def get_datasource_obj(self,
name=None,
id=None,
raw=False,
company_id=None):
try:
if name is not None:
datasource_record = session.query(Datasource).filter_by(
company_id=company_id, name=name).first()
else:
datasource_record = session.query(Datasource).filter_by(
company_id=company_id, id=id).first()
self.fs_store.get(
f'{company_id}@@@@@{name}',
f'datasource_{company_id}_{datasource_record.id}', self.dir)
creation_info = json.loads(datasource_record.creation_info)
if raw:
return creation_info
else:
return eval(creation_info['class'])(*creation_info['args'],
**creation_info['kwargs'])
except Exception as e:
log.error(f'Error getting datasource {name}, exception: {e}')
return None
def start_analysis(self, name):
datasource_record = session.query(Datasource).filter_by(
company_id=self.company_id, name=name).first()
if datasource_record.analysis is not None:
return None
semaphor_record = session.query(Semaphor).filter_by(
company_id=self.company_id,
entity_id=datasource_record.id,
entity_type='datasource').first()
if semaphor_record is None:
semaphor_record = Semaphor(company_id=self.company_id,
entity_id=datasource_record.id,
entity_type='datasource',
action='write')
session.add(semaphor_record)
session.commit()
else:
return
try:
analysis = self.mindsdb_native.analyse_dataset(
self.get_datasource_obj(name, raw=True))
datasource_record = session.query(Datasource).filter_by(
company_id=self.company_id, name=name).first()
datasource_record.analysis = json.dumps(analysis)
session.commit()
except Exception as e:
log.error(e)
finally:
semaphor_record = session.query(Semaphor).filter_by(
company_id=self.company_id,
entity_id=datasource_record.id,
entity_type='datasource').first()
session.delete(semaphor_record)
session.commit()
def delete(self, name):
try:
session.query(StreamDB).filter_by(company_id=COMPANY_ID,
name=name).delete()
session.commit()
except Exception as e:
log.error(e)
abort(400, str(e))
return '', 200
def delete_stream(self, predictor):
"""Deletes stream from database and stops it work by
setting up a special threading.Event flag."""
stream_name = f"{self.name}_{predictor}"
self.log.debug(f"Integration {self.name}: deleting {stream_name}")
session.query(Stream).filter_by(company_id=self.company_id, integration=self.name, name=stream_name).delete()
session.commit()
if stream_name in self.streams:
self.streams[stream_name].set()
del self.streams[stream_name]
def get_analysis(self, name, company_id=None):
dataset_record = session.query(Dataset).filter_by(
company_id=company_id, name=name).first()
if dataset_record.analysis_id is None:
return None
analysis_record = session.query(Analysis).get(
dataset_record.analysis_id)
if analysis_record is None:
return None
analysis = json.loads(analysis_record.analysis)
return analysis
def get_db_integration(name,
company_id,
sensitive_info=True,
case_sensitive=False):
if case_sensitive:
integration_record = session.query(Integration).filter_by(
company_id=company_id, name=name).first()
else:
integration_record = session.query(Integration).filter(
(Integration.company_id == company_id)
& (func.lower(Integration.name) == func.lower(name))).first()
return _get_integration_record_data(integration_record, sensitive_info)
def get(self, id=None, name=None, company_id=None):
if id is not None:
records = session.query(View).filter_by(
id=id, company_id=company_id).all()
elif name is not None:
records = session.query(View).filter_by(
name=name, company_id=company_id).all()
if len(records) == 0:
raise Exception(f"Can't find view with name/id: {name}/{id}")
elif len(records) > 1:
raise Exception(
f"There are multiple views with name/id: {name}/{id}")
record = records[0]
return self._get_view_record_data(record)
def get_files_names(self, company_id=None):
""" return list of files names
"""
return [
x[0]
for x in session.query(File.name).filter_by(company_id=company_id)
]
def _unlock_predictor(self, id: int) -> None:
from mindsdb.interfaces.storage.db import session, Semaphor
semaphor_record = session.query(Semaphor).filter_by(
entity_id=id, entity_type='predictor').first()
if semaphor_record is not None:
session.delete(semaphor_record)
session.commit()
def make_prediction(self):
predict_record = session.query(DBPredictor).filter_by(
company_id=self.company_id, name=self.predictor).first()
if predict_record is None:
log.error(
f"Error creating stream: requested predictor {self.predictor} is not exist"
)
return
while not self.stop_event.wait(0.5):
try:
msg_str = next(self.consumer)
when_data = json.loads(msg_str.value)
result = self.native_interface.predict(self.predictor,
self.format_flag,
when_data=when_data)
log.error(f"STREAM: got {result}")
for res in result:
in_json = json.dumps({"prediction": res})
to_send = in_json.encode('utf-8')
log.error(f"sending {to_send}")
self.producer.send(self.stream_out_name, to_send)
except StopIteration:
pass
log.error("Stopping stream..")
