mindsdb_native
mindsdb_native copied to clipboard
mindsdb
Machine Learning in one line of code
NOTE: should try and replicate in new lightwood as well ``` Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/mindsdb_native/libs/controllers/transaction.py", line 213, in _run input_data=self.input_data) File "/usr/local/lib/python3.6/dist-packages/mindsdb_native/libs/controllers/transaction.py", line 170, in _call_phase_module ret...
This is currently not being enforced, and model analysis might be ran on an unbalanced fold, like this: 
Model training fails because the datasource from Cassandra DB has an id as a UUID. ``` ERROR:mindsdb-logger-469ed6e6-eadf-11eb-8668-fdcec95042d5---no_report:/home/zoran/MyProjects/mindsdb-examples/mongodb/mdb/lib/python3.7/site-packages/mindsdb_native/libs/controllers/transaction.py:173 - Could not load module TypeDeductor ERROR:mindsdb-logger-469ed6e6-eadf-11eb-8668-fdcec95042d5---no_report:/home/zoran/MyProjects/mindsdb-examples/mongodb/mdb/lib/python3.7/site-packages/mindsdb_native/libs/controllers/transaction.py:263 - argument of type 'UUID' is...
In time series tasks, the model analysis phase should expose: - forecasts - actual series values - accuracy metrics (within bounds, balanced acc score, MSE, sMAPE, etc.) And particularly for...
A client is having issues when running the data_analysis using Mongo as a data source. Atm, we don't have an example of the data but if that is a blocker...
@AdamMCarrigan is getting the following error: `The lightwood model backend is unable to handle data of type None and subtype None !` when training a predictor with the SO dataset....
Scipy dependency fails to install and breaks the install on windows and osx 3.9
* Mindsdb version: current stable 2.41.0 For group-bys that have a high amount of combinations (e.g. origin-destination airports) it might be that the available data is less than the needed...