def test_predict_with_predict_params():
# tests that Pipeline passes predict_params to the final estimator
# when predict is invoked
pipe = Pipeline([('transf', Transf()), ('clf', DummyEstimatorParams())])
pipe.fit(None, None)
pipe.predict(X=None, got_attribute=True)
assert pipe.named_steps['clf'].got_attribute
def test_pipeline_methods_pca_svm():
# Test the various methods of the pipeline (pca + svm).
iris = load_iris()
X = iris.data
y = iris.target
# Test with PCA + SVC
clf = SVC(probability=True, random_state=0)
pca = PCA(svd_solver='full', n_components='mle', whiten=True)
pipe = Pipeline([('pca', pca), ('svc', clf)])
pipe.fit(X, y)
pipe.predict(X)
pipe.predict_proba(X)
pipe.predict_log_proba(X)
pipe.score(X, y)
def test_pipeline_methods_anova():
# Test the various methods of the pipeline (anova).
iris = load_iris()
X = iris.data
y = iris.target
# Test with Anova + LogisticRegression
clf = LogisticRegression()
filter1 = SelectKBest(f_classif, k=2)
pipe = Pipeline([('anova', filter1), ('logistic', clf)])
pipe.fit(X, y)
pipe.predict(X)
pipe.predict_proba(X)
pipe.predict_log_proba(X)
pipe.score(X, y)
def test_pipeline_methods_preprocessing_svm():
# Test the various methods of the pipeline (preprocessing + svm).
iris = load_iris()
X = iris.data
y = iris.target
n_samples = X.shape[0]
n_classes = len(np.unique(y))
scaler = StandardScaler()
pca = PCA(n_components=2, svd_solver='randomized', whiten=True)
clf = SVC(probability=True, random_state=0, decision_function_shape='ovr')
for preprocessing in [scaler, pca]:
pipe = Pipeline([('preprocess', preprocessing), ('svc', clf)])
pipe.fit(X, y)
# check shapes of various prediction functions
predict = pipe.predict(X)
assert predict.shape == (n_samples,)
proba = pipe.predict_proba(X)
assert proba.shape == (n_samples, n_classes)
log_proba = pipe.predict_log_proba(X)
assert log_proba.shape == (n_samples, n_classes)
decision_function = pipe.decision_function(X)
assert decision_function.shape == (n_samples, n_classes)
pipe.score(X, y)
def test_pipeline_fit_params():
# Test that the pipeline can take fit parameters
pipe = Pipeline([('transf', Transf()), ('clf', FitParamT())])
pipe.fit(X=None, y=None, clf__should_succeed=True)
# classifier should return True
assert pipe.predict(None)
# and transformer params should not be changed
assert pipe.named_steps['transf'].a is None
assert pipe.named_steps['transf'].b is None
# invalid parameters should raise an error message
assert_raise_message(
TypeError,
"fit() got an unexpected keyword argument 'bad'",
pipe.fit, None, None, clf__bad=True
)
def test_pipeline_memory():
iris = load_iris()
X = iris.data
y = iris.target
cachedir = mkdtemp()
try:
if LooseVersion(joblib.__version__) < LooseVersion('0.12'):
# Deal with change of API in joblib
memory = joblib.Memory(cachedir=cachedir, verbose=10)
else:
memory = joblib.Memory(location=cachedir, verbose=10)
# Test with Transformer + SVC
clf = SVC(probability=True, random_state=0)
transf = DummyTransf()
pipe = Pipeline([('transf', clone(transf)), ('svc', clf)])
cached_pipe = Pipeline([('transf', transf), ('svc', clf)],
memory=memory)
# Memoize the transformer at the first fit
cached_pipe.fit(X, y)
pipe.fit(X, y)
# Get the time stamp of the transformer in the cached pipeline
ts = cached_pipe.named_steps['transf'].timestamp_
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe.named_steps['transf'].means_)
assert not hasattr(transf, 'means_')
# Check that we are reading the cache while fitting
# a second time
cached_pipe.fit(X, y)
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe.named_steps['transf'].means_)
assert ts == cached_pipe.named_steps['transf'].timestamp_
# Create a new pipeline with cloned estimators
# Check that even changing the name step does not affect the cache hit
clf_2 = SVC(probability=True, random_state=0)
transf_2 = DummyTransf()
cached_pipe_2 = Pipeline([('transf_2', transf_2), ('svc', clf_2)],
