def stable_instance_statistics():
query = "SELECT * FROM stable_unique_classes_all_level;"
data = execute_query(query)
commitThresholds = data["level" == 1]["commitThreshold"]
plot_x_y(commitThresholds, data["unique_class_files_fraction"])
data = data.groupby("level")
return data
def query_raw(table_name: str, metrics, descriptor: str):
file_path = f"results/Metrics/{table_name}_{descriptor}_raw.csv"
Path(path.dirname(file_path)).mkdir(parents=True, exist_ok=True)
if not path.exists(file_path):
metrics_query = ', '.join([f"{metric}" for metric in metrics])
query = f"SELECT {metrics_query} FROM {table_name}"
dataframe = execute_query(query)
dataframe.to_csv(file_path, index=False)
log(f"Got the raw data from {table_name} for these metrics: {metrics}.")
else:
dataframe = pd.read_csv(file_path)
return dataframe
def get_non_refactored_instances(self, datasets: Iterable[str]):
"""
Get all non-refactored (stable) instances of the same level of the
refactoring, e.g. Level 2 for refactoring "Extract Method".
Parameter:
dataset (str) (optional): filter the non-refactored
for this dataset. If no dataset is specified, no filter is applied.
"""
return execute_query(
get_level_stable(int(self._level), self._commit_threshold,
datasets))
def get_refactored_instances(self,
datasets: Iterable[str] = [],
projects=[]):
"""
Get all refactoring instances for this refactoring,
e.g. for refactoring "Extract Method".
Parameter:
dataset (str) (optional): filter the refactoring instances
for this dataset. If no dataset is specified, no filter is applied.
"""
return execute_query(
get_level_refactorings(int(self._level), self._name, datasets))
def query_avg(table_name: str, function: str, metrics, descriptor: str, group: bool):
file_path = f"results/Metrics/{table_name}_{function}_{descriptor}.csv"
Path(path.dirname(file_path)).mkdir(parents=True, exist_ok=True)
if not path.exists(file_path):
metrics_query = ', '.join([f"{function}({metric}) AS \"{metric}\"" for metric in metrics])
if group:
query = f"SELECT {metrics_query} FROM {table_name} group by level"
else:
query = f"SELECT {metrics_query} FROM {table_name}"
dataframe = execute_query(query)
dataframe.to_csv(file_path, index=False)
log(f"Got the data from {table_name} for these metrics: {metrics} for the aggregate function: {function}.")
else:
dataframe = pd.read_csv(file_path)
return dataframe
def retrieve_columns(sql_query, columns, samples=-1):
# Hash the query
query_hash = hashlib.sha1(sql_query.encode()).hexdigest()
# Create the filepath
cache_dir = path.join(CACHE_DIR_PATH, "_cache")
file_path = path.join(cache_dir, f"{query_hash}.csv")
if path.exists(file_path):
data = pd.read_csv(file_path, usecols=columns)
if samples < 0 or len(data) < samples:
return data
else:
return data.sample(samples)
else:
return execute_query(sql_query)
from configs import DATASETS, Level, VALIDATION_DATASETS
from db.QueryBuilder import get_all_level_stable, get_level_refactorings_count, get_level_refactorings
from db.DBConnector import execute_query
from utils.log import log_init, log_close, log
import time
log_init()
log('Begin cache warm-up')
start_time = time.time()
for dataset in (DATASETS + VALIDATION_DATASETS):
log("\n**** dataset: " + dataset)
for level in Level:
log("-- non refactored instances for " + str(level))
non_refactored = execute_query(
get_all_level_stable(int(level), dataset))
log(
str(len(non_refactored)) +
" non-refactored instances were found for level: " + str(level))
log("-- " + str(level) + " refactoring types with count")
refactorings = execute_query(
get_level_refactorings_count(int(level), dataset))
log(refactorings.to_string())
for refactoring_name in refactorings['refactoring']:
refactoring_instances = execute_query(
get_level_refactorings(int(level), refactoring_name, dataset))
log('Cache warm-up took %s seconds.' % (time.time() - start_time))
log_close()
def get_non_refactored_instances(self, dataset):
return execute_query(get_all_level_stable(int(self._level), dataset))
def get_refactored_instances(self, dataset):
return execute_query(
get_level_refactorings(int(self._level), self._name, dataset))
