举个例来说明

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn import linear_model
from sklearn.preprocessing import Imputer
from sklearn.preprocessing import MinMaxScaler

def analyze_data(sData_Path, sUse_AllCol = True):
    csvType = '第一次测定 ---采用数据的全部列---'
    Use_cols = None
    Col_LastIndex = 8
    if not sUse_AllCol:
        csvType = '第二次测定 ---去掉[第2列（血糖浓度）][第5列（血清胰岛素）]---'
        Use_cols = [0, 2, 3, 5, 6, 7, 8]
        Col_LastIndex = len(Use_cols) - 1
    print('\n{}'.format(csvType))
    df = pd.read_csv(sData_Path, header=None, usecols=Use_cols)
    X = df.iloc[:, :Col_LastIndex]
    Y = df.iloc[:, Col_LastIndex:].values.flatten()
    # 缺失值处理
    imp_lastIndex = Col_LastIndex
    imp = Imputer(missing_values=0, strategy='median', axis=0)
    imp.fit(X.iloc[:, 1:imp_lastIndex])
    X.iloc[:, 1:imp_lastIndex] = imp.transform(X.iloc[:, 1:imp_lastIndex])
    # 特征缩放为[0 - 1]之间
    ms = MinMaxScaler()
    ms.fit(X)
    X = ms.transform(X)
    X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.15, random_state=0)
    svc = SVC()                             #使用支持向量机模型
    svc.fit(X_train, Y_train)               #训练模型
    print('评分 Test score: {:.3f}'.format(svc.score(X_test, Y_test)))  #评分 (预测的准确率)
    clf = linear_model.LinearRegression()   #线性回归模型
    clf.fit(X, Y)
    print("回归系数:")
    print(np.round(clf.coef_, 3))
    print('切片: {}'.format(round(clf.intercept_, 3)))

analyze_data("pima-indians-diabetes.data.csv", True)    #调用函数 第一次测定
analyze_data("pima-indians-diabetes.data.csv", False)   #调用函数 第二次测定