Default notebooks
As a data scientist, use the default Jupyter Notebooks as templates to build and train instances of a predictive model. The results of that model are used in Maximo Predict and Maximo Health.
The following notebook types are available. All of the notebooks are IBM Watson® Studio notebooks and use Python.
With every Python upgrade, new notebook templates and PMlib files must be downloaded, and models need to retrained so that the notebooks continue working.
PMI use Maximo Predict or Maximo Health pipelines. After the WS and DQLearn notebooks are used to test and determine data quality, use the PMI notebooks to build models for Maximo Predict or Maximo Health.
Additionally, you can configure custom notebooks that are either extensions of default notebooks or completely custom, but the models must be deployed in Watson™ Machine Learning.
Maximo Health includes asset class-specific notebooks that can be used to calculate scores or complete dissolved gas analysis (DGA). For predictions or anomaly detection, Maximo Health uses the same default notebooks as Maximo Predict.
Notebooks with Explainable_ in their file name can be used with the explainability service. Notebooks with ModelLifecycle_ in their file name can be used with the monitoring and testing service.
The following table describes the default notebooks. For more information, see Getting started for data scientists.
Notebook | Use case |
---|---|
AutoInspect_TS_MultiVariate.ipynb | Use a DQLearn pipeline for a multivariate data set. |
AutoInspect_TS_UniVariate.ipynb | Use a DQLearn pipeline for a univariate data set. |
AutoInspection_TS_Label.ipynb | Use a DQLearn pipeline for time series characteristics. |
Auto_Imputation.ipynb | Automatic imputation of missing values in a data set that has a single index, asset ID. |
Auto_Imputation_MultiIndex.ipynb | Automatic imputation of missing values in a data set that has multiple columns in the index, such as asset ID and timestamp or site. |
Custom0-RUL-LTSM-WML.ipynb | Train a remaining useful life (RUL) model and deploying the model on Watson Machine Learning. |
Custom1-RUL-LoadData.ipynb | Load data for an RUL model. |
Custom2-RUL-Scoring.ipynb | Invoke an RUL model that is deployed on Watson Machine Learning from Maximo Monitor to score new data. |
Custom3-RUL-in-Predict-UI.ipynb | Display results from an RUL model in Maximo Predict. |
DQLearn_AD.ipynb | Use a DQLearn a pipeline for anomaly detection. |
DQLearn_FPA.ipynb | Use a DQLearn pipeline for failure probability analysis. |
DQLearn_Label.ipynb | Use a DQLearn pipeline for failure labels. |
DQLearn_MissingPatternAnalysis.ipynb | Use a DQLearn pipeline for missing value analysis. |
DQLearn_Transactional_RegularUI.ipynb | Use a DQLearn pipeline for any data set that is not a time series data set and generate graphical output. |
DQLearn_Timeseries_Pipeline.ipynb | Use a DQLearn pipeline for univariate time series data with notebook-level interactive plots. |
DQLearn_Timeseries_Pipeline_MultiColumn.ipynb | Use a DQLearn pipeline for multivariate time series data by using a pipeline. |
DQLearn_Transactional_MinimalUI.ipynb | Use a DQLearn pipeline for independent and identically distributed (IID) data with minimal notebook-level plots. |
DQLearn_Transactional_Pipeline.ipynb | Use a DQLearn pipeline for IID data by using a pipeline. |
DQLearn_TimeSeries_RegularUI.ipynb | Use a DQLearn pipeline for IID data by using a pipeline with minimal notebook-level plots. |
Explainable_FailureProbability_Dataloader.ipynb | Load data for an explainable failure probability analysis model. |
Explainable_FailureProbability_Training.ipynb | Train and deploy a failure probability analysis model that includes explainability. |
Explainable_FailureProbability_Scoring.ipynb | Score the explainable failure probability analysis model. |
Explainble_FailureProbability_Results.ipynb | Retrieve and display explanations for a failure probability analysis model. |
Explainable_PredictedFailureDate_Dataloader.ipynb | Load data for an explainable predicted failure date model or time to event model. |
Explainable_PredictedFailureDate_Training.ipynb | Train and deploy a predicted failure date model or time to event model that includes explainability. |
Explainable_PredictedFailureDate_Scoring.ipynb | Score the explainable predicted failure date model or time to event model. |
Explainable_PredictedFailureDate_Results.ipynb | Retrieve and display explanations for explainable predicted failure date model or time to event model. |
Explainable_Unsupervised_AnomalyDetection_DataLoader.ipynb | Load data for an unsupervised anomaly detection model that use the explainability service. |
