def predict_proba(self, X, check_input=True):
"""Predict class probabilities of the input samples X.
The predicted class probability is the fraction of samples of the same
class in a leaf.
check_input : boolean, (default=True)
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
Parameters
----------
X : array-like or sparse matrix of shape = [n_samples, n_features]
The input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csr_matrix``.
Returns
-------
p : array of shape = [n_samples, n_classes], or a list of n_outputs
such arrays if n_outputs > 1.
The class probabilities of the input samples. The order of the
classes corresponds to that in the attribute `classes_`.
"""
check_is_fitted(self, 'n_outputs_')
if check_input:
X = check_array(X, dtype=DTYPE)
n_samples, n_features = X.shape
if self.tree_ is None:
raise NotFittedError("Tree not initialized. Perform a fit first.")
if self.n_features_ != n_features:
raise ValueError("Number of features of the model must "
" match the input. Model n_features is %s and "
" input n_features is %s " %
(self.n_features_, n_features))
proba = self.tree_.predict(X)
if self.n_outputs_ == 1:
proba = proba[:, :self.n_classes_]
normalizer = proba.sum(axis=1)[:, np.newaxis]
normalizer[normalizer == 0.0] = 1.0
proba /= normalizer
return proba
else:
all_proba = []
for k in range(self.n_outputs_):
proba_k = proba[:, k, :self.n_classes_[k]]
normalizer = proba_k.sum(axis=1)[:, np.newaxis]
normalizer[normalizer == 0.0] = 1.0
proba_k /= normalizer
all_proba.append(proba_k)
return all_proba
def fit(self, X, y):
""" Fit model with specified loss.
Parameters
----------
X : scipy.sparse.csc_matrix, (n_samples, n_features)
y : float | ndarray, shape = (n_samples, )
the targets have to be encodes as {-1, 1}.
"""
y = _validate_class_labels(y)
self.classes_ = np.unique(y)
if len(self.classes_) != 2:
raise ValueError("This solver only supports binary classification"
" but the data contains"
" class: %r" % self.classes_)
# fastFM-core expects labels to be in {-1,1}
y_train = y.copy()
i_class1 = (y_train == self.classes_[0])
y_train[i_class1] = -1
y_train[-i_class1] = 1
check_consistent_length(X, y)
y = y.astype(np.float64)
X = X.T
X = check_array(X, accept_sparse="csc", dtype=np.float64)
self.w0_, self.w_, self.V_ = ffm.ffm_sgd_fit(self, X, y)
return self
def _validate_mcmc_fit_input(X_train, y_train, X_test):
check_consistent_length(X_train, y_train)
assert_all_finite(y_train)
y_train = check_array(y_train, ensure_2d=False, dtype=np.float64)
assert X_train.shape[1] == X_test.shape[1]
X_train = check_array(X_train,
accept_sparse="csc",
dtype=np.float64,
order="F")
X_test = check_array(X_test,
accept_sparse="csc",
dtype=np.float64,
order="F")
return X_train, y_train, X_test
def predict_proba(self, X, check_input=True):
"""Predict class probabilities of the input samples X.
The predicted class probability is the fraction of samples of the same
class in a leaf.
check_input : boolean, (default=True)
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
Parameters
----------
X : array-like or sparse matrix of shape = [n_samples, n_features]
The input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csr_matrix``.
Returns
-------
p : array of shape = [n_samples, n_classes], or a list of n_outputs
such arrays if n_outputs > 1.
The class probabilities of the input samples. The order of the
classes corresponds to that in the attribute `classes_`.
"""
check_is_fitted(self, 'n_outputs_')
if check_input:
X = check_array(X, dtype=DTYPE)
n_samples, n_features = X.shape
if self.tree_ is None:
raise NotFittedError("Tree not initialized. Perform a fit first.")
if self.n_features_ != n_features:
raise ValueError("Number of features of the model must "
" match the input. Model n_features is %s and "
" input n_features is %s "
% (self.n_features_, n_features))
proba = self.tree_.predict(X)
if self.n_outputs_ == 1:
proba = proba[:, :self.n_classes_]
normalizer = proba.sum(axis=1)[:, np.newaxis]
normalizer[normalizer == 0.0] = 1.0
proba /= normalizer
return proba
else:
all_proba = []
for k in range(self.n_outputs_):
proba_k = proba[:, k, :self.n_classes_[k]]
normalizer = proba_k.sum(axis=1)[:, np.newaxis]
normalizer[normalizer == 0.0] = 1.0
proba_k /= normalizer
all_proba.append(proba_k)
return all_proba
def fit(self, X, y):
""" Fit model with specified loss.
