def train(cls, ptr: ReferencePointer, config: Mapping[str, Any], data_service: DataService,
files: Iterator[File], **data) -> FormatModel:
"""
Train a model given the files available.
:param ptr: Git repository state pointer.
:param config: configuration dict.
:param data: contains "files" - the list of files in the pointed state.
:param data_service: connection to the Lookout data retrieval service.
:param files: iterator of File records from the data service.
:return: AnalyzerModel containing the learned rules, per language.
"""
_log = logging.getLogger(cls.__name__)
train_config = cls._load_config(config)["train"]
_log.info("train %s %s %s %s", __version__, ptr.url, ptr.commit,
pformat(train_config, width=4096, compact=True))
model = FormatModel().generate(cls, ptr)
for language, files in files_by_language(files).items():
try:
lang_config = train_config[language]
except KeyError:
_log.warning("language %s is not supported, skipped", language)
continue
_log.info("effective train config for %s:\n%s", language,
pformat(lang_config, width=120, compact=True))
random_state = lang_config["random_state"]
files = filter_files(
files, lang_config["line_length_limit"], lang_config["overall_size_limit"],
random_state, _log)
submit_event("%s.train.%s.files" % (cls.name, language), len(files))
if len(files) == 0:
_log.info("zero files after filtering, language %s is skipped.", language)
continue
try:
fe = FeatureExtractor(language=language, **lang_config["feature_extractor"])
except ImportError:
_log.warning("skipped %d %s files - not supported", len(files), language)
continue
else:
_log.info("training on %d %s files", len(files), language)
train_files, test_files = FormatAnalyzer.split_train_test(
files, lang_config["test_dataset_ratio"], random_state=random_state)
# ensure that the features are reproducible
train_files = sorted(train_files, key=lambda x: x.path)
test_files = sorted(test_files, key=lambda x: x.path)
X_train, y_train, _ = fe.extract_features(train_files)
X_train, selected_features = fe.select_features(X_train, y_train)
if test_files:
X_test, y_test, _ = fe.extract_features(test_files)
if lang_config["test_dataset_ratio"]:
_log.debug("Real test ratio is %.3f",
X_test.shape[0] / (X_test.shape[0] + X_train.shape[0])
if test_files else 0)
lang_config["feature_extractor"]["selected_features"] = selected_features
lang_config["feature_extractor"]["label_composites"] = fe.labels_to_class_sequences
lower_bound_instances = lang_config["lower_bound_instances"]
if X_train.shape[0] < lower_bound_instances:
_log.warning("skipped %d %s files: too few samples (%d/%d)",
len(files), language, X_train.shape[0], lower_bound_instances)
continue
_log.info("extracted %d samples to train, searching for the best hyperparameters",
X_train.shape[0])
optimizer = Optimizer(**lang_config["optimizer"], random_state=random_state)
best_score, best_params = optimizer.optimize(X_train, y_train)
if _log.isEnabledFor(logging.DEBUG):
_log.debug("score of the best estimator found: %.6f", best_score)
_log.debug("params of the best estimator found: %s", str(best_params))
_log.debug("training the model with complete data")
else:
_log.info("finished hyperopt at %.6f, training the full model", -best_score)
lang_config["trainable_rules"].update(best_params)
trainable_rules = TrainableRules(**lang_config["trainable_rules"],
random_state=random_state,
origin_config=lang_config)
trainable_rules.fit(X_train, y_train)
importances = trainable_rules.feature_importances_
_log.debug(
"feature importances from %s:\n\t%s",
lang_config["trainable_rules"]["base_model_name"],
"\n\t".join("%-55s %.5E" % (fe.feature_names[i], importances[i])
for i in numpy.argsort(-importances)[:25] if importances[i] > 1e-5))
trainable_rules.prune_categorical_attributes(fe)
_log.info("obtained %d rules, generating the classification report",
len(trainable_rules.rules))
trainable_rules.rules.generate_classification_report(
X_train, y_train, "train", fe.composite_class_representations)
if test_files:
trainable_rules.rules.generate_classification_report(
X_test, y_test, "test", fe.composite_class_representations)
submit_event("%s.train.%s.rules" % (cls.name, language), len(trainable_rules.rules))
if trainable_rules.rules.rules:
model[language] = trainable_rules.rules
else:
_log.warning("model for %s has 0 rules. Skipped.", language)
_log.info("trained %s", model)
return model
def train(cls, ptr: ReferencePointer, config: Mapping[str, Any],
data_service: DataService, **data) -> FormatModel:
"""
Train a model given the files available.
:param ptr: Git repository state pointer.
:param config: configuration dict.
:param data: contains "files" - the list of files in the pointed state.
:param data_service: connection to the Lookout data retrieval service.
:return: AnalyzerModel containing the learned rules, per language.
"""
_log = logging.getLogger(cls.__name__)
_log.info("train %s %s %s", ptr.url, ptr.commit,
pformat(config, width=4096, compact=True))
model = FormatModel().construct(cls, ptr)
config = cls._load_train_config(config)
for language, files in files_by_language(data["files"]).items():
try:
lang_config = config[language]
except KeyError:
_log.warning("language %s is not supported, skipped", language)
continue
files = filter_files(files, lang_config["line_length_limit"], _log)
submit_event("%s.train.%s.files" % (cls.name, language),
len(files))
if len(files) == 0:
_log.info(
"zero files after filtering, language %s is skipped.",
language)
continue
try:
fe = FeatureExtractor(language=language,
**lang_config["feature_extractor"])
except ImportError:
_log.warning("skipped %d %s files - not supported", len(files),
language)
continue
else:
_log.info("training on %d %s files", len(files), language)
# we sort to make the features reproducible
X, y, _ = fe.extract_features(sorted(files, key=lambda x: x.path))
X, selected_features = fe.select_features(X, y)
lang_config["feature_extractor"][
"selected_features"] = selected_features
lang_config["feature_extractor"][
"label_composites"] = fe.labels_to_class_sequences
lower_bound_instances = lang_config["lower_bound_instances"]
if X.shape[0] < lower_bound_instances:
_log.warning("skipped %d %s files: too few samples (%d/%d)",
len(files), language, X.shape[0],
lower_bound_instances)
continue
_log.debug("training the rules model")
optimizer = Optimizer(
n_jobs=lang_config["n_jobs"],
n_iter=lang_config["n_iter"],
cv=lang_config["cv"],
random_state=lang_config["trainable_rules"]["random_state"])
best_score, best_params = optimizer.optimize(X, y)
_log.debug("score of the best estimator found: %.6f", best_score)
_log.debug("params of the best estimator found: %s",
str(best_params))
_log.debug("training the model with complete data")
lang_config["trainable_rules"].update(best_params)
trainable_rules = TrainableRules(**lang_config["trainable_rules"],
origin_config=lang_config)
trainable_rules.fit(X, y)
importances = trainable_rules.feature_importances_
_log.debug(
"feature importances from %s:\n\t%s",
lang_config["trainable_rules"]["base_model_name"], "\n\t".join(
"%-55s %.5E" % (fe.feature_names[i], importances[i])
for i in numpy.argsort(-importances)[:25]
if importances[i] > 1e-5))
submit_event("%s.train.%s.rules" % (cls.name, language),
len(trainable_rules.rules))
# TODO(vmarkovtsev): save the achieved precision, recall, etc. to the model
# throw away imprecise classes
if trainable_rules.rules.rules:
model[language] = trainable_rules.rules
else:
_log.warning("model for %s has 0 rules. Skipping.", language)
_log.info("trained %s", model)
return model
