def test_check_accuracy_on_digits():
# Non regression test to make sure that any further refactoring / optim
# of the NB models do not harm the performance on a slightly non-linearly
# separable dataset
X, y = load_digits(return_X_y=True)
binary_3v8 = np.logical_or(y == 3, y == 8)
X_3v8, y_3v8 = X[binary_3v8], y[binary_3v8]
# Multinomial NB
scores = cross_val_score(MultinomialNB(alpha=10), X, y, cv=10)
assert scores.mean() > 0.86
scores = cross_val_score(MultinomialNB(alpha=10), X_3v8, y_3v8, cv=10)
assert scores.mean() > 0.94
# Bernoulli NB
scores = cross_val_score(BernoulliNB(alpha=10), X > 4, y, cv=10)
assert scores.mean() > 0.83
scores = cross_val_score(BernoulliNB(alpha=10), X_3v8 > 4, y_3v8, cv=10)
assert scores.mean() > 0.92
# Gaussian NB
scores = cross_val_score(GaussianNB(), X, y, cv=10)
assert scores.mean() > 0.77
scores = cross_val_score(GaussianNB(var_smoothing=0.1), X, y, cv=10)
assert scores.mean() > 0.89
scores = cross_val_score(GaussianNB(), X_3v8, y_3v8, cv=10)
assert scores.mean() > 0.86
def test_load_digits():
digits = load_digits()
assert digits.data.shape == (1797, 64)
assert numpy.unique(digits.target).size == 10
# test return_X_y option
check_return_X_y(digits, partial(load_digits))
def test_pca_score_consistency_solvers(svd_solver):
# Check the consistency of score between solvers
X, _ = datasets.load_digits(return_X_y=True)
pca_full = PCA(n_components=30, svd_solver='full', random_state=0)
pca_other = PCA(n_components=30, svd_solver=svd_solver, random_state=0)
pca_full.fit(X)
pca_other.fit(X)
assert_allclose(pca_full.score(X), pca_other.score(X), rtol=5e-6)
def test_pca_sanity_noise_variance(svd_solver):
# Sanity check for the noise_variance_. For more details see
# https://github.com/scikit-learn/scikit-learn/issues/7568
# https://github.com/scikit-learn/scikit-learn/issues/8541
# https://github.com/scikit-learn/scikit-learn/issues/8544
X, _ = datasets.load_digits(return_X_y=True)
pca = PCA(n_components=30, svd_solver=svd_solver, random_state=0)
pca.fit(X)
assert np.all((pca.explained_variance_ - pca.noise_variance_) >= 0)
def test_adaboost_consistent_predict(algorithm):
# check that predict_proba and predict give consistent results
# regression test for:
# https://github.com/scikit-learn/scikit-learn/issues/14084
X_train, X_test, y_train, y_test = train_test_split(
*datasets.load_digits(return_X_y=True), random_state=42)
model = AdaBoostClassifier(algorithm=algorithm, random_state=42)
model.fit(X_train, y_train)
assert_array_equal(np.argmax(model.predict_proba(X_test), axis=1),
model.predict(X_test))
def get_data(N, D, dataset='dense'):
if dataset == 'dense':
np.random.seed(0)
return np.random.random((N, D))
elif dataset == 'digits':
X, _ = datasets.load_digits(return_X_y=True)
i = np.argsort(X[0])[::-1]
X = X[:, i]
return X[:N, :D]
else:
raise ValueError("invalid dataset: %s" % dataset)
def test_unsorted_indices():
# test that the result with sorted and unsorted indices in csr is the same
# we use a subset of digits as iris, blobs or make_classification didn't
# show the problem
X, y = load_digits(return_X_y=True)
X_test = sparse.csr_matrix(X[50:100])
X, y = X[:50], y[:50]
X_sparse = sparse.csr_matrix(X)
coef_dense = svm.SVC(kernel='linear', probability=True,
random_state=0).fit(X, y).coef_
sparse_svc = svm.SVC(kernel='linear', probability=True,
random_state=0).fit(X_sparse, y)
coef_sorted = sparse_svc.coef_
# make sure dense and sparse SVM give the same result
assert_array_almost_equal(coef_dense, coef_sorted.toarray())