Parameters
----------
X : scipy.sparse.csc_matrix, (n_samples, n_features)
y : float | ndarray, shape = (n_samples, )
"""
check_consistent_length(X, y)
y = check_array(y, ensure_2d=False, dtype=np.float64)
X = X.T
X = check_array(X, accept_sparse="csc", dtype=np.float64)
self.w0_, self.w_, self.V_ = ffm.ffm_sgd_fit(self, X, y)
return self
def predict(self, X_test):
""" Return predictions
Parameters
----------
X : scipy.sparse.csc_matrix, (n_samples, n_features)
Returns
------
T : array, shape (n_samples)
The labels are returned for classification.
"""
X_test = check_array(X_test, accept_sparse="csc", dtype=np.float64,
order="F")
assert sp.isspmatrix_csc(X_test)
assert X_test.shape[1] == len(self.w_)
return ffm.ffm_predict(self.w0_, self.w_, self.V_, X_test)
def fit(self, X, pairs):
""" Fit model with specified loss.
Parameters
----------
X : scipy.sparse.csc_matrix, (n_samples, n_features)
y : float | ndarray, shape = (n_compares, 2)
Each row `i` defines a pair of samples such that
the first returns a high value then the second
FM(X[i,0]) > FM(X[i, 1]).
"""
X = X.T
X = check_array(X, accept_sparse="csc", dtype=np.float64)
assert_all_finite(pairs)
pairs = pairs.astype(np.float64)
# check that pairs contain no real values
np.testing.assert_array_equal(pairs, pairs.astype(np.int32))
assert pairs.max() <= X.shape[1]
assert pairs.min() >= 0
self.w0_, self.w_, self.V_ = ffm.ffm_fit_sgd_bpr(self, X, pairs)
return self
def predict(self, X, check_input=True):
"""Predict class or regression value for X.
For a classification model, the predicted class for each sample in X is
returned. For a regression model, the predicted value based on X is
returned.
Parameters
----------
X : array-like or sparse matrix of shape = [n_samples, n_features]
The input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csr_matrix``.
check_input : boolean, (default=True)
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
Returns
-------
y : array of shape = [n_samples] or [n_samples, n_outputs]
The predicted classes, or the predict values.
"""
if check_input:
X = check_array(X, dtype=DTYPE)
n_samples, n_features = X.shape
if self.tree_ is None:
raise NotFittedError("Tree not initialized. Perform a fit first")
if self.n_features_ != n_features:
raise ValueError("Number of features of the model must "
" match the input. Model n_features is %s and "
" input n_features is %s " %
(self.n_features_, n_features))
proba = self.tree_.predict(X)
# Classification
if isinstance(self, ClassifierMixin):
if self.n_outputs_ == 1:
return self.classes_.take(np.argmax(proba, axis=1), axis=0)
else:
predictions = np.zeros((n_samples, self.n_outputs_))
for k in range(self.n_outputs_):
predictions[:,
k] = self.classes_[k].take(np.argmax(proba[:,
k],
axis=1),
axis=0)
return predictions
# Regression
else:
if self.n_outputs_ == 1:
return proba[:, 0]
else:
return proba[:, :, 0]
def fit(self, X, y, sample_weight=None, check_input=True):
"""Build a decision tree from the training set (X, y).
Parameters
----------
X : array-like or sparse matrix, shape = [n_samples, n_features]
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like, shape = [n_samples] or [n_samples, n_outputs]
The target values (class labels in classification, real numbers in
regression). In the regression case, use ``dtype=np.float64`` and
``order='C'`` for maximum efficiency.
sample_weight : array-like, shape = [n_samples] or None
Sample weights. If None, then samples are equally weighted. Splits
that would create child nodes with net zero or negative weight are
ignored while searching for a split in each node. In the case of
classification, splits are also ignored if they would result in any
single class carrying a negative weight in either child node.
check_input : boolean, (default=True)
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
Returns
-------
self : object
Returns self.
