로지스틱 회귀모델 (Logistic Regression)

0. 핵심개념 및 사이킷런 알고리즘 API 링크

sklearn.linear_model.LogisticRegression

1. 분석 데이터 준비

import warnings
warnings.filterwarnings("ignore")
import pandas as pd
data=pd.read_csv('breast-cancer-wisconsin.csv', encoding='utf-8')
X=data[data.columns[1:10]]
y=data[["Class"]]

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test=train_test_split(X, y, stratify=y, random_state=42)

from sklearn.preprocessing import MinMaxScaler
scaler=MinMaxScaler()
scaler.fit(X_train) # 훈련데이터의 변수들 최소, 최대값을 기준으로 삼는다
X_scaled_train=scaler.transform(X_train) # 정규화 변환해라
X_scaled_test=scaler.transform(X_test)

2. 기본모델 적용

from sklearn.linear_model import LogisticRegression
model=LogisticRegression()
model.fit(X_scaled_train, y_train)
pred_train=model.predict(X_scaled_train)
model.score(X_scaled_train, y_train)

0.97265625

from sklearn.metrics import confusion_matrix
confusion_train=confusion_matrix(y_train, pred_train)
print("훈련데이터 오차행렬:\n", confusion_train)

훈련데이터 오차행렬:
 [[328   5]
 [  9 170]]
 
from sklearn.metrics import classification_report
cfreport_train=classification_report(y_train, pred_train)
print("분류예측 레포트:\n", cfreport_train)


분류예측 레포트:
               precision    recall  f1-score   support

           0       0.97      0.98      0.98       333
           1       0.97      0.95      0.96       179

    accuracy                           0.97       512
   macro avg       0.97      0.97      0.97       512
weighted avg       0.97      0.97      0.97       512

pred_test=model.predict(X_scaled_test)
model.score(X_scaled_test, y_test)

0.9590643274853801

confusion_test=confusion_matrix(y_test, pred_test)
print("테스트데이터 오차행렬:\n", confusion_test)

테스트데이터 오차행렬:
 [[106   5]
 [  2  58]]
 
from sklearn.metrics import classification_report
cfreport_test=classification_report(y_test, pred_test)
print("분류예측 레포트:\n", cfreport_test)

분류예측 레포트:
               precision    recall  f1-score   support

           0       0.98      0.95      0.97       111
           1       0.92      0.97      0.94        60

    accuracy                           0.96       171
   macro avg       0.95      0.96      0.96       171
weighted avg       0.96      0.96      0.96       171

3. Grid Search

param_grid={'C': [0.001, 0.01, 0.1, 1, 10, 100]}
from sklearn.model_selection import GridSearchCV
grid_search=GridSearchCV(LogisticRegression(), param_grid, cv=5)
grid_search.fit(X_scaled_train, y_train)

GridSearchCV(cv=5, estimator=LogisticRegression(),
             param_grid={'C': [0.001, 0.01, 0.1, 1, 10, 100]})
             
print("Best Parameter: {}".format(grid_search.best_params_))
print("Best Score: {:.4f}".format(grid_search.best_score_))
print("TestSet Score: {:.4f}".format(grid_search.score(X_scaled_test, y_test)))

Best Parameter: {'C': 10}
Best Score: 0.9726
TestSet Score: 0.9591

4. Random Search

from scipy.stats import randint
param_distribs={'C': randint(low=0.001, high=100)}
from sklearn.model_selection import RandomizedSearchCV
random_search=RandomizedSearchCV(LogisticRegression(), 
                                 param_distributions=param_distribs, n_iter=100, cv=5)
random_search.fit(X_scaled_train, y_train)


RandomizedSearchCV(cv=5, estimator=LogisticRegression(), n_iter=100,
                   param_distributions={'C': <scipy.stats._distn_infrastructure.rv_frozen object at 0x000002621CED5FD0>})
                   
print("Best Parameter: {}".format(random_search.best_params_))
print("Best Score: {:.4f}".format(random_search.best_score_))
print("TestSet Score: {:.4f}".format(random_search.score(X_scaled_test, y_test)))

Best Parameter: {'C': 11}
Best Score: 0.9745
TestSet Score: 0.9591