def get_feature_vector(self, feature_id, cohort_id_array):
start = time.time()
async_params = [(feature_id, cohort_id_array)]
async_result = get_feature_vectors_with_user_data(async_params)
feature_type, feature_vec = async_result[feature_id]["type"], async_result[feature_id]["data"]
end = time.time()
time_elapsed = end - start
logging.info("Time elapsed: " + str(time_elapsed))
vms = VectorMergeSupport("NA", "sample_id", [feature_id])
vms.add_dict_array(feature_vec, feature_id, "value")
merged = vms.get_merged_dict()
return feature_type, merged
def prepare_feature_vector(self, input_vectors):
feature_vector_mapping = {}
vectors = []
for item in input_vectors:
feature_id, value_type, vector = item.feature_id, item.value_type, item.data
if value_type == ValueType.INTEGER or value_type == ValueType.FLOAT:
value_type = "N"
elif value_type == ValueType.STRING:
value_type = "C"
else:
value_type = "B"
feature_vector_mapping[feature_id] = (value_type, vector)
vectors.append(vector)
# Create merged feature vectors
feature_ids = [v.feature_id for v in input_vectors]
vms = VectorMergeSupport('NA', 'sample_id', 'case_id', row_ids=feature_ids)
for feature in feature_vector_mapping.keys():
vms.add_dict_array(feature_vector_mapping[feature][1], feature, 'value')
merged = vms.get_merged_dict()
rows = []
for feature in feature_vector_mapping.keys():
current_row = [feature_vector_mapping[feature][0] + ":" + feature]
for item in merged:
current_row.append(item[feature])
rows.append("\t".join(current_row))
return rows
def prepare_features(self, cohort_id, features):
# Get the feature data
feature_vector_mapping = {}
vectors = []
for feature in features:
value_type, vector = get_feature_vector(feature, cohort_id)
if value_type == ValueType.INTEGER or value_type == ValueType.FLOAT:
value_type = "N"
elif value_type == ValueType.STRING:
value_type = "C"
else:
value_type = "B"
feature_vector_mapping[feature] = (value_type, vector)
vectors.append(vector)
# Create merged feature vectors
vms = VectorMergeSupport('NA', 'sample_id', row_ids=features)
for feature in feature_vector_mapping.keys():
vms.add_dict_array(feature_vector_mapping[feature][1], feature, 'value')
merged = vms.get_merged_dict()
rows = []
for feature in feature_vector_mapping.keys():
current_row = [feature_vector_mapping[feature][0] + ":" + feature]
for item in merged:
current_row.append(item[feature])
rows.append("\t".join(current_row))
return rows
