jprdonnelly/MachineLearningNotebooks
1
0
Fork 0
mirror of https://github.com/Azure/MachineLearningNotebooks.git synced 2025-12-21 01:55:07 -05:00
Code Issues Projects Releases Wiki Activity

update samples from Release-168 as a part of SDK release

Browse Source
This commit is contained in:
amlrelsa-ms
2022-12-05 17:52:07 +00:00
parent 38d5743bbb
commit 4404e62f58
44 changed files with 187 additions and 814 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
how-to-use-azureml/automated-machine-learning/forecasting-backtest-many-models/auto-ml-forecasting-backtest-many-models.ipynb
View File

@@ -387,6 +387,7 @@
"| **node_count** | The number of compute nodes to be used for running the user script. We recommend to start with 3 and increase the node_count if the training time is taking too long. |\n",
"| **process_count_per_node** | Process count per node, we recommend 2:1 ratio for number of cores: number of processes per node. eg. If node has 16 cores then configure 8 or less process count per node or optimal performance. |\n",
"| **train_pipeline_parameters** | The set of configuration parameters defined in the previous section. |\n",
"| **run_invocation_timeout** | Maximum amount of time in seconds that the ``ParallelRunStep`` class is allowed. This is optional but provides customers with greater control on exit criteria. This must be greater than ``experiment_timeout_hours`` by at least 300 seconds. |\n",
"\n",
"Calling this method will create a new aggregated dataset which is generated dynamically on pipeline execution."
]
@@ -529,6 +530,8 @@
" target_column_name=TARGET_COLNAME,\n",
")\n",
"\n",
"output_file_name = \"parallel_run_step.csv\"\n",
"\n",
"inference_steps = AutoMLPipelineBuilder.get_many_models_batch_inference_steps(\n",
" experiment=experiment,\n",
" inference_data=test_data,\n",
@@ -540,6 +543,7 @@
" train_run_id=training_run.id,\n",
" train_experiment_name=training_run.experiment.name,\n",
" inference_pipeline_parameters=mm_parameters,\n",
" append_row_file_name=output_file_name,\n",
")"
]
},
@@ -587,18 +591,21 @@
"source": [
"from azureml.contrib.automl.pipeline.steps.utilities import get_output_from_mm_pipeline\n",
"\n",
"PREDICTION_COLNAME = \"Predictions\"\n",
"forecasting_results_name = \"forecasting_results\"\n",
"forecasting_output_name = \"many_models_inference_output\"\n",
"forecast_file = get_output_from_mm_pipeline(\n",
" inference_run, forecasting_results_name, forecasting_output_name\n",
" inference_run, forecasting_results_name, forecasting_output_name, output_file_name\n",
")\n",
"df = pd.read_csv(forecast_file, delimiter=\" \", header=None, parse_dates=[0])\n",
"df.columns = list(X_train.columns) + [\"predicted_level\"]\n",
"df = pd.read_csv(forecast_file, parse_dates=[0])\n",
"print(\n",
" \"Prediction has \", df.shape[0], \" rows. Here the first 10 rows are being displayed.\"\n",
")\n",
"# Save the scv file with header to read it in the next step.\n",
"df.rename(columns={TARGET_COLNAME: \"actual_level\"}, inplace=True)\n",
"# Save the csv file to read it in the next step.\n",
"df.rename(\n",
" columns={TARGET_COLNAME: \"actual_level\", PREDICTION_COLNAME: \"predicted_level\"},\n",
" inplace=True,\n",
")\n",
"df.to_csv(os.path.join(forecasting_results_name, \"forecast.csv\"), index=False)\n",
"df.head(10)"
]