def setup_data(self):
"""
This function performs all initializations necessary:
1. generates all the random values for our dynamic tests like the Gaussian
noise std, column count and row count for training/test data sets.
2. generate the appropriate data sets.
"""
# clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
# DEBUGGING setup_data, remember to comment them out once done.
# self.max_real_number = 5
# self.max_int_number = 5
# end DEBUGGING
# preload data sets
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filename))
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol-1
self.x_indices = list(range(self.y_index))
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir, ".csv", action='copy', new_dir_path=self.sandbox_dir)
def tear_down(self):
"""
This function performs teardown after the dynamic test is completed. If all tests
passed, it will delete all data sets generated since they can be quite large. It
will move the training/validation/test data sets into a Rsandbox directory so that
we can re-run the failed test.
"""
if self.test_failed: # some tests have failed. Need to save data sets for later re-runs
# create Rsandbox directory to keep data sets and weight information
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
# Do not want to save all data sets. Only save data sets that are needed for failed tests
pyunit_utils.move_files(self.sandbox_dir, self.training1_data_file, self.training1_filename)
# write out the jenkins job info into log files.
json_file = os.path.join(self.sandbox_dir, self.json_filename)
with open(json_file,'wb') as test_file:
json.dump(self.hyper_params, test_file)
else: # all tests have passed. Delete sandbox if if was not wiped before
pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, False)
# remove any csv files left in test directory
pyunit_utils.remove_csv_files(self.current_dir, ".csv")
pyunit_utils.remove_csv_files(self.current_dir, ".json")
def setup_data(self):
"""
This function performs all initializations necessary:
1. generates all the random parameter values for our dynamic tests like the Gaussian
noise std, column count and row count for training/test data sets.
2. with the chosen distribution family, generate the appropriate data sets
4. load the data sets and set the training set indices and response column index
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(
self.current_dir, self.test_name, True)
# preload data sets
self.training1_data = h2o.import_file(
path=pyunit_utils.locate(self.training1_filename))
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol - 1
self.x_indices = list(range(self.y_index))
# set response to be categorical for classification tasks
self.training1_data[self.y_index] = self.training1_data[
self.y_index].round().asfactor()
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir,
".csv",
action='copy',
new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
1. generates all the random values for our dynamic tests like the Gaussian
noise std, column count and row count for training/test data sets.
2. generate the appropriate data sets.
"""
# clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(
self.current_dir, self.test_name, True)
# DEBUGGING setup_data, remember to comment them out once done.
# self.max_real_number = 5
# self.max_int_number = 5
# end DEBUGGING
# preload data sets
self.training1_data = h2o.import_file(
path=pyunit_utils.locate(self.training1_filename))
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol - 1
self.x_indices = list(range(self.y_index))
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir,
".csv",
action='copy',
new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
load the data sets and set the training set indices and response column index
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(
self.current_dir, self.test_name, True)
# preload data sets
self.training1_data = h2o.import_file(
path=pyunit_utils.locate(self.training1_filename))
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol - 1
self.x_indices = list(range(self.y_index))
# set response to be categorical for classification tasks
self.training1_data[self.y_index] = self.training1_data[
self.y_index].round().asfactor()
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir,
".csv",
action='copy',
new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
1. generates all the random parameter values for our dynamic tests like the Gaussian
noise std, column count and row count for training/test data sets.
2. randomly choose the distribution family (gaussian, binomial, multinomial)
to test.
3. with the chosen distribution family, generate the appropriate data sets
4. load the data sets and set the training set indices and response column index
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
# DEBUGGING setup_data, remember to comment them out once done.
# self.max_real_number = 1
# self.max_int_number = 1
# end DEBUGGING
# This is used to generate dataset for regression or classification. Nothing to do
# with setting the distribution family in this case
# preload datasets
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filename))
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol-1
self.x_indices = list(range(self.y_index))
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir, ".csv", action='copy', new_dir_path=self.sandbox_dir)
def tear_down(self):
"""
This function performs teardown after the dynamic test is completed. If all tests
passed, it will delete all data sets generated since they can be quite large. It
will move the training/validation/test data sets into a Rsandbox directory so that
we can re-run the failed test.
