def fit(self, X, y):
"""Fit the model using X, y as training data.
Parameters
----------
X : array-like, shape = [n_samples, n_features]
Training data.
y : array-like, shape = [n_samples]
Target values. Will be cast to X's dtype if necessary
Returns
-------
self : object
Returns an instance of self.
"""
X, y = check_X_y(X,
y, ['csr', 'csc'],
y_numeric=True,
ensure_min_samples=2,
estimator=self)
X = as_float_array(X, copy=False)
n_samples, n_features = X.shape
X, y, X_offset, y_offset, X_scale = \
self._preprocess_data(X, y, self.fit_intercept, self.normalize)
estimator_func, params = self._make_estimator_and_params(X, y)
memory = self.memory
if memory is None:
memory = Memory(cachedir=None, verbose=0)
elif isinstance(memory, six.string_types):
memory = Memory(cachedir=memory, verbose=0)
elif not isinstance(memory, Memory):
raise ValueError("'memory' should either be a string or"
" a sklearn.utils.Memory"
" instance, got 'memory={!r}' instead.".format(
type(memory)))
scores_ = memory.cache(_resample_model,
ignore=['verbose', 'n_jobs', 'pre_dispatch'
])(estimator_func,
X,
y,
scaling=self.scaling,
n_resampling=self.n_resampling,
n_jobs=self.n_jobs,
verbose=self.verbose,
pre_dispatch=self.pre_dispatch,
random_state=self.random_state,
sample_fraction=self.sample_fraction,
**params)
if scores_.ndim == 1:
scores_ = scores_[:, np.newaxis]
self.all_scores_ = scores_
self.scores_ = np.max(self.all_scores_, axis=1)
return self
# Ward agglomeration followed by BayesianRidge
connectivity = grid_to_graph(n_x=size, n_y=size)
ward = FeatureAgglomeration(n_clusters=10,
connectivity=connectivity,
memory=mem)
clf = Pipeline([('ward', ward), ('ridge', ridge)])
# Select the optimal number of parcels with grid search
clf = GridSearchCV(clf, {'ward__n_clusters': [10, 20, 30]}, n_jobs=1, cv=cv)
clf.fit(X, y) # set the best parameters
coef_ = clf.best_estimator_.steps[-1][1].coef_
coef_ = clf.best_estimator_.steps[0][1].inverse_transform(coef_)
coef_agglomeration_ = coef_.reshape(size, size)
# Anova univariate feature selection followed by BayesianRidge
f_regression = mem.cache(feature_selection.f_regression) # caching function
anova = feature_selection.SelectPercentile(f_regression)
clf = Pipeline([('anova', anova), ('ridge', ridge)])
# Select the optimal percentage of features with grid search
clf = GridSearchCV(clf, {'anova__percentile': [5, 10, 20]}, cv=cv)
clf.fit(X, y) # set the best parameters
coef_ = clf.best_estimator_.steps[-1][1].coef_
coef_ = clf.best_estimator_.steps[0][1].inverse_transform(coef_.reshape(1, -1))
coef_selection_ = coef_.reshape(size, size)
# #############################################################################
# Inverse the transformation to plot the results on an image
plt.close('all')
plt.figure(figsize=(7.3, 2.7))
plt.subplot(1, 3, 1)
plt.imshow(coef, interpolation="nearest", cmap=plt.cm.RdBu_r)
def exp(solvers, penalties, single_target, n_samples=30000, max_iter=20,
dataset='rcv1', n_jobs=1, skip_slow=False):
mem = Memory(cachedir=expanduser('~/cache'), verbose=0)
if dataset == 'rcv1':
rcv1 = fetch_rcv1()
lbin = LabelBinarizer()
lbin.fit(rcv1.target_names)
X = rcv1.data
y = rcv1.target
y = lbin.inverse_transform(y)
le = LabelEncoder()
y = le.fit_transform(y)
if single_target:
y_n = y.copy()
y_n[y > 16] = 1
y_n[y <= 16] = 0
y = y_n
elif dataset == 'digits':
digits = load_digits()
X, y = digits.data, digits.target
if single_target:
y_n = y.copy()
y_n[y < 5] = 1
y_n[y >= 5] = 0
y = y_n
elif dataset == 'iris':
iris = load_iris()
X, y = iris.data, iris.target
elif dataset == '20newspaper':
ng = fetch_20newsgroups_vectorized()
X = ng.data
y = ng.target
if single_target:
y_n = y.copy()
y_n[y > 4] = 1
y_n[y <= 16] = 0
y = y_n
X = X[:n_samples]
y = y[:n_samples]
cached_fit = mem.cache(fit_single)
out = Parallel(n_jobs=n_jobs, mmap_mode=None)(
delayed(cached_fit)(solver, X, y,
penalty=penalty, single_target=single_target,
C=1, max_iter=max_iter, skip_slow=skip_slow)
for solver in solvers
for penalty in penalties)
res = []
idx = 0
for solver in solvers:
for penalty in penalties:
if not (skip_slow and solver == 'lightning' and penalty == 'l1'):
lr, times, train_scores, test_scores, accuracies = out[idx]
this_res = dict(solver=solver, penalty=penalty,
single_target=single_target,
times=times, train_scores=train_scores,
test_scores=test_scores,
accuracies=accuracies)
res.append(this_res)
idx += 1
with open('bench_saga.json', 'w+') as f:
json.dump(res, f)
mem = Memory(cachedir=cachedir, verbose=1)
# Ward agglomeration followed by BayesianRidge
connectivity = grid_to_graph(n_x=size, n_y=size)
ward = FeatureAgglomeration(n_clusters=10, connectivity=connectivity,
memory=mem)
clf = Pipeline([('ward', ward), ('ridge', ridge)])
# Select the optimal number of parcels with grid search
clf = GridSearchCV(clf, {'ward__n_clusters': [10, 20, 30]}, n_jobs=1, cv=cv)
clf.fit(X, y) # set the best parameters
coef_ = clf.best_estimator_.steps[-1][1].coef_
coef_ = clf.best_estimator_.steps[0][1].inverse_transform(coef_)
coef_agglomeration_ = coef_.reshape(size, size)
# Anova univariate feature selection followed by BayesianRidge
f_regression = mem.cache(feature_selection.f_regression) # caching function
anova = feature_selection.SelectPercentile(f_regression)
clf = Pipeline([('anova', anova), ('ridge', ridge)])
# Select the optimal percentage of features with grid search
clf = GridSearchCV(clf, {'anova__percentile': [5, 10, 20]}, cv=cv)
clf.fit(X, y) # set the best parameters
coef_ = clf.best_estimator_.steps[-1][1].coef_
coef_ = clf.best_estimator_.steps[0][1].inverse_transform(coef_.reshape(1, -1))
coef_selection_ = coef_.reshape(size, size)
# #############################################################################
# Inverse the transformation to plot the results on an image
plt.close('all')
plt.figure(figsize=(7.3, 2.7))
plt.subplot(1, 3, 1)
plt.imshow(coef, interpolation="nearest", cmap=plt.cm.RdBu_r)
