def predict_proba(self, X):
"""Predict label probabilities with the fitted estimator on
predictor(s) X.
Returns
-------
proba : array of shape = [n_samples]
The predicted label probabilities of the input samples.
"""
proba = []
X_subs = self._get_subdata(X)
for i in range(self.n_classes_):
e = self.estimators_[i]
X_i = X_subs[i]
pred = e.predict(X_i).reshape(-1, 1)
proba.append(pred)
proba = np.hstack(proba)
normalizer = proba.sum(axis=1)[:, np.newaxis]
normalizer[normalizer == 0.0] = 1.0
proba /= normalizer
assert_all_finite(proba)
return proba
def predict(self, X):
"""
Perform regression on an array of test vectors X.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples]
Predicted target values for X
"""
try:
assert_all_finite(self.coef_)
pred = safe_sparse_dot(X, self.coef_.T)
except ValueError:
n_samples = X.shape[0]
n_vectors = self.coef_.shape[0]
pred = np.zeros((n_samples, n_vectors))
if not self.outputs_2d_:
pred = pred.ravel()
return pred
def _check_X_y(X,
y,
dtype="numeric",
accept_sparse=False,
order=None,
copy=False,
force_all_finite=True,
ensure_2d=True):
if y is None:
raise ValueError("y cannot be None")
X = _check_array(X,
accept_sparse=accept_sparse,
dtype=dtype,
order=order,
copy=copy,
force_all_finite=force_all_finite,
ensure_2d=ensure_2d)
y = _column_or_1d(y)
if y.dtype.kind == 'O':
y = y.astype(np.float64)
# TODO: replace on daal4py
from sklearn.utils.validation import assert_all_finite
assert_all_finite(y)
lengths = [len(X), len(y)]
uniques = np.unique(lengths)
if len(uniques) > 1:
raise ValueError("Found input variables with inconsistent numbers of"
" samples: %r" % [int(length) for length in lengths])
return X, y
def _fit_diag(self, pairs, y):
"""Learn diagonal metric using MMC.
Parameters
----------
X : (n x d) data matrix
each row corresponds to a single instance
constraints : 4-tuple of arrays
(a,b,c,d) indices into X, with (a,b) specifying similar and (c,d)
dissimilar pairs
"""
num_dim = pairs.shape[2]
pos_pairs, neg_pairs = pairs[y == 1], pairs[y == -1]
s_sum = np.sum((pos_pairs[:, 0, :] - pos_pairs[:, 1, :]) ** 2, axis=0)
it = 0
error = 1.0
eps = 1e-6
reduction = 2.0
w = np.diag(self.A_).copy()
while error > self.convergence_threshold and it < self.max_iter:
fD0, fD_1st_d, fD_2nd_d = self._D_constraint(neg_pairs, w)
obj_initial = np.dot(s_sum, w) + self.diagonal_c * fD0
fS_1st_d = s_sum # first derivative of the similarity constraints
gradient = fS_1st_d - self.diagonal_c * fD_1st_d # gradient of the objective
hessian = -self.diagonal_c * fD_2nd_d + eps * np.eye(num_dim) # Hessian of the objective
step = np.dot(np.linalg.inv(hessian), gradient)
# Newton-Rapshon update
# search over optimal lambda
lambd = 1 # initial step-size
w_tmp = np.maximum(0, w - lambd * step)
obj = (np.dot(s_sum, w_tmp) + self.diagonal_c *
self._D_objective(neg_pairs, w_tmp))
assert_all_finite(obj)
obj_previous = obj + 1 # just to get the while-loop started
inner_it = 0
while obj < obj_previous:
obj_previous = obj
w_previous = w_tmp.copy()
lambd /= reduction
w_tmp = np.maximum(0, w - lambd * step)
obj = (np.dot(s_sum, w_tmp) + self.diagonal_c *
self._D_objective(neg_pairs, w_tmp))
inner_it += 1
assert_all_finite(obj)
w[:] = w_previous
error = np.abs((obj_previous - obj_initial) / obj_previous)
if self.verbose:
print('mmc iter: %d, conv = %f' % (it, error))
it += 1
self.A_ = np.diag(w)
self.transformer_ = transformer_from_metric(self.A_)
return self
def _scrub_x(self, X, missing, **kwargs):
'''
Sanitize input predictors and extract column names if appropriate.
'''
# Check for sparseness
if sparse.issparse(X):
raise TypeError('A sparse matrix was passed, but dense data '
'is required. Use X.toarray() to convert to dense.')
# Figure out missingness
if missing is None:
# Infer missingness
missing = np.isnan(X)
# Convert to internally used data type
missing = np.asarray(missing, dtype=BOOL, order='F')
assert_all_finite(missing)
if missing.ndim == 1:
missing = missing[:, np.newaxis]
X = np.asarray(X, dtype=np.float64, order='F')
if not self.allow_missing:
try:
assert_all_finite(X)
except ValueError:
raise ValueError("Input contains NaN, infinity or a value that's too large. Did you mean to set allow_missing=True?")
if X.ndim == 1:
X = X[:, np.newaxis]
# Ensure correct number of columns
if hasattr(self, 'basis_') and self.basis_ is not None:
if X.shape[1] != self.basis_.num_variables:
raise ValueError('Wrong number of columns in X')
return X, missing
def predict_proba(self, X):
""" Predict label probabilities with the fitted estimator
on predictor(s) X.
Returns
-------
proba : array of shape = [n_samples]
The predicted label probabilities of the input samples.
"""
proba = []
X_subs = self._get_subdata(X)
for i in range(self.n_classes_):
e = self.estimators_[i]
X_i = X_subs[i]
pred = e.predict(X_i).reshape(-1, 1)
proba.append(pred)
proba = np.hstack(proba)
normalizer = proba.sum(axis=1)[:, np.newaxis]
normalizer[normalizer == 0.0] = 1.0
proba /= normalizer
assert_all_finite(proba)
return proba
def _make_meta(self, X):
rows = []
for e in self.estimators_:
proba = e.predict_proba(X)
assert_all_finite(proba)
rows.append(proba)
return np.hstack(rows)
def _svd(self, array, n_components, n_discard):
"""Returns first `n_components` left and right singular
vectors u and v, discarding the first `n_discard`.
