分类预测，交叉验证调超参数

import numpy as np
from pandas import read_csv
import pandas as pd
import sys  
import importlib
from sklearn.neighbors import KNeighborsClassifier     
from sklearn.ensemble import GradientBoostingClassifier    
from sklearn import svm
from sklearn import cross_validation
from sklearn.metrics import hamming_loss
from sklearn import metrics    
importlib.reload(sys)
from sklearn.linear_model import LogisticRegression 
from imblearn.combine import SMOTEENN
from sklearn.tree import DecisionTreeClassifier 
from sklearn.ensemble import RandomForestClassifier  #92%
from sklearn import tree
from xgboost.sklearn import XGBClassifier
from sklearn.linear_model import SGDClassifier
from sklearn import neighbors
from sklearn.naive_bayes import BernoulliNB
import matplotlib as mpl
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
from numpy import mat
from sklearn.cross_validation import cross_val_score


‘‘‘分类0-1‘‘‘
root1="D:/ProgramData/station3/get_10.csv"
root2="D:/ProgramData/station3/get_more.csv"
root3="D:/ProgramData/station3/get_more9_10.csv"#现已删除

data1 = read_csv(root3) #数据转化为数组
#print(data1)
data1=data1.values
#print(root3)


‘‘‘设置调参的参数范围‘‘‘
k_range = range(10,30)
k_scores = []
for k in k_range:
    print(k)
    clf = XGBClassifier(learning_rate= 0.28, min_child_weight=0.7, max_depth=21,
                        gamma=0.2, n_estimators = k ,seed=1000)

    X_Train = data1[:,:-1]
    Y_Train = data1[:,-1]

    X, y = SMOTEENN().fit_sample(X_Train, Y_Train)
    
    ‘‘‘交叉验证，循环跑，cv是每次循的次数‘‘‘
    scores = cross_val_score(clf, X, y, cv=10, scoring=‘accuracy‘)
    ‘‘‘得到平均值‘‘‘
    k_scores.append(scores.mean())

print(k_scores)

‘‘‘画出图像‘‘‘
plt.plot(k_range, k_scores)
plt.xlabel("Value of K for KNN")
plt.ylabel("Cross validated accuracy")
plt.show()