Explainable_Unsupervised_AnomalyDetection_Training.ipynb | Train a model that use the explainability service and saliency maps for unsupervised anomaly detection. |
Explainable_Unsupervised_AnomalyDetection_Scoring.ipynb | Score for unsupervised anomaly detection that generates explanations by using saliency maps. |
Explainable_Unsupervised_AnomalyDetection_Results.ipynb | Retrieve explanations for unsupervised anomaly detection results by using saliency maps. |
Explainable_Regression_using_SHAP.ipynb | Use the SHAP technique to generate explanations for an example regression model. |
FastStart2021Loader-New.ipynb | Load data to train different models. |
IBM-Asset-HealthScore-Forecast-Sample-6.0.0.ipynb | Train prediction model with historical health scores for assets and deploy the model to WML. |
IBM-customized-score-sample-6.0.0.ipynb | Customize a score type sample. |
IBM-future-score-from-csv-sample-6.0.0.ipynb | Read future score from direct input or a CSV file. |
IBM-future-score-from-predict-sample-6.0.0.ipynb | Read predicted health score from Watson Machine Learning. |
PMI - Anomaly Detection-UnSupervised.ipynb | Detect anomalies by using unsupervised machine learning techniques. |
PMI - Anomaly Detection-SemiSupervised.ipynb | Detect anomalies by using semi-supervised machine learning techniques. This notebook requires labeled data. |
PMI - End of Life Curve.ipynb | Determine the end of life curve or asset degradation curve for a group of assets. |
PMI - Failure Probability-Binary Classification.ipynb | Complete binary-type failure classification. |
PMI - Failure Probability-MultiClassification.ipynb | Complete multiple-type failure classification. |
PMI - Predicted Failure Date-Smart Regression.ipynb | Predict failure dates by using a smart regression pipeline. |
PMI - Predicted Failure Date.ipynb | Predict failure date by using survive analysis techniques. |
PMI - Using Corrective Maintenance.ipynb | Complete a failure pattern analysis by using corrective maintenance records instead of failure records. |
PMI_Use_Aggregated_Data_in_Monitor | Use aggregated data in Maximo Monitor to predict failure dates. |
WS - SmartClassificationExample.ipynb | Use a smart classification pipeline. |
WS - SmartRegressionExample.ipynb | Use a smart regression pipeline. |
WS - Anomaly Detection - SemiSupervised.ipynb | Detect anomalies by using semi-supervised machine learning techniques. This notebook requires labeled data. |
WS - Anomaly Detection - UnSupervised.ipynb | Detect anomalies by using unsupervised machine learning techniques. |
WS - End of Life Curve.ipynb | Determine the end of life curve or asset degradation curve for a group of assets. |
WS - Failure Probability - BinaryClassification.ipynb | Complete binary-type failure classification. |
WS - Failure Probability - MultiClassification.ipynb | Complete multiple-type failure classification. |
WS - Predicted Failure Date.ipynb | Predict failure dates or time to an event by using survival analysis techniques. |
WS - Root Cause Analysis.ipynb | Determine factors that caused failure and generate a failure contribution breakdown. |
PMI - Model Development Tutorial.ipynb | Get started developing models by using the default notebooks. |
PMI - Custom Model Development | Get started developing models by using custom notebooks. |
PMI - Multiclass example.ipynb | Multiclassification for failure prediction that uses multiple modes of failures. |
ModelLifecycle_DataLoader.ipynb | Manage model lifecycle and drift for models. |
ModelLifecycle_FailureProbability_Training.ipynb | Train a model for failure probability and by using the monitoring and testing service. |
ModelLifecycle_FailureProbability_Scoring.ipynb | Determine failure probability and enable feedback from the monitoring and testing service as part of scoring. |
ModelLifecycle_FailureProbability_FeedbackLogging.ipynb | Provide user feedback for failure probability to determine data and model drift. |
ModelLifecycle_FailureProbability_DriftCharts.ipynb | Retrieve data and model drift scores from the database and visualizing the drifts. |
ModelLifecycle_PredictedFailureDate_Training.ipynb | Train a model for predicted failure dates and using the monitoring and testing service. |
ModelLifecycle_PredictedFailureDate_Scoring.ipynb | Determine predicted failure dates and enable feedback from the monitoring and testing service as part of scoring. |
ModelLifecycle_PredictedFailureDate_FeedbackLogging.ipynb | Provide user feedback for predicted failure dates to determine data and model drift. |