"""
if self.svd_method == 'randomized':
kwargs = {}
if self.n_svd_vecs is not None:
kwargs['n_oversamples'] = self.n_svd_vecs
u, _, vt = randomized_svd(array,
n_components,
random_state=self.random_state,
**kwargs)
elif self.svd_method == 'arpack':
u, _, vt = svds(array, k=n_components, ncv=self.n_svd_vecs)
if np.any(np.isnan(vt)):
# some eigenvalues of A * A.T are negative, causing
# sqrt() to be np.nan. This causes some vectors in vt
# to be np.nan.
_, v = eigsh(safe_sparse_dot(array.T, array),
ncv=self.n_svd_vecs)
vt = v.T
if np.any(np.isnan(u)):
_, u = eigsh(safe_sparse_dot(array, array.T),
ncv=self.n_svd_vecs)
assert_all_finite(u)
assert_all_finite(vt)
u = u[:, n_discard:]
vt = vt[n_discard:]
return u, vt.T
def _svd(self, array, n_components, n_discard):
"""Returns first `n_components` left and right singular
vectors u and v, discarding the first `n_discard`.
"""
if self.svd_method == "randomized":
kwargs = {}
if self.n_svd_vecs is not None:
kwargs["n_oversamples"] = self.n_svd_vecs
u, _, vt = randomized_svd(array, n_components, random_state=self.random_state, **kwargs)
elif self.svd_method == "arpack":
u, _, vt = svds(array, k=n_components, ncv=self.n_svd_vecs)
if np.any(np.isnan(vt)):
# some eigenvalues of A * A.T are negative, causing
# sqrt() to be np.nan. This causes some vectors in vt
# to be np.nan.
_, v = eigsh(safe_sparse_dot(array.T, array), ncv=self.n_svd_vecs)
vt = v.T
if np.any(np.isnan(u)):
_, u = eigsh(safe_sparse_dot(array, array.T), ncv=self.n_svd_vecs)
assert_all_finite(u)
assert_all_finite(vt)
u = u[:, n_discard:]
vt = vt[n_discard:]
return u, vt.T
def predict(self, X):
"""
Perform regression on an array of test vectors X.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Returns
-------
p : array, shape = [n_samples]
Predicted target values for X
"""
try:
assert_all_finite(self.coef_)
pred = safe_sparse_dot(X, self.coef_.T)
pred += self.intercept_
except ValueError:
n_samples = X.shape[0]
n_vectors = self.coef_.shape[0]
pred = np.zeros((n_samples, n_vectors))
if not self.outputs_2d_:
pred = pred.ravel()
return pred
def test_suppress_validation():
X = np.array([0, np.inf])
assert_raises(ValueError, assert_all_finite, X)
sklearn.set_config(assume_finite=True)
assert_all_finite(X)
sklearn.set_config(assume_finite=False)
assert_raises(ValueError, assert_all_finite, X)
def _fit_diag(self, pairs, y):
"""Learn diagonal metric using MMC.
Parameters
----------
X : (n x d) data matrix
each row corresponds to a single instance
constraints : 4-tuple of arrays
(a,b,c,d) indices into X, with (a,b) specifying similar and (c,d)
dissimilar pairs
"""
num_dim = pairs.shape[2]
pos_pairs, neg_pairs = pairs[y == 1], pairs[y == -1]
s_sum = np.sum((pos_pairs[:, 0, :] - pos_pairs[:, 1, :]) ** 2, axis=0)
it = 0
error = 1.0
eps = 1e-6
reduction = 2.0
w = np.diag(self.A_).copy()
while error > self.convergence_threshold and it < self.max_iter:
fD0, fD_1st_d, fD_2nd_d = self._D_constraint(neg_pairs, w)
obj_initial = np.dot(s_sum, w) + self.diagonal_c * fD0
fS_1st_d = s_sum # first derivative of the similarity constraints
gradient = fS_1st_d - self.diagonal_c * fD_1st_d # gradient of the objective
hessian = -self.diagonal_c * fD_2nd_d + eps * np.eye(num_dim) # Hessian of the objective
step = np.dot(np.linalg.inv(hessian), gradient)
# Newton-Rapshon update
# search over optimal lambda
lambd = 1 # initial step-size
w_tmp = np.maximum(0, w - lambd * step)
obj = (np.dot(s_sum, w_tmp) + self.diagonal_c *
self._D_objective(neg_pairs, w_tmp))
assert_all_finite(obj)
obj_previous = obj + 1 # just to get the while-loop started
inner_it = 0
while obj < obj_previous:
obj_previous = obj
w_previous = w_tmp.copy()
lambd /= reduction
w_tmp = np.maximum(0, w - lambd * step)
obj = (np.dot(s_sum, w_tmp) + self.diagonal_c *
self._D_objective(neg_pairs, w_tmp))
inner_it += 1
assert_all_finite(obj)
w[:] = w_previous
error = np.abs((obj_previous - obj_initial) / obj_previous)
if self.verbose:
print('mmc iter: %d, conv = %f' % (it, error))
it += 1
self.A_ = np.diag(w)
self.transformer_ = transformer_from_metric(self.A_)
return self
def fit(self, X, y):
"""Fit model according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : classifier
Returns self.
