关于sklearn框架下的SVM,NB,Decision Tree等机器学习算法的使用

import pandas as pd

import os

from sklearn.model_selection import train_test_split

from sklearn.model_selection import GridSearchCV

from sklearn import svm

from sklearn.externals import joblib

from sklearn import tree

from sklearn.ensemble import RandomForestClassifier

import sys

if len(sys.argv)!=5:

    print("Usage:"+sys.argv[0]+" <train set path> <train set read line numbers> <test set path> <test set read line numbers>")

    print("Example:"+sys.argv[0]+" train.csv 10000 test.csv 100")

    sys.exit(1)

datapath=sys.argv[1]

trainLines=sys.argv[2]

testpath=sys.argv[3]

testLines=sys.argv[4]

'''############################Data Set Build#################################'''

data = pd.read_csv(datapath, header=None, nrows=int(trainLines))

print("train set line numbers is "+str(len(data)))

 

x = data.ix[:, 0:5]

y = data.ix[:, 6:]

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.1, random_state=0)

 

'''############################ Model Train #################################'''

#Just modify the corresponding classification algorithm， for example SVM

clf = RandomForestClassifier(n_estimators=100, max_depth=2,random_state=0)

print("start train model")

clf.fit(x_train, y_train)

'''############################ Predict #################################'''

print("start predict data")

#y_predict=best_model.predict(x_test)

#print('Coefficients:%s, intercept %s'%(cls.coef_,cls.intercept_))

print('Validate Score: %.2f' % clf.score(x_test, y_test))

'''############################ Molde Save #################################'''

#save model

model_save_path = "./"

print("Decison Tree Model save...")

save_path_name = model_save_path + "tree_" + "train_model.m"

joblib.dump(clf, save_path_name)

'''############################ Test #################################'''

data = pd.read_csv(testpath, header=None,nrows=int(testLines))

print("test set line numbers is "+str(len(data)))

xtest = data.ix[:, 0:5]

ytest = data.ix[:, 6:]

#print(ytest)

arrytest=ytest[6].tolist()

file_handle=open('originLable.txt',mode='w')

for i in arrytest:

    file_handle.write(str(i)+"\n")

    #print(i)

file_handle.close()

ypredict=clf.predict(xtest)

print('Test Score: %.2f' % clf.score(xtest, ytest))

file_handle=open('predictLable.txt',mode='w')

for i in ypredict:

    file_handle.write(str(i)+"\n")

    #print(i)

file_handle.close()

'''############################END#################################'''

print("END")