def predict(self, mode='predict', ignore_columns=[]):
predict_dataframe, model_definition = self._create_ludwig_dataframe(mode)
model_definition = self.transaction.hmd['ludwig_data']['model_definition']
model = LudwigModel.load(self.transaction.lmd['ludwig_data']['ludwig_save_path'])
if self.transaction.lmd['model_order_by'] is None:
timeseries_cols = []
else:
timeseries_cols = list(map(lambda x: x[0], self.transaction.lmd['model_order_by']))
if len(timeseries_cols) > 0:
predict_dataframe, model_definition = self._translate_df_to_timeseries_format(predict_dataframe, model_definition, timeseries_cols)
for ignore_col in ignore_columns:
try:
predict_dataframe[ignore_col] = [None] * len(predict_dataframe[ignore_col])
except:
for date_appendage in ['_year', '_month','_day']:
predict_dataframe[ignore_col + date_appendage] = [None] * len(predict_dataframe[ignore_col + date_appendage])
with disable_ludwig_output():
model = LudwigModel.load(self.transaction.lmd['ludwig_data']['ludwig_save_path'])
predictions = model.predict(data_df=predict_dataframe)
for col_name in predictions:
col_name_normalized = col_name.replace('_predictions', '')
predictions = predictions.rename(columns = {col_name: col_name_normalized})
return predictions
def predict(self, mode='predict', ignore_columns=[]):
predict_dataframe, model_definition, timeseries_cols = self._create_ludwig_dataframe(
mode)
model_definition = self.transaction.hmd['ludwig_data'][
'model_definition']
if len(timeseries_cols) > 0:
predict_dataframe, model_definition = self._translate_df_to_timeseries_format(
predict_dataframe, model_definition, timeseries_cols)
for ignore_col in ignore_columns:
try:
predict_dataframe[ignore_col] = [None] * len(
predict_dataframe[ignore_col])
except:
for date_appendage in ['_year', '_month', '_day']:
predict_dataframe[ignore_col + date_appendage] = [
None
] * len(predict_dataframe[ignore_col + date_appendage])
with disable_ludwig_output(True):
model_dir = self.get_model_dir()
model = LudwigModel.load(model_dir=model_dir)
predictions = model.predict(data_df=predict_dataframe,
gpus=self.get_useable_gpus())
for col_name in predictions:
col_name_normalized = col_name.replace('_predictions', '')
predictions = predictions.rename(
columns={col_name: col_name_normalized})
return predictions
def train(self):
training_dataframe, model_definition = self._create_ludwig_dataframe('train')
if self.transaction.lmd['model_order_by'] is None:
timeseries_cols = []
else:
timeseries_cols = list(map(lambda x: x[0], self.transaction.lmd['model_order_by']))
if len(timeseries_cols) > 0:
training_dataframe, model_definition = self._translate_df_to_timeseries_format(training_dataframe, model_definition, timeseries_cols, 'train')
with disable_ludwig_output(True):
model = LudwigModel(model_definition)
# <---- Ludwig currently broken, since mode can't be initialized without train_set_metadata and train_set_metadata can't be obtained without running train... see this issue for any updates on the matter: https://github.com/uber/ludwig/issues/295
#model.initialize_model(train_set_metadata={})
#train_stats = model.train_online(data_df=training_dataframe) # ??Where to add model_name?? ----> model_name=self.transaction.lmd['name']
if self.transaction.lmd['rebuild_model'] is True:
train_stats = model.train(data_df=training_dataframe, model_name=self.transaction.lmd['name'], skip_save_model=True)
else:
model = LudwigModel.load(self.transaction.lmd['ludwig_data']['ludwig_save_path'])
train_stats = model.train(data_df=training_dataframe, model_name=self.transaction.lmd['name'], skip_save_model=True)
#,model_load_path=self.transaction.lmd['ludwig_data']['ludwig_save_path'])
for k in train_stats['train']:
if k not in self.transaction.lmd['model_accuracy']['train']:
self.transaction.lmd['model_accuracy']['train'][k] = []
self.transaction.lmd['model_accuracy']['test'][k] = []
elif k is not 'combined':
