def main():
# configure logging
logging.basicConfig(level=logging.INFO)
logging.info(cf_netSDM)
# Read inputs
data = io_helper.fetch_data()['data']
X = io_helper.fetch_dataframe(data['independent'])
y = io_helper.fetch_dataframe(data['dependent']).iloc[:, 0]
if len(X) >= 2000:
logging.warning(
'HINMine runs in quadratic time, processing {} samples could be very slow.'
.format(len(X)))
normalize = parameters.get_param('normalize', bool, 'True')
damping = parameters.get_param('damping', float, '0.85')
if normalize:
X = X.apply(lambda x: x / np.linalg.norm(x))
network = construct_adjacency_graph(range(len(X)), X.values, y.values)
propositionalized = timecall(cf_netSDM.hinmine_propositionalize)(
network, damping)['train_features']['data']
results_dict = _construct_results(propositionalized)
io_helper.save_results(json.dumps(results_dict),
shapes.Shapes.TABULAR_DATA_RESOURCE)
def main():
# configure logging
logging.basicConfig(level=logging.INFO)
logging.info(cf_netSDM)
# Read inputs
inputs = io_helper.fetch_data()
data = inputs['data']
normalize = parameters.get_param('normalize', bool, 'True')
damping = parameters.get_param('damping', float, '0.85')
data_array = np.zeros(
(len(data['independent'][0]['series']), len(data['independent'])))
col_number = 0
row_number = 0
for var in data['independent']:
for value in var['series']:
data_array[row_number, col_number] = value
row_number += 1
col_number += 1
row_number = 0
if normalize:
for col_number in range(data_array.shape[1]):
data_array[:,
col_number] = data_array[:,
col_number] / np.linalg.norm(
data_array[:, col_number])
network = construct_adjacency_graph(range(data_array.shape[0]), data_array,
data['dependent'][0]['series'])
propositionalized = cf_netSDM.hinmine_propositionalize(
network, damping)['train_features']['data']
results_dict = {
'profile': 'tabular-data-resource',
'name': 'hinmine-features',
'data': [],
'schema': {
'fields': [],
'primaryKey': 'id'
}
}
n = propositionalized.shape[0]
for row_index in range(n):
instance = {"id": row_index}
for col_index in range(n):
instance["feature_%i" %
(col_index + 1)] = propositionalized[row_index, col_index]
results_dict['data'].append(instance)
for col_index in range(n):
results_dict['schema']['fields'].append({
'name':
'feature_%i' % (col_index + 1),
'type':
'float'
})
io_helper.save_results(json.dumps(results_dict), 'text/plain')
def compute():
"""Create PFA for kNN."""
# Read intermediate inputs from jobs
logging.info("Fetching intermediate data...")
inputs = io_helper.fetch_data()
indep_vars = inputs["data"]["independent"]
# Extract hyperparameters from ENV variables
k = parameters.get_param('n_clusters', int, DEFAULT_N_CLUSTERS)
# featurization
featurizer = _create_featurizer(indep_vars)
# convert variables into dataframe
X = io_helper.fetch_dataframe(variables=indep_vars)
X = utils.remove_nulls(X, errors='ignore')
X = featurizer.transform(X)
estimator = KMeans(n_clusters=k)
estimator.fit(X)
# Generate PFA for kmeans
types = [(var['name'], var['type']['name']) for var in indep_vars]
pfa = sklearn_to_pfa(estimator, types, featurizer.generate_pretty_pfa())
# Add centroids as metadata
pfa['metadata'] = {
'centroids': json.dumps(estimator.cluster_centers_.tolist())
}
# Save or update job_result
logging.info('Saving PFA to job_results table')
io_helper.save_results(json.dumps(pfa), shapes.Shapes.PFA)
logging.info("DONE")
def main():
"""Calculate histogram of dependent variable in a single-node mode and return output in highcharts JSON."""
