
0            7.4              0.70         0.00             1.9      0.076   
1            7.8              0.88         0.00             2.6      0.098   
2            7.8              0.76         0.04             2.3      0.092   
3           11.2              0.28         0.56             1.9      0.075   
4            7.4              0.70         0.00             1.9      0.076   

   free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \
0                 11.0                  34.0   0.9978  3.51       0.56   
1                 25.0                  67.0   0.9968  3.20       0.68   
2                 15.0                  54.0   0.9970  3.26       0.65   
3                 17.0                  60.0   0.9980  3.16       0.58   
4                 11.0                  34.0   0.9978  3.51       0.56   

   alcohol  quality  color  
0      9.4        5      1  
1      9.8        5      1  
2      9.8        5      1  
3      9.8        6      1  
4      9.4        5      1

맛 등급 추가

In [21]:

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

X = wine.drop(['taste', 'quality'], axis=1)
y = wine['taste']

데이터 분리

In [22]:

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=42, stratify=y)

logistic regression 적용

In [23]:

from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler

estimators = [
    ('scaler', StandardScaler()),
    ('lr', LogisticRegression(solver='liblinear', random_state=42))
]
pipe = Pipeline(estimators)
pipe.fit(X_train, y_train)

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

print("Train Accuracy: {:.3f}".format(accuracy_score(y_train, y_pred_tr)))
print("Test Accuracy: {:.3f}".format(accuracy_score(y_test, y_pred_test)))

Train Accuracy: 0.742
Test Accuracy: 0.739

decision tree 적용

In [24]:

from sklearn.tree import DecisionTreeClassifier

dt = DecisionTreeClassifier(max_depth=2, random_state=42)
dt.fit(X_train, y_train)

models = {
    'Logistic Regression': pipe,
    'Decision Tree': dt
}

ROC AUC 그래프를 이용한 모델간 비교

In [25]:

from sklearn.metrics import roc_curve
import matplotlib.pyplot as plt

plt.figure(figsize=(10, 8))
plt.plot([0, 1], [0, 1])
for model_name, model in models.items():
    pred = model.predict_proba(X_test)[:, 1]
    fpr, tpr, thresholds = roc_curve(y_test, pred)
    plt.plot(fpr, tpr, label=model_name)

plt.grid()
plt.legend()
plt.show()

현재 상황에서 두 모델을 비교했을 때, logistic regression 모델이 decision tree 모델보다 낫다는 것을 알 수 있다.