def solution(filename):
# Считывание данных
data = pd.read_csv(filename + '.csv')
# data['class'] = pd.factorize(data['class'])[0]
y = data['class'].values
x = data.drop(['class'], axis=1).values
# Разбиение данных на тестовую и тренировочную выборки
# x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.15)
# Алгоритм бустинга
if filename == 'chips':
learning_rate = 0.15
else:
learning_rate = 1.15
model = AdaBoostClassifier(learning_rate=learning_rate, n_estimators=150)
model.fit(x, y)
# Построение графика для каждого шага алгоритма
plt.figure()
plt.scatter(x[:, 0], x[:, 1], c=colors(y), cmap=plt.cm.Paired)
ax = plt.gca()
xlim = ax.get_xlim()
ylim = ax.get_ylim()
xx = np.linspace(xlim[0], xlim[1], 30)
yy = np.linspace(ylim[0], ylim[1], 30)
YY, XX = np.meshgrid(yy, xx)
xy = np.vstack([XX.ravel(), YY.ravel()]).T
y_pred = model.staged_predict(x)
decision_funcs = model.staged_decision_function(xy)
i = 1
for _, func in zip(y_pred, decision_funcs):
plt.clf()
plt.scatter(x[:, 0], x[:, 1], c=colors(y), cmap=plt.cm.Paired)
f = func.reshape(XX.shape)
ax = plt.gca()
ax.contour(XX,
YY,
f,
colors='k',
levels=[-1, 0, 1],
alpha=0.5,
linestyles=['--', '-', '--'])
plt.legend([f'Step number {i}'])
plt.savefig(filename + '/' + str(i) + '.png')
i += 1
def test_sparse_classification():
# Check classification with sparse input.
class CustomSVC(SVC):
"""SVC variant that records the nature of the training set."""
def fit(self, X, y, sample_weight=None):
"""Modification on fit caries data type for later verification."""
super(CustomSVC, self).fit(X, y, sample_weight=sample_weight)
self.data_type_ = type(X)
return self
X, y = datasets.make_multilabel_classification(n_classes=1, n_samples=15,
n_features=5,
random_state=42)
# Flatten y to a 1d array
y = np.ravel(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
for sparse_format in [csc_matrix, csr_matrix, lil_matrix, coo_matrix,
dok_matrix]:
X_train_sparse = sparse_format(X_train)
X_test_sparse = sparse_format(X_test)
# Trained on sparse format
sparse_classifier = AdaBoostClassifier(
base_estimator=CustomSVC(probability=True),
random_state=1,
algorithm="SAMME"
).fit(X_train_sparse, y_train)
# Trained on dense format
dense_classifier = AdaBoostClassifier(
base_estimator=CustomSVC(probability=True),
random_state=1,
algorithm="SAMME"
).fit(X_train, y_train)
# predict
sparse_results = sparse_classifier.predict(X_test_sparse)
dense_results = dense_classifier.predict(X_test)
assert_array_equal(sparse_results, dense_results)
# decision_function
sparse_results = sparse_classifier.decision_function(X_test_sparse)
dense_results = dense_classifier.decision_function(X_test)
assert_array_equal(sparse_results, dense_results)
# predict_log_proba
sparse_results = sparse_classifier.predict_log_proba(X_test_sparse)
dense_results = dense_classifier.predict_log_proba(X_test)
assert_array_equal(sparse_results, dense_results)
# predict_proba
sparse_results = sparse_classifier.predict_proba(X_test_sparse)
dense_results = dense_classifier.predict_proba(X_test)
assert_array_equal(sparse_results, dense_results)
# score
sparse_results = sparse_classifier.score(X_test_sparse, y_test)
dense_results = dense_classifier.score(X_test, y_test)
assert_array_equal(sparse_results, dense_results)
# staged_decision_function
sparse_results = sparse_classifier.staged_decision_function(
X_test_sparse)
dense_results = dense_classifier.staged_decision_function(X_test)
for sprase_res, dense_res in zip(sparse_results, dense_results):
assert_array_equal(sprase_res, dense_res)
# staged_predict
sparse_results = sparse_classifier.staged_predict(X_test_sparse)
dense_results = dense_classifier.staged_predict(X_test)
for sprase_res, dense_res in zip(sparse_results, dense_results):
assert_array_equal(sprase_res, dense_res)
# staged_predict_proba
sparse_results = sparse_classifier.staged_predict_proba(X_test_sparse)
dense_results = dense_classifier.staged_predict_proba(X_test)
for sprase_res, dense_res in zip(sparse_results, dense_results):
assert_array_equal(sprase_res, dense_res)
# staged_score
sparse_results = sparse_classifier.staged_score(X_test_sparse,
y_test)
dense_results = dense_classifier.staged_score(X_test, y_test)
for sprase_res, dense_res in zip(sparse_results, dense_results):
assert_array_equal(sprase_res, dense_res)
# Verify sparsity of data is maintained during training
types = [i.data_type_ for i in sparse_classifier.estimators_]
assert all([(t == csc_matrix or t == csr_matrix)
for t in types])
def test_sparse_classification():
# Check classification with sparse input.
class CustomSVC(SVC):
"""SVC variant that records the nature of the training set."""
