def main(argv=sys.argv):
if len(argv) != 2 and len(argv) != 3:
usage(argv)
config_uri = argv[1]
conf_parser_args = argv[2]
conf_parser = dict((k, True) for k in conf_parser_args.split(','))
setup_logging(config_uri)
settings = get_appsettings(config_uri)
engine = engine_from_config(settings, 'sqlalchemy.')
DBSession.configure(bind=engine)
script_dir = os.path.dirname(__file__)
rel_path_source_data = "./csv/"
source_data_dir = os.path.join(script_dir, rel_path_source_data)
csv_data = parse_data(source_data_dir)
analyze(csv_data, conf_parser)
if len(sys.argv) < 2 or sys.argv[1] == "--help":
print "Usage: control.py controlfile"
print "Usage: control.py -lda trainingfile testfile"
print " Control files look like: "
print " First line: trainingfilename, testfilename"
print " Any number of subsequent lines: epsilon,stepsize,iteration limit, restarts"
print " Training and test files are CSV's with the output variable last"
print " Results are stored in testfilename_resultX where X is the line number from the control CSV"
sys.exit(0)
#lda control here
if sys.argv[1] == "-lda" or sys.argv[1] == "-bayes":
if len(sys.argv) != 4:
print "Usage: control.py (-lda|-bayes) trainingfile testfile"
sys.exit(0)
(x,y)= csv_parser.parse_data(sys.argv[2])
(testX, testY) = csv_parser.parse_data(sys.argv[3])
if sys.argv[1] == "-lda":
runLDA(x,y, testX, testY, sys.argv[3])
else:
runBayes(x,y, testX, testY, sys.argv[3])
sys.exit(0)
#default is logistic regression
(controls, training, test) = csv_parser.parse_control(sys.argv[1])
(x,y)= csv_parser.parse_data(training)
(testX, testY) = csv_parser.parse_data(test)
for i in xrange(len(controls)):
params = controls[i]
if(y[i] == 0):
train_x.append(x[i])
train_y.append(y[i])
del x[i]
del y[i]
num_positives = num_positives - 1
print "size of x: " + str(len(train_x)) + " size of y: " + str(len(train_y)) + "size of testset: " + str(len(testset[0]))
#start off by doing feature selection
#(results, temp_x_onlyspon, temp_x_congress, temp_x_nopers) = testfeaturesubsets(k, train_x, train_y, testset[0], testset[1])
(results) = testfeaturesubsets(k, train_x, train_y, testset[0], testset[1])
for set_name, algo_data in results.iteritems():
print (set_name + "\n LR train" + "\t" + str(algo_data[0]) + "\t accuracy: " + str(accuracycalc(algo_data[0])) + "\t accuracy: " + str(fcalc(algo_data[0]))
+ "\n LR valid" + "\t" + str(algo_data[1]) + "\t A: " + str(accuracycalc(algo_data[1])) + "\t F: " + str(fcalc(algo_data[1]))
+ "\n LR isolated" + "\t" + str(algo_data[2]) + "\t Acuracy: " + str(accuracycalc(algo_data[2])) + "\t F: " + str(fcalc(algo_data[2]))
+ "\n LDA train" + "\t" + str(algo_data[3]) + "\t A: " + str(accuracycalc(algo_data[3])) + "\t F: " + str(fcalc(algo_data[3]))
+ "\n LDA valid" + "\t" + str(algo_data[4]) + "\t A: " + str(accuracycalc(algo_data[4])) + "\t F: " + str(fcalc(algo_data[4]))
+ "\n LDA isolated" + "\t" + str(algo_data[5]) + "\t A: " + str(accuracycalc(algo_data[5])) + "\t F: " + str(fcalc(algo_data[5]))
+ "\n NB train" + "\t" + str(algo_data[6]) + "\t A: " + str(accuracycalc(algo_data[6])) + "\t F: " + str(fcalc(algo_data[6]))
+ "\n NB valid" + "\t" + str(algo_data[7]) + "\t A: " + str(accuracycalc(algo_data[7])) + "\t F: " + str(fcalc(algo_data[7]))
+ "\n NB isolated" + "\t" + str(algo_data[8]) + "\t A: " + str(accuracycalc(algo_data[8])) + "\t F: " + str(fcalc(algo_data[8]))
+ "\n")
print "parsing..."
(x,y) = csv_parser.parse_data("final_data.csv")
print "parsed"
kfolds_control(4, x, y)
#(results, temp_x_onlyspon, temp_x_congress, temp_x_nopers) = testfeaturesubsets(k, train_x, train_y, testset[0], testset[1])
(results) = testfeaturesubsets(k, train_x, train_y, testset[0], testset[1])
for set_name, algo_data in results.iteritems():
print(set_name + "\n LR train" + "\t" + str(algo_data[0]) +
"\t accuracy: " + str(accuracycalc(algo_data[0])) +
"\t accuracy: " + str(fcalc(algo_data[0])) + "\n LR valid" +
"\t" + str(algo_data[1]) + "\t A: " +
str(accuracycalc(algo_data[1])) + "\t F: " +
str(fcalc(algo_data[1])) + "\n LR isolated" + "\t" +
str(algo_data[2]) + "\t Acuracy: " +
str(accuracycalc(algo_data[2])) + "\t F: " +
str(fcalc(algo_data[2])) + "\n LDA train" + "\t" +
str(algo_data[3]) + "\t A: " + str(accuracycalc(algo_data[3])) +
"\t F: " + str(fcalc(algo_data[3])) + "\n LDA valid" + "\t" +
str(algo_data[4]) + "\t A: " + str(accuracycalc(algo_data[4])) +
"\t F: " + str(fcalc(algo_data[4])) + "\n LDA isolated" + "\t" +
str(algo_data[5]) + "\t A: " + str(accuracycalc(algo_data[5])) +
"\t F: " + str(fcalc(algo_data[5])) + "\n NB train" + "\t" +
str(algo_data[6]) + "\t A: " + str(accuracycalc(algo_data[6])) +
"\t F: " + str(fcalc(algo_data[6])) + "\n NB valid" + "\t" +
str(algo_data[7]) + "\t A: " + str(accuracycalc(algo_data[7])) +
"\t F: " + str(fcalc(algo_data[7])) + "\n NB isolated" + "\t" +
str(algo_data[8]) + "\t A: " + str(accuracycalc(algo_data[8])) +
"\t F: " + str(fcalc(algo_data[8])) + "\n")
print "parsing..."
(x, y) = csv_parser.parse_data("final_data.csv")
print "parsed"
kfolds_control(4, x, y)
