def test_gradient_boosting():
runner = Runner(
'model/experiment/output/gradient_boosting_basic',
load_clean_sample_data_frame(),
'arrest',
gradient_boosting_pipeline,
hyper_parameters=hyper_parameters
)
runner.run_classification_search_experiment(
'roc_auc',
sample=sample,
n_iter=iterations,
record_predict_proba=True
)
runner = Runner(
'model/experiment/output/gradient_boosting_under_sampled',
load_clean_sample_data_frame(),
'arrest',
gradient_boosting_pipeline,
hyper_parameters=hyper_parameters
)
runner.run_classification_search_experiment(
'roc_auc',
sample=sample,
n_iter=iterations,
record_predict_proba=True,
sampling=RandomUnderSampler()
)
runner = Runner(
'model/experiment/output/gradient_boosting_over_sampled',
load_clean_sample_data_frame(),
'arrest',
gradient_boosting_pipeline,
hyper_parameters=hyper_parameters
)
runner.run_classification_search_experiment(
'roc_auc',
sample=sample,
n_iter=iterations,
record_predict_proba=True,
sampling=SMOTE()
)
runner = Runner(
'model/experiment/output/gradient_boosting_combine_sampled',
load_clean_sample_data_frame(),
'arrest',
gradient_boosting_pipeline,
hyper_parameters=hyper_parameters
)
runner.run_classification_search_experiment(
'roc_auc',
sample=sample,
n_iter=iterations,
record_predict_proba=True,
sampling=SMOTEENN()
)
def test_sgd_log_loss():
runner = Runner('model/experiment/output/sgd_log_loss_basic',
load_clean_sample_data_frame(), 'arrest',
SGDClassifier(loss='log'))
runner.run_classification_experiment(
sample=sample,
record_predict_proba=True,
transformer=binned_geo_one_hot_data_mapper,
fit_increment=fit_increment,
max_iters=max_iters,
n_jobs=1)
runner = Runner('model/experiment/output/sgd_log_loss_under_sampled',
load_clean_sample_data_frame(), 'arrest',
SGDClassifier(loss='log'))
runner.run_classification_experiment(
sample=sample,
record_predict_proba=True,
transformer=binned_geo_one_hot_data_mapper,
fit_increment=fit_increment,
max_iters=max_iters,
n_jobs=1,
sampling=RandomUnderSampler())
runner = Runner('model/experiment/output/sgd_log_loss_over_sampled',
load_clean_sample_data_frame(), 'arrest',
SGDClassifier(loss='log'))
runner.run_classification_experiment(
sample=sample,
record_predict_proba=True,
transformer=binned_geo_one_hot_data_mapper,
fit_increment=fit_increment,
max_iters=max_iters,
n_jobs=1,
sampling=SMOTE())
runner = Runner('model/experiment/output/sgd_log_loss_combine_sampled',
load_clean_sample_data_frame(), 'arrest',
SGDClassifier(loss='log'))
runner.run_classification_experiment(
sample=sample,
record_predict_proba=True,
transformer=binned_geo_one_hot_data_mapper,
fit_increment=fit_increment,
max_iters=max_iters,
n_jobs=1,
sampling=SMOTEENN())
def test_gaussian_naive_bayes():
runner = Runner('model/experiment/output/gaussian_naive_bayes_basic',
load_clean_sample_data_frame(), 'arrest', GaussianNB())
runner.run_classification_experiment(
sample=sample,
record_predict_proba=True,
transformer=binned_geo_one_hot_data_mapper,
fit_increment=fit_increment,
n_jobs=1)
runner = Runner(
'model/experiment/output/gaussian_naive_bayes_under_sampled',
load_clean_sample_data_frame(), 'arrest', GaussianNB())
runner.run_classification_experiment(
sample=sample,
record_predict_proba=True,
transformer=binned_geo_one_hot_data_mapper,
fit_increment=fit_increment,
n_jobs=1,
sampling=RandomUnderSampler())
runner = Runner(
'model/experiment/output/gaussian_naive_bayes_over_sampled',
load_clean_sample_data_frame(), 'arrest', GaussianNB())
runner.run_classification_experiment(
sample=sample,
record_predict_proba=True,
transformer=binned_geo_one_hot_data_mapper,
fit_increment=fit_increment,
n_jobs=1,
sampling=SMOTE())
runner = Runner(
'model/experiment/output/gaussian_naive_bayes_combine_sampled',
load_clean_sample_data_frame(), 'arrest', GaussianNB())
runner.run_classification_experiment(
sample=sample,
record_predict_proba=True,
transformer=binned_geo_one_hot_data_mapper,
fit_increment=fit_increment,
n_jobs=1,
sampling=SMOTEENN())
def test_neural_network():
runner = Runner(
'model/experiment/output/neural_network_basic',
load_clean_sample_data_frame(), 'arrest',
MLPClassifier(hidden_layer_sizes=(
750,
125,
), verbose=True))
runner.run_classification_experiment(
sample=sample,
record_predict_proba=True,
transformer=binned_geo_one_hot_data_mapper,
fit_increment=fit_increment,
max_iters=max_iters,
n_jobs=1)
runner = Runner(
'model/experiment/output/neural_network_under_sampled',
load_clean_sample_data_frame(), 'arrest',
MLPClassifier(hidden_layer_sizes=(
750,
125,
), verbose=True))
runner.run_classification_experiment(
sample=sample,
record_predict_proba=True,
transformer=binned_geo_one_hot_data_mapper,
fit_increment=fit_increment,
max_iters=max_iters,
n_jobs=1,
sampling=RandomUnderSampler())
runner = Runner(
'model/experiment/output/neural_network_over_sampled',
load_clean_sample_data_frame(), 'arrest',
MLPClassifier(hidden_layer_sizes=(
750,
125,
), verbose=True))
runner.run_classification_experiment(
sample=sample,
record_predict_proba=True,
transformer=binned_geo_one_hot_data_mapper,
fit_increment=fit_increment,
max_iters=max_iters,
n_jobs=1,
sampling=SMOTE())
runner = Runner(
'model/experiment/output/neural_network_combine_sampled',
load_clean_sample_data_frame(), 'arrest',
MLPClassifier(hidden_layer_sizes=(
750,
125,
), verbose=True))
runner.run_classification_experiment(
sample=sample,
record_predict_proba=True,
transformer=binned_geo_one_hot_data_mapper,
fit_increment=fit_increment,
max_iters=max_iters,
n_jobs=1,
sampling=SMOTEENN())