"""
random_state = check_random_state(self.random_state)
if check_input:
X = check_array(X, dtype=DTYPE)
# Determine output settings
n_samples, self.n_features_ = X.shape
is_classification = isinstance(self, ClassifierMixin)
y = np.atleast_1d(y)
expanded_class_weight = None
if y.ndim == 1:
# reshape is necessary to preserve the data contiguity against vs
# [:, np.newaxis] that does not.
y = np.reshape(y, (-1, 1))
self.n_outputs_ = y.shape[1]
if is_classification:
y = np.copy(y)
self.classes_ = []
self.n_classes_ = []
if self.class_weight is not None:
y_original = np.copy(y)
for k in range(self.n_outputs_):
classes_k, y[:, k] = np.unique(y[:, k], return_inverse=True)
self.classes_.append(classes_k)
self.n_classes_.append(classes_k.shape[0])
if self.class_weight is not None:
expanded_class_weight = compute_sample_weight(
self.class_weight, y_original)
else:
self.classes_ = [None] * self.n_outputs_
self.n_classes_ = [1] * self.n_outputs_
self.n_classes_ = np.array(self.n_classes_, dtype=np.intp)
if getattr(y, "dtype", None) != DOUBLE or not y.flags.contiguous:
y = np.ascontiguousarray(y, dtype=DOUBLE)
# Check parameters
max_depth = ((2**31) - 1 if self.max_depth is None else self.max_depth)
max_leaf_nodes = (-1 if self.max_leaf_nodes is None else
self.max_leaf_nodes)
if isinstance(self.max_features, string_types):
if self.max_features == "auto":
if is_classification:
max_features = max(1, int(np.sqrt(self.n_features_)))
else:
max_features = self.n_features_
elif self.max_features == "sqrt":
max_features = max(1, int(np.sqrt(self.n_features_)))
elif self.max_features == "log2":
max_features = max(1, int(np.log2(self.n_features_)))
else:
raise ValueError(
'Invalid value for max_features. Allowed string '
'values are "auto", "sqrt" or "log2".')
elif self.max_features is None:
max_features = self.n_features_
elif isinstance(self.max_features, (numbers.Integral, np.integer)):
max_features = self.max_features
else: # float
if self.max_features > 0.0:
max_features = max(1,
int(self.max_features * self.n_features_))
else:
max_features = 0
self.max_features_ = max_features
if len(y) != n_samples:
raise ValueError("Number of labels=%d does not match "
"number of samples=%d" % (len(y), n_samples))
if self.min_samples_split <= 0:
raise ValueError("min_samples_split must be greater than zero.")
if self.min_samples_leaf <= 0:
raise ValueError("min_samples_leaf must be greater than zero.")
if not 0 <= self.min_weight_fraction_leaf <= 0.5:
raise ValueError("min_weight_fraction_leaf must in [0, 0.5]")
if max_depth <= 0:
raise ValueError("max_depth must be greater than zero. ")
if not (0 < max_features <= self.n_features_):
raise ValueError("max_features must be in (0, n_features]")
if not isinstance(max_leaf_nodes, (numbers.Integral, np.integer)):
raise ValueError("max_leaf_nodes must be integral number but was "
"%r" % max_leaf_nodes)
if -1 < max_leaf_nodes < 2:
raise ValueError(("max_leaf_nodes {0} must be either smaller than "
"0 or larger than 1").format(max_leaf_nodes))
if sample_weight is not None:
if (getattr(sample_weight, "dtype", None) != DOUBLE
or not sample_weight.flags.contiguous):
sample_weight = np.ascontiguousarray(sample_weight,
dtype=DOUBLE)
if len(sample_weight.shape) > 1:
raise ValueError("Sample weights array has more "
"than one dimension: %d" %
len(sample_weight.shape))
if len(sample_weight) != n_samples:
raise ValueError("Number of weights=%d does not match "
"number of samples=%d" %
(len(sample_weight), n_samples))
if expanded_class_weight is not None:
if sample_weight is not None:
sample_weight = sample_weight * expanded_class_weight
else:
sample_weight = expanded_class_weight
# Set min_weight_leaf from min_weight_fraction_leaf
if self.min_weight_fraction_leaf != 0. and sample_weight is not None:
min_weight_leaf = (self.min_weight_fraction_leaf *
np.sum(sample_weight))
else:
min_weight_leaf = 0.