"""
rs = check_random_state(self.random_state)
reencode = self.multiclass
y, n_classes, n_vectors = self._set_label_transformers(y, reencode)
ds = get_dataset(X)
n_samples = ds.get_n_samples()
n_features = ds.get_n_features()
self.coef_ = np.zeros((n_vectors, n_features), dtype=np.float64)
self.intercept_ = np.zeros(n_vectors, dtype=np.float64)
loss = self._get_loss()
penalty = self._get_penalty()
if n_vectors == 1 or not self.multiclass:
Y = np.asfortranarray(self.label_binarizer_.fit_transform(y),
dtype=np.float64)
for i in xrange(n_vectors):
_binary_sgd(self, self.coef_, self.intercept_, i, ds,
Y[:, i], loss, penalty, self.alpha,
self._get_learning_rate(), self.eta0, self.power_t,
self.fit_intercept, self.intercept_decay,
int(self.max_iter * n_samples), self.shuffle, rs,
self.callback, self.n_calls, self.verbose)
elif self.multiclass:
_multiclass_sgd(self, self.coef_, self.intercept_, ds,
y.astype(np.int32), loss, penalty, self.alpha,
self._get_learning_rate(), self.eta0, self.power_t,
self.fit_intercept, self.intercept_decay,
int(self.max_iter * n_samples), self.shuffle, rs,
self.callback, self.n_calls, self.verbose)
else:
raise ValueError("Wrong value for multiclass.")
try:
assert_all_finite(self.coef_)
except ValueError:
warnings.warn("coef_ contains infinite values")
return self
def test_gibbs_smoke():
"""Check if we don't get NaNs sampling the full digits dataset."""
rng = np.random.RandomState(42)
X = Xdigits.astype(np.float32)
rbm1 = BernoulliRBM(X.shape[1], n_hidden=42, batch_size=40,
n_iter=20, random_state=rng)
rbm1.fit(X)
X_sampled = rbm1.gibbs(X)
assert_all_finite(X_sampled)
def test_gibbs_smoke():
""" just seek if we don't get NaNs sampling the full digits dataset """
rng = np.random.RandomState(42)
X = Xdigits
rbm1 = BernoulliRBM(n_components=42, batch_size=10,
n_iter=20, random_state=rng)
rbm1.fit(X)
X_sampled = rbm1.gibbs(X)
assert_all_finite(X_sampled)
def test_gibbs_smoke():
"""Check if we don't get NaNs sampling the full digits dataset.
Also check that sampling again will yield different results."""
X = Xdigits
rbm1 = BernoulliRBM(n_components=42, batch_size=40, n_iter=20, random_state=42)
rbm1.fit(X)
X_sampled = rbm1.gibbs(X)
assert_all_finite(X_sampled)
X_sampled2 = rbm1.gibbs(X)
assert_true(np.all((X_sampled != X_sampled2).max(axis=1)))
def test_gibbs_smoke():
# Check if we don't get NaNs sampling the full digits dataset.
# Also check that sampling again will yield different results.
X = Xdigits
rbm1 = BernoulliRBM(n_components=42, batch_size=40, n_iter=20, random_state=42)
rbm1.fit(X)
X_sampled = rbm1.gibbs(X)
assert_all_finite(X_sampled)
X_sampled2 = rbm1.gibbs(X)
assert np.all((X_sampled != X_sampled2).max(axis=1))
def bad_rows(X, is_X=True):
bad = []
from sklearn.utils.validation import assert_all_finite
for i in range(X.shape[0]):
try:
assert_all_finite(X[i])
except ValueError:
print("Index %s was not finite" % i)
bad.append(i)
print_bad(X[i], i, is_X)
return bad
def custom_svd(array, n_components, n_discard,n_svd_vecs): u, _, vt = svds(array, k=n_components, ncv=n_svd_vecs) if np.any(np.isnan(vt)): _, v = eigsh(safe_sparse_dot(array.T, array),ncv=n_svd_vecs) vt = v.T if np.any(np.isnan(u)): _, u = eigsh(safe_sparse_dot(array, array.T),ncv=n_svd_vecs) assert_all_finite(u) assert_all_finite(vt) u = u[:, n_discard:] vt = vt[n_discard:] return u, vt.T
def fit(self, X, y):
"""Fit model according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples] or [n_samples, n_targets]
Target values.
Returns
-------
self : regressor
Returns self.
"""
rs = check_random_state(self.random_state)
ds = get_dataset(X)
n_samples = ds.get_n_samples()
n_features = ds.get_n_features()
self.outputs_2d_ = len(y.shape) == 2
if self.outputs_2d_:
Y = y
else:
Y = y.reshape(-1, 1)
Y = np.asfortranarray(Y)
n_vectors = Y.shape[1]
self.coef_ = np.zeros((n_vectors, n_features), dtype=np.float64)
self.intercept_ = np.zeros(n_vectors, dtype=np.float64)
loss = self._get_loss()
penalty = self._get_penalty()
for k in range(n_vectors):
_binary_sgd(self,
self.coef_, self.intercept_, k,
ds, Y[:, k], loss, penalty, self.alpha,
self._get_learning_rate(),
self.eta0, self.power_t,
self.fit_intercept,
self.intercept_decay,
int(self.max_iter * n_samples), self.shuffle, rs,
self.callback, self.n_calls, self.verbose)
try:
assert_all_finite(self.coef_)
except ValueError:
warnings.warn("coef_ contains infinite values")
return self
def test_gibbs_smoke():
"""Check if we don't get NaNs sampling the full digits dataset."""
rng = np.random.RandomState(42)
X = Xdigits.astype(np.float32)
rbm1 = BernoulliRBM(X.shape[1],
n_hidden=42,
batch_size=40,
n_iter=20,
random_state=rng)
rbm1.fit(X)
X_sampled = rbm1.gibbs(X)
assert_all_finite(X_sampled)
def fit(self, X, y):
"""Fit model according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples] or [n_samples, n_targets]
Target values.
Returns
-------
self : regressor
Returns self.
