def __init__(self,
train_dataset_path: str,
test_dataset_path: str,
target_column: str,
categorical_columns: Optional[List[str]] = None,
drop_columns: Optional[List[str]] = None):
self.wave_model = build_model(train_file_path=train_dataset_path,
target_column=target_column,
model_type=ModelType.H2O3,
categorical_columns=categorical_columns,
drop_columns=drop_columns,
_h2o3_max_runtime_secs=30,
_h2o3_nfolds=0,
_h2o3_include_algos=['DRF', 'GBM'])
self.model = self.wave_model.model
self.test_df = h2o.import_file(path=test_dataset_path)
for column in categorical_columns:
self.test_df[column] = self.test_df[column].asfactor()
self.churn_probabilities = self.model.predict(
self.test_df)[:, -1].as_data_frame().values
self.contributions_df = self.model.predict_contributions(
self.test_df).drop('BiasTerm').as_data_frame()
async def serve(q: Q):
if q.args.train:
# train WaveML Model using H2O-3 AutoML
copy_expando(q.args, q.client)
q.client.wave_model = build_model(
train_df=q.client.train_df,
target_column='target',
model_type=ModelType.H2O3,
_h2o3_max_runtime_secs=30,
_h2o3_nfolds=2,
_h2o3_include_algos=[q.client.algo]
)
model_id = q.client.wave_model.model.model_id
accuracy = round(100 - q.client.wave_model.model.mean_per_class_error() * 100, 2)
# show training details and prediction option
q.page['example'].items[1].choice_group.value = q.client.algo
q.page['example'].items[2].buttons.items[1].button.disabled = False
q.page['example'].items[3].message_bar.type = 'success'
q.page['example'].items[3].message_bar.text = 'Training successfully completed!'
q.page['example'].items[4].text.content = f'''**H2O AutoML model id:** {model_id} <br />
**Accuracy:** {accuracy}%'''
q.page['example'].items[5].text.content = ''
elif q.args.predict:
# predict on test data
preds = q.client.wave_model.predict(test_df=q.client.test_df)
# show predictions
q.page['example'].items[3].message_bar.text = 'Prediction successfully completed!'
q.page['example'].items[5].text.content = f'''**Example predictions:** <br />
{preds[0]} <br /> {preds[1]} <br /> {preds[2]}'''
else:
# prepare sample train and test dataframes
data = load_wine(as_frame=True)['frame']
q.client.train_df, q.client.test_df = train_test_split(data, train_size=0.8)
# algos
algo_choices = [ui.choice(x, x) for x in ['DRF', 'GLM', 'XGBoost', 'GBM', 'DeepLearning']]
# display ui
q.page['example'] = ui.form_card(
box='1 1 -1 -1',
items=[
ui.text(content='''The sample dataset used is the
<a href="https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_wine.html" target="_blank">wine dataset</a>.'''),
ui.choice_group(name='algo', label='Select Algo', choices=algo_choices, value='DRF'),
ui.buttons(items=[
ui.button(name='train', label='Train', primary=True),
ui.button(name='predict', label='Predict', primary=True, disabled=True),
]),
ui.message_bar(type='warning', text='Training will take a few seconds'),
ui.text(content=''),
ui.text(content='')
]
)
await q.page.save()
def model(self):
if not self._model:
wave_model = build_model(
train_file_path=self._train_csv,
target_column=self._target_column,
model_type=ModelType.H2O3,
drop_columns=[self._id_column],
_h2o3_max_runtime_secs=30,
_h2o3_nfolds=0,
_h2o3_include_algos=['DRF', 'XGBoost', 'GBM']
)
self._model = wave_model.model
return self._model
async def serve(q: Q):
if q.args.train:
# train WaveML Model using H2O-3 AutoML
wave_model = build_model(train_df=q.client.train_df,
target_column='target',
model_type=ModelType.H2O3,
_h2o3_max_runtime_secs=5,
_h2o3_nfolds=2)
model_id = wave_model.model.model_id
accuracy = round(100 - wave_model.model.mean_per_class_error() * 100,
2)
# save model to local folder
q.client.path_model = save_model(model=wave_model,
output_dir_path='./mymodelfolder')
# show training details and prediction option
q.page['example'].items[1].buttons.items[1].button.disabled = False
q.page['example'].items[2].message_bar.type = 'success'
q.page['example'].items[
2].message_bar.text = 'Training successfully completed!'
