import pandas as pd import numpy as np from sklearn import preprocessing import matplotlib.pyplot as plt from sklearn.linear_model import LogisticRegression from sklearn.model_selection import train_test_split import seaborn as sns

d = pd.read_csv("diabetes_data_upload.csv") d.head()

d.columns = ['age', 'gender', 'polyuria','polydipsia','swl','weak', 'polyphagia', 'gt', 'vb', 'itch','irritate','dh', 'pp', 'ms', 'alopesia', 'obesity', 'class']

le = preprocessing.LabelEncoder() for i in d.columns: encode = le.fit_transform(d[i]) d[i] = encode d.head()

d.shape

d['class'].value_counts()

d.groupby('class').mean()

for i in d.columns: pd.crosstab(d[i],d['class']).plot(kind='bar') plt.title('diabetes vs'+ i) plt.xlabel(i) plt.ylabel('counts')

X = d.loc[:, d.columns != 'class'] y = d.loc[:, d.columns == 'class']

!pip install imblearn

from imblearn.over_sampling import SMOTE os = SMOTE(random_state=0) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0) columns = X_train.columns

os_data_X, os_data_y = os.fit_sample(X_train, y_train)

print("length of oversampled data is ",len(os_data_X)) print("Number of no diabetes in oversampled data",len(os_data_y[os_data_y['class']==0])) print("Number of people with diabetes",len(os_data_y[os_data_y['class']==1])) print("Proportion of no diabetes data in oversampled data is ",len(os_data_y[os_data_y['class']==0])/len(os_data_X)) print("Proportion of diabetes data in oversampled data is ",len(os_data_y[os_data_y['class']==1])/len(os_data_X))

d_vars=d.columns.values.tolist() y=['class'] X=[i for i in d_vars if i not in y]

from sklearn.feature_selection import RFE from sklearn.linear_model import LogisticRegression logreg = LogisticRegression() rfe = RFE(logreg, 20) ##这里的20指的是number of features to select, 只要填大于variables的数量的数字即可 rfe = rfe.fit(os_data_X, os_data_y)

print(rfe.support_) print(rfe.ranking_)

import statsmodels.api as sm logit_model=sm.Logit(y_train,X_train) result=logit_model.fit() print(result.summary2())

import statsmodels.api as sm logit_model=sm.Logit(os_data_y,os_data_X) result=logit_model.fit() print(result.summary2())

import statsmodels.api as sm logit_model=sm.Logit(y_test,X_test) result=logit_model.fit() print(result.summary2())

from sklearn.linear_model import LogisticRegression from sklearn import metrics logreg = LogisticRegression() logreg.fit(X_train, y_train)

y_pred = logreg.predict(X_test) print('Accuracy of logistic regression classifier on test set: {:.2f}'.format(logreg.score(X_test, y_test)))

##绘制一个roc curve来检验模型。 ###roc curve距离直线越远越好

from sklearn.metrics import roc_auc_score from sklearn.metrics import roc_curve logit_roc_auc = roc_auc_score(y_test, logreg.predict(X_test)) fpr, tpr, thresholds = roc_curve(y_test, logreg.predict_proba(X_test)[:,1]) plt.figure() plt.plot(fpr, tpr, label='Logistic Regression (area = %0.2f)' % logit_roc_auc) plt.plot([0, 1], [0, 1],'r--') plt.xlim([0.0, 1.0]) plt.ylim([0.0, 1.05]) plt.xlabel('False Positive Rate') plt.ylabel('True Positive Rate') plt.title('Receiver operating characteristic') plt.legend(loc="lower right") plt.savefig('Log_ROC') plt.show()