机器学习入门数据集--5.皮马人糖尿病预测数据集

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

from sklearn.linear_model import LogisticRegression
import pandas as  pd
import numpy as np

df = pd.read_csv("/Users/wangsen/ai/13/homework/diabetes.csv")
df.info()
target = df.pop("Outcome")
data = df.values
print(data[:5])

lr = LogisticRegression()
lr.fit(data,target)
score = lr.score(data,target)
print("训练集上的预测准确率",score)

from sklearn.feature_selection import SelectKBest 
from sklearn.feature_selection import chi2

select_top_4 = SelectKBest(score_func=chi2, k =4)
select_top_4.fit(data,target)
data_4 = select_top_4.transform(data)

from sklearn.preprocessing import StandardScaler
X = StandardScaler().fit_transform(data_4)
X = data
y = target
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import SVC
from xgboost import XGBClassifier
import sklearn

models = []
models.append(("LR", LogisticRegression())) #逻辑回归
models.append(("NB", GaussianNB())) # 高斯朴素贝叶斯
models.append(("KNN", KNeighborsClassifier(10))) #K近邻分类
models.append(("DT", DecisionTreeClassifier())) #决策树分类
models.append(("SVM", SVC())) # 支持向量机分类
models.append(("xgboost", XGBClassifier())) # xgboost
'''
estimator：数据对象 
X：数据 
y：预测数据 
soring：调用的方法
cv：交叉验证生成器或可迭代的次数 
n_jobs：同时工作的cpu个数（-1代表全部）
verbose：详细程度
fit_params：传递给估计器的拟合方法的参数
pre_dispatch：控制并行执行期间调度的作业数量。
'''
results = []
names = []
for name, model in models:
    kflod = KFold(n_splits=10, random_state=22)
    cv_result = cross_val_score(model, X,y, cv = kflod,scoring="accuracy")
    names.append(name)
    results.append(cv_result)
 
for i in range(len(names)):
    print(names[i], results[i].mean())

LR 0.7695146958304853
NB 0.7551777170198223
KNN 0.74865003417635
DT 0.6952494873547506
SVM 0.6510252904989747
xgboost 0.7668660287081339