n = 10 # repeat the CV procedure 10 times to get more precise results
nFeatures = X.shape[0]
niter = 10
SEED = 42
rnd = np.random.RandomState(SEED)
cct = 0
# xtrain = rf.getRFX(X)
# xtest = rf.getRFX_test(X_test)
# for j in range(xtest.shape[0]):
# mini = np.min(xtest[j,:])
# if mini == 0:
# cct += 1
print "utils train test..."
util_train, util_test = utils.getTrainTest()
if (CreateSub == 0):
# print "total rows with 0s: ", cct
#===============================================================================
cv = cross_validation.ShuffleSplit(nFeatures, n_iter=niter, test_size=0.3, random_state=rnd)
mean_auc = 0.0; i = 0
for train, test in cv:
print "======================================= CROSS VALIDATION LOOP: ", (i+1)
num_train = len(train)
xtrain = X.ix[train]; ytrain = y.values[train]
xtest = X.ix[test]; ytest = y.values[test]
xtrain = rf.getRFX(xtrain)
xtest = rf.getRFX_test(xtest)
#xtrain = utils.get_numerical_features(xtrain, test=False)
n = 10 # repeat the CV procedure 10 times to get more precise results nFeatures = X.shape[0] niter = 10 SEED = 42 rnd = np.random.RandomState(SEED) cct = 0 # xtrain = rf.getRFX(X) # xtest = rf.getRFX_test(X_test) # for j in range(xtest.shape[0]): # mini = np.min(xtest[j,:]) # if mini == 0: # cct += 1 print "utils train test..." util_train, util_test, util_train_nsp, util_test_nsp = utils.getTrainTest() # blendTrain = np.empty((num_train, 3)) # blendTest = np.zeros((X_test.shape[0],5)) # blendTestTemp1 = np.empty((X_test.shape[0],10)) # blendTestTemp2 = np.empty((X_test.shape[0],10)) # blendTestTemp3 = np.empty((X_test.shape[0],10)) # blendTestTemp4 = np.empty((X_test.shape[0],10)) # blendTestTemp5 = np.empty((X_test.shape[0],10)) # blendTestTemp6 = np.empty((X_test.shape[0],10)) n_folds = 10 verbose = True shuffle = False skf = list(StratifiedKFold(y, n_folds))
