Carlos-Francisco Méndez-Cruz

Obtaining training and test data sets

...@@ -38,17 +38,11 @@ from nltk.corpus import stopwords ...@@ -38,17 +38,11 @@ from nltk.corpus import stopwords
38 # 1) Best model 38 # 1) Best model
39 39
40 # Examples 40 # Examples
41 -# Sentences 41 +# python3.4 training-validation-v1.py
42 -# C:\Anaconda2\python trainingTesting_Sklearn_crfsuite.py --inputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS\trainingTest_Datasets --trainingFile sentencesTraining.txt --testFile sentencesTest.txt --outputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS > output.TrainingTestingCRF.20161106_1.txt 42 +# --inputPath /export/space1/users/compu2/bionlp/conditional-random-fields/data-sets
43 -# C:\Anaconda2\python trainingTesting_Sklearn_crfsuite.py --inputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS\trainingTest_Datasets --trainingFile sentencesTraining.txt --testFile sentencesTest.txt --outputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS --filterStopWords > output.TrainingTestingCRF.20161106_2.txt 43 +# --trainingFile training-data-set-70.txt
44 -# C:\Anaconda2\python trainingTesting_Sklearn_crfsuite.py --inputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS\trainingTest_Datasets --trainingFile sentencesTraining.txt --testFile sentencesTest.txt --outputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS --filterSymbols > output.TrainingTestingCRF.20161106_3.txt 44 +# --testFile test-data-set-30.txt
45 -# C:\Anaconda2\python trainingTesting_Sklearn_crfsuite.py --inputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS\trainingTest_Datasets --trainingFile sentencesTraining.txt --testFile sentencesTest.txt --outputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS --filterStopWords --filterSymbols > output.TrainingTestingCRF.20161106_4.txt 45 +# --outputPath /export/space1/users/compu2/bionlp/conditional-random-fields/reports
46 -
47 -# Aspects
48 -# C:\Anaconda2\python trainingTesting_Sklearn_crfsuite.py --inputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS\trainingTest_Datasets --trainingFile aspectsTraining.txt --testFile aspectsTest.txt --outputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS > output.TrainingTestingCRF.20161106_5.txt
49 -# C:\Anaconda2\python trainingTesting_Sklearn_crfsuite.py --inputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS\trainingTest_Datasets --trainingFile aspectsTraining.txt --testFile aspectsTest.txt --outputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS --filterStopWords > output.TrainingTestingCRF.20161106_6.txt
50 -# C:\Anaconda2\python trainingTesting_Sklearn_crfsuite.py --inputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS\trainingTest_Datasets --trainingFile aspectsTraining.txt --testFile aspectsTest.txt --outputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS --filterSymbols > output.TrainingTestingCRF.20161106_7.txt
51 -# C:\Anaconda2\python trainingTesting_Sklearn_crfsuite.py --inputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS\trainingTest_Datasets --trainingFile aspectsTraining.txt --testFile aspectsTest.txt --outputPath C:\Users\cmendezc\Documents\GENOMICAS\AUTOMATIC_SUMMARIZATION_TFS\trainingTest_CRF_TERM_TAGS --filterStopWords --filterSymbols > output.TrainingTestingCRF.20161106_8.txt
52 46
53 ################################# 47 #################################
54 # FUNCTIONS # 48 # FUNCTIONS #
......