https://community.databricks.com/t5/get-started-discussions/problem-when-use-synapse-ml-lightgbm-with-feature-store/m-p/101284#M4636 <PRE>&nbsp;</PRE><P><SPAN class="">I'm running a model using LGBM with Spark, within Pipeline, but when I log it to MlFlow using the log_model feature store function, I can't replicate the pipeline in prediction.<BR /></SPAN></P><P><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="eduardo_v_2-1733517977930.png" style="width: 976px;"><img src="https://community.databricks.com/t5/image/serverpage/image-id/13377i96CD9E314F1B175D/image-dimensions/976x61?v=v2" width="976" height="61" role="button" title="eduardo_v_2-1733517977930.png" alt="eduardo_v_2-1733517977930.png" /></span></P><P>&nbsp;</P><P><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="eduardo_v_1-1733517924811.png" style="width: 400px;"><img src="https://community.databricks.com/t5/image/serverpage/image-id/13376iC6DC8E683FE788AA/image-size/medium?v=v2&amp;px=400" role="button" title="eduardo_v_1-1733517924811.png" alt="eduardo_v_1-1733517924811.png" /></span></P><P>When I execute:</P><DIV><DIV><SPAN>predict </SPAN><SPAN>=</SPAN><SPAN> fs.score_batch(logged_model, df_pred)</SPAN></DIV><DIV><SPAN>&nbsp;display(predict);&nbsp; I have this error:</SPAN></DIV><DIV><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="eduardo_v_3-1733518156483.png" style="width: 643px;"><img src="https://community.databricks.com/t5/image/serverpage/image-id/13378i5BF234136D685A1C/image-dimensions/643x328?v=v2" width="643" height="328" role="button" title="eduardo_v_3-1733518156483.png" alt="eduardo_v_3-1733518156483.png" /></span><P>&nbsp;</P></DIV></DIV><P>&nbsp;</P><P><SPAN class="">&nbsp;</SPAN></P> Fri, 06 Dec 2024 20:52:30 GMT eduardo_v 2024-12-06T20:52:30Z https://community.databricks.com/t5/get-started-discussions/problem-when-use-synapse-ml-lightgbm-with-feature-store/m-p/101284#M4636 <PRE>&nbsp;</PRE><P><SPAN class="">I'm running a model using LGBM with Spark, within Pipeline, but when I log it to MlFlow using the log_model feature store function, I can't replicate the pipeline in prediction.<BR /></SPAN></P><P><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="eduardo_v_2-1733517977930.png" style="width: 976px;"><img src="https://community.databricks.com/t5/image/serverpage/image-id/13377i96CD9E314F1B175D/image-dimensions/976x61?v=v2" width="976" height="61" role="button" title="eduardo_v_2-1733517977930.png" alt="eduardo_v_2-1733517977930.png" /></span></P><P>&nbsp;</P><P><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="eduardo_v_1-1733517924811.png" style="width: 400px;"><img src="https://community.databricks.com/t5/image/serverpage/image-id/13376iC6DC8E683FE788AA/image-size/medium?v=v2&amp;px=400" role="button" title="eduardo_v_1-1733517924811.png" alt="eduardo_v_1-1733517924811.png" /></span></P><P>When I execute:</P><DIV><DIV><SPAN>predict </SPAN><SPAN>=</SPAN><SPAN> fs.score_batch(logged_model, df_pred)</SPAN></DIV><DIV><SPAN>&nbsp;display(predict);&nbsp; I have this error:</SPAN></DIV><DIV><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="eduardo_v_3-1733518156483.png" style="width: 643px;"><img src="https://community.databricks.com/t5/image/serverpage/image-id/13378i5BF234136D685A1C/image-dimensions/643x328?v=v2" width="643" height="328" role="button" title="eduardo_v_3-1733518156483.png" alt="eduardo_v_3-1733518156483.png" /></span><P>&nbsp;</P></DIV></DIV><P>&nbsp;</P><P><SPAN class="">&nbsp;</SPAN></P> Fri, 06 Dec 2024 20:52:30 GMT https://community.databricks.com/t5/get-started-discussions/problem-when-use-synapse-ml-lightgbm-with-feature-store/m-p/101284#M4636 eduardo_v 2024-12-06T20:52:30Z