self.producer.close()
self.consumer.close()
session.close()
def get_all(self, company_id=None):
view_records = session.query(View).filter_by(
company_id=company_id).all()
views_dict = {}
for record in view_records:
views_dict[record.name] = self._get_view_record_data(record)
return views_dict
def make_timeseries_predictions(self):
log.error("STREAM: running 'make_timeseries_predictions'")
predict_record = session.query(DBPredictor).filter_by(
company_id=self.company_id, name=self.predictor).first()
if predict_record is None:
log.error(
f"Error creating stream: requested predictor {self.predictor} is not exist"
)
return
self.target = self._get_target()
self.window = self._get_window_size()
self.gb = self._get_gb()
self.dt = self._get_dt()
while not self.stop_event.wait(0.5):
try:
msg_str = next(self.consumer)
when_data = json.loads(msg_str.value)
self.to_cache(when_data)
except StopIteration:
pass
log.error("Stopping stream..")
self.producer.close()
self.consumer.close()
session.close()
def save_datasource(self, name, source_type, source, file_path=None, company_id=None):
if source_type == 'file' and (file_path is None):
raise Exception('`file_path` argument required when source_type == "file"')
datasource_record = session.query(Datasource).filter_by(company_id=company_id, name=name).first()
while datasource_record is not None:
raise Exception(f'Datasource with name {name} already exists')
try:
datasource_record = Datasource(
company_id=company_id,
name=name,
datasources_version=mindsdb_datasources.__version__,
mindsdb_version=mindsdb_version
)
session.add(datasource_record)
session.commit()
ds_meta_dir = os.path.join(self.dir, f'{company_id}@@@@@{name}')
os.mkdir(ds_meta_dir)
ds, creation_info = self.create_datasource(source_type, source, file_path, company_id, ds_meta_dir)
if hasattr(ds, 'get_columns') and hasattr(ds, 'get_row_count'):
try:
column_names = ds.get_columns()
row_count = ds.get_row_count()
except Exception:
df = ds.df
column_names = list(df.keys())
row_count = len(df)
else:
df = ds.df
column_names = list(df.keys())
row_count = len(df)
if '' in column_names or len(column_names) != len(set(column_names)):
shutil.rmtree(ds_meta_dir)
raise Exception('Each column in datasource must have unique non-empty name')
datasource_record.creation_info = json.dumps(creation_info)
datasource_record.data = json.dumps({
'source_type': source_type,
'source': source,
'row_count': row_count,
'columns': [dict(name=x) for x in column_names]
})
self.fs_store.put(f'{company_id}@@@@@{name}', f'datasource_{company_id}_{datasource_record.id}', self.dir)
session.commit()
except Exception as e:
log.error(f'Error creating datasource {name}, exception: {e}')
try:
self.delete_datasource(name, company_id=company_id)
except Exception:
pass
raise e
return self.get_datasource_obj(name, raw=True, company_id=company_id)
def run_fit(predictor_id: int, df: pd.DataFrame) -> None:
try:
predictor_record = session.query(db.Predictor).filter_by(id=predictor_id).first()
assert predictor_record is not None
fs_store = FsStore()
config = Config()
predictor_record.data = {'training_log': 'training'}
session.commit()
predictor: lightwood.PredictorInterface = lightwood.predictor_from_code(predictor_record.code)
predictor.learn(df)
session.refresh(predictor_record)
fs_name = f'predictor_{predictor_record.company_id}_{predictor_record.id}'
pickle_path = os.path.join(config['paths']['predictors'], fs_name)
predictor.save(pickle_path)
fs_store.put(fs_name, fs_name, config['paths']['predictors'])
predictor_record.data = predictor.model_analysis.to_dict()
predictor_record.dtype_dict = predictor.dtype_dict
session.commit()
dbw = DatabaseWrapper(predictor_record.company_id)
mi = ModelInterfaceWrapper(ModelInterface(), predictor_record.company_id)
dbw.register_predictors([mi.get_model_data(predictor_record.name)])
except Exception as e:
session.refresh(predictor_record)
predictor_record.data = {'error': f'{traceback.format_exc()}\nMain error: {e}'}
session.commit()
raise e
def get_logs(min_timestamp, max_timestamp, context, level, log_from, limit):
logs = session.query(Log).filter(
