本文整理汇总了Python中mlxtend.data.iris_data函数的典型用法代码示例。如果您正苦于以下问题:Python iris_data函数的具体用法?Python iris_data怎么用?Python iris_data使用的例子?那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。
在下文中一共展示了iris_data函数的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_scoring
def test_scoring():
X, y = iris_data()
clf1 = LogisticRegression(random_state=1)
clf2 = DecisionTreeClassifier(random_state=1)
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=0.25,
random_state=123)
score1 = clf1.fit(X_train, y_train).score(X_test, y_test)
score2 = clf2.fit(X_train, y_train).score(X_test, y_test)
assert round(score1, 2) == 0.97
assert round(score2, 2) == 0.95
t, p = paired_ttest_5x2cv(estimator1=clf1,
estimator2=clf2,
X=X, y=y,
scoring='accuracy',
random_seed=1)
assert round(t, 3) == -1.539, t
assert round(p, 3) == 0.184, p
t, p = paired_ttest_5x2cv(estimator1=clf1,
estimator2=clf2,
X=X, y=y,
scoring='f1_macro',
random_seed=1)
assert round(t, 3) == -1.510, t
assert round(p, 3) == 0.191, p
示例2: test_scoring
def test_scoring():
X, y = iris_data()
clf1 = LogisticRegression(random_state=1,
solver='liblinear',
multi_class='ovr')
clf2 = DecisionTreeClassifier(random_state=1)
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=0.5,
random_state=123)
score1 = clf1.fit(X_train, y_train).score(X_test, y_test)
score2 = clf2.fit(X_train, y_train).score(X_test, y_test)
assert round(score1, 2) == 0.96, round(score1, 2)
assert round(score2, 2) == 0.91, round(score2, 2)
t, p = paired_ttest_kfold_cv(estimator1=clf1,
estimator2=clf2,
X=X, y=y,
scoring='accuracy',
random_seed=1)
assert round(t, 3) == -1.861, t
assert round(p, 3) == 0.096, p
t, p = paired_ttest_kfold_cv(estimator1=clf1,
estimator2=clf2,
X=X, y=y,
scoring='recall_micro',
random_seed=1)
assert round(t, 3) == -1.861, t
assert round(p, 3) == 0.096, p
示例3: test_iris_data_uci
def test_iris_data_uci():
tmp = np.genfromtxt(fname=DATA_PATH, delimiter=',')
original_uci_data_x, original_uci_data_y = tmp[:, :-1], tmp[:, -1]
original_uci_data_y = original_uci_data_y.astype(int)
iris_x, iris_y = iris_data()
assert_array_equal(original_uci_data_x, iris_x)
assert_array_equal(original_uci_data_y, iris_y)
示例4: test_not_fitted
def test_not_fitted():
np.random.seed(123)
meta = LogisticRegression(multi_class='ovr', solver='liblinear')
clf1 = RandomForestClassifier(n_estimators=10)
clf2 = GaussianNB()
sclf = StackingCVClassifier(classifiers=[clf1, clf2],
use_probas=True,
meta_classifier=meta, shuffle=False)
X, y = iris_data()
assert_raises(NotFittedError,
"This StackingCVClassifier instance is not fitted yet."
" Call 'fit' with appropriate arguments"
" before using this method.",
sclf.predict,
X)
assert_raises(NotFittedError,
"This StackingCVClassifier instance is not fitted yet."
" Call 'fit' with appropriate arguments"
" before using this method.",
sclf.predict_proba,
X)
assert_raises(NotFittedError,
"This StackingCVClassifier instance is not fitted yet."
" Call 'fit' with appropriate arguments"
" before using this method.",
sclf.predict_meta_features,
X)
示例5: test_threshold
def test_threshold():
X, y = iris_data()
ax, threshold, count = ecdf(x=X[:, 0],
x_label='sepal length (cm)',
percentile=0.8)
assert threshold == 6.5
assert count == 120
示例6: test_iris_data_r
def test_iris_data_r():
tmp = np.genfromtxt(fname=DATA_PATH, delimiter=',')
original_r_data_x, original_r_data_y = tmp[:, :-1], tmp[:, -1]
original_r_data_y = original_r_data_y.astype(int)
original_r_data_x[34] = [4.9, 3.1, 1.5, 0.2]
original_r_data_x[37] = [4.9, 3.6, 1.4, 0.1]
iris_x, iris_y = iris_data(version='corrected')
assert_array_equal(original_r_data_x, iris_x)
示例7: test_verbose
def test_verbose():
np.random.seed(123)
meta = LogisticRegression(solver='liblinear',
multi_class='ovr')
clf1 = RandomForestClassifier(n_estimators=10)
clf2 = GaussianNB()
sclf = StackingClassifier(classifiers=[clf1, clf2],
use_probas=True,
meta_classifier=meta,
verbose=3)
X, y = iris_data()
sclf.fit(X, y)
示例8: test_gridsearch_enumerate_names
def test_gridsearch_enumerate_names():
np.random.seed(123)
meta = LogisticRegression(multi_class='ovr', solver='liblinear')
clf1 = RandomForestClassifier(n_estimators=10)
clf2 = GaussianNB()
sclf = StackingCVClassifier(classifiers=[clf1, clf1, clf2],
meta_classifier=meta,
shuffle=False)
params = {'meta_classifier__C': [1.0, 100.0],
'randomforestclassifier-1__n_estimators': [5, 10],
'randomforestclassifier-2__n_estimators': [5, 20],
'use_probas': [True, False]}
grid = GridSearchCV(estimator=sclf, param_grid=params, cv=5, iid=False)
X, y = iris_data()
grid = grid.fit(X, y)
示例9: test_use_features_in_secondary_predict_proba