"""
rs = check_random_state(self.random_state)
ds = get_dataset(X)
n_samples = ds.get_n_samples()
n_features = ds.get_n_features()
self.outputs_2d_ = len(y.shape) == 2
if self.outputs_2d_:
Y = y
else:
Y = y.reshape(-1, 1)
Y = np.asfortranarray(Y)
n_vectors = Y.shape[1]
self.coef_ = np.zeros((n_vectors, n_features), dtype=np.float64)
self.intercept_ = np.zeros(n_vectors, dtype=np.float64)
loss = self._get_loss()
penalty = self._get_penalty()
for k in xrange(n_vectors):
_binary_sgd(self,
self.coef_, self.intercept_, k,
ds, Y[:, k], loss, penalty, self.alpha,
self._get_learning_rate(),
self.eta0, self.power_t,
self.fit_intercept,
self.intercept_decay,
int(self.max_iter * n_samples), self.shuffle, rs,
self.callback, self.n_calls, self.verbose)
try:
assert_all_finite(self.coef_)
except ValueError:
warnings.warn("coef_ contains infinite values")
return self
def main(name, num, useSpecial=False):
labels = []
with open("C:/MissingWord/corrScoring/" + name + "Labels.txt", "r") as f:
for line in f:
labels.append(float(line))
features = []
with open("C:/MissingWord/corrScoring/1000features.txt", "r") as f:
for line in f:
features.append([float(elem) for elem in line.split(",")])
specialFeatures = getSpecialFeatures(len(features))
if useSpecial:
for i in range(min(len(specialFeatures), len(features))):
features[i].extend(specialFeatures[i])
features = features[:num]
labels = labels[:num]
for i in range(len(features)):
if len(features[i]) != len(features[0]):
print(i)
try:
assert_all_finite(features[i])
except:
print(i)
cutoff = int(len(features) * 7 / 10)
trainFeatures = features[:cutoff]
testFeatures = features[cutoff:]
trainLabels = labels[:cutoff]
testLabels = labels[cutoff:]
#regr = svm.SVR(C=1)
regr = RandomForestRegressor(n_estimators=300, n_jobs=7)
#regr = linear_model.LinearRegression()
regr.fit(trainFeatures, trainLabels)
print("Train Residual sum of squares: %.2f" % np.mean(
(regr.predict(trainFeatures) - trainLabels)**2))
print("Test Residual sum of squares: %.2f" % np.mean(
(regr.predict(testFeatures) - testLabels)**2))
print('Variance score: %.2f' % regr.score(testFeatures, testLabels))
with open("C:/MissingWord/corrScoring/" + name + ".regr", "wb") as f:
pickle.dump(regr, f)
def check_input_arrays(*args, validate_len=True, force_all_finite=True):
"""Cast input sequences into numpy arrays.
Only inputs that are sequence-like will be converted, all other inputs will be left as is.
When `validate_len` is True, the sequences will be checked for equal length.
Parameters
----------
args : scalar or array_like
Inputs to be checked.
validate_len : bool (default=True)
Whether to check if the input arrays have the same length.
force_all_finite : bool (default=True)
Whether to allow inf and nan in input arrays.
Returns
-------
args: array-like
List of inputs where sequence-like objects have been cast to numpy arrays.
"""
n = None
args = list(args)
for i, arg in enumerate(args):
if np.ndim(arg) > 0:
new_arg = check_array(arg,
dtype=None,
ensure_2d=False,
accept_sparse=True,
force_all_finite=force_all_finite)
if not force_all_finite:
# For when checking input values is disabled
try:
assert_all_finite(new_arg)
except ValueError:
warnings.warn(
"Input contains NaN, infinity or a value too large for dtype('float64') "
"but input check is disabled. Check the inputs before proceeding."
)
if validate_len:
m = new_arg.shape[0]
if n is None:
n = m
else:
assert (
m == n
), "Input arrays have incompatible lengths: {} and {}".format(
n, m)
args[i] = new_arg
return args
def test_cd_linear_trivial():
# trivial example that failed due to gh#4
loss = Squared()
alpha = 1e-5
n_features = 100
x = np.zeros((1, n_features))
x[0, 1] = 1
y = np.ones(1)
cb = Callback(x, y, alpha)
w = _fit_linear(x, y, alpha, n_iter=20, loss=loss, callback=cb)
assert_all_finite(w)
assert_all_finite(cb.losses_)
def predict(self, X):
try:
assert_all_finite(self.coef_)
pred = safe_sparse_dot(X, self.coef_.T)
except ValueError:
n_samples = X.shape[0]
n_vectors = self.coef_.shape[0]
pred = np.zeros((n_samples, n_vectors))
if not self.outputs_2d_:
pred = pred.ravel()
return pred
def _check_alphas(self):
create_path = self.alphas is None
if create_path:
if self.n_alphas <= 0:
raise ValueError("n_alphas must be a positive integer")
alphas = numpy.empty(int(self.n_alphas), dtype=numpy.float64)
else:
alphas = column_or_1d(self.alphas, warn=True)
assert_all_finite(alphas)
check_non_negative(alphas, "alphas")
assert_all_finite(alphas)
return alphas, create_path
def fit(self, X, y):
rs = check_random_state(self.random_state)
reencode = self.multiclass
y, n_classes, n_vectors = self._set_label_transformers(y, reencode)
ds = get_dataset(X)
n_samples = ds.get_n_samples()
n_features = ds.get_n_features()
self.coef_ = np.zeros((n_vectors, n_features), dtype=np.float64)
self.intercept_ = np.zeros(n_vectors, dtype=np.float64)
loss = self._get_loss()
penalty = self._get_penalty()
if n_vectors == 1 or not self.multiclass:
Y = np.asfortranarray(self.label_binarizer_.fit_transform(y),
dtype=np.float64)
for i in xrange(n_vectors):
_binary_sgd(self,
self.coef_, self.intercept_, i,
ds, Y[:, i], loss, penalty,
self.alpha,
self._get_learning_rate(),
self.eta0, self.power_t,
self.fit_intercept,
self.intercept_decay,
int(self.max_iter * n_samples), self.shuffle, rs,
self.callback, self.n_calls, self.verbose)
elif self.multiclass:
_multiclass_sgd(self, self.coef_, self.intercept_,
ds, y.astype(np.int32), loss, penalty,
self.alpha, self._get_learning_rate(),
self.eta0, self.power_t, self.fit_intercept,
self.intercept_decay,
int(self.max_iter * n_samples),
self.shuffle, rs, self.callback, self.n_calls,
self.verbose)
else:
raise ValueError("Wrong value for multiclass.")
