def _params_producer() -> tuple:
""" Generates parameters for imbalance training.
Returns:
----------
Bugs description, classes codes, SMOTE instance and model name.
"""
for metric in filtered_classes.keys():
if metric == "Priority" or metric == "Time to Resolve":
filtered_df = df[df[metric].isin(filtered_classes[metric])]
smt = SMOTE(
ratio="minority",
random_state=0,
kind="borderline1",
n_jobs=4,
)
smt.k_neighbors = get_k_neighbors(df[metric.lower() +
"_codes"])
classes_codes = filtered_df[metric.lower() + "_codes"]
model_name = metric.split("_")[0]
yield filtered_df.Description_tr, classes_codes, smt, model_name
else:
for class_ in filtered_classes[metric]:
df_index = ("Resolution_" +
class_ if metric == "Resolution" else class_)
smt = SMOTE(
ratio="minority",
random_state=0,
kind="borderline1",
n_jobs=4,
)
smt.k_neighbors = get_k_neighbors(df[df_index])
yield df.Description_tr, df[df_index], smt, class_
def train_model(model_path, dataframe_path, areas_of_testing, resolution):
if not exists(model_path):
makedirs(model_path)
df = read_pickle(dataframe_path)
if not check_bugs_count(df, 100):
raise ValueError(
'Oops! Too little data to analyze. Model can\'t be trained.')
filtered_classes, dataframes = prepare_df(df, areas_of_testing, resolution)
for _class in filtered_classes:
check_classes_count(filtered_classes[_class])
# model/ folder cleanup
remove_models()
# updated predictions parameters writing
write_classes(filtered_classes)
from main.config_processor import load_config_to_session
load_config_to_session(
str(Path(__file__).parents[1]) + '/models/selected/' +
'predictions_parameters.ini')
smt = SMOTE(ratio='minority', random_state=0, kind='borderline1', n_jobs=4)
svm_imb = SVC(gamma=2, C=1, probability=True, class_weight='balanced')
chi2 = feature_selection.chi2
# areas of testing models training
for area in filtered_classes['areas_of_testing_classes']:
smt.k_neighbors = get_k_neighbors(
df[areas_of_testing[area]['series_name']])
training_imbalance(df['Description_tr'],
df[areas_of_testing[area]['series_name']],
session['tfidf'], smt, chi2, 50, svm_imb,
model_path + secure_filename(area))
# priority models training
smt.k_neighbors = get_k_neighbors(
dataframes['priority_df']['Priority_codes'])
training_imbalance(dataframes['priority_df']['Description_tr'],
dataframes['priority_df']['Priority_codes'],
session['tfidf'], smt, chi2, 50, svm_imb,
model_path + secure_filename('priority'))
# ttr models training
smt.k_neighbors = get_k_neighbors(
dataframes['ttr_df']['coded_ttr_intervals'])
training_imbalance(dataframes['ttr_df']['Description_tr'],
dataframes['ttr_df']['coded_ttr_intervals'],
session['tfidf'], smt, chi2, 50, svm_imb,
model_path + secure_filename('ttr'))
# resolution models training
for resol in filtered_classes['resolutions_classes']:
smt.k_neighbors = get_k_neighbors(
dataframes['resolution_df']['Resolution_' + resol])
training_imbalance(dataframes['resolution_df']['Description_tr'],
dataframes['resolution_df']['Resolution_' + resol],
session['tfidf'], smt, chi2, 50, svm_imb,
model_path + secure_filename(resol))
