import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# 载入数据
data = pd.read_csv('./diabetes.csv')
data.head()

# 查看数据类型
data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 768 entries, 0 to 767
Data columns (total 7 columns):
Pregnancies                 768 non-null int64
Glucose                     768 non-null float64
BloodPressure               768 non-null float64
BMI                         768 non-null float64
DiabetesPedigreeFunction    768 non-null float64
Age                         768 non-null int64
Outcome                     768 non-null int64
dtypes: float64(4), int64(3)
memory usage: 42.1 KB

# 查看数据基本信息
data.describe()

# 查看标签分布
print(data.Outcome.value_counts())
# 使用柱状图的方式画出标签个数统计
data.Outcome.value_counts().plot(kind="bar")
plt.show()

0    500
1    268
Name: Outcome, dtype: int64

# 查看两个目标分类下，各个特征的数据分布
sns.pairplot(data, hue = 'Outcome')
plt.show()

# 将葡萄糖，血压，皮肤厚度，胰岛素，身体质量指数中的0替换为nan
colume = ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI']
data[colume] = data[colume].replace(0,np.nan)

# 查看数据类型
data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 768 entries, 0 to 767
Data columns (total 9 columns):
Pregnancies                 768 non-null int64
Glucose                     763 non-null float64
BloodPressure               733 non-null float64
SkinThickness               541 non-null float64
Insulin                     394 non-null float64
BMI                         757 non-null float64
DiabetesPedigreeFunction    768 non-null float64
Age                         768 non-null int64
Outcome                     768 non-null int64
dtypes: float64(6), int64(3)
memory usage: 54.1 KB

# 设定阀值，非空值需要超过总数量的80%以上
thresh_count = data.shape[0]*0.8
# 若某一列数据缺失的数量超过20%就会被删除
data = data.dropna(thresh=thresh_count, axis=1) 

# 导入插补库
from sklearn.preprocessing import Imputer 
# 此处采用均值插补的方法来填充缺失值
imr = Imputer(missing_values='NaN', strategy='mean', axis=0) 
colume =  ['Glucose', 'BloodPressure', 'BMI']
# 进行插补
data[colume] = imr.fit_transform(data[colume]) 

D:\anaconda3\lib\site-packages\ipykernel_launcher.py:7: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  import sys
D:\anaconda3\lib\site-packages\pandas\core\indexing.py:543: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  self.obj[item] = s

plt.figure(figsize=(12,10))  
# 画热力图，数值为两个变量之间的相关系数
p=sns.heatmap(data.corr(), annot=True) 
plt.show()

# 把数据切分为特征x和标签y
x = data.drop("Outcome",axis = 1)
y = data.Outcome

from sklearn.model_selection import train_test_split
# 切分数据集，stratify=y表示切分后训练集和测试集中的数据类型的比例跟切分前y中的比例一致
# 比如切分前y中0和1的比例为1:2，切分后y_train和y_test中0和1的比例也都是1:2
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3, stratify=y)

# 此处使用逻辑回归进行建模
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report
LR = LogisticRegression()
LR.fit(x_train,y_train)
pre_result= LR.predict(x_test)
print(classification_report(y_test, pre_result))

             precision    recall  f1-score   support
          0       0.78      0.91      0.84       150
          1       0.76      0.52      0.62        81
avg / total       0.77      0.77      0.76       231