Training, crossvalidation and testing binding thrombin dataset

@@ -5,11 +5,13 @@ from time import time
 import argparse
 from sklearn.naive_bayes import BernoulliNB
 from sklearn.svm import SVC
-from sklearn.neighbors import NearestCentroid
+from sklearn.neighbors import KNeighborsClassifier
 from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix, \
     classification_report
 from sklearn.externals import joblib
+from sklearn import model_selection
 from scipy.sparse import csr_matrix
+import scipy
 
 __author__ = 'CMendezC'
 
@@ -47,7 +49,7 @@ __author__ = 'CMendezC'
 # --kernel linear
 
 # 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-model.mod --outputReportPath /home/compu2/bionlp/lcg-bioinfoI-bionlp/clasificacion-automatica/binding-thrombin-dataset/reports --outputReportFile SVM.txt --classifier SVM
+# 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
 
 ###########################################################
 #                       MAIN PROGRAM                      #
@@ -77,6 +79,9 @@ if __name__ == "__main__":
                       choices=('BernoulliNB', 'SVM', 'NearestCentroid'), default='SVM')
     parser.add_argument("--saveData", dest="saveData", action='store_true',
                       help="Save matrices")
+    parser.add_argument("--kernel", dest="kernel",
+                      help="Kernel SVM", metavar="NAME",
+                      choices=('linear', 'rbf', 'poly'), default='linear')
 
     args = parser.parse_args()
 
@@ -92,6 +97,7 @@ if __name__ == "__main__":
     print("File to place evaluation report: " + str(args.outputReportFile))
     print("Classifier: " + str(args.classifier))
     print("Save matrices: " + str(args.saveData))
+    print("Kernel: " + str(args.kernel))
 
     # Start time
     t0 = time()
@@ -157,15 +163,45 @@ if __name__ == "__main__":
     print("   Number of testing class I: {}".format(y_test.count('I')))
     print("   Shape of testing matrix: {}".format(X_test.shape))
 
-    if args.classifier == "BernoulliNB":
-        classifier = BernoulliNB()
-    elif args.classifier == "SVM":
+    jobs = -1
+    paramGrid = []
+    nIter = 20
+    crossV = 10
+    print("Defining randomized grid search...")
+    if args.classifier == 'SVM':
+        # SVM
         classifier = SVC()
-    elif args.classifier == "NearestCentroid":
-        classifier = NearestCentroid()
+        if args.kernel == 'rbf':
+            paramGrid = {'C': scipy.stats.expon(scale=100),
+                         'gamma': scipy.stats.expon(scale=.1),
+                         'kernel': ['rbf'], 'class_weight': ['balanced', None]}
+        elif args.kernel == 'linear':
+            paramGrid = {'C': scipy.stats.expon(scale=100),
+                         'kernel': ['linear'],
+                         'class_weight': ['balanced', None]}
+        elif args.kernel == 'poly':
+            paramGrid = {'C': scipy.stats.expon(scale=100),
+                         'gamma': scipy.stats.expon(scale=.1), 'degree': [2, 3],
+                         'kernel': ['poly'], 'class_weight': ['balanced', None]}
+        myClassifier = model_selection.RandomizedSearchCV(classifier,
+                    paramGrid, n_iter=nIter,
+                    cv=crossV, n_jobs=jobs, verbose=3)
+    elif args.classifier == 'BernoulliNB':
+        # BernoulliNB
+        classifier = BernoulliNB()
+        paramGrid = {'alpha': scipy.stats.expon(scale=1.0)}
+        myClassifier = model_selection.RandomizedSearchCV(classifier, paramGrid, n_iter=nIter,
+                                                          cv=crossV, n_jobs=jobs, verbose=3)
+    elif args.classifier == 'kNN':
+        # kNN
+        classifier = KNeighborsClassifier()
+        paramGrid = {'n_neighbors ': [3, 5, 7]}
+        myClassifier = model_selection.RandomizedSearchCV(classifier, paramGrid, n_iter=nIter,
+                                                          cv=crossV, n_jobs=jobs, verbose=3)
     else:
         print("Bad classifier")
         exit()
+    print("   Done!")
 
     print("Training...")
     classifier.fit(X_train, y_train)