try:
assert_all_finite(self.coef_)
except ValueError:
warnings.warn("coef_ contains infinite values")
return self
def main(name, num, useSpecial = False):
labels = []
with open("C:/MissingWord/corrScoring/"+name+"Labels.txt", "r") as f:
for line in f:
labels.append(float(line))
features = []
with open("C:/MissingWord/corrScoring/1000features.txt", "r") as f:
for line in f:
features.append([float(elem) for elem in line.split(",")])
specialFeatures = getSpecialFeatures(len(features))
if useSpecial:
for i in range(min(len(specialFeatures), len(features))):
features[i].extend(specialFeatures[i])
features = features[:num]
labels = labels[:num]
for i in range(len(features)):
if len(features[i]) != len(features[0]):
print(i)
try:
assert_all_finite(features[i])
except:
print(i)
cutoff = int(len(features) * 7 / 10)
trainFeatures = features[:cutoff]
testFeatures = features[cutoff:]
trainLabels = labels[:cutoff]
testLabels = labels[cutoff:]
#regr = svm.SVR(C=1)
regr = RandomForestRegressor(n_estimators = 300, n_jobs = 7)
#regr = linear_model.LinearRegression()
regr.fit(trainFeatures, trainLabels)
print("Train Residual sum of squares: %.2f"% np.mean((regr.predict(trainFeatures) - trainLabels) ** 2))
print("Test Residual sum of squares: %.2f"% np.mean((regr.predict(testFeatures) - testLabels) ** 2))
print('Variance score: %.2f' % regr.score(testFeatures, testLabels))
with open("C:/MissingWord/corrScoring/"+name+".regr", "wb") as f:
pickle.dump(regr, f)
def _check_params(self, n_features):
if not 0 < self.l1_ratio <= 1:
raise ValueError("l1_ratio must be in interval ]0;1], but was %f" % self.l1_ratio)
if self.tol <= 0:
raise ValueError("tolerance must be positive, but was %f" % self.tol)
if self.penalty_factor is None:
penalty_factor = numpy.ones(n_features, dtype=numpy.float64)
else:
pf = column_or_1d(self.penalty_factor, warn=True)
if pf.shape[0] != n_features:
raise ValueError("penalty_factor must be array of length n_features (%d), "
"but got %d" % (n_features, pf.shape[0]))
assert_all_finite(pf)
check_non_negative(pf, "penalty_factor")
penalty_factor = pf * n_features / pf.sum()
assert_all_finite(penalty_factor)
create_path = self.alphas is None
if create_path:
if self.n_alphas <= 0:
raise ValueError("n_alphas must be a positive integer")
alphas = numpy.empty(int(self.n_alphas), dtype=numpy.float64)
else:
alphas = column_or_1d(self.alphas, warn=True)
assert_all_finite(alphas)
check_non_negative(alphas, "alphas")
assert_all_finite(alphas)
if self.max_iter <= 0:
raise ValueError("max_iter must be a positive integer")
return create_path, alphas.astype(numpy.float64), penalty_factor.astype(numpy.float64)
def _check_penalty_factor(self, n_features):
if self.penalty_factor is None:
penalty_factor = numpy.ones(n_features, dtype=numpy.float64)
else:
pf = column_or_1d(self.penalty_factor, warn=True)
if pf.shape[0] != n_features:
raise ValueError(
"penalty_factor must be array of length n_features (%d), "
"but got %d" % (n_features, pf.shape[0]))
assert_all_finite(pf)
check_non_negative(pf, "penalty_factor")
penalty_factor = pf * n_features / pf.sum()
assert_all_finite(penalty_factor)
return penalty_factor
def fit(self, X, X_error=None):
"""Implements the standard fitting function for a DL8.5 classifier.
Parameters
----------
X : array-like, shape (n_samples, n_features)
The training input samples. If X_error is provided, it represents explanation input
X_error : array-like, shape (n_samples, n_features_1)
The training input used to calculate error. If it is not provided X is used to calculate error
Returns
-------
self : object
Returns self.
"""
# Check that X_error has correct shape and raise ValueError if not
if X_error is not None:
assert_all_finite(X_error)
X_error = check_array(X_error, dtype='int32')
if self.error_function is None:
if X_error is None:
self.error_function = lambda tids: self.default_error(tids, X)
else:
if X_error.shape[0] == X.shape[0]:
self.error_function = lambda tids: self.default_error(
tids, X_error)
else:
raise ValueError(
"X_error does not have the same number of rows as X")
if self.leaf_value_function is None:
if X_error is None:
self.leaf_value_function = lambda tids: self.default_leaf_value(
tids, X)
else:
if X_error.shape[0] == X.shape[0]:
self.leaf_value_function = lambda tids: self.default_leaf_value(
tids, X_error)
else:
raise ValueError(
"X_error does not have the same number of rows as X")
# call fit method of the predictor
DL85Predictor.fit(self, X)
# print(self.tree_)
# Return the classifier
return self
def _scrub(self, X, y, sample_weight, **kwargs):
'''
Sanitize input data.
'''
# Check for sparseness
if sparse.issparse(y):
raise TypeError(
'A sparse matrix was passed, but dense data '
'is required. Use y.toarray() to convert to dense.')
if sparse.issparse(sample_weight):
raise TypeError(
'A sparse matrix was passed, but dense data '
'is required. Use sample_weight.toarray() to convert to dense.'
