import sys
import os
import numpy
if len(sys.argv) < 2:
print ERROR+" Please provide the target CSV file containing the data.\n"
sys.exit()
file_name = str(sys.argv[1])
if not os.path.isfile(file_name):
print ERROR+" File "+file_name+" not found.\n"
sys.exit()
#load everything into a matrix (not very scalable I think)
data_matrix = files.load_into_matrix(file_name,num_targets=NUM_TARGETS,num_attributes=NUM_ATTRS,input_delimiter=INPUT_DELIMITER,skip_first=HAS_HEADER)
#normalizing and shuffling
data_matrix = prep.normalize(data_matrix,NUM_ATTRS,NUM_TARGETS,NORMALIZE_TARGETS)
data_matrix = prep.shuffle(data_matrix)
#training set is twice as large as test set
train_set_matrix = prep.take_train_set(data_matrix,TRAIN_RATIO)
test_set_matrix = prep.take_test_set(data_matrix,TRAIN_RATIO)
# finding out the target directory where i should save the partitions
current_dir = os.path.dirname(os.path.realpath(__file__))
partitions_directory = files.get_partitions_dir_from_file_name(file_name)
constants.py\n"""
sys.exit()
dir_name = sys.argv[1].lstrip('.').rstrip('/').strip(" ")
if not os.path.isfile(dir_name+'/train_set.csv'):
print ERROR+" File "+dir_name+"/train_set.csv not found.\n"
sys.exit()
if not os.path.isfile(dir_name+'/test_set.csv'):
print ERROR+" File "+dir_name+"/test_set.csv not found.\n"
sys.exit()
train_set_file = dir_name+'/train_set.csv'
train_set = files.load_into_matrix(train_set_file,skip_first=False)
# we won't load the targets because they're what we're trying to predict
prediction_set = files.load_into_matrix(dir_name+'/test_set.csv',skip_first=False,num_attributes=NUM_ATTRS,load_targets=False,num_targets=NUM_TARGETS)
#some attributes may be ignored if user has set config option EXCLUDE_ATTRS
attributes_to_use = filter(lambda x: False if x in EXCLUDE_ATTRS else True,np.arange(NUM_ATTRS))
#training the network
#this is where the weights (between the input and the hidden layers) are kept
wij = ann.init_input_weights(len(attributes_to_use),NUM_NEURONS_HIDDEN_LAYER,NUM_DIGITS)
#these are the weights between the hidden layer and the output neuron (one per neuron in the hidden layer)
wj = ann.init_output_weights(NUM_NEURONS_HIDDEN_LAYER,NUM_DIGITS)