"""
if self.test_failed: # some tests have failed. Need to save data sets for later re-runs
# create Rsandbox directory to keep data sets and weight information
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
# Do not want to save all data sets. Only save data sets that are needed for failed tests
pyunit_utils.move_files(self.sandbox_dir, self.training1_data_file, self.training1_filename)
# write out the jenkins job info into log files.
json_file = os.path.join(self.sandbox_dir, self.json_filename)
with open(json_file,'wb') as test_file:
json.dump(self.hyper_params, test_file)
else: # all tests have passed. Delete sandbox if if was not wiped before
pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, False)
# remove any csv files left in test directory
pyunit_utils.remove_csv_files(self.current_dir, ".csv")
pyunit_utils.remove_csv_files(self.current_dir, ".json")
def setup_data(self):
"""
This function performs all initializations necessary:
load the data sets and set the training set indices and response column index
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
# randomly choose which family of GBM algo to use
self.family = self.families[random.randint(0, len(self.families)-1)]
# preload datasets, set x_indices, y_index and change response to factor for classification
if 'multinomial' in self.family:
self.training_metric = 'logloss'
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filenames[1]))
self.y_index = self.training1_data.ncol-1
self.x_indices = list(range(self.y_index))
self.training1_data[self.y_index] = self.training1_data[self.y_index].round().asfactor()
self.scale_model = 1
else:
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filenames[0]))
self.y_index = self.training1_data.ncol-1
self.x_indices = list(range(self.y_index))
self.scale_model = 0.75
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir, ".csv", action='copy', new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
load the data sets and set the training set indices and response column index
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
# randomly choose which family of GBM algo to use
self.family = self.families[random.randint(0, len(self.families)-1)]
# preload datasets, set x_indices, y_index and change response to factor for classification
if 'multinomial' in self.family:
self.training_metric = 'logloss'
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filenames[1]))
self.y_index = self.training1_data.ncol-1
self.x_indices = list(range(self.y_index))
self.training1_data[self.y_index] = self.training1_data[self.y_index].round().asfactor()
self.scale_model = 1
else:
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filenames[0]))
self.y_index = self.training1_data.ncol-1
self.x_indices = list(range(self.y_index))
self.scale_model = 0.75
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir, ".csv", action='copy', new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
load the data sets and set the training set indices
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filenames))
self.x_indices = list(range(self.training1_data.ncol))
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir, ".csv", action='copy', new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
load the data sets and set the training set indices
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filenames))
self.x_indices = list(range(self.training1_data.ncol))
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir, ".csv", action='copy', new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
1. generates all the random parameter values for our dynamic tests like the Gaussian
noise std, column count and row count for training/test data sets.
2. randomly choose the distribution family (gaussian, binomial, multinomial)
to test.
3. with the chosen distribution family, generate the appropriate data sets
4. load the data sets and set the training set indices and response column index
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(
self.current_dir, self.test_name, True)
