#===================================================
# Learning to rank - Train
#===================================================

print "\nStarting Training Phase:\n"

arrays = []
ys = []
namess = []

for subdir, dirs, files in os.walk("train"):
    for i, file in enumerate(files):
        if file.lower().endswith('.txt'):
            # get the file names iteratively
            (prefix, sep, suffix) = file.rpartition('.')
            the_file = os.path.join(os.getcwd(), subdir + os.path.sep + prefix + '.txt')
            the_key_file =  os.path.join(os.getcwd(), subdir + os.path.sep + prefix + '.key')

            try:
                print the_file
                print the_key_file
                # get the features
                feature_array, y, names = get_features_from_file_name(the_file, the_key_file)
                ##print "dimensions", feature_array.shape
                # save the features into lists of arrays
                arrays.append(feature_array)
                ys.append(y)
                namess += names
                print "done", i
            except UnicodeDecodeError:
                "Unicode decode error, skipping"


print "Finished"