def setUp(self):
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data,
iris.target,
test_size=0.30,
random_state=0)
model = RandomForestClassifier()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
y_score = model.predict_proba(X_test)
target_names = ['setosa', 'versicolor', 'virginica']
feature_names = range(4)
model_name = 'a model'
self.results = ClassifierEvaluator(estimator=model,
y_true=y_test,
y_pred=y_pred,
y_score=y_score,
feature_names=feature_names,
target_names=target_names,
estimator_name=model_name)
self.empty = ClassifierEvaluator(estimator=None,
y_true=None,
y_pred=None,
y_score=None,
feature_names=None,
target_names=None,
estimator_name=None)
self.template = '''
class TestReportGeneration(TestCase):
def setUp(self):
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data,
iris.target,
test_size=0.30,
random_state=0)
model = RandomForestClassifier()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
y_score = model.predict_proba(X_test)
target_names = ['setosa', 'versicolor', 'virginica']
feature_names = range(4)
model_name = 'a model'
self.results = ClassifierEvaluator(estimator=model,
y_true=y_test,
y_pred=y_pred,
y_score=y_score,
feature_names=feature_names,
target_names=target_names,
estimator_name=model_name)
def test_can_create_report(self):
self.results.make_report()
def setUp(self):
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data,
iris.target,
test_size=0.30,
random_state=0)
model = RandomForestClassifier()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
y_score = model.predict_proba(X_test)
target_names = ['setosa', 'versicolor', 'virginica']
feature_names = range(4)
model_name = 'a model'
self.results = ClassifierEvaluator(estimator=model, y_true=y_test,
y_pred=y_pred, y_score=y_score,
feature_names=feature_names,
target_names=target_names,
estimator_name=model_name)
self.empty = ClassifierEvaluator(estimator=None, y_true=None,
y_pred=None, y_score=None,
feature_names=None,
target_names=None,
estimator_name=None)
self.template = '''
def test_can_plot():
data = datasets.make_classification(200, 10, 5, class_sep=0.65)
X = data[0]
y = data[1]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
est = RandomForestClassifier()
est.fit(X_train, y_train)
evaluator = ClassifierEvaluator(est, y_true=y_test, X=X_test)
evaluator.confusion_matrix()
def visualize(X, y, estimator, test_size=0.33, path=None, html=True):
"""Visualize Result
:param numpy matrix X: dataset.
:param numpy matrix y: label matrix.
:param float test_size: testset's size/alldataset's size.
"""
result = split_train_test(X, y, estimator, test_size)
target_names = [
'business', 'entertainment', 'health', 'politics', 'sports',
'technology'
]
ce = ClassifierEvaluator(estimator,
result['y_test'],
result['y_pred'],
result['y_score'],
target_names=target_names)
if html and path:
template = '''
# Report
###1. Estimator Name.
`{estimator_type}`
###2. Confusion Matrix.
{confusion_matrix}
###3. ROC Graph.
{roc}
###4. Precision Recall Graph.
{precision_recall}
'''
ce.generate_report(template, path=path)
else:
ce.confusion_matrix
class TestReportGeneration(TestCase):
def setUp(self):
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data,
iris.target,
test_size=0.30,
random_state=0)
model = RandomForestClassifier()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
y_score = model.predict_proba(X_test)
target_names = ['setosa', 'versicolor', 'virginica']
feature_names = range(4)
model_name = 'a model'
self.results = ClassifierEvaluator(estimator=model, y_true=y_test,
y_pred=y_pred, y_score=y_score,
feature_names=feature_names,
target_names=target_names,
estimator_name=model_name)
self.template = '''
# Report
{estimator_type}
{date}
{confusion_matrix}
{roc}
{precision_recall}
{feature_importances_table}
{feature_importances}
'''
def test_report_creation_no_style(self):
self.results.generate_report(self.template)
def test_report_creation_no_style_save_file(self):
self.results.generate_report(self.template, 'report.html')
def test_report_creation_style_save_file(self):
self.results.generate_report(self.template,
style='static/simple.css')
def test_report_creation_style(self):
self.results.generate_report(self.template, 'report.html',
style='static/simple.css')
def visualize(X, y, estimator, test_size=0.4, html=False):
result = split_train_test(X, y, estimator, test_size)
target_names = [
'business', 'entertainment', 'health', 'politics', 'sports',
'technology'
]
ce = ClassifierEvaluator(estimator,
result['y_test'],
result['y_pred'],
result['y_score'],
target_names=target_names)
if html:
template = '''
# Report
{estimator_type}
{date}
{confusion_matrix}
{roc}
{precision_recall}
'''
ce.generate_report(template, path='report.html')
else:
ce.confusion_matrix
# Learn to predict each class against the other
classifier = RandomForestClassifier()
classifier = classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
y_score = classifier.predict_proba(X_test)
feature_list = range(4)
target_names = ['setosa', 'versicolor', 'virginica']
