Kaggle Project - Pima Indians Diabetes Database

1. Pima Indians Diabetes Database

 

 

2. logistic 회귀 이용 코드

 

 

 

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
 
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
from sklearn.metrics import roc_auc_score
 
def get_clf_eval(y_test,pred):
    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_score = roc_auc_score(y_test,pred)
    print("오차행렬")
    print(confusion)
    print('정확도 : {0:.4f}, 정밀도 : {1:.4f}, 재현율 : {2:.4f}, F1 : {3:.4f}, ROC AUC 값 {4:.4f}: '.format(accuracy, precision, recall, f1, roc_score))
 
 
diabets_data = pd.read_csv('diabetes.csv')
print(diabets_data['Outcome'].value_counts())
"""
0    500
1    268
"""
 
 
print(diabets_data.head(5))
"""
Name: Outcome, dtype: int64
   Pregnancies  Glucose  BloodPressure  ...  DiabetesPedigreeFunction  Age  Outcome
0            6      148             72  ...                     0.627   50        1
1            1       85             66  ...                     0.351   31        0
2            8      183             64  ...                     0.672   32        1
3            1       89             66  ...                     0.167   21        0
4            0      137             40  ...                     2.288   33        1
"""
 
 
 
print(diabets_data.info())
"""
[5 rows x 9 columns]
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 768 entries, 0 to 767
Data columns (total 9 columns):
Pregnancies                 768 non-null int64
Glucose                     768 non-null int64
BloodPressure               768 non-null int64
SkinThickness               768 non-null int64
Insulin                     768 non-null int64
BMI                         768 non-null float64
DiabetesPedigreeFunction    768 non-null float64
Age                         768 non-null int64
Outcome                     768 non-null int64
"""
 
 
X = diabets_data.iloc[:,:-1]
y = diabets_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()
lr_clf.fit(X_train,y_train)
pred = lr_clf.predict(X_test)
get_clf_eval(y_test,pred)
 
"""
오차행렬
[[87 13]
 [22 32]]
정확도 : 0.7727, 정밀도 : 0.7111, 재현율 : 0.5926, F1 : 0.6465, ROC AUC 값 0.7313:
"""
 
 

 

<출처> 

1. 파이썬 머신러닝 완벽 가이드