)
# Check whether X is the output of patsy.dmatrices
if y is None and isinstance(X, tuple):
y, X = X
# Handle X separately
X = self._scrub_x(X, **kwargs)
# Convert y to internally used data type
y = np.asarray(y, dtype=np.float64)
assert_all_finite(y)
y = y.reshape(y.shape[0])
# Deal with sample_weight
if sample_weight is None:
sample_weight = np.ones(y.shape[0], dtype=y.dtype)
else:
sample_weight = np.asarray(sample_weight)
assert_all_finite(sample_weight)
sample_weight = sample_weight.reshape(sample_weight.shape[0])
# Make sure dimensions match
if y.shape[0] != X.shape[0]:
raise ValueError('X and y do not have compatible dimensions.')
if y.shape != sample_weight.shape:
raise ValueError(
'y and sample_weight do not have compatible dimensions.')
# Make sure everything is finite
assert_all_finite(X)
assert_all_finite(y)
assert_all_finite(sample_weight)
return X, y, sample_weight
def _validate_inputs(self, X, y):
X, y = check_X_y(X, y, accept_sparse=False)
assert_all_finite(X, y)
if np.any(np.iscomplex(X)) or np.any(np.iscomplex(y)):
raise ValueError("Complex data not supported")
if np.issubdtype(X.dtype, np.object_) or np.issubdtype(
y.dtype, np.object_):
try:
X = X.astype(float)
y = y.astype(int)
except TypeError:
raise TypeError("argument must be a string.* number")
return (X, y)
def predict(self, X):
assert_all_finite(X)
check_is_fitted(self, 'is_fitted_')
X = check_array(X, accept_sparse=True)
n_iteration = len(self.clf) #ensemble the number of choosen classifier
self.pred1 = np.zeros((X.shape[0], n_iteration))
self.ensemble_pred1 = np.zeros((X.shape[0], ))
for i in range(n_iteration):
pred1 = self.clf[i].predict(X)
self.pred1[:, i] = pred1
self.ensemble_pred1 = (self.pred1 *
self.alpha[:, :n_iteration]).sum(axis=1)
result = sgn(self.ensemble_pred1)
return np.where(result == -1, 0, result)
def _scrub(self, X, y, sample_weight, **kwargs):
'''
Sanitize input data.
'''
# Check for sparseness
if sparse.issparse(y):
raise TypeError('A sparse matrix was passed, but dense data '
'is required. Use y.toarray() to convert to dense.')
if sparse.issparse(sample_weight):
raise TypeError('A sparse matrix was passed, but dense data '
'is required. Use sample_weight.toarray()'
'to convert to dense.')
# Check whether X is the output of patsy.dmatrices
if y is None and isinstance(X, tuple):
y, X = X
# Handle X separately
X = self._scrub_x(X, **kwargs)
# Convert y to internally used data type
y = np.asarray(y, dtype=np.float64)
assert_all_finite(y)
y = y.reshape(y.shape[0])
# Deal with sample_weight
if sample_weight is None:
sample_weight = np.ones(y.shape[0], dtype=y.dtype)
else:
sample_weight = np.asarray(sample_weight)
assert_all_finite(sample_weight)
sample_weight = sample_weight.reshape(sample_weight.shape[0])
# Make sure dimensions match
if y.shape[0] != X.shape[0]:
raise ValueError('X and y do not have compatible dimensions.')
if y.shape != sample_weight.shape:
raise ValueError(
'y and sample_weight do not have compatible dimensions.')
# Make sure everything is finite
assert_all_finite(X)
assert_all_finite(y)
assert_all_finite(sample_weight)
return X, y, sample_weight
def predict_proba(self, X):
proba = []
X_subs = self._get_subdata(X)
for i in range(self.n_classes_):
e = self.estimators_[i]
X_i = X_subs[i]
pred = e.predict(X_i).reshape(-1, 1)
proba.append(pred)
proba = np.hstack(proba)
normalizer = proba.sum(axis=1)[:, np.newaxis]
normalizer[normalizer == 0.0] = 1.0
proba /= normalizer
assert_all_finite(proba)
return proba
def _base_estimator_predict(self, e, X):
"""Predict label values with the specified estimator on predictor(s) X.
Parameters
----------
e : int
The estimator object.
X : np.ndarray, shape=(n, m)
The feature data for which to compute the predicted outputs.
Returns
-------
pred : np.ndarray, shape=(len(X), 1)
The mean of the label probabilities predicted by the specified
estimator for each fold for each instance X.
"""
# Generate array for the base-level testing set, which is n x n_folds.
pred = e.predict(X)
assert_all_finite(pred)
return pred
def _scrub_x(self, X, **kwargs):
'''
Sanitize input predictors and extract column names if appropriate.
'''
# Check for sparseness
if sparse.issparse(X):
raise TypeError('A sparse matrix was passed, but dense data '
'is required. Use X.toarray() to convert to dense.')
# Convert to internally used data type
X = np.asarray(X, dtype=np.float64, order='F')
assert_all_finite(X)
if X.ndim == 1:
X = X[:, np.newaxis]
# Ensure correct number of columns
if hasattr(self, 'basis_') and self.basis_ is not None:
if X.shape[1] != self.basis_.num_variables:
raise ValueError('Wrong number of columns in X')
return X
def _base_estimator_predict(self, e, X):
"""Predict label values with the specified estimator on predictor(s) X.
Parameters
----------
e : int
The estimator object.
X : np.ndarray, shape=(n, m)
The feature data for which to compute the predicted outputs.
Returns
-------
pred : np.ndarray, shape=(len(X), 1)
The mean of the label probabilities predicted by the specified
estimator for each fold for each instance X.
"""
# Generate array for the base-level testing set, which is n x n_folds.
pred = e.predict(X)
assert_all_finite(pred)
return pred
def _scrub_x(self, X, **kwargs):
'''
Sanitize input predictors and extract column names if appropriate.
'''
# Check for sparseness
if sparse.issparse(X):
raise TypeError(
'A sparse matrix was passed, but dense data '
'is required. Use X.toarray() to convert to dense.')