# DEBUGGING setup_data, remember to comment them out once done.
# self.max_real_number = 1
# self.max_int_number = 1
# end DEBUGGING
# This is used to generate dataset for regression or classification. Nothing to do
# with setting the distribution family in this case
# randomly choose which family of GBM algo to use
self.family = self.families[random.randint(0, len(self.families) - 1)]
# set class number for classification
if 'multinomial' in self.family:
self.training_metric = 'logloss'
self.training1_data = h2o.import_file(
path=pyunit_utils.locate(self.training1_filenames[1]))
self.y_index = self.training1_data.ncol - 1
self.x_indices = list(range(self.y_index))
self.training1_data[self.y_index] = self.training1_data[
self.y_index].round().asfactor()
self.scale_model = 1
else:
# preload data sets
self.training1_data = h2o.import_file(
path=pyunit_utils.locate(self.training1_filenames[0]))
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol - 1
self.x_indices = list(range(self.y_index))
self.scale_model = 0.75
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir,
".csv",
action='copy',
new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
1. Randomly choose which distribution family to use
2. load the correct data sets and set the training set indices and response column index
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(
self.current_dir, self.test_name, True)
# randomly choose which family of GLM algo to use
self.family = self.families[random.randint(0, len(self.families) - 1)]
# set class number for classification
if 'binomial' in self.family:
self.training1_data = h2o.import_file(
path=pyunit_utils.locate(self.training1_filename[1]))
self.training2_data = h2o.import_file(
path=pyunit_utils.locate(self.training2_filename[1]))
elif 'multinomial' in self.family:
self.training1_data = h2o.import_file(
path=pyunit_utils.locate(self.training1_filename[2]))
self.training2_data = h2o.import_file(
path=pyunit_utils.locate(self.training2_filename[2]))
else:
self.training1_data = h2o.import_file(
path=pyunit_utils.locate(self.training1_filename[0]))
self.training2_data = h2o.import_file(
path=pyunit_utils.locate(self.training2_filename[0]))
self.scale_model = 0.75
self.hyper_params["fold_assignment"] = ['AUTO', 'Random', 'Modulo']
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol - 1
self.x_indices = list(range(self.y_index))
# set response to be categorical for classification tasks
if ('binomial' in self.family) or ('multinomial' in self.family):
self.training1_data[self.y_index] = self.training1_data[
self.y_index].round().asfactor()
self.training2_data[self.y_index] = self.training2_data[
self.y_index].round().asfactor()
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir,
".csv",
action='copy',
new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
1. generates all the random parameter values for our dynamic tests like the Gaussian
noise std, column count and row count for training/test data sets.
2. randomly choose the distribution family (gaussian, binomial, multinomial)
to test.
3. with the chosen distribution family, generate the appropriate data sets
4. load the data sets and set the training set indices and response column index
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
# randomly determine data set size in terms of column and row counts
# DEBUGGING setup_data, remember to comment them out once done.
# self.max_real_number = 3
# self.max_int_number = 3
# end DEBUGGING
# randomly choose which family of GLM algo to use
self.family = self.families[random.randint(0, len(self.families)-1)]
self.family = 'gaussian'
# set class number for classification
if 'binomial' in self.family:
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filename[1]))
self.training2_data = h2o.import_file(path=pyunit_utils.locate(self.training2_filename[1]))
elif 'multinomial' in self.family:
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filename[2]))
self.training2_data = h2o.import_file(path=pyunit_utils.locate(self.training2_filename[2]))
else:
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filename[0]))
self.training2_data = h2o.import_file(path=pyunit_utils.locate(self.training2_filename[0]))
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol-1
self.x_indices = list(range(self.y_index))
# set response to be categorical for classification tasks
if ('binomial' in self.family) or ('multinomial' in self.family):
self.training1_data[self.y_index] = self.training1_data[self.y_index].round().asfactor()
self.training2_data[self.y_index] = self.training2_data[self.y_index].round().asfactor()
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir, ".csv", action='copy', new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
load the data sets and set the training set indices and response column index
"""
# clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
# preload data sets
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filename))
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol-1
self.x_indices = list(range(self.y_index))
self.training1_data[self.y_index] = self.training1_data[self.y_index].round().asfactor()
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir, ".csv", action='copy', new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
1. Randomly choose which distribution family to use
2. load the correct data sets and set the training set indices and response column index
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
# randomly choose which family of GLM algo to use
self.family = self.families[random.randint(0, len(self.families)-1)]
# set class number for classification
if 'binomial' in self.family:
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filename[1]))
self.training2_data = h2o.import_file(path=pyunit_utils.locate(self.training2_filename[1]))
elif 'multinomial' in self.family:
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filename[2]))
self.training2_data = h2o.import_file(path=pyunit_utils.locate(self.training2_filename[2]))
else:
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filename[0]))
self.training2_data = h2o.import_file(path=pyunit_utils.locate(self.training2_filename[0]))
self.scale_model = 0.75
self.hyper_params["fold_assignment"] = ['AUTO', 'Random', 'Modulo']
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol-1
self.x_indices = list(range(self.y_index))
# set response to be categorical for classification tasks
if ('binomial' in self.family) or ('multinomial' in self.family):
self.training1_data[self.y_index] = self.training1_data[self.y_index].round().asfactor()
self.training2_data[self.y_index] = self.training2_data[self.y_index].round().asfactor()
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir, ".csv", action='copy', new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
1. generates all the random parameter values for our dynamic tests like the Gaussian
noise std, column count and row count for training/test data sets.