def fit(self, X, y, sample_weight=None):
"""Modification on fit caries data type for later verification."""
super(CustomSVC, self).fit(X, y, sample_weight=sample_weight)
self.data_type_ = type(X)
return self
X, y = datasets.make_multilabel_classification(n_classes=1,
n_samples=15,
n_features=5,
random_state=42)
# Flatten y to a 1d array
y = np.ravel(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
for sparse_format in [
csc_matrix, csr_matrix, lil_matrix, coo_matrix, dok_matrix
]:
X_train_sparse = sparse_format(X_train)
X_test_sparse = sparse_format(X_test)
# Trained on sparse format
sparse_classifier = AdaBoostClassifier(
base_estimator=CustomSVC(probability=True),
random_state=1,
algorithm="SAMME").fit(X_train_sparse, y_train)
# Trained on dense format
dense_classifier = AdaBoostClassifier(
base_estimator=CustomSVC(probability=True),
random_state=1,
algorithm="SAMME").fit(X_train, y_train)
# predict
sparse_results = sparse_classifier.predict(X_test_sparse)
dense_results = dense_classifier.predict(X_test)
assert_array_equal(sparse_results, dense_results)
# decision_function
sparse_results = sparse_classifier.decision_function(X_test_sparse)
dense_results = dense_classifier.decision_function(X_test)
assert_array_equal(sparse_results, dense_results)
# predict_log_proba
sparse_results = sparse_classifier.predict_log_proba(X_test_sparse)
dense_results = dense_classifier.predict_log_proba(X_test)
assert_array_equal(sparse_results, dense_results)
# predict_proba
sparse_results = sparse_classifier.predict_proba(X_test_sparse)
dense_results = dense_classifier.predict_proba(X_test)
assert_array_equal(sparse_results, dense_results)
# score
sparse_results = sparse_classifier.score(X_test_sparse, y_test)
dense_results = dense_classifier.score(X_test, y_test)
assert_array_equal(sparse_results, dense_results)
# staged_decision_function
sparse_results = sparse_classifier.staged_decision_function(
X_test_sparse)
dense_results = dense_classifier.staged_decision_function(X_test)
for sprase_res, dense_res in zip(sparse_results, dense_results):
assert_array_equal(sprase_res, dense_res)
# staged_predict
sparse_results = sparse_classifier.staged_predict(X_test_sparse)
dense_results = dense_classifier.staged_predict(X_test)
for sprase_res, dense_res in zip(sparse_results, dense_results):
assert_array_equal(sprase_res, dense_res)
# staged_predict_proba
sparse_results = sparse_classifier.staged_predict_proba(X_test_sparse)
dense_results = dense_classifier.staged_predict_proba(X_test)
for sprase_res, dense_res in zip(sparse_results, dense_results):
assert_array_equal(sprase_res, dense_res)
# staged_score
sparse_results = sparse_classifier.staged_score(X_test_sparse, y_test)
dense_results = dense_classifier.staged_score(X_test, y_test)
for sprase_res, dense_res in zip(sparse_results, dense_results):
assert_array_equal(sprase_res, dense_res)
# Verify sparsity of data is maintained during training
types = [i.data_type_ for i in sparse_classifier.estimators_]
assert all([(t == csc_matrix or t == csr_matrix) for t in types])
attributes[:, 1],
c=colors(targetValues),
cmap=pyplot.cm.Paired)
axes = pyplot.gca()
xLim = axes.get_xlim()
yLim = axes.get_ylim()
xs = numpy.linspace(xLim[0], xLim[1], 30)
ys = numpy.linspace(yLim[0], yLim[1], 30)
xCoords, yCoords = numpy.meshgrid(xs, ys)
xyCoords = numpy.vstack([xCoords.ravel(), yCoords.ravel()]).T
Z = classifier.staged_decision_function(xyCoords)
iterationsCount = []
accuracies = []
os.mkdir(fileName)
i = 1
for item, z in zip(targetValuePredictedFunctions, Z):
pyplot.clf()
pyplot.xlabel("Step number " + str(i))
pyplot.scatter(attributes[:, 0],
attributes[:, 1],
c=colors(targetValues),
cmap=pyplot.cm.Paired)
# Plot the training points
ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
# and testing points
ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6)
ax.set_xlim(xx.min(), xx.max())
ax.set_ylim(yy.min(), yy.max())
ax.set_xticks(())
ax.set_yticks(())
i = 1
plt.show()
clf.fit(X_train, y_train)
score = clf.staged_score(X_test, y_test)
step = 1
for S, Z, est in zip(
score, clf.staged_decision_function(np.c_[xx.ravel(),
yy.ravel()]),
clf.estimators_):
# iterate over classifiers
ax = plt.subplot(1, 1, i)
# Put the result into a color plot
Z = Z.reshape(xx.shape)
ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)
#size = np.repeat(2.0, X_train.shape[0]) + (6-2.0)*(est.sample_weight - est.sample_weight.min())/(est.sample_weight.max() - est.sample_weight.min() + 0.0001)
size = np.repeat(2.0, X_train.shape[0])
size = 2 * np.pi * size**2
# Plot also the training points
ax.scatter(X_train[:, 0],
X_train[:, 1],
c=y_train,
