机器学习专题：python实现（1）

模型选择

# -*- coding: utf-8 -*-
"""
Created on Tue Sep  3 10:10:10 2019

@author: xllix
"""

# R2 Score
 
def lets_try(train,labels):
    results={}
    def test_model(clf):
        
        cv = KFold(n_splits=5,shuffle=True,random_state=45)
        r2 = make_scorer(r2_score)
        r2_val_score = cross_val_score(clf, train, labels, cv=cv,scoring=r2)
        scores=[r2_val_score.mean()]
        return scores
 
    clf = linear_model.LinearRegression()
    results["Linear"]=test_model(clf)
    
    clf = svm.SVR()
    results["SVM RBF"]=test_model(clf)
    
    #clf = linear_model.Ridge()
    #results["Ridge"]=test_model(clf)
    
    #clf = linear_model.BayesianRidge()
    #results["Bayesian Ridge"]=test_model(clf)
    
    #clf = linear_model.HuberRegressor()
    #results["Hubber"]=test_model(clf)
    
    #clf = linear_model.Lasso(alpha=1e-4)
    #results["Lasso"]=test_model(clf)
    
    #clf = BaggingRegressor()
    #results["Bagging"]=test_model(clf)
    
    #clf = RandomForestRegressor()
    #results["RandomForest"]=test_model(clf)
    
    #clf = AdaBoostRegressor()
    #results["AdaBoost"]=test_model(clf)
    
    #clf = svm.SVR(kernel="linear")
    #results["SVM Linear"]=test_model(clf)
    
    results = pd.DataFrame.from_dict(results,orient='index')
    results.columns=["R Square Score"] 
    results=results.sort(columns=["R Square Score"],ascending=False)
    results.plot(kind="bar",title="Model Scores")
    axes = plt.gca()
    axes.set_ylim([0.5,1])
    return results
#————————————————
#版权声明：本文为CSDN博主「DASEason」的原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接及本声明。
#原文链接：https://blog.csdn.net/qq547276542/article/details/75455629

SVM 网格调参

# -*- coding: utf-8 -*-
"""
Created on Fri Aug 30 21:26:42 2019

@author: xllix
"""
import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

from sklearn import datasets
from sklearn import preprocessing
from sklearn import neighbors
from sklearn import svm
from sklearn import tree

from time import time

from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import train_test_split

from sklearn.svm import SVC
from sklearn.linear_model import LogisticRegression

from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import RandomForestClassifier

from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import LabelEncoder

from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline
from sklearn.metrics import classification_report

iris = datasets.load_iris()

#构建参数字典
parameters = {'kernel':('linear', 'rbf'), 'C':[1, 2, 4], 'gamma':[0.125, 0.25, 0.5 ,1, 2, 4]}

svr = svm.SVC()
clf = GridSearchCV(svr, parameters, n_jobs=-1)
clf.fit(iris.data, iris.target)
cv_result = pd.DataFrame.from_dict(clf.cv_results_)
with open('cv_result.csv','w') as f:
     cv_result.to_csv(f)   
print('The parameters of the best model are: ')
print(clf.best_params_)
y_pred = clf.predict(iris.data)
print(classification_report(y_true=iris.target, y_pred=y_pred))

#————————————————
#版权声明：本文为CSDN博主「Young_618」的原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接及本声明。
#原文链接：https://blog.csdn.net/cymy001/article/details/78578665

k折交叉验证

# -*- coding: utf-8 -*-
"""
Created on Tue Sep  3 08:57:44 2019

@author: xllix
"""
#https://blog.csdn.net/cymy001/article/details/78578665
#首要工作：切分数据集train/validation/test（训练集上再切出来一部分作为验证集，用于评估模型，防止过拟合 ）
from sklearn.datasets import load_iris 

from sklearn.model_selection import KFold
iris = load_iris()
kfold = KFold(n_splits=5)
scores = cross_val_score(logreg, iris.data, iris.target, cv=kfold)

#或shuffle添加了随机扰动,打乱样本顺序,再进行k折切分样本------------
from sklearn.model_selection import KFold
kfold = KFold(n_splits=3, shuffle=True, random_state=0)
scores = cross_val_score(logreg, iris.data, iris.target, cv=kfold)