2. with the chosen distribution family, generate the appropriate data sets
4. load the data sets and set the training set indices and response column index
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
# preload data sets
self.training1_data = h2o.import_file(path=pyunit_utils.locate(self.training1_filename))
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol-1
self.x_indices = list(range(self.y_index))
# set response to be categorical for classification tasks
self.training1_data[self.y_index] = self.training1_data[self.y_index].round().asfactor()
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir, ".csv", action='copy', new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
1. generates all the random parameter values for our dynamic tests like the Gaussian
noise std, column count and row count for training/test data sets.
2. randomly choose the distribution family (gaussian, binomial, multinomial)
to test.
3. with the chosen distribution family, generate the appropriate data sets
4. load the data sets and set the training set indices and response column index
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(
self.current_dir, self.test_name, True)
# randomly set Gaussian noise standard deviation as a fraction of actual predictor standard deviation
self.noise_std = random.uniform(
0, math.sqrt(pow((self.max_p_value - self.min_p_value), 2) / 12))
self.noise_var = self.noise_std * self.noise_std
# randomly determine data set size in terms of column and row counts
self.train_col_count = random.randint(1, self.max_col_count)
self.train_row_count = round(
self.train_col_count *
random.uniform(self.min_col_count_ratio, self.max_col_count_ratio))
# DEBUGGING setup_data, remember to comment them out once done.
self.train_col_count = 3
self.train_row_count = 200
# self.max_real_number = 1
# self.max_int_number = 1
# end DEBUGGING
#### This is used to generate dataset for regression or classification. Nothing to do
#### with setting the distribution family in this case
# randomly choose which family of GLM algo to use
self.family = self.families[random.randint(0, len(self.families) - 1)]
# set class number for classification
if 'multinomial' in self.family:
self.class_number = random.randint(
2, self.max_class_number) # randomly set number of classes K
# generate real value weight vector and training/validation/test data sets for GLM
pyunit_utils.write_syn_floating_point_dataset_glm(
self.training1_data_file,
self.training2_data_file,
self.training3_data_file,
self.weight_data_file,
self.train_row_count,
self.train_col_count,
2,
self.max_p_value,
self.min_p_value,
self.max_w_value,
self.min_w_value,
self.noise_std,
self.family,
self.train_row_count,
self.train_row_count,
class_number=self.class_number,
class_method=['probability', 'probability', 'probability'])
# preload data sets
self.training1_data = h2o.import_file(
pyunit_utils.locate(self.training1_data_file))
self.training2_data = h2o.import_file(
pyunit_utils.locate(self.training2_data_file))
self.training3_data = h2o.import_file(
pyunit_utils.locate(self.training3_data_file))
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol - 1
self.x_indices = list(range(self.y_index))
# set response to be categorical for classification tasks
if 'multinomial' in self.family:
self.training1_data[self.y_index] = self.training1_data[
self.y_index].round().asfactor()
# check to make sure all response classes are represented, otherwise, quit
if self.training1_data[
self.y_index].nlevels()[0] < self.class_number:
print(
"Response classes are not represented in training dataset."
