"""
this is a example shows load saved model and test new samples
notice in GlobalInfo.Init and other initialize functions
the second parameter - LoadFromFile is true, means load trained result
"""
import sys, os
sys.path.append(os.path.join(os.getcwd(), '../'))
from pymining.math.matrix import Matrix
from pymining.math.text2matrix import Text2Matrix
from pymining.nlp.segmenter import Segmenter
from pymining.common.global_info import GlobalInfo
from pymining.common.configuration import Configuration
from pymining.preprocessor.chisquare_filter import ChiSquareFilter
from pymining.classifier.naive_bayes import NaiveBayes
if __name__ == "__main__":
config = Configuration.FromFile("conf/test.xml")
GlobalInfo.Init(config, "__global__", True)
txt2mat = Text2Matrix(config, "__matrix__", True)
chiFilter = ChiSquareFilter(config, "__filter__", True)
nbModel = NaiveBayes(config, "naive_bayes", True)
[testx, testy] = txt2mat.CreatePredictMatrix("data/test.txt")
[testx, testy] = chiFilter.MatrixFilter(testx, testy)
[resultY, precision] = nbModel.Test(testx, testy)
print precision
import sys, os
sys.path.append(os.path.join(os.getcwd(), '../'))
from pymining.math.matrix import Matrix
from pymining.math.text2matrix import Text2Matrix
from pymining.nlp.segmenter import Segmenter
from pymining.common.global_info import GlobalInfo
from pymining.common.configuration import Configuration
from pymining.preprocessor.chisquare_filter import ChiSquareFilter
from pymining.classifier.naive_bayes import NaiveBayes
from pymining.classifier.lda import Lda
if __name__ == "__main__":
config = Configuration.FromFile("conf/test.xml")
GlobalInfo.Init(config, "__global__")
txt2mat = Text2Matrix(config, "__matrix__")
[trainx, trainy] = txt2mat.CreateTrainMatrix("data/cluster.200")
chiFilter = ChiSquareFilter(config, "__filter__")
chiFilter.TrainFilter(trainx, trainy)
[trainx, trainy] = chiFilter.MatrixFilter(trainx, trainy)
lda = Lda(config, "lda")
lda.Train(trainx, trainy, 10)
from pymining.preprocessor.data_format import *
import time
from time import clock as now
if __name__ == "__main__":
config = Configuration.FromFile("conf/test.xml")
#---------------------------------------------------------------------------------1.text data-----------------------------------------------------------------------------------
### C=100 kernel=RBF p=0.03
### Recall = 0.973913043478 Precision = 0.888888888889 Accuracy = 0.886666666667
### F(beta=1) = 0.604792440094 F(beta=2) = 0.738299274885 AUCb = 0.786956521739
GlobalInfo.Init(config, "__global__")
txt2mat = Text2Matrix(config, "__matrix__")
[trainx, trainy] = txt2mat.CreateTrainMatrix("data/train.txt")
chiFilter = ChiSquareFilter(config, "__filter__")
chiFilter.TrainFilter(trainx, trainy)
[trainx, trainy] = chiFilter.MatrixFilter(trainx, trainy)
for i in range(0, trainx.nRow):
if trainy[i] == 3:
trainy[i] = 1
else:
trainy[i] = -1
[testx, testy] = txt2mat.CreatePredictMatrix("data/test.txt")
[testx, testy] = chiFilter.MatrixFilter(testx, testy)
testx.nCol = trainx.nCol
for i in range(0, testx.nRow):
if testy[i] == 3:
testy[i] = 1
else:
testy[i] = -1