Log.company_id == os.environ.get('MINDSDB_COMPANY_ID', None),
Log.created_at > min_timestamp
)
if max_timestamp is not None:
logs = logs.filter(Log.created_at < max_timestamp)
if context is not None:
# e.g. datasource/predictor and assoicated id
pass
if level is not None:
logs = logs.filter(Log.log_type == level)
if log_from is not None:
# mindsdb/native/lightwood/all
pass
if limit is not None:
logs = logs.limit(limit)
logs = [fmt_log_record(x) for x in logs]
return logs
def get_analysis(self, name, company_id=None):
datasource_record = session.query(Datasource).filter_by(
company_id=company_id, name=name).first()
if datasource_record.analysis is None:
return None
analysis = json.loads(datasource_record.analysis)
return analysis
def get_ai_tables(self):
''' get list of ai tables
'''
aitable_records = [
x.__dict__ for x in session.query(AITable).filter_by(
company_id=self.company_id)
]
return aitable_records
def should_i_exist(self):
config_record = session.query(Configuration).filter_by(
company_id=self.company_id).first()
if config_record is None:
return False
integrations = json.loads(config_record.data)["integrations"]
if self.name not in integrations:
return False
return True
def start_analysis(self, name, company_id=None):
dataset_record = session.query(Dataset).filter_by(
company_id=company_id, name=name).first()
if dataset_record.analysis_id is not None:
return None
semaphor_record = session.query(Semaphor).filter_by(
company_id=company_id,
entity_id=dataset_record.id,
entity_type='dataset').first()
if semaphor_record is None:
semaphor_record = Semaphor(company_id=company_id,
entity_id=dataset_record.id,
entity_type='dataset',
action='write')
session.add(semaphor_record)
session.commit()
else:
return
try:
analysis = self.model_interface.analyse_dataset(
ds=self.get_datasource_obj(name,
raw=True,
company_id=company_id),
company_id=company_id)
dataset_record = session.query(Dataset).filter_by(
company_id=company_id, name=name).first()
analysis_record = Analysis(
analysis=json.dumps(analysis, cls=CustomJSONEncoder))
session.add(analysis_record)
session.flush()
dataset_record.analysis_id = analysis_record.id
session.commit()
except Exception as e:
log.error(e)
finally:
semaphor_record = session.query(Semaphor).filter_by(
company_id=company_id,
entity_id=dataset_record.id,
entity_type='dataset').first()
session.delete(semaphor_record)
session.commit()
def get_db_integrations(company_id, sensitive_info=True):
integration_records = session.query(Integration).filter_by(
company_id=company_id).all()
integration_dict = {}
for record in integration_records:
if record is None or record.data is None:
continue
integration_dict[record.name] = _get_integration_record_data(
record, sensitive_info)
return integration_dict
def get_file_meta(self, name, company_id=None):
file_record = session.query(File).filter_by(company_id=company_id,
name=name).first()
if file_record is None:
return None
return {
'name': file_record.name,
'columns': file_record.columns,
'row_count': file_record.row_count
}
def modify_db_integration(name, data, company_id):
integration_record = session.query(Integration).filter_by(
company_id=company_id, name=name).first()
old_data = deepcopy(integration_record.data)
for k in old_data:
if k not in data:
data[k] = old_data[k]
integration_record.data = data
session.commit()
def get_datasources(self, name=None):
datasource_arr = []
if name is not None:
datasource_record_arr = session.query(Datasource).filter_by(
company_id=self.company_id, name=name)
else:
datasource_record_arr = session.query(Datasource).filter_by(
company_id=self.company_id)
for datasource_record in datasource_record_arr:
try:
datasource = json.loads(datasource_record.data)
datasource['created_at'] = datasource_record.created_at
datasource['updated_at'] = datasource_record.updated_at
datasource['name'] = datasource_record.name
datasource['id'] = datasource_record.id
datasource_arr.append(datasource)
except Exception as e:
log.error(e)
return datasource_arr
def delete_file(self, name, company_id):
file_record = session.query(File).filter_by(company_id=company_id,
name=name).first()