# Convert to internally used data type
X = np.asarray(X, dtype=np.float64)
assert_all_finite(X)
if len(X.shape) == 1:
X = X.reshape((X.shape[0], 1))
# Ensure correct number of columns
if hasattr(self, 'basis_') and self.basis_ is not None:
if X.shape[1] != self.basis_.num_variables:
raise ValueError('Wrong number of columns in X')
return X
def _validate_inputs(self, X):
# Things we don't want to allow until we've tested them:
# - Sparse inputs
# - Multiclass outputs (e.g., more than 2 classes in `y`)
# - Non-finite inputs
# - Complex inputs
if isinstance(X, pd.DataFrame):
X = X.to_numpy()
X = check_array(X, accept_sparse=False, allow_nd=False)
assert_all_finite(X)
if np.any(np.iscomplex(X)):
raise ValueError("Complex data not supported")
if np.issubdtype(X.dtype, np.object_):
try:
X = X.astype(float)
except (TypeError, ValueError):
raise ValueError("argument must be a string.* number")
return (X)
def fit(self, X, y):
rs = check_random_state(self.random_state)
ds = get_dataset(X)
n_samples = ds.get_n_samples()
n_features = ds.get_n_features()
self.outputs_2d_ = len(y.shape) == 2
if self.outputs_2d_:
Y = y
else:
Y = y.reshape(-1, 1)
Y = np.asfortranarray(Y)
n_vectors = Y.shape[1]
self.coef_ = np.zeros((n_vectors, n_features), dtype=np.float64)
self.intercept_ = np.zeros(n_vectors, dtype=np.float64)
loss = self._get_loss()
penalty = self._get_penalty()
for k in xrange(n_vectors):
_binary_sgd(self,
self.coef_, self.intercept_, k,
ds, Y[:, k], loss, penalty, self.alpha,
self._get_learning_rate(),
self.eta0, self.power_t,
self.fit_intercept,
self.intercept_decay,
int(self.max_iter * n_samples), self.shuffle, rs,
self.callback, self.n_calls, self.verbose)
try:
assert_all_finite(self.coef_)
except ValueError:
warnings.warn("coef_ contains infinite values")
return self
def _scrub_x(self, X, missing, **kwargs):
'''
Sanitize input predictors and extract column names if appropriate.
'''
# Check for sparseness
if sparse.issparse(X):
raise TypeError(
'A sparse matrix was passed, but dense data '
'is required. Use X.toarray() to convert to dense.')
X = np.asarray(X, dtype=np.float64, order='F')
# Figure out missingness
if missing is None:
# Infer missingness
missing = np.isnan(X)
# Convert to internally used data type
missing = np.asarray(missing, dtype=BOOL, order='F')
assert_all_finite(missing)
if missing.ndim == 1:
missing = missing[:, np.newaxis]
if not self.allow_missing:
try:
assert_all_finite(X)
except ValueError:
raise ValueError(
"Input contains NaN, infinity or a value that's too large. Did you mean to set allow_missing=True?"
)
if X.ndim == 1:
X = X[:, np.newaxis]
# Ensure correct number of columns
if hasattr(self, 'basis_') and self.basis_ is not None:
if X.shape[1] != self.basis_.num_variables:
raise ValueError('Wrong number of columns in X')
return X, missing
def test_make_biclusters():
X, rows, cols = make_biclusters(shape=(100, 100), n_clusters=4, shuffle=True, random_state=0)
assert_equal(X.shape, (100, 100), "X shape mismatch")
assert_equal(rows.shape, (4, 100), "rows shape mismatch")
assert_equal(cols.shape, (4, 100), "columns shape mismatch")
assert_all_finite(X)
assert_all_finite(rows)
assert_all_finite(cols)
X2, _, _ = make_biclusters(shape=(100, 100), n_clusters=4, shuffle=True, random_state=0)
assert_array_equal(X, X2)
def test_make_checkerboard():
X, rows, cols = make_checkerboard(shape=(100, 100), n_clusters=(20, 5), shuffle=True, random_state=0)
assert_equal(X.shape, (100, 100), "X shape mismatch")
assert_equal(rows.shape, (100, 100), "rows shape mismatch")
assert_equal(cols.shape, (100, 100), "columns shape mismatch")
X, rows, cols = make_checkerboard(shape=(100, 100), n_clusters=2, shuffle=True, random_state=0)
assert_all_finite(X)
assert_all_finite(rows)
assert_all_finite(cols)
X1, _, _ = make_checkerboard(shape=(100, 100), n_clusters=2, shuffle=True, random_state=0)
X2, _, _ = make_checkerboard(shape=(100, 100), n_clusters=2, shuffle=True, random_state=0)
assert_array_equal(X1, X2)
def fit(self, X, y):
"""Fit model according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : classifier
Returns self.
"""
rs = check_random_state(self.random_state)
reencode = self.multiclass
y, n_classes, n_vectors = self._set_label_transformers(y, reencode)
self.train_x = get_dataset(X)
n_samples = self.train_x.get_n_samples()
n_features = self.train_x.get_n_features()
#self.coef_ = np.zeros((n_vectors, n_features), dtype=np.float64)
self.upd_ = np.zeros(int(self.max_iter * n_samples)+1, dtype=np.float64)
self.seq_ = np.zeros(int(self.max_iter * n_samples)+1, dtype=np.int32)
self.intercept_ = np.zeros(n_vectors, dtype=np.float64)
loss = self._get_loss()
penalty = self._get_penalty()
if n_vectors == 1 or not self.multiclass:
Y = np.asfortranarray(self.label_binarizer_.fit_transform(y),
dtype=np.float64)
for i in xrange(n_vectors):
(self.upd_, self.tr_err) = _karma_sgd(self,
#self.coef_,
self.upd_, self.seq_,
self.intercept_, i,
self.train_x, Y[:, i], loss, penalty,
self.alpha,
self._get_learning_rate(),
self.eta0, self.power_t,
self.fit_intercept,
self.intercept_decay,
int(self.max_iter * n_samples), self.shuffle, rs,
self.callback, self.n_calls, self.gamma, self.verbose)
# elif self.multiclass:
# _multiclass_sgd(self, self.coef_, self.intercept_,
# ds, y.astype(np.int32), loss, penalty,
# self.alpha, self._get_learning_rate(),
# self.eta0, self.power_t, self.fit_intercept,
# self.intercept_decay,
# int(self.max_iter * n_samples),
# self.shuffle, rs, self.callback, self.n_calls,
# self.verbose)
else:
raise ValueError("Wrong value for multiclass.")
try:
assert_all_finite(self.upd_)
assert_all_finite(self.seq_)
except ValueError:
warnings.warn("coef_ contains infinite values")
return self
def fit(self, X, X_test, y, y_test):
"""Fit model according to X and y.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : classifier
Returns self.
