def frozen(
ctx,
credential, # shared options
config_path):
config = ctx.obj['config']
cmd = 'frozen'
if not config.is_valid(cmds=[cmd]):
raise Exception('configuration file error')
project = Project(**config.get_params(cmd='environment'))
if not hasattr(project, 'dr_project') or project.dr_project is None:
raise NotSpecifiedValidParam(
'project id is not supplied. you should run build command befor, or apply command'
)
model_id = config.get_param(cmd, param='model_id')
with section('Freezing model'):
if model_id is None:
sort_key = Utils.get_appropriate_dataset(project.cv_method,
project.validation_type,
project.validation_params)
model = project.search_models(sort_key=sort_key)[0]
model_id = model.id
config.set_params(cmd, params={'model_id': model_id})
new_model_id = project.frozen(**config.get_params(cmd))
ctx.obj['model_id'] = new_model_id
click.echo('frozen command is succeed.')
click.echo(f"'{model_id}' is frozen -> new model_id: {new_model_id}")
def fit(
ctx,
credential, # shared options
config_path):
config = ctx.obj['config']
cmd = 'fit'
if not config.is_valid(cmds=[cmd]):
raise Exception('configuration file error')
project = Project(**config.get_params(cmd='environment'))
if not hasattr(project, 'dr_project') or project.dr_project is None:
raise NotSpecifiedValidParam(
'project id is not supplied. you should run build command befor, or apply command'
)
with section("Training"):
featurelist_name, model_type = project.fit(**config.get_params(cmd))
# set params for successor process
ctx.obj['featurelist_name'] = featurelist_name
if model_type == 'autopilot':
sort_key = Utils.get_appropriate_dataset(project.cv_method,
project.validation_type,
project.validation_params)
ctx.obj['model_id'] = project.search_models(
featurelist_name=featurelist_name, sort_key=sort_key)[0].id
else:
ctx.obj['model_id'] = config.get_param(cmd, param='model_id')
click.echo("fit command is succeed.")
click.echo(f"'{model_type}' with featurelist: '{featurelist_name}'")
click.echo(f"model_id: {ctx.obj['model_id']}")
def get_project(
ctx,
credential, # shared options
project_id,
verbose):
# FIXME: awful
project = Project(project_id=project_id)
metric = project.metric
click.echo("### params")
for k, v in yaml.load(project.to_yml()).items():
click.echo(f"{k} : {v}")
click.echo("\n### feature list")
for featurelist in project.dr_project.get_featurelists():
click.echo(f"* {featurelist.name}")
if verbose:
data = []
for feature, attr in project.get_features(
featurelist.name).items():
d = [feature]
for k, v in attr.items():
d.append(v)
data.append(d)
else:
columns = ['name'] + list(attr.keys())
Utils.prettyprint_table(columns, data, [24])
click.echo()
click.echo(f"### top 10 models with {project.metric}")
sort_key = Utils.get_appropriate_dataset(project.cv_method,
project.validation_type,
project.validation_params)
models = project.search_models(featurelist_name=None,
sort_key=sort_key)[:10]
data = [(model.model_type, model.id, model.is_frozen,
model.metrics[project.metric][sort_key], model.featurelist_name)
for model in models]
columns = ['type', 'id', 'is_frozen', f"{sort_key}", 'featurelist_name']
Utils.prettyprint_table(columns, data, max_len=[16, 24, 9, 16, 16])
click.echo()
if verbose:
click.echo(f"### frozen models")
models = project.search_models(featurelist_name=None,
is_frozen=True,
sort_key=sort_key)
data = [(model.model_type, model.id, model.is_frozen,
model.metrics[project.metric][sort_key]) for model in models]
columns = ['type', 'id', 'is_frozen', f"{sort_key} : {project.metric}"]
Utils.prettyprint_table(columns, data, max_len=[16, 24, 9, 24])
def predict(
ctx,
credential, # shared options
config_path):
cmd = 'predict'
config = ctx.obj['config']
if not config.is_valid(cmds=[cmd]):
raise Exception('configuration file error')
project = Project(**config.get_params(cmd='environment'))
if not hasattr(project, 'dr_project') or project.dr_project is None:
raise NotSpecifiedValidParam(
'project id is not supplied. you should run build command befor, or apply command'
)
prediction_column = Utils.get_appropriate_prediction_column(
project.dr_project.target_type)
params = config.get_params(cmd)
model_id = config.get_param(cmd, param='model_id')
with section('Upload dataset'):
input_df = IOManager(io_type='input',
io_params=config.get_param(
cmd, param='input')).to_df()
dataset = project.upload_dataset(input_df)
click.echo(
f"#rows: {dataset.num_rows}, #columns: {dataset.num_columns}")
with section('Prediction'):
# auto select best result
if model_id is None:
sort_key = Utils.get_appropriate_dataset(project.cv_method,
project.validation_type,
project.validation_params)
model = project.search_models(sort_key=sort_key)[0]
model_id = model.id
predictions = project.predict(model_id=model_id, dataset_id=dataset.id)
if config.get_param(cmd, param='feature_impact') or config.get_param(
cmd, param='reasoncode'):
feature_impacts = project.get_feature_impact(model_id)
feature_impacts = pd.DataFrame(feature_impacts)
# feature_impacts.to_csv(f"feature_impact_{model_id}.csv", index=False)
if config.get_param(cmd, 'reasoncode'):
max_codes = config.get_param(cmd, param='max_codes') or 3
rc_job = project.get_reasoncode_job(model_id,
dataset.id,
max_codes=max_codes)
# TODO: parameterize in config
time_to_wait_for_reasoncode = 20 * 60 # sec
reasoncode = rc_job.get_result_when_complete(
time_to_wait_for_reasoncode)
reasoncodes = pd.DataFrame(reasoncode.get_all_as_dataframe())
reasoncodes.drop(columns=[prediction_column], inplace=True)
predictions = pd.merge(left=predictions,
right=reasoncodes,
on='row_id')
if config.get_param(cmd, param='merge_origin'):
predictions = merge_dataset(predictions, input_df)
with section('Output result'):
IOManager(io_type='output',
io_params=config.get_param(
cmd, param='output')).output(predictions)
with section('clearning'):
if config.get_param(cmd, param='del_dataset') is not False:
project.delete_dataset(dataset.id)