if file_record is None:
return None
file_id = file_record.id
session.delete(file_record)
session.commit()
self.fs_store.delete(f'file_{company_id}_{file_id}')
return True
def save_datasource(self,
name,
source_type,
source=None,
file_path=None,
company_id=None):
dataset_record = session.query(Dataset).filter_by(
company_id=company_id, name=name).first()
while dataset_record is not None:
raise Exception(f'Dataset with name {name} already exists')
if source_type == 'views':
source_type = 'view_query'
elif source_type == 'files':
source_type = 'file'
try:
dataset_record = Dataset(
company_id=company_id,
name=name,
datasources_version=mindsdb_datasources.__version__,
mindsdb_version=mindsdb_version)
session.add(dataset_record)
session.commit()
ds, creation_info = self.create_datasource(source_type, source,
file_path, company_id)
ds_meta = self._get_ds_meta(ds)
column_names = ds_meta['column_names']
row_count = ds_meta['row_count']
dataset_record.ds_class = creation_info['class']
dataset_record.creation_info = json.dumps(creation_info)
dataset_record.data = json.dumps({
'source_type':
source_type,
'source':
source,
'row_count':
row_count,
'columns': [dict(name=x) for x in column_names]
})
session.commit()
except Exception as e:
log.error(f'Error creating dataset {name}, exception: {e}')
try:
self.delete_datasource(name, company_id=company_id)
except Exception:
pass
raise e
return self.get_datasource_obj(name, raw=True, company_id=company_id)
def get_analysis(self, name):
datasource_record = session.query(Datasource).filter_by(
company_id=self.company_id, name=name).first()
if datasource_record.analysis is None:
datasource_record.analysis = json.dumps(
self.mindsdb_native.analyse_dataset(
self.get_datasource_obj(name)))
session.commit()
analysis = json.loads(datasource_record.analysis)
return analysis
def stop_deleted_streams(self):
existed_streams = session.query(Stream).filter_by(company_id=self.company_id, integration=self.name)
actual_streams = [x.name for x in existed_streams]
for stream in self.streams.copy():
if stream not in actual_streams:
# this stream is still running but it has been deleted from database.
# need to stop it.
self.log.error(f"INTEGRATION {self.name}: deleting {stream} stream.")
self.streams[stream].set()
del self.streams[stream]
def get_datasets(self, name=None, company_id=None):
dataset_arr = []
if name is not None:
dataset_record_arr = session.query(Dataset).filter_by(
company_id=company_id, name=name)
else:
dataset_record_arr = session.query(Dataset).filter_by(
company_id=company_id)
for dataset_record in dataset_record_arr:
try:
if dataset_record.data is None:
continue
dataset = json.loads(dataset_record.data)
dataset['created_at'] = dataset_record.created_at
dataset['updated_at'] = dataset_record.updated_at
dataset['name'] = dataset_record.name
dataset['id'] = dataset_record.id
dataset_arr.append(dataset)
except Exception as e:
log.error(e)
return dataset_arr
def delete_datasource(self, name, company_id=None):
datasource_record = Datasource.query.filter_by(company_id=company_id,
name=name).first()
if not Config()["force_datasource_removing"]:
linked_models = Predictor.query.filter_by(
company_id=company_id,
datasource_id=datasource_record.id).all()
if linked_models:
raise Exception(
"Can't delete {} datasource because there are next models linked to it: {}"
.format(name, [model.name for model in linked_models]))
session.query(Semaphor).filter_by(company_id=company_id,
entity_id=datasource_record.id,
entity_type='datasource').delete()
session.delete(datasource_record)
session.commit()
self.fs_store.delete(f'datasource_{company_id}_{datasource_record.id}')
try:
shutil.rmtree(os.path.join(self.dir, f'{company_id}@@@@@{name}'))
except Exception:
pass
def _save(self):
self._db_config = _null_to_empty(self._db_config)
config_record = session.query(Configuration).filter_by(
company_id=self.company_id).first()
if config_record is not None:
config_record.data = json.dumps(self._db_config)
else:
config_record = Configuration(company_id=self.company_id,
data=json.dumps(self._db_config))
session.add(config_record)
session.commit()