)
sys.exit(0)
self.training2_data[self.y_index] = self.training2_data[
self.y_index].round().asfactor()
self.training3_data[self.y_index] = self.training2_data[
self.y_index].round().asfactor()
# self.hyper_params["validation_frame"] = [self.training1_data.frame_id, self.training2_data.frame_id,
# self.training3_data.frame_id]
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir,
".csv",
action='copy',
new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
1. generates all the random values for our dynamic tests like the Gaussian
noise std, column count and row count for training/test data sets.
2. generate the appropriate data sets.
"""
# clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(
self.current_dir, self.test_name, True)
# randomly set Gaussian noise standard deviation as a fraction of actual predictor standard deviation
self.noise_std = random.uniform(
0, math.sqrt(pow((self.max_p_value - self.min_p_value), 2) / 12))
self.noise_var = self.noise_std * self.noise_std
# randomly determine data set size in terms of column and row counts
self.train_col_count = random.randint(1, self.max_col_count)
self.train_row_count = round(
self.train_col_count *
random.uniform(self.min_col_count_ratio, self.max_col_count_ratio))
# DEBUGGING setup_data, remember to comment them out once done.
# self.train_col_count = 3
# self.train_row_count = 200
# self.max_real_number = 5
# self.max_int_number = 5
# end DEBUGGING
if 'gaussian' in self.family: # increase data range
self.max_p_value *= 50
self.min_p_value *= 50
self.max_w_value *= 50
self.min_w_value *= 50
# generate real value weight vector and training/validation/test data sets for GLM
pyunit_utils.write_syn_floating_point_dataset_glm(
self.training1_data_file,
"",
"",
self.weight_data_file,
self.train_row_count,
self.train_col_count,
self.data_type,
self.max_p_value,
self.min_p_value,
self.max_w_value,
self.min_w_value,
self.noise_std,
self.family,
self.train_row_count,
self.train_row_count,
class_number=self.class_number,
class_method=[
self.class_method, self.class_method, self.test_class_method
],
class_margin=[self.margin, self.margin, self.test_class_margin])
# preload data sets
self.training1_data = h2o.import_file(
pyunit_utils.locate(self.training1_data_file))
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol - 1
self.x_indices = list(range(self.y_index))
# set response to be categorical for classification tasks
if ('binomial' in self.family):
self.training1_data[self.y_index] = self.training1_data[
self.y_index].round().asfactor()
# check to make sure all response classes are represented, otherwise, quit
if self.training1_data[
self.y_index].nlevels()[0] < self.class_number:
print(
"Response classes are not represented in training dataset."
)
sys.exit(0)
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir,
".csv",
action='copy',
new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
1. generates all the random parameter values for our dynamic tests like the Gaussian
noise std, column count and row count for training/test data sets.
2. randomly choose the distribution family (gaussian, binomial, multinomial)
to test.
3. with the chosen distribution family, generate the appropriate data sets
4. load the data sets and set the training set indices and response column index
"""
# create and clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
# randomly set Gaussian noise standard deviation as a fraction of actual predictor standard deviation
self.noise_std = random.uniform(0, math.sqrt(pow((self.max_p_value - self.min_p_value), 2) / 12))
self.noise_var = self.noise_std*self.noise_std
# randomly determine data set size in terms of column and row counts
self.train_col_count = random.randint(1, self.max_col_count)
self.train_row_count = round(self.train_col_count * random.uniform(self.min_col_count_ratio,
self.max_col_count_ratio))