memory=memory)
cached_pipe_2.fit(X, y)
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe_2.predict(X))
assert_array_equal(pipe.predict_proba(X),
cached_pipe_2.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe_2.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe_2.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe_2.named_steps['transf_2'].means_)
assert ts == cached_pipe_2.named_steps['transf_2'].timestamp_
finally:
shutil.rmtree(cachedir)
y = true_fun(X) + np.random.randn(n_samples) * 0.1
plt.figure(figsize=(14, 5))
for i in range(len(degrees)):
ax = plt.subplot(1, len(degrees), i + 1)
plt.setp(ax, xticks=(), yticks=())
polynomial_features = PolynomialFeatures(degree=degrees[i],
include_bias=False)
linear_regression = LinearRegression()
pipeline = Pipeline([("polynomial_features", polynomial_features),
("linear_regression", linear_regression)])
pipeline.fit(X[:, np.newaxis], y)
# Evaluate the models using crossvalidation
scores = cross_val_score(pipeline, X[:, np.newaxis], y,
scoring="neg_mean_squared_error", cv=10)
X_test = np.linspace(0, 1, 100)
plt.plot(X_test, pipeline.predict(X_test[:, np.newaxis]), label="Model")
plt.plot(X_test, true_fun(X_test), label="True function")
plt.scatter(X, y, edgecolor='b', s=20, label="Samples")
plt.xlabel("x")
plt.ylabel("y")
plt.xlim((0, 1))
plt.ylim((-2, 2))
plt.legend(loc="best")
plt.title("Degree {}\nMSE = {:.2e}(+/- {:.2e})".format(
degrees[i], -scores.mean(), scores.std()))
plt.show()
vectorizer = TfidfVectorizer(ngram_range=(1, 3),
analyzer='char',
use_idf=False)
# TASK: Build a vectorizer / classifier pipeline using the previous analyzer
# the pipeline instance should stored in a variable named clf
clf = Pipeline([
('vec', vectorizer),
('clf', Perceptron()),
])
# TASK: Fit the pipeline on the training set
clf.fit(docs_train, y_train)
# TASK: Predict the outcome on the testing set in a variable named y_predicted
y_predicted = clf.predict(docs_test)
# Print the classification report
print(
metrics.classification_report(y_test,
y_predicted,
target_names=dataset.target_names))
# Plot the confusion matrix
cm = metrics.confusion_matrix(y_test, y_predicted)
print(cm)
#import matlotlib.pyplot as plt
#plt.matshow(cm, cmap=plt.cm.jet)
#plt.show()
]),
1),
],
# weight components in ColumnTransformer
transformer_weights={
'subject': 0.8,
'body_bow': 0.5,
'body_stats': 1.0,
})),
# Use a SVC classifier on the combined features
('svc', LinearSVC(dual=False)),
],
verbose=True)
# limit the list of categories to make running this example faster.
categories = ['alt.atheism', 'talk.religion.misc']
X_train, y_train = fetch_20newsgroups(random_state=1,
subset='train',
categories=categories,
return_X_y=True)
X_test, y_test = fetch_20newsgroups(random_state=1,
subset='test',
categories=categories,
return_X_y=True)
pipeline.fit(X_train, y_train)
y_pred = pipeline.predict(X_test)
print(classification_report(y_pred, y_test))
# fitting time
rbm.n_components = 100
logistic.C = 6000
# Training RBM-Logistic Pipeline
rbm_features_classifier.fit(X_train, Y_train)
# Training the Logistic regression classifier directly on the pixel
raw_pixel_classifier = clone(logistic)
raw_pixel_classifier.C = 100.
raw_pixel_classifier.fit(X_train, Y_train)
# #############################################################################
# Evaluation
Y_pred = rbm_features_classifier.predict(X_test)
print("Logistic regression using RBM features:\n%s\n" %
(metrics.classification_report(Y_test, Y_pred)))
Y_pred = raw_pixel_classifier.predict(X_test)
print("Logistic regression using raw pixel features:\n%s\n" %
(metrics.classification_report(Y_test, Y_pred)))
# #############################################################################
# Plotting
plt.figure(figsize=(4.2, 4))
for i, comp in enumerate(rbm.components_):
plt.subplot(10, 10, i + 1)
plt.imshow(comp.reshape((8, 8)),
cmap=plt.cm.gray_r,