def run(self):
'''Runs the pipeline step.
'''
labels = persistence.json_to_obj(self.input['label_dict'])
classifier = Classifier(
persistence.bin_to_obj(self.input['TrainClassifier_vectorizer']),
persistence.bin_to_obj(self.input['TrainClassifier_model']),
labels)
def update_label(row):
return labels[str(row['expected'])]
def predict(row):
classification = classifier.predict(row['name'])
return classification['label']['name']
df = pd.read_csv(self.input['predictions'])
df['expected'] = df.apply(update_label, axis=1)
df['actual'] = df.apply(predict, axis=1)
def print_incorrect(row):
if row['actual'] != row['expected']:
self.print(
'\'{name}\' [ expected: {expected}, actual: {actual} ]',
name=row['name'],
expected=row['expected'],
actual=row['actual'])
df.apply(print_incorrect, axis=1)
def __score_model(self, classifier, features, labels, title):
classes = persistence.json_to_obj(self.input['label_dict'])
plot_confusion_matrix(
estimator=classifier,
X=features,
y_true=labels,
display_labels=classes.values(),
normalize='true')
plt.title(title)
plt.savefig(self.output['{title}_results'.format(title=title)])
def predict(filename, model_id='latest'):
''' Makes a prediction using the classification model.
Args:
filenanme (string): The filename to evaluate.
model_id (string): the id of the model to use.
'''
model_path = __get_model_path(model_id)
classifier = Classifier(
persistence.bin_to_obj(model_path + 'classifier_vec.pickle'),
persistence.bin_to_obj(model_path + 'classifier_mdl.pickle'),
persistence.json_to_obj('data/processed/label_dictionary.json')
)
classification = classifier.predict(filename)
return (classification['label'], classification['probability'])
def fixture_labels():
return persistence.json_to_obj('models/label_dictionary.json')
def test_json_to_obj_null_path_throws_exception():
with pytest.raises(TypeError):
persistence.json_to_obj(None)
def test_json_to_obj_not_null():
assert persistence.json_to_obj('models/label_dictionary.json') is not None
def test_json_to_obj_empty_path_throws_exception():
with pytest.raises(FileNotFoundError):
persistence.json_to_obj('')
def fixture_model():
return Classifier(persistence.bin_to_obj('models/classifier_vec.pickle'),
persistence.bin_to_obj('models/classifier_mdl.pickle'),
persistence.json_to_obj('models/label_dictionary.json'))