def test_use_features_in_secondary_predict_proba():
np.random.seed(123)
X, y = iris_data()
meta = LogisticRegression(solver='liblinear',
multi_class='ovr',
random_state=1)
clf1 = RandomForestClassifier(n_estimators=10, random_state=1)
clf2 = GaussianNB()
sclf = StackingClassifier(classifiers=[clf1, clf2],
use_features_in_secondary=True,
meta_classifier=meta)
sclf.fit(X, y)
idx = [0, 1, 2]
y_pred = sclf.predict_proba(X[idx])[:, 0]
expect = np.array([0.916, 0.828, 0.889])
np.testing.assert_almost_equal(y_pred, expect, 3)
示例10: test_use_features_in_secondary_sparse_input_predict
def test_use_features_in_secondary_sparse_input_predict():
np.random.seed(123)
X, y = iris_data()
meta = LogisticRegression(solver='liblinear',
multi_class='ovr',
random_state=1)
clf1 = RandomForestClassifier(n_estimators=10, random_state=1)
sclf = StackingClassifier(classifiers=[clf1],
use_features_in_secondary=True,
meta_classifier=meta)
scores = cross_val_score(sclf,
sparse.csr_matrix(X),
y,
cv=5,
scoring='accuracy')
scores_mean = (round(scores.mean(), 2))
assert scores_mean == 0.97, scores_mean
示例11: test_use_features_in_secondary_predict
def test_use_features_in_secondary_predict():
np.random.seed(123)
X, y = iris_data()
meta = LogisticRegression(solver='liblinear',
multi_class='ovr')
clf1 = RandomForestClassifier(n_estimators=10)
clf2 = GaussianNB()
sclf = StackingClassifier(classifiers=[clf1, clf2],
use_features_in_secondary=True,
meta_classifier=meta)
scores = cross_val_score(sclf,
X,
y,
cv=5,
scoring='accuracy')
scores_mean = (round(scores.mean(), 2))
assert scores_mean == 0.95, scores_mean
示例12: test_01_loss_tree
def test_01_loss_tree():
X, y = iris_data()
X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.3,
random_state=123,
shuffle=True,
stratify=y)
tree = DecisionTreeClassifier(random_state=123)
avg_expected_loss, avg_bias, avg_var = bias_variance_decomp(
tree, X_train, y_train, X_test, y_test,
loss='0-1_loss',
random_seed=123)
assert round(avg_expected_loss, 3) == 0.062
assert round(avg_bias, 3) == 0.022
assert round(avg_var, 3) == 0.040
示例13: test_classifier_defaults
def test_classifier_defaults():
X, y = iris_data()
clf1 = LogisticRegression(multi_class='ovr',
solver='liblinear',
random_state=1)
clf2 = DecisionTreeClassifier(random_state=1)
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=0.25,
random_state=123)
score1 = clf1.fit(X_train, y_train).score(X_test, y_test)
score2 = clf2.fit(X_train, y_train).score(X_test, y_test)
assert round(score1, 2) == 0.97
assert round(score2, 2) == 0.95
t, p = paired_ttest_resampled(estimator1=clf1,
estimator2=clf2,
X=X, y=y,
random_seed=1)
if Version(sklearn_version) < Version("0.20"):
assert round(t, 3) == -1.809, t
assert round(p, 3) == 0.081, p
else:
assert round(t, 3) == -1.702, t
assert round(p, 3) == 0.10, p
# change maxdepth of decision tree classifier
clf2 = DecisionTreeClassifier(max_depth=1, random_state=1)
score3 = clf2.fit(X_train, y_train).score(X_test, y_test)
assert round(score3, 2) == 0.63
t, p = paired_ttest_resampled(estimator1=clf1,
estimator2=clf2,
X=X, y=y,
random_seed=1)
assert round(t, 3) == 39.214, t
assert round(p, 3) == 0.000, p
示例14: test_train_size
def test_train_size():
X, y = iris_data()
clf1 = LogisticRegression(solver='liblinear', multi_class='ovr')
clf2 = DecisionTreeClassifier()
expected_err_msg = ("train_size must be of type int or float. "
"Got <class 'NoneType'>.")
if sys.version_info < (3, 0):
expected_err_msg = expected_err_msg.replace('<class', '<type')
assert_raises(ValueError,
expected_err_msg,
paired_ttest_resampled,
clf1,
clf2,
X,
y,
test_size=None)
示例15: test_scoring
def test_scoring():
X, y = iris_data()
clf1 = LogisticRegression(multi_class='ovr',
solver='liblinear',
random_state=1)
clf2 = DecisionTreeClassifier(random_state=1)
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=0.25,
random_state=123)
score1 = clf1.fit(X_train, y_train).score(X_test, y_test)
score2 = clf2.fit(X_train, y_train).score(X_test, y_test)
assert round(score1, 2) == 0.97
assert round(score2, 2) == 0.95
t, p = paired_ttest_resampled(estimator1=clf1,
estimator2=clf2,
X=X, y=y,
scoring='accuracy',
random_seed=1)
if Version(sklearn_version) < Version('0.20'):
assert round(t, 3) == -1.809, t
assert round(p, 3) == 0.081, p
else:
assert round(t, 3) == -1.702, t
assert round(p, 3) == 0.1, p
t, p = paired_ttest_resampled(estimator1=clf1,
estimator2=clf2,
X=X, y=y,
scoring='f1_macro',
random_seed=1)
if Version(sklearn_version) < Version("0.20"):
assert round(t, 3) == -1.690, t
assert round(p, 3) == 0.102, p
else:
assert round(t, 3) == -1.561, t
assert round(p, 3) == 0.129, p