"""
rs = check_random_state(self.random_state)
reencode = self.multiclass
y, _, n_vectors = self._set_label_transformers(y, reencode)
y_test, _, n_vectors_test = self._set_label_transformers(y_test, reencode)
#assert n_vectors==n_vectors_test
ds = get_dataset(X)
ds_test = get_dataset(X_test)
n_samples = ds.get_n_samples()
n_features = ds.get_n_features()
self.coef_ = np.zeros((n_vectors, n_features), dtype=np.float64)
self.intercept_ = np.zeros(n_vectors, dtype=np.float64)
loss = self._get_loss()
penalty = self._get_penalty()
if n_vectors == 1 or not self.multiclass:
Y = np.asfortranarray(self.label_binarizer_.fit_transform(y),
dtype=np.float64)
Y_test = np.asfortranarray(self.label_binarizer_.fit_transform(y_test),
dtype=np.float64)
for i in xrange(n_vectors):
_binary_sgd_test(self,
self.coef_, self.intercept_, i,
ds, Y[:, i], ds_test, Y_test[:, i], loss, penalty,
self.alpha,
self._get_learning_rate(),
self.eta0, self.power_t,
self.fit_intercept,
self.intercept_decay,
int(self.max_iter * n_samples), self.shuffle, rs,
self.callback, self.n_calls, self.verbose, self.black_out, (self.disp_freq * n_samples), (self.test_freq * n_samples))
elif self.multiclass:
_multiclass_sgd(self, self.coef_, self.intercept_,
ds, y.astype(np.int32), loss, penalty,
self.alpha, self._get_learning_rate(),
self.eta0, self.power_t, self.fit_intercept,
self.intercept_decay,
int(self.max_iter * n_samples),
self.shuffle, rs, self.callback, self.n_calls,
self.verbose)
else:
raise ValueError("Wrong value for multiclass.")
try:
assert_all_finite(self.coef_)
except ValueError:
warnings.warn("coef_ contains infinite values")
return self
def _scrub(self, X, y, sample_weight, output_weight, missing, **kwargs):
'''
Sanitize input data.
'''
# Check for sparseness
if sparse.issparse(y):
raise TypeError('A sparse matrix was passed, but dense data '
'is required. Use y.toarray() to convert to dense.')
if sparse.issparse(sample_weight):
raise TypeError('A sparse matrix was passed, but dense data '
'is required. Use sample_weight.toarray()'
'to convert to dense.')
if sparse.issparse(output_weight):
raise TypeError('A sparse matrix was passed, but dense data '
'is required. Use output_weight.toarray()'
'to convert to dense.')
# Check whether X is the output of patsy.dmatrices
if y is None and isinstance(X, tuple):
y, X = X
# Handle X separately
X, missing = self._scrub_x(X, missing, **kwargs)
# Convert y to internally used data type
y = np.asarray(y, dtype=np.float64)
assert_all_finite(y)
if len(y.shape) == 1:
y = y[:, np.newaxis]
# Deal with sample_weight
if sample_weight is None:
sample_weight = np.ones(y.shape[0], dtype=y.dtype)
else:
sample_weight = np.asarray(sample_weight)
assert_all_finite(sample_weight)
# Deal with output_weight
if output_weight is None:
output_weight = np.ones(y.shape[1], dtype=y.dtype)
else:
output_weight = np.asarray(output_weight)
assert_all_finite(output_weight)
# Make sure dimensions match
if y.shape[0] != X.shape[0]:
raise ValueError('X and y do not have compatible dimensions.')
if y.shape[0] != sample_weight.shape[0]:
raise ValueError(
'y and sample_weight do not have compatible dimensions.')
if y.shape[1] != output_weight.shape[0]:
raise ValueError(
'y and output_weight do not have compatible dimensions.')
# Make sure everything is finite (except X, which is allowed to have
# missing values)
assert_all_finite(missing)
assert_all_finite(y)
assert_all_finite(sample_weight)
assert_all_finite(output_weight)
# Make sure everything is consistent
check_X_y(X, y, accept_sparse=None, multi_output=True,
force_all_finite=False)
return X, y, sample_weight, output_weight, missing
def _base_estimator_predict_proba(self, e, X):
pred = e.predict_proba(X)
assert_all_finite(pred)
return pred
__author__ = 'SEOKHO' from sklearn.utils.validation import assert_all_finite import numpy as np print(assert_all_finite(np.array([1.5465978588774336, 13.173744467937684, 0.7164582594283925, 6.073044534100405, 0.563888990932914, 9.253016646256619, 1.5479898935732566, 13.172805509656142, 1.76135884564872, 15.4882753202587, 0.6621080655920463, 7.368970402194793, 0.5638305796422928, 9.249753374333018, 0.6931471805599453, 3.4011973816621555, 1.7616927591930054, 15.488775300844194, 0.5637344396624081, 9.249657234353133, 1.791759469228055, 1.791759469228055, 4.240504214996096, 9.587611745713565, 0.8472978603872037, 4.584967478670572, 1.78673244403277, 15.47979284224048, 1.7552292288982276, 15.488951473171578, 1.5461643256320923, 13.173248488496412, 1.7612086097539006, 15.48839602164465, 1.6084169832999933, 7.579678823090456, 1.5475324485137967, 13.172303356473655, 1.761260622260961, 15.488375937043429, 6.163314804034641, 3.258096538021482])))