def dnn_model_kfold(k=10):
""" Run kfold cross validation in parallel
Keyword Arguments:
k {integer} -- the number of folds (default: {10})
"""
samples = csv2dict(DATASET.features)
# These collections are speed up the process while calculating top-k accuracy
sample_dict, bug_reports, br2files_dict = helper_collections(samples)
np.random.shuffle(samples)
# K-fold Cross Validation in parallel
acc_dicts = Parallel(n_jobs=-2)( # Uses all cores but one
delayed(train_dnn)(
i, k, samples, start, step, sample_dict, bug_reports, br2files_dict
)
for i, (start, step) in enumerate(kfold_split_indexes(k, len(samples)))
)
# Calculating the average accuracy from all folds
avg_acc_dict = {}
for key in acc_dicts[0].keys():
avg_acc_dict[key] = round(sum([d[key] for d in acc_dicts]) / len(acc_dicts), 3)
return avg_acc_dict
def rsvm_model():
samples = csv2dict(DATASET.features)
# rvsm_list = [float(sample["rVSM_similarity"]) for sample in samples]
# These collections are speed up the process while calculating top-k accuracy
sample_dict, bug_reports, br2files_dict = helper_collections(samples, True)
acc_dict = topk_accuarcy(bug_reports, sample_dict, br2files_dict)
return acc_dict
from util import csv2dict, tsv2dict
import numpy as np
from sklearn.neural_network import MLPRegressor
from sklearn.model_selection import train_test_split, KFold
samples = csv2dict()
rvsm_list = [float(sample['rVSM_similarity']) for sample in samples]
sample_dict = {}
for sample in samples:
sample_dict[sample["report_id"]] = []
for sample in samples:
temp_dict = {}
temp_dict[sample["file"]] = [float(sample['rVSM_similarity'])]
sample_dict[sample["report_id"]].append(temp_dict)
bug_reports = tsv2dict()
bug_reports_files_dict = {}
for bug_report in bug_reports:
bug_reports_files_dict[bug_report["id"]] = bug_report["files"]
topk_counters = [0] * 20
negative_total = 0
for bug_report in bug_reports:
dnn_input = []
corresponding_files = []
bug_id = bug_report["id"]
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument(
"context",
help=
"Path to a CSV file with the data context for the template. Each row in the CSV will result in one sent email. The template is filled with associated data from a given row. Must have a column named 'email' for To: address."
)
parser.add_argument(
"template",
help="Path to a Jinja2 template file that can be filled by the context"
)
parser.add_argument(
"subject",
help=
"Quoted string with email's subject line, subject string is NOT filled as a template"
)
parser.add_argument("-q",
"--quiet",
help="Supress printing of all filled templates.",
action="store_true")
parser.add_argument(
"-d",
"--dryrun",
help="Don't actually send emails, just print them to screen.",
action="store_true")
args = parser.parse_args()
context = util.csv2dict(args.context)
template = util.readtemplate(args.template)
subject = args.subject
main()
from util import csv2dict, tsv2dict
import numpy as np
from sklearn.neural_network import MLPRegressor
from sklearn.model_selection import train_test_split, KFold
samples_ = csv2dict()
samples = []
# oversampling
for i, sample in enumerate(samples_):
samples.append(sample)
if i % 51 in [0]:
for _ in range(9):
samples.append(sample)
np.random.shuffle(samples)
x_ = np.zeros((len(samples), 5))
y_ = np.zeros((len(samples), 1))
for i, sample in enumerate(samples):
x_[i][0] = float(sample['rVSM_similarity'])
x_[i][1] = float(sample['collab_filter'])
x_[i][2] = float(sample['classname_similarity'])
x_[i][3] = float(sample['bug_recency'])
x_[i][4] = float(sample['bug_frequency'])
y_[i] = float(sample['match'])
data_train, data_test, labels_train, labels_test = train_test_split(
x_, y_, test_size=0.20, random_state=42)