Carlos-Francisco Méndez-Cruz / lcg-bioinfoI-bionlp

Go to a project
Toggle navigation Toggle navigation pinning
Carlos-Francisco Méndez-Cruz
367fcf6a 1 parent c893be3f

Training, crossvalidation and testing dataset

Inline Side-by-side
Showing 2 changed files with 11 additions and 2 deletions
...@@ -237,6 +237,7 @@ if __name__ == "__main__": ...@@ -237,6 +237,7 @@ if __name__ == "__main__":
237 if args.reduction is not None: 237 if args.reduction is not None:
238 X_test = reduc.transform(X_test) 238 X_test = reduc.transform(X_test)
239 y_pred = myClassifier.predict(X_test) 239 y_pred = myClassifier.predict(X_test)
240 + best_parameters = myClassifier.best_estimator_.get_params()
240 print(" Done!") 241 print(" Done!")
241 242
242 print("Saving report...") 243 print("Saving report...")
...@@ -253,6 +254,8 @@ if __name__ == "__main__": ...@@ -253,6 +254,8 @@ if __name__ == "__main__":
253 oFile.write(str(confusion_matrix(y_test, y_pred)) + '\n') 254 oFile.write(str(confusion_matrix(y_test, y_pred)) + '\n')
254 oFile.write('Classification report: \n') 255 oFile.write('Classification report: \n')
255 oFile.write(classification_report(y_test, y_pred) + '\n') 256 oFile.write(classification_report(y_test, y_pred) + '\n')
257 + for param in sorted(best_parameters.keys()):
258 + oFile.write("\t%s: %r\n" % (param, best_parameters[param]))
256 print(" Done!") 259 print(" Done!")
257 260
258 print("Training and testing done in: %fs" % (time() - t0)) 261 print("Training and testing done in: %fs" % (time() - t0))
......
...@@ -54,14 +54,16 @@ __author__ = 'CMendezC' ...@@ -54,14 +54,16 @@ __author__ = 'CMendezC'
54 # --outputModelPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/structural-domain-dataset/models 54 # --outputModelPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/structural-domain-dataset/models
55 # --outputModelFile SVM-lineal-model.mod 55 # --outputModelFile SVM-lineal-model.mod
56 # --outputReportPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/structural-domain-dataset/reports 56 # --outputReportPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/structural-domain-dataset/reports
57 -# --outputReportFile SVM-lineal.txt 57 +# --outputReportFile SVM-linear.txt
58 # --classifier SVM 58 # --classifier SVM
59 # --saveData 59 # --saveData
60 # --kernel linear 60 # --kernel linear
61 # --reduction SVD200 61 # --reduction SVD200
62 # --removeStopWords 62 # --removeStopWords
63 # --vectorizer b 63 # --vectorizer b
64 -# python training-crossvalidation-testing-dom.py --inputPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/structural-domain-dataset --inputTrainingData trainData.txt --inputTrainingClasses trainClasses.txt --inputTestingData testData.txt --inputTestingClasses testClasses.txt --outputModelPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/structural-domain-dataset/models --outputModelFile SVM-lineal-model.mod --outputReportPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/structural-domain-dataset/reports --outputReportFile SVM-lineal.txt --classifier SVM --kernel linear --saveData --vectorizer b 64 +# --ngrinitial 2
65 +# --ngrfinal 2
66 +# python training-crossvalidation-testing-dom.py --inputPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/structural-domain-dataset --inputTrainingData trainData.txt --inputTrainingClasses trainClasses.txt --inputTestingData testData.txt --inputTestingClasses testClasses.txt --outputModelPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/structural-domain-dataset/models --outputModelFile SVM-lineal-model.mod --outputReportPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/structural-domain-dataset/reports --outputReportFile SVM-linear.txt --classifier SVM --kernel linear --saveData --vectorizer b --ngrinitial 2 --ngrfinal 2 --removeStopWords
65 # --reduction SVD200 67 # --reduction SVD200
66 # --removeStopWords 68 # --removeStopWords
67 69
...@@ -283,6 +285,7 @@ if __name__ == "__main__": ...@@ -283,6 +285,7 @@ if __name__ == "__main__":
283 if args.reduction is not None: 285 if args.reduction is not None:
284 X_test = reduc.transform(X_test) 286 X_test = reduc.transform(X_test)
285 y_pred = myClassifier.predict(X_test) 287 y_pred = myClassifier.predict(X_test)
288 + best_parameters = myClassifier.best_estimator_.get_params()
286 print(" Done!") 289 print(" Done!")
287 290
288 print("Saving report...") 291 print("Saving report...")
...@@ -299,6 +302,9 @@ if __name__ == "__main__": ...@@ -299,6 +302,9 @@ if __name__ == "__main__":
299 oFile.write(str(confusion_matrix(y_test, y_pred)) + '\n') 302 oFile.write(str(confusion_matrix(y_test, y_pred)) + '\n')
300 oFile.write('Classification report: \n') 303 oFile.write('Classification report: \n')
301 oFile.write(classification_report(y_test, y_pred) + '\n') 304 oFile.write(classification_report(y_test, y_pred) + '\n')
305 + for param in sorted(best_parameters.keys()):
306 + oFile.write("\t%s: %r\n" % (param, best_parameters[param]))
307 +
302 print(" Done!") 308 print(" Done!")
303 309
304 print("Training and testing done in: %fs" % (time() - t0)) 310 print("Training and testing done in: %fs" % (time() - t0))
......