sklearn实战：糖尿病预测（knn算法）

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

# 加载数据
data = pd.read_csv('datasets/pima-indians-diabetes/diabetes.csv')
print('dataset shape {}'.format(data.shape))
data.head()

dataset shape (768, 9)

.dataframe tbody tr th:only-of-type { vertical-align: middle; } .dataframe tbody tr th { vertical-align: top; } .dataframe thead th { text-align: right; }

	Pregnancies	Glucose	BloodPressure	SkinThickness	Insulin	BMI	DiabetesPedigreeFunction	Age	Outcome
0	6	148	72	35	0	33.6	0.627	50	1
1	1	85	66	29	0	26.6	0.351	31	0
2	8	183	64	0	0	23.3	0.672	32	1
3	1	89	66	23	94	28.1	0.167	21	0
4	0	137	40	35	168	43.1	2.288	33	1

data.groupby("Outcome").size()