피마 인디언 당뇨병 예측

 

 

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline

from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, precision_score, recall_score, roc_auc_score
from sklearn.metrics import f1_score, confusion_matrix, precision_recall_curve, roc_curve
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

diabetes_data = pd.read_csv('diabetes.csv')
print(diabetes_data['Outcome'].value_counts())
diabetes_data.head(3)

diabetes_data.info()

def get_clf_eval(y_test, pred=None, pred_proba=None):
    confusion = confusion_matrix(y_test, pred)
    accuracy = accuracy_score(y_test, pred)
    precision = precision_score(y_test, pred)
    recall = recall_score(y_test, pred)
    f1 = f1_score(y_test, pred)
    roc_auc = roc_auc_score(y_test, pred_proba)
    print('오차행렬')
    print(confusion)
    print('정확도: {0:.4f}, 정밀도: {1:.4f}, 재현율: {2:.4f}, F1: {3:.4f}, AUC: {4:.4f}'.format(accuracy, precision, recall, f1, roc_auc))

X = diabetes_data.iloc[:,:-1]
y = diabetes_data.iloc[:, -1]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 156, stratify=y)

lr_clf = LogisticRegression(solver= 'liblinear')
lr_clf.fit(X_train, y_train)
pred = lr_clf.predict(X_test)
pred_proba = lr_clf.predict_proba(X_test)[:,1]

get_clf_eval(y_test, pred, pred_proba)

diabetes_data.describe()

plt.hist(diabetes_data['Glucose'], bins=100)
plt.show()

zero_features = ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI']
total_count = diabetes_data['Glucose'].count()
for feature in zero_features:
    zero_count = diabetes_data[diabetes_data[feature]==0][feature].count()
    print('{0} 0 건수는 {1}, 퍼센트는 {2:.2f} %'.format(feature, zero_count, 100*zero_count/total_count))

#zero_features 리스트 내부에 저장된 개별 피처들에 대해서 0값을 평균값으로 대체
mean_zero_features = diabetes_data[zero_features].mean()
diabetes_data[zero_featrues] = diabetes_data[zero_features].replace(0, mean_zero_features)

X = diabetes_data.iloc[:, :-1]
y = diabetes_data.iloc[:, -1]

scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size = 0.2, random_state = 156, stratify =y)

lr_clf = LogisticRegression()
lr_clf.fit(X_train, y_train)
pred = lr_clf.predict(X_test)
pred_proba = lr_clf.predict_proba(X_test)[:, 1]

get_clf_eval(y_test, pred, pred_proba)

#임계값을 0.48로 설정한 Binarizer 생성
binarizer = Binarizer(threshold=0.48)
pred_th_048 = binarizer.fit_transform(pred_proba[:,1].reshape(-1,1))