def __init__(self,
dataset: "DataSet",
n_estimators=500,
max_leaf_nodes=16,
verbose=0,
model: RandomForestClassifier = None,
logger=None):
self.scores = scores = [
'recall_weighted', 'precision_micro', 'precision_weighted'
]
self.tuned_parameters = {
'criterion': ['gini', 'entropy'],
'class_weight': ['balanced', None],
'n_estimators': [10, 30, 50, 100, 150, 200],
'max_depth': [2, 3, 4, 5, 6, 7, None],
'bootstrap': [True, False]
}
if model == None:
self.classifier = RandomForestClassifier(n_estimators=150,
max_depth=5,
criterion='gini',
class_weight=None,
bootstrap=True)
# self.classifier = RandomForestClassifier(n_estimators=n_estimators, max_leaf_nodes=16, n_jobs=-1,
# verbose=verbose)
else:
self.classifier = model
SklearnClassifier.__init__(self, self.classifier)
Classifier.__init__(self, dataset, logger=logger)
def __init__(self,
dataset: "DataSet",
verbose=0,
model: SGDClassifier = None,
logger=None):
self.scores = scores = ['precision_weighted']
self.tuned_parameters_tf = {
'vect__ngram_range': [(1, 1), (1, 2), (1, 3), (1, 4)],
'tfidf__use_idf': [True, False],
'tfidf__smooth_idf': [True, False],
'tfidf__sublinear_tf': [True, False],
'clf__loss': ['hinge', 'modified_huber'],
'clf__penalty': ['none', 'l1', 'l2', 'elasticnet'],
'clf__class_weight': ['balanced', None],
'clf__fit_intercept': [True, False]
}
self.tuned_parameters = {
'loss': ['hinge', 'modified_huber'],
'penalty': ['none', 'l1', 'l2', 'elasticnet'],
'class_weight': ['balanced', None],
'fit_intercept': [True, False]
}
if model == None:
self.classifier = SGDClassifier()
else:
self.classifier = model
SklearnClassifier.__init__(self, self.classifier)
Classifier.__init__(self, dataset, logger=logger)
def __init__(self,
dataset,
estimators: [(str, BaseEstimator)],
logger=None,
voting='hard',
weights=None,
*args,
**kwargs):
"""
Parameters
----------
voting: str, {‘hard’, ‘soft’} (default=’hard’)
If ‘hard’, uses predicted class labels for majority rule voting. Else if ‘soft’,
predicts the class label based on the argmax of the sums of the predicted probabilities,
which is recommended for an ensemble of well-calibrated classifiers.
weights: array-like, shape = [n_classifiers], optional (default=`None`)
Sequence of weights (float or int) to weight the occurrences of predicted class labels (hard voting)
or class probabilities before averaging (soft voting). Uses uniform weights if None.
"""
self.classifier = VotingClassifier(estimators,
voting=voting,
weights=weights)
SklearnClassifier.__init__(self, self.classifier)
Classifier.__init__(self, dataset, logger)
def __init__(self, dataset: "DataSet", loss='squared_hinge', max_iter=1000, verbose=0, model=None,
logger: "Logger" = None):
# self.scores = scores = ['recall_weighted', 'precision_weighted']
self.scores = scores = ['precision_weighted']
self.tuned_parameters = {'C': [1, 10, 100, 1000], 'gamma': [1e-3, 1e-4, 'auto'],
'kernel': ['rbf', 'linear', 'poly'], 'class_weight': ['balanced', None],
'degree': [3, 4, 5]}
if model == None:
self.classifier = SVC()
else:
self.classifier = model
SklearnClassifier.__init__(self, self.classifier)
Classifier.__init__(self, dataset, logger=logger)
def __init__(self, dataset: "DataSet", verbose=0, model: MultinomialNB = None, logger=None):
self.scores = scores = ['precision_weighted']
self.tuned_parameters = {'vect__ngram_range': [(1, 1), (1, 2), (1, 3), (1, 4)],
'tfidf__use_idf': [True, False],
'tfidf__smooth_idf': [True, False],
'tfidf__sublinear_tf': [True, False],
'clf__alpha': [1e-2, 1e-3, 1e-4],
'clf__fit_prior': [True, False]}
if model == None:
self.classifier = MultinomialNB()
else:
self.classifier = model
SklearnClassifier.__init__(self, self.classifier)
Classifier.__init__(self, dataset, logger=logger)
def __init__(self,
dataset: "DataSet",
n_estimators=120,
verbose=0,
model=None,
logger: "Logger" = None):
self.scores = scores = ['recall_weighted', 'precision_weighted']
self.tuned_parameters = {
'loss': ['deviance'],
'learning_rate': [0.3, 0.1, 0.03, 0.01, 0.003, 0.001],
'n_estimators': [10, 30, 50, 100, 150, 200],
'max_depth': [2, 3, 4, 5, 6, 7, None]
}
if model == None:
self.classifier = GradientBoostingClassifier(n_estimators=100,
max_depth=5,
loss='deviance',
learning_rate=0.1)
# self.classifier = GradientBoostingClassifier(max_depth=2, n_estimators=n_estimators, verbose=verbose)
else:
self.classifier = model
SklearnClassifier.__init__(self, self.classifier)
Classifier.__init__(self, dataset, logger=logger)
def __init__(self, path, train_df, test_df, features):
Classifier.__init__(self, path, train_df, test_df, features)