# reverse each row's indices
def scramble_indices(X):
new_data = []
new_indices = []
for i in range(1, len(X.indptr)):
row_slice = slice(*X.indptr[i - 1:i + 1])
new_data.extend(X.data[row_slice][::-1])
new_indices.extend(X.indices[row_slice][::-1])
return sparse.csr_matrix((new_data, new_indices, X.indptr),
shape=X.shape)
X_sparse_unsorted = scramble_indices(X_sparse)
X_test_unsorted = scramble_indices(X_test)
assert not X_sparse_unsorted.has_sorted_indices
assert not X_test_unsorted.has_sorted_indices
unsorted_svc = svm.SVC(kernel='linear', probability=True,
random_state=0).fit(X_sparse_unsorted, y)
coef_unsorted = unsorted_svc.coef_
# make sure unsorted indices give same result
assert_array_almost_equal(coef_unsorted.toarray(), coef_sorted.toarray())
assert_array_almost_equal(sparse_svc.predict_proba(X_test_unsorted),
sparse_svc.predict_proba(X_test))
# License: BSD 3 clause
print(__doc__)
# Standard scientific Python imports
import matplotlib.pyplot as plt
import numpy as np
from time import time
# Import datasets, classifiers and performance metrics
from mrex import datasets, svm, pipeline
from mrex.kernel_approximation import (RBFSampler, Nystroem)
from mrex.decomposition import PCA
# The digits dataset
digits = datasets.load_digits(n_class=9)
##################################################################
# Timing and accuracy plots
# --------------------------------------------------
# To apply an classifier on this data, we need to flatten the image, to
# turn the data in a (samples, feature) matrix:
n_samples = len(digits.data)
data = digits.data / 16.
data -= data.mean(axis=0)
# We learn the digits on the first half of the digits
data_train, targets_train = (data[:n_samples // 2],
digits.target[:n_samples // 2])
# Now predict the value of the digit on the second half:
# some parameter combinations will not converge as can be seen on the
# plots so they are ignored here
with warnings.catch_warnings():
warnings.filterwarnings("ignore",
category=ConvergenceWarning,
module="mrex")
mlp.fit(X, y)
mlps.append(mlp)
print("Training set score: %f" % mlp.score(X, y))
print("Training set loss: %f" % mlp.loss_)
for mlp, label, args in zip(mlps, labels, plot_args):
ax.plot(mlp.loss_curve_, label=label, **args)
fig, axes = plt.subplots(2, 2, figsize=(15, 10))
# load / generate some toy datasets
iris = datasets.load_iris()
X_digits, y_digits = datasets.load_digits(return_X_y=True)
data_sets = [(iris.data, iris.target), (X_digits, y_digits),
datasets.make_circles(noise=0.2, factor=0.5, random_state=1),
datasets.make_moons(noise=0.3, random_state=0)]
for ax, data, name in zip(axes.ravel(), data_sets,
['iris', 'digits', 'circles', 'moons']):
plot_on_dataset(*data, ax=ax, name=name)
fig.legend(ax.get_lines(), labels, ncol=3, loc="upper center")
plt.show()
# larger number of dimensions ``n_components``.
#
# - for the 20 newsgroups dataset some 500 documents with 100k
# features in total are projected using a sparse random matrix to smaller
# euclidean spaces with various values for the target number of dimensions
# ``n_components``.
#
# The default dataset is the digits dataset. To run the example on the twenty
# newsgroups dataset, pass the --twenty-newsgroups command line argument to
# this script.
if '--twenty-newsgroups' in sys.argv:
# Need an internet connection hence not enabled by default
data = fetch_20newsgroups_vectorized().data[:500]
else:
data = load_digits().data[:500]