# We should be adding the accuracy here but we only have it for combined, so, for now use that, will only affect multi-output scenarios anyway
pass
else:
self.transaction.lmd['model_accuracy']['train'][k].extend(train_stats['train'][k]['accuracy'])
self.transaction.lmd['model_accuracy']['test'][k].extend(train_stats['test'][k]['accuracy'])
'''
@ TRAIN ONLINE BIT That's not working
model = LudwigModel.load(self.transaction.lmd['ludwig_data']['ludwig_save_path'])
for i in range(0,100):
train_stats = model.train_online(data_df=training_dataframe)
# The resulting train_stats are "None"... wonderful -_-
'''
ludwig_model_savepath = os.path.join(CONFIG.MINDSDB_STORAGE_PATH, self.transaction.lmd['name'] + '_ludwig_data')
model.save(ludwig_model_savepath)
model.close()
self.transaction.lmd['ludwig_data'] = {'ludwig_save_path': ludwig_model_savepath}
self.transaction.hmd['ludwig_data'] = {'model_definition': model_definition}
def train(self):
training_dataframe, model_definition, timeseries_cols = self._create_ludwig_dataframe(
'train')
if len(timeseries_cols) > 0:
training_dataframe, model_definition = self._translate_df_to_timeseries_format(
training_dataframe, model_definition, timeseries_cols, 'train')
with disable_ludwig_output(True):
# <---- Ludwig currently broken, since mode can't be initialized without train_set_metadata and train_set_metadata can't be obtained without running train... see this issue for any updates on the matter: https://github.com/uber/ludwig/issues/295
#model.initialize_model(train_set_metadata={})
#train_stats = model.train_online(data_df=training_dataframe) # ??Where to add model_name?? ----> model_name=self.transaction.lmd['name']
ludwig_save_is_working = False
if not ludwig_save_is_working:
shutil.rmtree('results', ignore_errors=True)
if self.transaction.lmd['rebuild_model'] is True:
model = LudwigModel(model_definition)
merged_model_definition = model.model_definition
train_set_metadata = build_metadata(
training_dataframe,
(merged_model_definition['input_features'] +
merged_model_definition['output_features']),
merged_model_definition['preprocessing'])
model.initialize_model(train_set_metadata=train_set_metadata,
gpus=self.get_useable_gpus())
train_stats = model.train(
data_df=training_dataframe,
model_name=self.transaction.lmd['name'],
skip_save_model=ludwig_save_is_working,
skip_save_progress=True,
gpus=self.get_useable_gpus())
else:
model = LudwigModel.load(model_dir=self.get_model_dir())
train_stats = model.train(
data_df=training_dataframe,
model_name=self.transaction.lmd['name'],
skip_save_model=ludwig_save_is_working,
skip_save_progress=True,
gpus=self.get_useable_gpus())
for k in train_stats['train']:
if k not in self.transaction.lmd['model_accuracy']['train']:
self.transaction.lmd['model_accuracy']['train'][k] = []
self.transaction.lmd['model_accuracy']['test'][k] = []
elif k is not 'combined':
# We should be adding the accuracy here but we only have it for combined, so, for now use that, will only affect multi-output scenarios anyway
pass
else:
self.transaction.lmd['model_accuracy']['train'][k].extend(
train_stats['train'][k]['accuracy'])
self.transaction.lmd['model_accuracy']['test'][k].extend(
train_stats['test'][k]['accuracy'])
'''
@ TRAIN ONLINE BIT That's not working
model = LudwigModel.load(self.transaction.lmd['ludwig_data']['ludwig_save_path'])
for i in range(0,100):
train_stats = model.train_online(data_df=training_dataframe)
# The resulting train_stats are "None"... wonderful -_-
'''
ludwig_model_savepath = os.path.join(
CONFIG.MINDSDB_STORAGE_PATH,
self.transaction.lmd['name'] + '_ludwig_data')
if ludwig_save_is_working:
model.save(ludwig_model_savepath)
model.close()
else:
shutil.rmtree(ludwig_model_savepath, ignore_errors=True)
shutil.move(os.path.join('results',
os.listdir('results')[0]),
ludwig_model_savepath)
self.transaction.lmd['ludwig_data'] = {
'ludwig_save_path': ludwig_model_savepath
}
self.transaction.hmd['ludwig_data'] = {
'model_definition': model_definition
}