# Create a trained model instance
ce = ClassifierEvaluator(classifier,
y_test,
y_pred,
y_score,
feature_list,
target_names,
estimator_name='super awesome SVC')
template = '''
# Report
{estimator_type}
{date}
{confusion_matrix}
{roc}
{precision_recall}
'''
ce.generate_report(template, 'report.html')
# shuffle and split training and test sets
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=.5,
random_state=0)
# Learn to predict each class against the other
classifier = RandomForestClassifier()
classifier = classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
y_score = classifier.predict_proba(X_test)
feature_list = range(4)
target_names = ['setosa', 'versicolor', 'virginica']
# Create a trained model instance
ce = ClassifierEvaluator(classifier,
y_test,
y_pred,
y_score,
feature_list,
target_names,
estimator_name='super awesome SVC')
report = ce.make_report()
# this will automativally render in Jupyter, or you can do report.save('/path')
report
class TestReportGeneration(TestCase):
def setUp(self):
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data,
iris.target,
test_size=0.30,
random_state=0)
model = RandomForestClassifier()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
y_score = model.predict_proba(X_test)
target_names = ['setosa', 'versicolor', 'virginica']
feature_names = range(4)
model_name = 'a model'
self.results = ClassifierEvaluator(estimator=model,
y_true=y_test,
y_pred=y_pred,
y_score=y_score,
feature_names=feature_names,
target_names=target_names,
estimator_name=model_name)
self.empty = ClassifierEvaluator(estimator=None,
y_true=None,
y_pred=None,
y_score=None,
feature_names=None,
target_names=None,
estimator_name=None)
self.template = '''
# Report
{estimator_type}
{date}
{confusion_matrix}
{roc}
{precision_recall}
{feature_importances_table}
{feature_importances}
'''
def test_no_style(self):
self.results.generate_report(template=self.template)
def test_no_style_save(self):
self.results.generate_report(template=self.template,
path='tmp_report.html')
def test_generate_with_all_attr_none(self):
self.empty.generate_report(template='# Title')
def test_apply_custom_css(self):
with open('baseline_html/empty.html') as f:
expected = f.read()
result = self.empty.generate_report(template='# Title\n ## Section',
style='static/simple.css')
assert expected == result
def test_returning_and_saving_are_the_same(self):
self.empty.generate_report(template='# Title\n ## Section',
path='tmp_report.html')
with open('tmp_report.html') as f:
saved = f.read()
returned = self.empty.generate_report(template='# Title\n ## Section')
assert saved == returned
# shuffle and split training and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5,
random_state=0)
# Learn to predict each class against the other
classifier = OneVsRestClassifier(svm.SVC(kernel='linear', probability=True,
random_state=random_state))
classifier = classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
y_score = classifier.decision_function(X_test)
feature_list = range(4)
target_names = ['setosa', 'versicolor', 'virginica']
# Create a trained model instance
ce = ClassifierEvaluator(classifier, y_test, y_pred, y_score,
feature_list, target_names,
estimator_name='super awesome SVC')
template = '''
# Report
{estimator_type}
{date}
{confusion_matrix}
{roc}
{precision_recall}
'''
ce.generate_report(template, 'report.html')
class TestReportGeneration(TestCase):
def setUp(self):
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data,
iris.target,
test_size=0.30,
random_state=0)
model = RandomForestClassifier()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
y_score = model.predict_proba(X_test)
target_names = ['setosa', 'versicolor', 'virginica']
feature_names = range(4)
model_name = 'a model'
self.results = ClassifierEvaluator(estimator=model, y_true=y_test,
y_pred=y_pred, y_score=y_score,
feature_names=feature_names,
target_names=target_names,
estimator_name=model_name)
self.empty = ClassifierEvaluator(estimator=None, y_true=None,
y_pred=None, y_score=None,
feature_names=None,
target_names=None,
estimator_name=None)
self.template = '''
# Report
{estimator_type}
{date}
{confusion_matrix}
{roc}
{precision_recall}
{feature_importances_table}
{feature_importances}
'''
def test_no_style(self):
self.results.generate_report(template=self.template)
def test_no_style_save(self):
self.results.generate_report(template=self.template,
path='tmp_report.html')
def test_generate_with_all_attr_none(self):
self.empty.generate_report(template='# Title')
def test_apply_custom_css(self):
with open('baseline_html/empty.html') as f:
expected = f.read()
result = self.empty.generate_report(template='# Title\n ## Section',
style='static/simple.css')
assert expected == result
def test_returning_and_saving_are_the_same(self):
self.empty.generate_report(template='# Title\n ## Section',
path='tmp_report.html')
with open('tmp_report.html') as f:
saved = f.read()
returned = self.empty.generate_report(template='# Title\n ## Section')
assert saved == returned