q.page['example'].items[
3].text.content = f'''**H2O AutoML model id:** {model_id} <br />
**Accuracy:** {accuracy}%'''
q.page['example'].items[4].text.content = ''
elif q.args.predict:
# load model from local path
wave_model = load_model(file_path=q.client.path_model)
# predict on test data
preds = wave_model.predict(test_df=q.client.test_df)
# show predictions
q.page['example'].items[
2].message_bar.text = 'Prediction successfully completed!'
q.page['example'].items[
4].text.content = f'''**Example predictions:** <br />
{preds[0]} <br /> {preds[1]} <br /> {preds[2]}'''
else:
# prepare sample train and test dataframes
data = load_wine(as_frame=True)['frame']
q.client.train_df, q.client.test_df = train_test_split(data,
train_size=0.8)
# display ui
q.page['example'] = ui.form_card(
box='1 1 -1 -1',
items=[
ui.text(content='''The sample dataset used is the
<a href="https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_wine.html" target="_blank">wine dataset</a>.'''
),
ui.buttons(items=[
ui.button(name='train', label='Train', primary=True),
ui.button(name='predict',
label='Predict',
primary=True,
disabled=True),
]),
ui.message_bar(type='warning',
text='Training will take a few seconds'),
ui.text(content=''),
ui.text(content='')
])
await q.page.save()
async def serve(q: Q):
if q.args.train:
# train WaveML Model using H2O-3 AutoML
q.client.wave_model = build_model(
train_df=q.client.train_df,
target_column='target',
model_type=ModelType.H2O3,
_h2o3_max_runtime_secs=5,
_h2o3_nfolds=2,
_h2o3_include_algos=['DRF', 'XGBoost', 'GBM'])
model_id = q.client.wave_model.model.model_id
accuracy = round(q.client.wave_model.model.accuracy()[0][1] * 100, 2)
# show training details and prediction option
q.page['example'].items[1].buttons.items[1].button.disabled = False
q.page['example'].items[2].message_bar.type = 'success'
q.page['example'].items[
2].message_bar.text = 'Training successfully completed!'
q.page['example'].items[
3].text.content = f'''**H2O AutoML model id:** {model_id} <br />
**Accuracy:** {accuracy}%'''
q.page['example'].items[4].text.content = ''
q.page['example'].items[5].text.content = ''
elif q.args.predict:
# predict on test data
preds = q.client.wave_model.predict(test_df=q.client.test_df)
shaps = q.client.wave_model.model.predict_contributions(
H2OFrame(q.client.test_df)).as_data_frame()
# show predictions
q.page['example'].items[
2].message_bar.text = 'Prediction successfully completed!'
q.page['example'].items[
4].text.content = f'''**Example predictions:** <br />
{preds[0]} <br /> {preds[1]} <br /> {preds[2]}'''
q.page['example'].items[
5].text.content = f'''**Example SHAP contributions:** <br />
{shaps.head(3).to_html()}'''
else:
# prepare sample train and test dataframes
data = load_breast_cancer(as_frame=True)['frame']
q.client.train_df, q.client.test_df = train_test_split(data,
train_size=0.8)
# display ui
q.page['example'] = ui.form_card(
box='1 1 -1 -1',
items=[
ui.text(content='''The sample dataset used is the
<a href="https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_breast_cancer.html#sklearn.datasets.load_breast_cancer" target="_blank">breast cancer dataset</a>.'''
),
ui.buttons(items=[
ui.button(name='train', label='Train', primary=True),
ui.button(name='predict',
label='Predict',
primary=True,
disabled=True),
]),
ui.message_bar(type='warning',
text='Training will take a few seconds'),
ui.text(content=''),
ui.text(content=''),
ui.text(content='')
])
await q.page.save()