Training, crossvalidation and testing binding thrombin dataset

@@ -10,7 +10,9 @@ from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_sc
     classification_report
     classification_report
 from sklearn.externals import joblib
 from sklearn.externals import joblib
 from sklearn import model_selection
 from sklearn import model_selection
+from sklearn.feature_selection import SelectKBest, chi2
 from scipy.sparse import csr_matrix
 from scipy.sparse import csr_matrix
+from sklearn.decomposition import TruncatedSVD
 import scipy
 import scipy
 
 
 __author__ = 'CMendezC'
 __author__ = 'CMendezC'
@@ -29,13 +31,14 @@ __author__ = 'CMendezC'
 # 9) --classifier Classifier: BernoulliNB, SVM, NearestCentroid.
 # 9) --classifier Classifier: BernoulliNB, SVM, NearestCentroid.
 # 10) --saveData Save matrices
 # 10) --saveData Save matrices
 # 11) --kernel Kernel
 # 11) --kernel Kernel
+# 12) --reduction Feature selection or dimensionality reduction
 
 
 # Ouput:
 # Ouput:
 # 1) Classification model and evaluation report.
 # 1) Classification model and evaluation report.
 
 
 # Execution:
 # Execution:
 
 
-# python training-testing-binding-thrombin.py
+# python training-crossvalidation-testing-binding-thrombin.py
 # --inputPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset
 # --inputPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset
 # --inputTrainingData thrombin.data
 # --inputTrainingData thrombin.data
 # --inputTestingData Thrombin.testset
 # --inputTestingData Thrombin.testset
@@ -47,9 +50,10 @@ __author__ = 'CMendezC'
 # --classifier SVM
 # --classifier SVM
 # --saveData
 # --saveData
 # --kernel linear
 # --kernel linear
+# --reduction SVD200
 
 
 # source activate python3
 # source activate python3
-# python training-testing-binding-thrombin.py --inputPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset --inputTrainingData thrombin.data --inputTestingData Thrombin.testset --inputTestingClasses Thrombin.testset.class --outputModelPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset/models --outputModelFile SVM-linear-model.mod --outputReportPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset/reports --outputReportFile SVM-linear.txt --classifier SVM --kernel linear
+# python training-crossvalidation-testing-binding-thrombin.py --inputPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset --inputTrainingData thrombin.data --inputTestingData Thrombin.testset --inputTestingClasses Thrombin.testset.class --outputModelPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset/models --outputModelFile SVM-linear-model.mod --outputReportPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset/reports --outputReportFile SVM-linear.txt --classifier SVM --kernel linear --reduction SVD200
 
 
 ###########################################################
 ###########################################################
 #                       MAIN PROGRAM                      #
 #                       MAIN PROGRAM                      #
@@ -82,6 +86,9 @@ if __name__ == "__main__":
     parser.add_argument("--kernel", dest="kernel",
     parser.add_argument("--kernel", dest="kernel",
                       help="Kernel SVM", metavar="NAME",
                       help="Kernel SVM", metavar="NAME",
                       choices=('linear', 'rbf', 'poly'), default='linear')
                       choices=('linear', 'rbf', 'poly'), default='linear')
+    parser.add_argument("--reduction", dest="reduction",
+                      help="Feature selection or dimensionality reduction", metavar="NAME",
+                      choices=('SVD200', 'SVD300', 'CHI250', 'CHI2100'), default='SVD200')
 
 
     args = parser.parse_args()
     args = parser.parse_args()
 
 
@@ -98,6 +105,7 @@ if __name__ == "__main__":
     print("Classifier: " + str(args.classifier))
     print("Classifier: " + str(args.classifier))
     print("Save matrices: " + str(args.saveData))
     print("Save matrices: " + str(args.saveData))
     print("Kernel: " + str(args.kernel))
     print("Kernel: " + str(args.kernel))
+    print("Reduction: " + str(args.reduction))
 
 
     # Start time
     # Start time
     t0 = time()
     t0 = time()
@@ -163,6 +171,24 @@ if __name__ == "__main__":
     print("   Number of testing class I: {}".format(y_test.count('I')))
     print("   Number of testing class I: {}".format(y_test.count('I')))
     print("   Shape of testing matrix: {}".format(X_test.shape))
     print("   Shape of testing matrix: {}".format(X_test.shape))
 
 
+    # Feature selection and dimensional reduction
+    if args.reduction is not None:
+        print('Performing dimensionality reduction or feature selection...', args.reduction)
+        if args.reduction == 'SVD200':
+            reduc = TruncatedSVD(n_components=200, random_state=42)
+            X_train = reduc.fit_transform(X_train)
+        if args.reduction == 'SVD300':
+            reduc = TruncatedSVD(n_components=300, random_state=42)
+            X_train = reduc.fit_transform(X_train)
+        elif args.reduction == 'CHI250':
+            reduc = SelectKBest(chi2, k=50)
+            X_train = reduc.fit_transform(X_train, y_train)
+        elif args.reduction == 'CHI2100':
+            reduc = SelectKBest(chi2, k=100)
+            X_train = reduc.fit_transform(X_train, y_train)
+        print("   Done!")
+        print('     New shape of training matrix: ', X_train.shape)
+
     jobs = -1
     jobs = -1
     paramGrid = []
     paramGrid = []
     nIter = 20
     nIter = 20