##########################################################
# For each value of ``n_components``, we plot:
#
# - 2D distribution of sample pairs with pairwise distances in original
# and projected spaces as x and y axis respectively.
#
# - 1D histogram of the ratio of those distances (projected / original).
n_samples, n_features = data.shape
print("Embedding %d samples with dim %d using various random projections" %
(n_samples, n_features))
n_components_range = np.array([300, 1000, 10000])
dists = euclidean_distances(data, squared=True).ravel()
def exp(solvers,
penalty,
single_target,
n_samples=30000,
max_iter=20,
dataset='rcv1',
n_jobs=1,
skip_slow=False):
dtypes_mapping = {
"float64": np.float64,
"float32": np.float32,
}
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':
X, y = load_digits(return_X_y=True)
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]
out = Parallel(n_jobs=n_jobs, mmap_mode=None)(
delayed(fit_single)(solver,
X,
y,
penalty=penalty,
single_target=single_target,
dtype=dtype,
C=1,
max_iter=max_iter,
skip_slow=skip_slow) for solver in solvers
for dtype in dtypes_mapping.values())
res = []
idx = 0
for dtype_name in dtypes_mapping.keys():
for solver in solvers:
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,
dtype=dtype_name,
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)
"""
print(__doc__)
from time import time
import numpy as np
import matplotlib.pyplot as plt
from mrex import metrics
from mrex.cluster import KMeans
from mrex.datasets import load_digits
from mrex.decomposition import PCA
from mrex.preprocessing import scale
np.random.seed(42)
X_digits, y_digits = load_digits(return_X_y=True)
data = scale(X_digits)
n_samples, n_features = data.shape
n_digits = len(np.unique(y_digits))
labels = y_digits
sample_size = 300
print("n_digits: %d, \t n_samples %d, \t n_features %d" %
(n_digits, n_samples, n_features))
print(82 * '_')
print('init\t\ttime\tinertia\thomo\tcompl\tv-meas\tARI\tAMI\tsilhouette')
a digit classification task.
.. note::
See also :ref:`sphx_glr_auto_examples_feature_selection_plot_rfe_with_cross_validation.py`
"""
print(__doc__)
from mrex.svm import SVC
from mrex.datasets import load_digits
from mrex.feature_selection import RFE
import matplotlib.pyplot as plt
# Load the digits dataset
digits = load_digits()
X = digits.images.reshape((len(digits.images), -1))
y = digits.target
# Create the RFE object and rank each pixel
svc = SVC(kernel="linear", C=1)
rfe = RFE(estimator=svc, n_features_to_select=1, step=1)
rfe.fit(X, y)
ranking = rfe.ranking_.reshape(digits.images[0].shape)
# Plot pixel ranking
plt.matshow(ranking, cmap=plt.cm.Blues)
plt.colorbar()
plt.title("Ranking of pixels with RFE")
plt.show()
# Authors: Vighnesh Birodkar <*****@*****.**>
# Raghav RV <*****@*****.**>
# License: BSD 3 clause
import time
import numpy as np
import matplotlib.pyplot as plt
from mrex import ensemble
from mrex import datasets
from mrex.model_selection import train_test_split
print(__doc__)
data_list = [datasets.load_iris(), datasets.load_digits()]
data_list = [(d.data, d.target) for d in data_list]
data_list += [datasets.make_hastie_10_2()]
names = ['Iris Data', 'Digits Data', 'Hastie Data']
n_gb = []
score_gb = []
time_gb = []
n_gbes = []
score_gbes = []
time_gbes = []
n_estimators = 500
for X, y in data_list:
X_train, X_test, y_train, y_test = train_test_split(X,
from mrex.datasets import load_digits, load_boston, load_iris
from mrex.datasets import make_regression, make_multilabel_classification
from mrex.exceptions import ConvergenceWarning
from io import StringIO
from mrex.metrics import roc_auc_score
from mrex.neural_network import MLPClassifier
from mrex.neural_network import MLPRegressor
from mrex.preprocessing import LabelBinarizer
from mrex.preprocessing import StandardScaler, MinMaxScaler
from scipy.sparse import csr_matrix
from mrex.utils.testing import assert_raises, ignore_warnings
from mrex.utils.testing import assert_raise_message
ACTIVATION_TYPES = ["identity", "logistic", "tanh", "relu"]
X_digits, y_digits = load_digits(n_class=3, return_X_y=True)
X_digits_multi = MinMaxScaler().fit_transform(X_digits[:200])
y_digits_multi = y_digits[:200]
X_digits, y_digits = load_digits(n_class=2, return_X_y=True)
X_digits_binary = MinMaxScaler().fit_transform(X_digits[:200])
y_digits_binary = y_digits[:200]
classification_datasets = [(X_digits_multi, y_digits_multi),
(X_digits_binary, y_digits_binary)]
boston = load_boston()
Xboston = StandardScaler().fit_transform(boston.data)[:200]
def test_load_digits_n_class_lt_10():
digits = load_digits(9)
assert digits.data.shape == (1617, 64)
assert numpy.unique(digits.target).size == 9
simultaneously using grid search, but pick only the ones deemed most important.