# DEBUGGING setup_data, remember to comment them out once done.
self.train_col_count = 3
self.train_row_count = 200
# self.max_real_number = 1
# self.max_int_number = 1
# end DEBUGGING
#### This is used to generate dataset for regression or classification. Nothing to do
#### with setting the distribution family in this case
# randomly choose which family of GLM algo to use
self.family = self.families[random.randint(0, len(self.families)-1)]
# set class number for classification
if 'multinomial' in self.family:
self.class_number = random.randint(2, self.max_class_number) # randomly set number of classes K
# generate real value weight vector and training/validation/test data sets for GLM
pyunit_utils.write_syn_floating_point_dataset_glm(self.training1_data_file, self.training2_data_file,
self.training3_data_file, self.weight_data_file,
self.train_row_count, self.train_col_count, 2,
self.max_p_value, self.min_p_value, self.max_w_value,
self.min_w_value, self.noise_std, self.family,
self.train_row_count, self.train_row_count,
class_number=self.class_number,
class_method=['probability', 'probability',
'probability'])
# preload data sets
self.training1_data = h2o.import_file(pyunit_utils.locate(self.training1_data_file))
self.training2_data = h2o.import_file(pyunit_utils.locate(self.training2_data_file))
self.training3_data = h2o.import_file(pyunit_utils.locate(self.training3_data_file))
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol-1
self.x_indices = list(range(self.y_index))
# set response to be categorical for classification tasks
if 'multinomial' in self.family:
self.training1_data[self.y_index] = self.training1_data[self.y_index].round().asfactor()
# check to make sure all response classes are represented, otherwise, quit
if self.training1_data[self.y_index].nlevels()[0] < self.class_number:
print("Response classes are not represented in training dataset.")
sys.exit(0)
self.training2_data[self.y_index] = self.training2_data[self.y_index].round().asfactor()
self.training3_data[self.y_index] = self.training2_data[self.y_index].round().asfactor()
# self.hyper_params["validation_frame"] = [self.training1_data.frame_id, self.training2_data.frame_id,
# self.training3_data.frame_id]
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir, ".csv", action='copy', new_dir_path=self.sandbox_dir)
def setup_data(self):
"""
This function performs all initializations necessary:
1. generates all the random values for our dynamic tests like the Gaussian
noise std, column count and row count for training/test data sets.
2. generate the appropriate data sets.
"""
# clean out the sandbox directory first
self.sandbox_dir = pyunit_utils.make_Rsandbox_dir(self.current_dir, self.test_name, True)
# randomly set Gaussian noise standard deviation as a fraction of actual predictor standard deviation
self.noise_std = random.uniform(0, math.sqrt(pow((self.max_p_value - self.min_p_value), 2) / 12))
self.noise_var = self.noise_std*self.noise_std
# randomly determine data set size in terms of column and row counts
self.train_col_count = random.randint(1, self.max_col_count)
self.train_row_count = round(self.train_col_count * random.uniform(self.min_col_count_ratio,
self.max_col_count_ratio))
# DEBUGGING setup_data, remember to comment them out once done.
# self.train_col_count = 3
# self.train_row_count = 200
# self.max_real_number = 1
# self.max_int_number = 1
# end DEBUGGING
if 'gaussian' in self.family: # increase data range
self.max_p_value *= 50
self.min_p_value *= 50
self.max_w_value *= 50
self.min_w_value *= 50
# generate real value weight vector and training/validation/test data sets for GLM
pyunit_utils.write_syn_floating_point_dataset_glm(self.training1_data_file, "",
"", self.weight_data_file,
self.train_row_count, self.train_col_count, self.data_type,
self.max_p_value, self.min_p_value, self.max_w_value,
self.min_w_value, self.noise_std, self.family,
self.train_row_count, self.train_row_count,
class_number=self.class_number,
class_method=[self.class_method, self.class_method,
self.test_class_method],
class_margin=[self.margin, self.margin,
self.test_class_margin])
# preload data sets
self.training1_data = h2o.import_file(pyunit_utils.locate(self.training1_data_file))
# set data set indices for predictors and response
self.y_index = self.training1_data.ncol-1
self.x_indices = list(range(self.y_index))
# set response to be categorical for classification tasks
if 'binomial' in self.family:
self.training1_data[self.y_index] = self.training1_data[self.y_index].round().asfactor()
# check to make sure all response classes are represented, otherwise, quit
if self.training1_data[self.y_index].nlevels()[0] < self.class_number:
print("Response classes are not represented in training dataset.")
sys.exit(0)
# save the training data files just in case the code crashed.
pyunit_utils.remove_csv_files(self.current_dir, ".csv", action='copy', new_dir_path=self.sandbox_dir)
