def preprocess(lower_threshold, numlines_train, numlines_test, only_trainingset):
csv_train, storage_train, features_train, targets_train, csv_test, \
storage_test, features_test = create_names(lower_threshold, upper_threshold,
numlines_train, numlines_test,
only_trainingset, 1)
'''preprocesses the training data and optionally a separate test data file. Creates features
and extracts targets.
'''
prep = pp(lower_threshold, upper_threshold, numlines_train, numlines_test,
only_trainingset)
#import data from csv files:
prep.import_csv(csv_train, csv_test, storage_train, storage_test)
#create features and save to new csv files:
prep.create_new_csvs(features_train, targets_train, features_test,
storage_train, storage_test)
'''
from NaiveBayes import NaiveBayes
from create_filenames import create_names
import numpy as np
from slice_merge import slice_csv, merge_csvs
lower_threshold = 7
upper_threshold = 100
numlines_train = 5000 # 0 will be interpreted as all lines
numlines_test = 0 # 0 will be interpreted as all lines
slice_size = 1000
use_only_trainingset_and_split = True
features_file_train, targets_file_train, features_file_test, \
predictions_file_test = create_names(lower_threshold, upper_threshold,
numlines_train, numlines_test, 0, 0)
def main():
features_train = None
IDs_train = None
all_targets_train = None
features_file_test = None
try:
print 'load training features...'
features_train, IDs_train = load_features(features_file_train, 1)
print 'load training targets...'
all_targets_train = load_targets(targets_file_train)
print 'load test features...'
features_file_test = load_features(features_file_test, 1)
except IOError:
print "The corresponding files have not been created yet."
'''
from NaiveBayes import NaiveBayes
from create_filenames import create_names
import numpy as np
from slice_merge import slice_csv, merge_csvs
lower_threshold = 5
upper_threshold = 100
numlines_train = 100 # 0 will be interpreted as all lines
split_at = 0.7
features_file_train, targets_file_train, features_file_test, \
probabilities_filename, predictions_filename = create_names(lower_threshold, upper_threshold,
numlines_train, 0, 1, 0)
def main():
features = None
IDs = None
all_targets = None
try:
print 'load training features...'
features, IDs = load_features(features_file_train, 1)
print 'load training targets...'
all_targets = load_targets(targets_file_train)
except IOError:
print "The corresponding files have not been created yet."
print "Please run preprocessing with the same parameters and try again."
raise SystemExit(0)