from data.stock import Stock from predictor import Predictor from score import auc from preprocess import Preprocess data, targets, cv_targets = Stock.train() #data = Preprocess.scale(data) #cv_targets = Preprocess.scale(cv_targets) #data = Preprocess.polynomial(data, 5) half = len(data)/2 tr_data, holdout_data = data[:half], data[half:] train_targets, holdout_targets = targets[:half], targets[half:] Predictor.train(tr_data, train_targets) preds = Predictor.multi_predict(holdout_data) print 'AUC ', auc(preds, cv_targets) print Predictor.multi_predict([[0.]]) print Predictor.multi_predict([[0.1]]) print Predictor.multi_predict([[-0.1]]) print Predictor.multi_predict([[0.01]]) print Predictor.multi_predict([[-0.01]])
import sys
from data.stock import Stock
from predictor import Predictor
from score import auc
from preprocess import Preprocess
submission_number = sys.argv[1]
print submission_number
def submission(ids, preds):
name = "submissions/submission{0}.csv".format(submission_number)
f = open(name, 'w')
if len(ids) != len(preds):
raise Exception("The number of IDs and the number of predictions are different")
string = 'id,prediction\n'
for index,i in enumerate(ids):
string += str(i) + ',' + str(preds[index]) + "\n"
f.write(str(string))
f.close()
data, targets, _ = Stock.train()
holdout_data, ids = Stock.test()
assert len(data) == len(targets)
Predictor.train(data, targets)
preds = Predictor.multi_predict(holdout_data)
print preds[0:50]
submission(ids, preds)
from data.stock import Stock
data, targets = Stock.train(categorize=False)
pos, neg = [], []
for delta in targets:
if delta > 0:
pos.append(delta)
elif delta < 0:
neg.append(delta)
print sum(pos)/len(pos)
print sum(neg)/len(neg)