def fit(self,
X,
y=None,
max_depth=10,
min_samples_leaf=1,
sample_weight=False,
random_state=None):
log.info("Checking parameters...")
self.config.set_parameters({
"max_depth": max_depth,
"min_samples_leaf": min_samples_leaf,
"random_state": random_state
})
# create a model
self.tree = DecisionTreeClassifier(
max_depth=self.config.get_parameter("max_depth"),
min_samples_leaf=self.config.get_parameter("min_samples_leaf"),
random_state=self.config.get_parameter("random_state"))
log.info("Generating features for {} samples...".format(len(X)))
# Features and labels are useful for training.
features, tokens, labels = self.feature_extractor.transform(
X, entity_labels=self.entity_labels)
log.info("Training Decision Tree...")
weights = to_weights(labels) if sample_weight else None
self.tree.fit(features, labels, sample_weight=weights)
return self
def fit(self, X, y=None, n_estimators=9, max_features="auto",
min_samples_leaf=1, sample_weight=False, random_state=None):
log.info("Generating features for {} samples...".format(len(X)))
# Features and labels are useful for training.
features, tokens, labels = self.feature_extractor.transform(X, entity_labels=self.entity_labels)
log.info("Checking parameters...")
if type(max_features) == str:
if max_features == "auto":
max_features = self._get_max_features(features)
elif max_features == "log":
max_features = self._get_max_features(features, method=log2)
elif max_features == "sqrt":
max_features = self._get_max_features(features, method=sqrt)
else:
raise ValueError("Unknown method '{}' for feature selection in Random Forest".format(max_features))
if type(max_features) != int:
raise TypeError("The parameter 'max_features' must be either a string or integer.")
self.config.set_parameters({"n_estimators": n_estimators,
"max_features": max_features,
"random_state": random_state,
"min_samples_leaf": min_samples_leaf})
# create a model
self.rf = RandomForestClassifier(
n_estimators=self.config.get_parameter("n_estimators"),
max_features=self.config.get_parameter("max_features"),
min_samples_leaf=self.config.get_parameter("min_samples_leaf"),
random_state=self.config.get_parameter("random_state"))
log.info("Training Random Forest...")
weights = to_weights(labels) if sample_weight else None
self.rf.fit(features, labels, sample_weight=weights)
return self
def fit(self,
X,
y=None,
n_estimators=9,
max_features="auto",
sample_weight=False,
random_state=None):
# get features and labels
features, labels = self.feature_extractor.transform(
X, relation_labels=self.relation_labels)
if is_empty(features):
log.error("No examples to train, quiting...")
return self
log.info("Checking parameters...")
if type(max_features) == str:
if max_features == "auto":
max_features = self._get_max_features(features)
elif max_features == "log":
max_features = self._get_max_features(features, method=log2)
elif max_features == "sqrt":
max_features = self._get_max_features(features, method=sqrt)
else:
raise ValueError(
"Unknown method '{}' for feature selection in Random Forest"
.format(max_features))
if type(max_features) != int:
raise TypeError(
"The parameter 'max_features' must be either a string or integer."
)
self.config.set_parameters({
"n_estimators": n_estimators,
"max_features": max_features,
"random_state": random_state
})
# create a model
self.rf = RandomForestClassifier(
n_estimators=self.config.get_parameter("n_estimators"),
max_features=self.config.get_parameter("max_features"),
random_state=self.config.get_parameter("random_state"))
log.info("Training Random Forest...")
weights = to_weights(labels) if sample_weight else None
self.rf.fit(features, labels, sample_weight=weights)
return self
def fit(self, X, y=None, sample_weight=False):
log.info("Checking parameters...")
self.config.validate()
# create a model
self.nb = MultinomialNB()
# get features and labels
features, labels = self.feature_extractor.transform(
X, relation_labels=self.relation_labels)
if is_empty(features):
log.error("No examples to train, quiting...")
return self
log.info("Training Naive Bayes...")
weights = to_weights(labels) if sample_weight else None
self.nb.fit(features, labels, sample_weight=weights)
return self
def fit(self, X, y=None, max_iterations=100, C=1, sample_weight=False):
log.info("Checking parameters...")
self.config.set_parameters({"max_iterations": max_iterations, "C": C})
self.config.validate()
# create a model
self.svm = CalibratedClassifierCV(
LinearSVC(max_iter=self.config.get_parameter("max_iterations"),
C=self.config.get_parameter("C")))
# get features and labels
features, labels = self.feature_extractor.transform(
X, relation_labels=self.relation_labels)
if is_empty(features):
log.error("No examples to train, quiting...")
return self
log.info("Training SVM...")
weights = to_weights(labels) if sample_weight else None
self.svm.fit(features, labels, sample_weight=weights)
return self