def __init__(self, _type, bandits, agent, runs, exp_nums, logdir, k_vec,
k_probs):
self._type = _type
self.esr_vector = []
self.esr_probs = []
self.f1_score = []
self.f1 = []
#self.plotter = Plotter()
self.metrics = Metrics()
self.k_vec = k_vec
self.k_probs = k_probs
self.f1_df = pd.DataFrame()
self.esrBandit = Agent(0, 10)
self.logdir = logdir
for i in range(len(k_vec)):
self.esrBandit.manual_distribution(k_vec[i], k_probs[i])
if self._type == "bandit":
self.bandits = bandits
self.agent = agent
self.runs = runs
self.exp_nums = exp_nums
def classify(self):
metrics: Metrics = Metrics(len(self.data_frame.df.index), self.data_frame.df)
if self.ui_classify.euklidianRadio.isChecked():
if self.ui_classify.checkBoxNormalize.isChecked():
metrics.classify_euclidean_normalize()
else:
metrics.classify_euclidean()
elif self.ui_classify.manhattanRadio.isChecked():
if self.ui_classify.checkBoxNormalize.isChecked():
metrics.classify_manhattan_normalize()
else:
metrics.classify_manhattan()
elif self.ui_classify.chebyshevRadio.isChecked():
if self.ui_classify.checkBoxNormalize.isChecked():
metrics.classify_chebyshev_normalize()
else:
metrics.classify_chebyshev()
elif self.ui_classify.mahalanobisRadio.isChecked():
if self.ui_classify.checkBoxNormalize.isChecked():
metrics.classify_mahalanobis_normalize()
else:
metrics.classify_mahalanobis()
self.close_classify_dialog()
def main():
parser = argparse.ArgumentParser()
parser.add_argument("--project", "-p", help="Project path", required=True)
parser.add_argument("--stop_words", "-s", help="Path to stopwords file")
parser.add_argument("--k_topics",
"-k",
help="Number of topics for given project")
parser.add_argument(
"--resolution",
"-r",
help=
"Resolution number parameter in Louvain community detection. A value in range of 0.3 to 1 is advised. A smaller resolution will identify smaller communities and vice versa. By default the whole range is tested and communities for each community saved."
)
parser.add_argument(
"--metrics",
"-m",
help=
"Execute metrics for a given project name after normal parsing and execution (relative path to set root path) (At the current time it does NOT work independently from the identification process)",
action="store_true")
parser.add_argument("--draw",
"-d",
help="Enable plotting of graphs",
action="store_true")
parser.add_argument("--lda-plotting",
"-l",
help="Enable plotting of LDA topics",
action="store_true")
args = parser.parse_args()
Settings.DRAW = True if args.draw else False
Settings.LDA_PLOTTING = True if args.lda_plotting else False
Settings.K_TOPICS = int(args.k_topics) if args.k_topics else None
Settings.RESOLUTION = float(args.resolution) if args.resolution else None
Settings.set_stop_words(args.stop_words)
print(f"Setting Directory as: {Settings.DIRECTORY}")
if args.project:
project_name = str(args.project.split('/')[-1])
project_path = str(args.project)
Settings.PROJECT_PATH = project_path
Settings.PROJECT_NAME = project_name
# cluster_results = (clusters, modularity, resolution)
clusters_results = identify_clusters_in_project(
project_name, project_path)
metrics = Metrics()
for cluster in clusters_results:
Settings.create_id()
# TODO: Refactor MetricExecutor into ProcessResultOutput and MetricExecutor, currently sharing many responsabilities
metric_executor = MetricExecutor()
metric_executor.add_project(project_name, str(cluster[0]))
metric_executor.dump_to_json_file()
if args.metrics:
# TODO: refactor
metrics.set_metric_executor(metric_executor)
metrics.set_cluster_results(clusters_results)
metrics.calculate()
if args.metrics:
metrics.save()