"""
print(__doc__)
import numpy as np
from time import time
from scipy.stats import randint as sp_randint
from mrex.model_selection import GridSearchCV
from mrex.model_selection import RandomizedSearchCV
from mrex.datasets import load_digits
from mrex.ensemble import RandomForestClassifier
# get some data
X, y = load_digits(return_X_y=True)
# build a classifier
clf = RandomForestClassifier(n_estimators=20)
# Utility function to report best scores
def report(results, n_top=3):
for i in range(1, n_top + 1):
candidates = np.flatnonzero(results['rank_test_score'] == i)
for candidate in candidates:
print("Model with rank: {0}".format(i))
print("Mean validation score: {0:.3f} (std: {1:.3f})".format(
results['mean_test_score'][candidate],
results['std_test_score'][candidate]))
print("Parameters: {0}".format(results['params'][candidate]))
=============================================
Cross-validation on Digits Dataset Exercise
=============================================
A tutorial exercise using Cross-validation with an SVM on the Digits dataset.
This exercise is used in the :ref:`cv_generators_tut` part of the
:ref:`model_selection_tut` section of the :ref:`stat_learn_tut_index`.
"""
print(__doc__)
import numpy as np
from mrex.model_selection import cross_val_score
from mrex import datasets, svm
X, y = datasets.load_digits(return_X_y=True)
svc = svm.SVC(kernel='linear')
C_s = np.logspace(-10, 0, 10)
scores = list()
scores_std = list()
for C in C_s:
svc.C = C
this_scores = cross_val_score(svc, X, y, n_jobs=1)
scores.append(np.mean(this_scores))
scores_std.append(np.std(this_scores))
# Do the plotting
import matplotlib.pyplot as plt
plt.figure()
print(__doc__) # Authors: Clay Woolam <*****@*****.**> # License: BSD import numpy as np import matplotlib.pyplot as plt from scipy import stats from mrex import datasets from mrex.semi_supervised import label_propagation from mrex.metrics import confusion_matrix, classification_report digits = datasets.load_digits() rng = np.random.RandomState(2) indices = np.arange(len(digits.data)) rng.shuffle(indices) X = digits.data[indices[:340]] y = digits.target[indices[:340]] images = digits.images[indices[:340]] n_total_samples = len(y) n_labeled_points = 40 indices = np.arange(n_total_samples) unlabeled_set = indices[n_labeled_points:]
import sys
import re
import numpy as np
from scipy.sparse import csc_matrix, csr_matrix, lil_matrix
from mrex.utils.testing import (assert_almost_equal, assert_array_equal)
from mrex.datasets import load_digits
from io import StringIO
from mrex.neural_network import BernoulliRBM
from mrex.utils.validation import assert_all_finite
Xdigits, _ = load_digits(return_X_y=True)
Xdigits -= Xdigits.min()
Xdigits /= Xdigits.max()
def test_fit():
X = Xdigits.copy()
rbm = BernoulliRBM(n_components=64,
learning_rate=0.1,
batch_size=10,
n_iter=7,
random_state=9)
rbm.fit(X)
assert_almost_equal(rbm.score_samples(X).mean(), -21., decimal=0)
# in-place tricks shouldn't have modified X
assert_array_equal(X, Xdigits)