# Set min_samples_split sensibly
min_samples_split = max(self.min_samples_split,
2 * self.min_samples_leaf)
# Build tree
criterion = self.criterion
if not isinstance(criterion, Criterion):
if is_classification:
criterion = CRITERIA_CLF[self.criterion](self.n_outputs_,
self.n_classes_)
else:
criterion = CRITERIA_REG[self.criterion](self.n_outputs_)
SPLITTERS = DENSE_SPLITTERS
splitter = self.splitter
if not isinstance(self.splitter, Splitter):
splitter = SPLITTERS[self.splitter](criterion, self.max_features_,
self.min_samples_leaf,
min_weight_leaf, random_state)
self.tree_ = Tree(self.n_features_, self.n_classes_, self.n_outputs_)
# Use BestFirst if max_leaf_nodes given; use DepthFirst otherwise
if max_leaf_nodes < 0:
builder = DepthFirstTreeBuilder(splitter, min_samples_split,
self.min_samples_leaf,
min_weight_leaf, max_depth)
else:
builder = BestFirstTreeBuilder(splitter, min_samples_split,
self.min_samples_leaf,
min_weight_leaf, max_depth,
max_leaf_nodes)
builder.build(self.tree_, X, y, sample_weight)
if self.n_outputs_ == 1:
self.n_classes_ = self.n_classes_[0]
self.classes_ = self.classes_[0]
return self
def _validate_class_labels(y):
assert len(set(y)) == 2
assert y.min() == -1
assert y.max() == 1
return check_array(y, ensure_2d=False, dtype=np.float64)
def fit(self, X, y, sample_weight=None, check_input=True):
"""Build a decision tree from the training set (X, y).
Parameters
----------
X : array-like or sparse matrix, shape = [n_samples, n_features]
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like, shape = [n_samples] or [n_samples, n_outputs]
The target values (class labels in classification, real numbers in
regression). In the regression case, use ``dtype=np.float64`` and
``order='C'`` for maximum efficiency.
sample_weight : array-like, shape = [n_samples] or None
Sample weights. If None, then samples are equally weighted. Splits
that would create child nodes with net zero or negative weight are
ignored while searching for a split in each node. In the case of
classification, splits are also ignored if they would result in any
single class carrying a negative weight in either child node.
check_input : boolean, (default=True)
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
Returns
-------
self : object
Returns self.
"""
random_state = check_random_state(self.random_state)
if check_input:
X = check_array(X, dtype=DTYPE)
# Determine output settings
n_samples, self.n_features_ = X.shape
is_classification = isinstance(self, ClassifierMixin)
y = np.atleast_1d(y)
expanded_class_weight = None
if y.ndim == 1:
# reshape is necessary to preserve the data contiguity against vs
# [:, np.newaxis] that does not.
y = np.reshape(y, (-1, 1))
self.n_outputs_ = y.shape[1]
if is_classification:
y = np.copy(y)
self.classes_ = []
self.n_classes_ = []
if self.class_weight is not None:
y_original = np.copy(y)
for k in range(self.n_outputs_):
classes_k, y[:, k] = np.unique(y[:, k], return_inverse=True)
self.classes_.append(classes_k)
self.n_classes_.append(classes_k.shape[0])
if self.class_weight is not None:
expanded_class_weight = compute_sample_weight(
self.class_weight, y_original)
else:
self.classes_ = [None] * self.n_outputs_
self.n_classes_ = [1] * self.n_outputs_
self.n_classes_ = np.array(self.n_classes_, dtype=np.intp)
if getattr(y, "dtype", None) != DOUBLE or not y.flags.contiguous:
y = np.ascontiguousarray(y, dtype=DOUBLE)
# Check parameters
max_depth = ((2 ** 31) - 1 if self.max_depth is None
else self.max_depth)
max_leaf_nodes = (-1 if self.max_leaf_nodes is None
else self.max_leaf_nodes)
if isinstance(self.max_features, string_types):
if self.max_features == "auto":
if is_classification:
max_features = max(1, int(np.sqrt(self.n_features_)))
else:
max_features = self.n_features_
elif self.max_features == "sqrt":
max_features = max(1, int(np.sqrt(self.n_features_)))
elif self.max_features == "log2":
max_features = max(1, int(np.log2(self.n_features_)))
else:
raise ValueError(
'Invalid value for max_features. Allowed string '
'values are "auto", "sqrt" or "log2".')
elif self.max_features is None:
max_features = self.n_features_
elif isinstance(self.max_features, (numbers.Integral, np.integer)):
max_features = self.max_features
else: # float
if self.max_features > 0.0:
max_features = max(1, int(self.max_features * self.n_features_))
else:
max_features = 0
self.max_features_ = max_features
if len(y) != n_samples:
raise ValueError("Number of labels=%d does not match "
"number of samples=%d" % (len(y), n_samples))
if self.min_samples_split <= 0:
raise ValueError("min_samples_split must be greater than zero.")
if self.min_samples_leaf <= 0:
raise ValueError("min_samples_leaf must be greater than zero.")
