Loading demo links...
What to study for each CDP-6001 domain
Cloudera Machine Learning
Covers working in Cloudera Machine Learning workspaces and projects, including sessions, jobs, and collaborative development. It also addresses experiments, Applied ML Prototypes (AMPs), data visualizations, runtimes, data connections, and GPU-enabled workloads.
Key skills
Workspaces, projects, experiments, AMP accelerators, data visualizations, runtimes, GPUs, data connections, resource profiles
Spark
Covers Apache Spark fundamentals for machine learning data preparation, centered on DataFrames and Spark SQL operations. It also addresses common file types such as Parquet, ORC, CSV, and JSON, plus window functions for ranking and period-over-period analysis.
Key skills
DataFrames, file types (Parquet, ORC, CSV, JSON), window functions, partitioning, lazy evaluation, caching
Spark MLlib
Covers building machine learning workflows with Spark MLlib, including feature transformers, estimators, and pipelines. It also addresses fitting and evaluating models and model selection and tuning with cross-validation and parameter grids.
Key skills
Pipelines, model selection and tuning, CrossValidator, TrainValidationSplit, fitting and evaluating models, evaluators, feature engineering
Deploying a Machine Learning Model
Covers deploying trained models in Cloudera Machine Learning as applications and REST APIs for programmatic scoring. It also addresses autoscaling and performance, model metrics and monitoring for drift and degradation, and MLflow tracking and model management.
Key skills
Applications and APIs, autoscaling and performance, model metrics and monitoring, MLflow, model versioning and rollback
Deep Learning and General Machine Learning
Covers general machine learning concepts that underpin work in Cloudera Machine Learning and Spark MLlib, including supervised and unsupervised learning. It also addresses common algorithms for classification, regression, clustering, ensembles, and deep learning for images and sequences.
Key skills
General machine learning, supervised and unsupervised learning, common algorithms, overfitting, precision and recall, neural networks