try:
# Read inputs
inputs = io_helper.fetch_data()
try:
dep_var = inputs["data"]["dependent"][0]
except KeyError:
logging.warning("Cannot find dependent variables data")
dep_var = []
try:
indep_vars = inputs["data"]["independent"]
except KeyError:
logging.warning("Cannot find independent variables data")
indep_vars = []
nb_bins = parameters.get_param(BINS_PARAM, int, DEFAULT_BINS)
# Compute histograms (JSON formatted for HighCharts)
histograms_results = compute_histograms(dep_var, indep_vars, nb_bins)
if not INCLUDE_NO_DATA:
histograms_results = [
_remove_no_data(hist) for hist in histograms_results
]
# Store results
io_helper.save_results(json.dumps(histograms_results),
shapes.Shapes.HIGHCHARTS)
except errors.UserError as e:
logging.error(e)
strict = parameters.get_boolean_param(STRICT_PARAM, DEFAULT_STRICT)
if strict:
# Will be handled by catch_user_error
raise e
else:
# Display something to the user and then exit
histograms_results = error_histograms(dep_var, indep_vars)
io_helper.save_results(histograms_results,
shapes.Shapes.HIGHCHARTS)
utils.exit_on_error()
def intermediate_kmeans():
"""Calculate k-Means locally."""
# Read inputs
logging.info("Fetching data...")
inputs = io_helper.fetch_data()
indep_vars = inputs["data"]["independent"]
# Extract hyperparameters from ENV variables
k = parameters.get_param('n_clusters', int, DEFAULT_N_CLUSTERS)
# Load data into a Pandas dataframe
logging.info("Loading data...")
X = io_helper.fetch_dataframe(variables=indep_vars)
# Return variables info, but remove actual data points
results = {'indep_vars': []}
for var in indep_vars:
if var['type']['name'] in ('integer', 'real'):
new_var = {k: v for k, v in var.items() if k != 'series'}
mean, std = _get_moments(var)
new_var['mean'] = mean
new_var['std'] = std
else:
new_var = var
results['indep_vars'].append(new_var)
# Drop NaN values
X = utils.remove_nulls(X, errors='ignore')
if len(X) == 0:
logging.warning("All data are NULL, returning empty centroids.")
results['centroids'] = []
io_helper.save_results(json.dumps(results), shapes.Shapes.JSON)
return
# Generate results
logging.info("Generating results...")
# featurization
featurizer = _create_featurizer(indep_vars)
X = featurizer.transform(X)
m, n = X.shape
num_iter = 0
not_converged = True
# Run k-Means locally
# Have each site compute k initial clusters locally
local_centroids = local.initialize_own_centroids(X, k)
# Local Optimization Loop
while not_converged:
# Each local site computes its cluster
cluster_labels = local.compute_clustering(X, local_centroids)
if OPTIMIZATION == 'lloyd':
# Computes its local mean if doing lloyd, and updates centroids
local_means = local.compute_mean(X, cluster_labels, k)
local_centroids, previous_centroids = local.mean_step(
local_means, local_centroids)
elif OPTIMIZATION == 'gradient':
# Computes the local gradient if doing GD, and takes a GD step
local_grad = local.compute_gradient(X, cluster_labels,
local_centroids, LR)
local_centroids, previous_centroids = local.gradient_step(
local_grad, local_centroids)
# Check local stopping conditions
not_converged, local_delta = local.check_stopping(
local_centroids, previous_centroids, EPSILON)
num_iter += 1
logging.info("Single-Shot {} ; iter : {} delta : {}".format(
OPTIMIZATION, num_iter, local_delta))
results['centroids'] = [lc.tolist() for lc in local_centroids]
logging.info("Results:\n{}".format(results))
io_helper.save_results(json.dumps(results), shapes.Shapes.JSON)
logging.info("DONE")
from subprocess import call
from mip_helper import io_helper, parameters
import preprocess
DEFAULT_DOCKER_IMAGE = 'python-jsi-hedwig'
if __name__ == '__main__':
# Configure logging
logging.basicConfig(level=logging.INFO)
# Read inputs
inputs = io_helper.fetch_data()
data = inputs["data"]
beam = parameters.get_param('beam', int, 10)
support = parameters.get_param('support', float, '0.00001')
out_file = 'input.csv'
rules_out_file = 'rules.txt'
matrix, attributes = preprocess.to_matrix(data)
preprocess.dump_to_csv(matrix, attributes, out_file)
# Call hedwig with sensible defaults
examples_file = out_file
empty_bk = tempfile.mkdtemp()
call([
'python', '-m'
'hedwig.__main__', empty_bk, examples_file, '--beam',
str(beam), '--support',
