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

Go to a project
Toggle navigation Toggle navigation pinning
Carlos-Francisco Méndez-Cruz
01169cd8 1 parent 32da8634

Training, crossvalidation and testing dataset

Inline Side-by-side
Showing 1 changed file with 36 additions and 36 deletions
......@@ -157,38 +157,6 @@ if __name__ == "__main__":
print(" Number of training class I: {}".format(y_train.count('I')))
print(" Shape of training matrix: {}".format(X_train.shape))
print("Reading testing data and true classes...")
X_test = None
if args.saveData:
y_test = []
testingData = []
with open(os.path.join(args.inputPath, args.inputTestingData), encoding='utf8', mode='r') \
as iFile:
for line in iFile:
line = line.strip('\r\n')
listLine = line.split(',')
testingData.append(listLine[1:])
X_test = csr_matrix(testingData, dtype='double')
with open(os.path.join(args.inputPath, args.inputTestingClasses), encoding='utf8', mode='r') \
as iFile:
for line in iFile:
line = line.strip('\r\n')
y_test.append(line)
print(" Saving matrix and classes...")
joblib.dump(X_test, os.path.join(args.outputModelPath, args.inputTestingData + '.jlb'))
joblib.dump(y_test, os.path.join(args.outputModelPath, args.inputTestingClasses + '.class.jlb'))
print(" Done!")
else:
print(" Loading matrix and classes...")
X_test = joblib.load(os.path.join(args.outputModelPath, args.inputTestingData + '.jlb'))
y_test = joblib.load(os.path.join(args.outputModelPath, args.inputTestingClasses + '.class.jlb'))
print(" Done!")
print(" Number of testing classes: {}".format(len(y_test)))
print(" Number of testing class A: {}".format(y_test.count('A')))
print(" Number of testing class I: {}".format(y_test.count('I')))
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)
......@@ -252,12 +220,44 @@ if __name__ == "__main__":
X_train, y_train = sm.fit_sample(X_train, y_train)
print(" After transformtion with {}".format(args.imbalanced))
print(" Number of testing classes: {}".format(len(y_test)))
print(" Number of testing class A: {}".format(y_test.count('A')))
print(" Number of testing class I: {}".format(y_test.count('I')))
print(" Shape of testing matrix: {}".format(X_test.shape))
print(" Number of training classes: {}".format(len(y_train)))
print(" Number of training class A: {}".format(y_train.count('A')))
print(" Number of training class I: {}".format(y_train.count('I')))
print(" Shape of training matrix: {}".format(X_train.shape))
print(" Data transformation done in : %fs" % (time() - t1))
print("Reading testing data and true classes...")
X_test = None
if args.saveData:
y_test = []
testingData = []
with open(os.path.join(args.inputPath, args.inputTestingData), encoding='utf8', mode='r') \
as iFile:
for line in iFile:
line = line.strip('\r\n')
listLine = line.split(',')
testingData.append(listLine[1:])
X_test = csr_matrix(testingData, dtype='double')
with open(os.path.join(args.inputPath, args.inputTestingClasses), encoding='utf8', mode='r') \
as iFile:
for line in iFile:
line = line.strip('\r\n')
y_test.append(line)
print(" Saving matrix and classes...")
joblib.dump(X_test, os.path.join(args.outputModelPath, args.inputTestingData + '.jlb'))
joblib.dump(y_test, os.path.join(args.outputModelPath, args.inputTestingClasses + '.class.jlb'))
print(" Done!")
else:
print(" Loading matrix and classes...")
X_test = joblib.load(os.path.join(args.outputModelPath, args.inputTestingData + '.jlb'))
y_test = joblib.load(os.path.join(args.outputModelPath, args.inputTestingClasses + '.class.jlb'))
print(" Done!")
print(" Number of testing classes: {}".format(len(y_test)))
print(" Number of testing class A: {}".format(y_test.count('A')))
print(" Number of testing class I: {}".format(y_test.count('I')))
print(" Shape of testing matrix: {}".format(X_test.shape))
jobs = -1
paramGrid = []
nIter = 20
......