def testNormalizeLike(self):
a = np.empty((10, 3))
a[:, 0] = np.random.random(10)
a[:, 1] = np.random.random(10)
a[:, 2] = np.random.random(10)
b = np.empty((10, 3))
b[:, 0] = np.random.random(10)
b[:, 1] = np.random.random(10)
b[:, 2] = np.random.random(10)
b = b * 2
c = normalizeArrayLike(b, a)
# Should be normalized like a
mean = []
std = []
mean.append(np.mean(a[:, 0]))
mean.append(np.mean(a[:, 1]))
mean.append(np.mean(a[:, 2]))
std.append(np.std(a[:, 0]))
std.append(np.std(a[:, 1]))
std.append(np.std(a[:, 2]))
# Check all values
for col in xrange(b.shape[1]):
for bval, cval in zip(b[:, col].flat, c[:, col].flat):
print cval, (bval - mean[col]) / std[col]
print cval, bval
assert cval == (bval - mean[col]) / std[col]
print ("TestNormalizeLike success")
def loadData():
trnfile = ('/home/gibson/jonask/DataSets/breast_cancer_1/' +
'n4369_trainingtwothirds.csv')
testfile = ('/home/gibson/jonask/DataSets/breast_cancer_1/' +
'n4369_targetthird.csv')
columns = ['age', 'log(1+lymfmet)', 'n_pos', 'tumsize',
'log(1+er_cyt)', 'log(1+pgr_cyt)', 'pgr_cyt_pos',
'er_cyt_pos', 'size_gt_20', 'er_cyt', 'pgr_cyt']
targets = ['time_10y', 'event_10y']
# Normalize the test data as we normalized the training data
normP, bah = parse_file(trnfile, inputcols=columns,
targetcols=targets, normalize=False,
separator=',', use_header=True)
unNormedTestP, test_targets = parse_file(testfile, inputcols=columns,
targetcols=targets, normalize=False,
separator=',', use_header=True)
test_data = normalizeArrayLike(unNormedTestP, normP)
#If you want to return train data instead
trn_data, trn_targets = parse_file(trnfile, inputcols=columns,
targetcols=targets, normalize=True,
separator=',', use_header=True)
#return trn_data, trn_targets
return test_data, test_targets
def loadData():
trnfile = ('/home/gibson/jonask/DataSets/breast_cancer_1/' +
'n4369_trainingtwothirds.csv')
testfile = ('/home/gibson/jonask/DataSets/breast_cancer_1/' +
'n4369_targetthird.csv')
columns = [
'age', 'log(1+lymfmet)', 'n_pos', 'tumsize', 'log(1+er_cyt)',
'log(1+pgr_cyt)', 'pgr_cyt_pos', 'er_cyt_pos', 'size_gt_20', 'er_cyt',
'pgr_cyt'
]
targets = ['time_10y', 'event_10y']
# Normalize the test data as we normalized the training data
normP, bah = parse_file(trnfile,
inputcols=columns,
targetcols=targets,
normalize=False,
separator=',',
use_header=True)
unNormedTestP, test_targets = parse_file(testfile,
inputcols=columns,
targetcols=targets,
normalize=False,
separator=',',
use_header=True)
test_data = normalizeArrayLike(unNormedTestP, normP)
#If you want to return train data instead
trn_data, trn_targets = parse_file(trnfile,
inputcols=columns,
targetcols=targets,
normalize=True,
separator=',',
use_header=True)
#return trn_data, trn_targets
return test_data, test_targets
trnfile = '/home/gibson/jonask/DataSets/breast_cancer_1/n4369_trainingtwothirds.csv'
columns = ['age', 'log(1+lymfmet)', 'n_pos', 'tumsize',
'log(1+er_cyt)', 'log(1+pgr_cyt)', 'pgr_cyt_pos',
'er_cyt_pos', 'size_gt_20', 'er_cyt', 'pgr_cyt']
targets = ['time_10y', 'event_10y']
# Normalize the test data as we normalized the training data
normP, bah = parse_file(trnfile, inputcols = columns,
targetcols = targets, normalize = False, separator = ',',
use_header = True)
unNormedTestP, test_targets = parse_file(testfile, inputcols = columns,
targetcols = targets, normalize = False,
separator = ',', use_header = True)
test_data = normalizeArrayLike(unNormedTestP, normP)
# Read the model from file
savefile = '/home/gibson/jonask/Dropbox/Ann-Survival-Phd/publication_data/ann/cens_10y/2_tanh_1328829716.pcom'
with open(savefile, 'r') as FILE:
model = pickle.load(FILE)
# Get a proper header map
column_map = parse_headers_in_file(columns, testfile)
# Explore variable changes
variable_changes = main(model, test_data, test_targets, column_map)
#Print results, sort by change
print("\nCovariates, sorted by importance:")
inputcols=columns,
targetcols=targets,
normalize=False,
separator=',',
use_header=True)
print("Retrieving test data...")
unNormedTestP, T = parse_file(testdata,
inputcols=columns,
targetcols=targets,
normalize=False,
separator=',',
use_header=True)
print("Normalizing test data...")
P = normalizeArrayLike(unNormedTestP, normP)
#Scatter training data
model_output_file = test_model(model,
trainingdata,
targets[0],
targets[1],
',',
time_step_size=2,
*columns)
scatterplot_files(model_output_file, 0, 2, model_output_file, 1)
#Scatter test data
model_output_file = test_model_arrays(model,
testdata,
P,
if __name__ == "__main__":
#Test the model on the test data!
model = '/home/gibson/jonask/Dropbox/Ann-Survival-Phd/publication_data/ann/cens_10y/2_tanh_1328829716.pcom'
testdata = '/home/gibson/jonask/DataSets/breast_cancer_1/n4369_targetthird.csv'
columns = ['age', 'log(1+lymfmet)', 'n_pos', 'tumsize', 'log(1+er_cyt)', 'log(1+pgr_cyt)', 'pgr_cyt_pos',
'er_cyt_pos', 'size_gt_20', 'er_cyt', 'pgr_cyt']
#targets = ['time_10y', 'event_10y']
trainingdata = '/home/gibson/jonask/DataSets/breast_cancer_1/n4369_trainingtwothirds.csv'
print("Retrieving training data...")
# Normalize the test data as we normalized the training data
normP, bah = parse_file(trainingdata, inputcols = columns, normalize = False, separator = ',',
use_header = True)
print("Retrieving test data...")
unNormedTestP, uT = parse_file(testdata, inputcols = columns, normalize = False, separator = ',',
use_header = True)
print("Normalizing test data...")
P = normalizeArrayLike(unNormedTestP, normP)
print("Getting outputs for test data...")
#Wihtout targets, we only get the outputs
outputs = test_model_arrays(model, testdata, P, None)
print("We have outputs! Length: {}".format(len(outputs)))
#model_output_file = test_model(model, testdata, None, None, *columns)
#scatterplot_files(model_output_file, 0, 2, model_output_file, 1)
