def test_training_not_save(self):
matrix = self.matrix
assert matrix.target_variable.name == "major_group"
occ_trainer = OccupationClassifierTrainer(matrix,
k_folds=2,
grid_config=grid,
scoring=['accuracy'])
occ_trainer.train(save=False)
assert list(occ_trainer.cls_cv_result['accuracy'].keys()) == [
'ExtraTreesClassifier'
]
def test_training_save(self, mock_getcwd):
with tempfile.TemporaryDirectory() as td:
mock_getcwd.return_value = td
matrix = self.matrix
assert matrix.target_variable.name == "major_group"
occ_trainer = OccupationClassifierTrainer(matrix,
k_folds=2,
storage=FSStore(td),
grid_config=grid,
scoring=['accuracy'])
occ_trainer.train(save=True)
assert set(os.listdir(os.getcwd())) == set(
[occ_trainer.train_time])
def test_training(self):
jp_f = JobPostingFilterer(self.jobpostings, [self.has_soc_filter])
matrix = create_training_set(jp_f, SOCMajorGroup(),
self.embedding_model)
assert matrix.target_variable.name == "major_group"
occ_trainer = OccupationClassifierTrainer(matrix,
k_folds=2,
grid_config=grid,
scoring=['accuracy'])
occ_trainer.train()
assert list(occ_trainer.cls_cv_result['accuracy'].keys()) == [
'ExtraTreesClassifier'
]
assert occ_trainer.matrix.embedding_model.model_name == self.embedding_model.model_name
def test_tester(self):
document_schema_fields = ['description','experienceRequirements', 'qualifications', 'skills']
corpus_generator = Word2VecGensimCorpusCreator(JobPostingCollectionSample(num_records=30), document_schema_fields=document_schema_fields)
w2v = Word2VecModel(size=10, min_count=3, iter=4, window=6, workers=3)
trainer = EmbeddingTrainer(w2v)
trainer.train(corpus_generator)
jp = JobPostingCollectionSample()
train_gen = islice(jp, 30)
test_gen = islice(jp, 30, None)
train_matrix = DesignMatrix(train_gen, self.fullsoc, self.pipe_x, self.pipe_y)
train_matrix.build()
occ_trainer = OccupationClassifierTrainer(train_matrix, 2, grid_config=self.grid_config)
occ_trainer.train(save=False)
cc = CombinedClassifier(w2v, occ_trainer.best_estimators[0])
steps = self.pipe_x.generators[:-1]
test_gen = (t for t in test_gen if t['onet_soc_code'] is not '')
tester = OccupationClassifierTester(test_data_generator=test_gen, preprocessing=steps, classifier=cc)
result = list(tester)
assert len(tester) == len(result) == 18
'max_depth': [20, 50],
'max_features': ['log2'],
'min_samples_split': [10, 20]
},
'sklearn.neural_network.MLPClassifier': {
'hidden_layer_sizes': [100, 200, 300, 500, 1000],
'activation': ['identity', 'logistic', 'tanh', 'relu'],
'solver': ['lbfgs', 'sgd', 'adam']
},
'sklearn.svm.SVC': {
'C': [0.1, 1, 10, 100, 1000],
'kernel': ['linear', 'poly', 'sigmoid', 'rbf', 'precomputed'],
'shrinking': [True, False],
'decision_function_shape': ['ovo', 'ovr']
}
}
trainer = OccupationClassifierTrainer(
matrix=matrix,
k_folds=3,
grid_config=grid_config,
storage=FSStore('tmp/soc_classifiers'),
n_jobs = num_of_worker
)
trainer.train()
fs = FSStore(os.path.join('soc_classifiers', trainer.train_time))
fs.write(train_bytes, "train.data")
fs.write(test_bytes, "test_data")