if not 0 <= self.min_weight_fraction_leaf <= 0.5:
raise ValueError("min_weight_fraction_leaf must in [0, 0.5]")
if max_depth <= 0:
raise ValueError("max_depth must be greater than zero. ")
if not (0 < max_features <= self.n_features_):
raise ValueError("max_features must be in (0, n_features]")
if not isinstance(max_leaf_nodes, (numbers.Integral, np.integer)):
raise ValueError("max_leaf_nodes must be integral number but was "
"%r" % max_leaf_nodes)
if -1 < max_leaf_nodes < 2:
raise ValueError(("max_leaf_nodes {0} must be either smaller than "
"0 or larger than 1").format(max_leaf_nodes))
if sample_weight is not None:
if (getattr(sample_weight, "dtype", None) != DOUBLE or
not sample_weight.flags.contiguous):
sample_weight = np.ascontiguousarray(
sample_weight, dtype=DOUBLE)
if len(sample_weight.shape) > 1:
raise ValueError("Sample weights array has more "
"than one dimension: %d" %
len(sample_weight.shape))
if len(sample_weight) != n_samples:
raise ValueError("Number of weights=%d does not match "
"number of samples=%d" %
(len(sample_weight), n_samples))
if expanded_class_weight is not None:
if sample_weight is not None:
sample_weight = sample_weight * expanded_class_weight
else:
sample_weight = expanded_class_weight
# Set min_weight_leaf from min_weight_fraction_leaf
if self.min_weight_fraction_leaf != 0. and sample_weight is not None:
min_weight_leaf = (self.min_weight_fraction_leaf *
np.sum(sample_weight))
else:
min_weight_leaf = 0.
# Set min_samples_split sensibly
min_samples_split = max(self.min_samples_split,
2 * self.min_samples_leaf)
# Build tree
criterion = self.criterion
if not isinstance(criterion, Criterion):
if is_classification:
criterion = CRITERIA_CLF[self.criterion](self.n_outputs_,
self.n_classes_)
else:
criterion = CRITERIA_REG[self.criterion](self.n_outputs_)
SPLITTERS = DENSE_SPLITTERS
splitter = self.splitter
if not isinstance(self.splitter, Splitter):
splitter = SPLITTERS[self.splitter](criterion,
self.max_features_,
self.min_samples_leaf,
min_weight_leaf,
random_state)
self.tree_ = Tree(self.n_features_, self.n_classes_, self.n_outputs_)
# Use BestFirst if max_leaf_nodes given; use DepthFirst otherwise
if max_leaf_nodes < 0:
builder = DepthFirstTreeBuilder(splitter, min_samples_split,
self.min_samples_leaf,
min_weight_leaf,
max_depth)
else:
builder = BestFirstTreeBuilder(splitter, min_samples_split,
self.min_samples_leaf,
min_weight_leaf,
max_depth,
max_leaf_nodes)
builder.build(self.tree_, X, y, sample_weight)
if self.n_outputs_ == 1:
self.n_classes_ = self.n_classes_[0]
self.classes_ = self.classes_[0]
return self
def predict(self, X, check_input=True):
"""Predict class or regression value for X.
For a classification model, the predicted class for each sample in X is
returned. For a regression model, the predicted value based on X is
returned.
Parameters
----------
X : array-like or sparse matrix of shape = [n_samples, n_features]
The input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csr_matrix``.
check_input : boolean, (default=True)
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
Returns
-------
y : array of shape = [n_samples] or [n_samples, n_outputs]
The predicted classes, or the predict values.
"""
if check_input:
X = check_array(X, dtype=DTYPE)
n_samples, n_features = X.shape
if self.tree_ is None:
raise NotFittedError("Tree not initialized. Perform a fit first")
if self.n_features_ != n_features:
raise ValueError("Number of features of the model must "
" match the input. Model n_features is %s and "
" input n_features is %s "
% (self.n_features_, n_features))
proba = self.tree_.predict(X)
# Classification
if isinstance(self, ClassifierMixin):
if self.n_outputs_ == 1:
return self.classes_.take(np.argmax(proba, axis=1), axis=0)
else:
predictions = np.zeros((n_samples, self.n_outputs_))
for k in range(self.n_outputs_):
predictions[:, k] = self.classes_[k].take(
np.argmax(proba[:, k], axis=1),
axis=0)
return predictions
# Regression
else:
if self.n_outputs_ == 1:
return proba[:, 0]
else:
return proba[:, :, 0]