糖尿病数据分类（KNN、Decision tree、SVC、Naive bayes、Gradient boosting、Neural network）

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import os
import scipy as sp
import warnings
warnings.filterwarnings('ignore')

diabetes = pd.read_csv('diabetes.csv')
#
# print(diabetes.groupby('Outcome').size())
# print(diabetes.describe())
sns.countplot(diabetes['Outcome'],label="Count")
plt.show()

corr_data = diabetes.corr()
sns.clustermap(corr_data,annot = True, fmt = '.2f')
plt.show()

sns.set_palette(sns.color_palette("Set1", 8))
plt.figure(figsize=(15,7))
sns.heatmap(diabetes.corr(),annot=True,vmin=-1,vmax=1,cmap="YlGnBu")
plt.show()

sns.set_palette(sns.color_palette("Set1", 8))
sns.pairplot(data=diabetes,hue="Outcome",corner=True)
plt.show()

sns.lineplot(x='Glucose', y= 'Insulin', data=diabetes)
plt.show()

from sklearn import metrics
from sklearn.metrics import  classification_report, accuracy_score, precision_score, recall_score,f1_score
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import confusion_matrix,ConfusionMatrixDisplay,plot_confusion_matrix
plt.style.use('ggplot')
from sklearn.model_selection import train_test_split
X = diabetes.drop(columns = 'Outcome')
y = diabetes['Outcome']

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.33,random_state=42)

"""
KNN
"""
from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors=10)
knn.fit(X_train,y_train)
y_pred=knn.predict(X_test)

from sklearn.metrics import accuracy_score,classification_report,confusion_matrix
from sklearn.metrics import r2_score
from sklearn.metrics import mean_squared_error

print("Classification Report is:\n",classification_report(y_test,y_pred))
print("Confusion Matrix:\n",confusion_matrix(y_test,y_pred))
print("Training Score:\n",knn.score(X_train,y_train)*100)
print("Mean Squared Error:\n",mean_squared_error(y_test,y_pred))
print("R2 score is:\n",r2_score(y_test,y_pred))
print(accuracy_score(y_test,y_pred)*100)
print('Accuracy of K-NN classifier on training set: {:.2f}'.format(knn.score(X_train, y_train)))
print('Accuracy of K-NN classifier on test set: {:.2f}'.format(accuracy_score(y_test,y_pred)))

"""
Decision tree
"""
from sklearn.tree import DecisionTreeClassifier
dtree = DecisionTreeClassifier(max_depth=8, random_state=100,criterion='entropy')

dtree.fit(X_train,y_train)
y_pred=dtree.predict(X_test)
from sklearn.metrics import accuracy_score,classification_report,confusion_matrix
from sklearn.metrics import r2_score
from sklearn.metrics import mean_squared_error
print("Classification Report is:\n",classification_report(y_test,y_pred))
print("Confusion Matrix:\n",confusion_matrix(y_test,y_pred))
print("Training Score:\n",dtree.score(X_train,y_train)*100)
print("Mean Squared Error:\n",mean_squared_error(y_test,y_pred))
print("R2 score is:\n",r2_score(y_test,y_pred))
print(accuracy_score(y_test,y_pred)*100)
print("Accuracy on training set: {:.3f}".format(dtree.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(accuracy_score(y_test,y_pred)))

"""
Support vector machine
"""
from sklearn.svm import SVC

svc = SVC()
svc.fit(X_train, y_train)
y_pred=svc.predict(X_test)
from sklearn.metrics import accuracy_score,classification_report,confusion_matrix
from sklearn.metrics import r2_score
from sklearn.metrics import mean_squared_error
print("Classification Report is:\n",classification_report(y_test,y_pred))
print("Confusion Matrix:\n",confusion_matrix(y_test,y_pred))
print("Training Score:\n",svc.score(X_train,y_train)*100)
print("Mean Squared Error:\n",mean_squared_error(y_test,y_pred))
print("R2 score is:\n",r2_score(y_test,y_pred))
print(accuracy_score(y_test,y_pred)*100)
print("Accuracy on training set: {:.3f}".format(svc.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(accuracy_score(y_test,y_pred)))


"""
Naive bayes
"""
from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()
gnb.fit(X_train,y_train)
y_pred=gnb.predict(X_test)
from sklearn.metrics import accuracy_score,classification_report,confusion_matrix
from sklearn.metrics import r2_score
from sklearn.metrics import mean_squared_error
print("Classification Report is:\n",classification_report(y_test,y_pred))
print("Confusion Matrix:\n",confusion_matrix(y_test,y_pred))
print("Training Score:\n",gnb.score(X_train,y_train)*100)
print("Mean Squared Error:\n",mean_squared_error(y_test,y_pred))
print("R2 score is:\n",r2_score(y_test,y_pred))
print(accuracy_score(y_test,y_pred)*100)
print("Accuracy on training set: {:.3f}".format(gnb.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(accuracy_score(y_test,y_pred)))



"""
Gradient boosting
"""
from sklearn.ensemble import GradientBoostingClassifier
gbc=GradientBoostingClassifier()
gbc.fit(X_train,y_train)
y_pred=gbc.predict(X_test)
from sklearn.metrics import accuracy_score,classification_report,confusion_matrix
from sklearn.metrics import r2_score
from sklearn.metrics import mean_squared_error
print("Classification Report is:\n",classification_report(y_test,y_pred))
print("Confusion Matrix:\n",confusion_matrix(y_test,y_pred))
print("Training Score:\n",gbc.score(X_train,y_train)*100)
print("Mean Squared Error:\n",mean_squared_error(y_test,y_pred))
print("R2 score is:\n",r2_score(y_test,y_pred))
print(accuracy_score(y_test,y_pred)*100)
print("Accuracy on training set: {:.3f}".format(gbc.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(accuracy_score(y_test,y_pred)))



"""
Neural network
"""
from sklearn.neural_network import MLPClassifier
mlp = MLPClassifier(random_state=42)
mlp.fit(X_train, y_train)
print("Accuracy on training set: {:.2f}".format(mlp.score(X_train, y_train)))
print("Accuracy on test set: {:.2f}".format(mlp.score(X_test, y_test)))
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.fit_transform(X_test)
mlp = MLPClassifier(random_state=0)
mlp.fit(X_train_scaled, y_train)
print("Accuracy on training set: {:.3f}".format(
    mlp.score(X_train_scaled, y_train)))
print("Accuracy on test set: {:.3f}".format(mlp.score(X_test_scaled, y_test)))
mlp = MLPClassifier(max_iter=1000, alpha=1, random_state=0)
mlp.fit(X_train_scaled, y_train)
print("Accuracy on training set: {:.3f}".format(
    mlp.score(X_train_scaled, y_train)))
print("Accuracy on test set: {:.3f}".format(mlp.score(X_test_scaled, y_test)))

数据集下载