def main(argv):
""" function: main
--------------
KDD process for Reuter article database
:param argv: commend line arguments
"""
start_time = time.time()
# Preprocessing =
# 1. Text Extraction
# 2. Feature Selection
# 3. Feature Vector Generation
print('Step 1: Preprocessing')
fv = preprocessing.begin()
# Classification = 3x2 Experiment Set
# K-Nearest-Neighbors, Decision-Tree, Naive Bayes
# Standard & Pared-Down Feature Vector
print('\nStep 2: Classification (Skipped); Uncomment to Run')
# classification.begin(fv)
# Clustering = 2x2x2 Experiment Set
print('\nStep 3: Clustering')
clustering.begin(fv)
# Report Total Running Time
end_time = time.time() - start_time
print '\nProcess finished in', end_time, 'seconds!'
def main(argv):
""" function: main
--------------
KDD process for Reuter article database
:param argv: commend line arguments
"""
start_time = time.time()
# Preprocessing =
# 1. Text Extraction
# 2. Feature Selection
# 3. Feature Vector Generation
print('Step 1: Preprocessing')
fv = preprocessing.begin()
# Classification = 3x2 Experiment Set
# K-Nearest-Neighbors, Decision-Tree, Naive Bayes
# Standard & Pared-Down Feature Vector
print('\nStep 2: Classification (Skipped); Uncomment to Run')
# classification.begin(fv)
# Clustering = 2x2x2 Experiment Set
print('\nStep 3: Clustering')
clustering.begin(fv)
# Report Total Running Time
end_time = time.time() - start_time
print '\nProcess finished in', end_time, 'seconds!'
def main(argv):
""" function: main
--------------
KDD process for Reuter article database
:param argv: commend line arguments
"""
start_time = time.time()
# Preprocessing =
# 1. Text Extraction
# 2. Feature Selection
# 3. Feature Vector Generation
print ("Step 1: Preprocessing")
fv = preprocessing.begin()
# Minhash for k = 16, 32, 64, 128, 256
print ("\nStep 2: K-Minwise Hashing:")
minwisehash.begin(fv)
# Report Total Running Time
end_time = time.time() - start_time
print "\nProcess finished in", end_time, "seconds!"
