Databricks Certified Machine Learning Associate Flashcards¶

90 minutes

48 scored multiple-choice and multiple-selection (up to 10 more unscored)

Not published by Databricks

$200 USD plus applicable taxes (stated by Databricks, checked 2026-11-07)

Online proctored or test center

2 years

a Databricks Runtime variant that comes with machine learning and deep learning libraries pre-installed and tested together, so a team does not build the environment itself.

the cluster access mode that is set automatically when you pick the machine learning runtime, and that Unity Catalog data access from ML compute requires.

a Databricks capability that prepares data, trains and tunes models across several algorithms, picks the best, and generates editable notebooks for the trials.

the generated source code for a single AutoML trial, which you can review, reproduce and modify.

a Delta table with a primary key (and optionally a time series column) that stores computed features for reuse in training and inference.

the Python client in databricks.feature_engineering used to create, write, read and tag feature tables and to build training sets.

the object that tells a training set which table, which features and which lookup key to join in.

the governed Delta table used for training and batch scoring, queried in bulk.

a low-latency store holding the latest feature values so a real-time endpoint can look features up by key.

one execution of model training code, which records parameters, metrics, tags and artifacts.

a named group of related runs that you can compare and filter.

the MLflow client call that queries runs, with order_by such as metrics.rmse ASC, and returns them (as a pandas DataFrame from mlflow.search_runs).

MLflow's automatic capture of parameters, metrics and the model for supported libraries, the easiest way to start tracking.

the registry that stores models as three-level named, versioned Unity Catalog objects with centralized access control, auditing, lineage and cross-workspace discovery.

a mutable, named reference (such as champion) to one version of a registered model, set with set_registered_model_alias.

a key-value label on a registered model or model version, set with set_model_version_tag and removed with delete_model_version_tag.

the convention of giving the serving version the champion alias and the candidate the challenger alias, and promoting by moving champion to the winner.

the two promotion strategies; code promotion is the usual recommendation, and model promotion fits cases where retraining in production is not possible.

a Spark DataFrame method that returns count, mean, stddev, min, quartiles and max for the columns it is called on, or the statistics you ask for.

the Databricks notebook utility that displays summary statistics and charts for a Spark or pandas DataFrame, with approximate results unless precise=True.

an outlier rule that removes values more than a chosen number of standard deviations from the mean; it assumes roughly normal data and is distorted by the outliers it seeks.

an outlier rule that removes values below Q1 minus 1.5 times the IQR or above Q3 plus 1.5 times the IQR; it is based on percentiles and is robust to skew.

filling missing numeric values with the column mean; suited to symmetric distributions and sensitive to outliers.

filling missing numeric values with the column median; preferred for skewed data or data with outliers.

filling missing values with the most frequent value; the standard choice for categorical features.

turning a categorical feature into one binary column per category, so a numeric model does not read a false order into the values.

a Spark ML estimator that maps string labels to numeric indices (most frequent label first by default).

a Spark ML estimator that turns category indices into binary vectors, usually applied after StringIndexer.

applying a logarithm to a right-skewed, strictly positive variable to compress large values and make its distribution closer to symmetric.

the natural log of one plus the value, a common way to log-transform data that contains zeros.

give the minority class a higher misclassification weight (class_weight in scikit-learn, a weight column in Spark ML). This is the direct answer to "mitigate the bias toward the majority" in the guide's sample question.

oversample the minority class (including synthetic samples such as SMOTE) or undersample the majority.

judge by precision, recall, F1 or area under the precision-recall curve, and move the threshold.

keep the class ratio in every training and validation split.

a training set where one class is far more common than another, so a model can score high accuracy while missing the minority class.

a train/validation split that preserves the class proportions in every part.

a Spark ML component with a transform() method that turns one DataFrame into another, usually by adding columns.

a Spark ML component with a fit() method that learns from a DataFrame and returns a Model, which is a Transformer.

an ordered chain of transformers and estimators that is itself an estimator; fitting it returns a PipelineModel.

a Python library for hyperparameter search; fmin minimizes an objective over a search space (not maintained upstream, and not in Databricks Runtime ML after 16.4 LTS ML).

the Hyperopt function that runs a search, taking an objective function, a search space, an algorithm, max_evals and a trials object.

the Hyperopt trials class that runs single-machine model trials in parallel as Spark tasks; do not use it with distributed algorithms such as MLlib.

tuning by sampling hyperparameter combinations at random from the allowed ranges.

tuning that uses the results of earlier trials to choose the next hyperparameters, as TPE does.

estimating performance by training k times, each time validating on a different fold, and averaging the scores.

estimating performance from one split of the data; cheaper than cross-validation but noisier on small data.

the Spark ML utility that builds the grid of hyperparameter combinations (a list of param maps) for a tuner.

share of correct predictions. Misleading on imbalanced data (above: 0.901 with recall 0.25).

of the rows predicted positive, how many are positive. Recall: of the actual positives, how many were found.

scikit-learn describes the F-measure as "a weighted harmonic mean of the precision and recall"; F1 weights them equally and is best at 1 and worst at 0. Use it when both false positives and false negatives matter and the classes are imbalanced.

area under the ROC curve, which plots true positive rate against false positive rate across all thresholds. It measures ranking quality independent of any threshold: 0.5 is chance, 1.0 is perfect.

scikit-learn: "also called logistic regression loss or cross-entropy loss, is defined on probability estimates". It punishes confident wrong predictions heavily, so it is the metric when you care about calibrated probabilities. Lower is better.

the share of variance in the target the model explains; unit-free, 1 is perfect. scikit-learn notes R-squared gives the same ranking as squared error.

apply the inverse of a log transform (exp) so predictions and metrics are in original units.

error from a model that is too simple, which shows as high error on training and validation data (underfitting).

error from a model that is too sensitive to the training data, which shows as low training error and high validation error (overfitting).

a penalty that constrains model complexity to reduce overfitting.

scoring a whole dataset on a schedule and storing the predictions, which is the simplest and cheapest pattern when no per-request latency is required.

scoring individual requests through a low-latency REST endpoint such as a Model Serving endpoint.

scoring records continuously as they arrive in a streaming pipeline.

the MLflow call that loads any logged model as a generic Python function with a predict method.

the MLflow call that wraps a logged model as a Spark UDF so it can score a Spark DataFrame on a cluster, in batch or streaming.

the Databricks declarative pipeline framework (now Lakeflow Spark Declarative Pipelines) for managed batch and streaming data pipelines, including model inference through a Spark UDF.

Spark's streaming engine, which scores arriving records with the same DataFrame operations and UDFs as batch.

the model (a Unity Catalog model name and version) that a Model Serving endpoint serves, with its compute settings.

an endpoint setting that releases compute when idle; not recommended for production because capacity is not guaranteed and the first request is slow.

the recommended JSON input format for tabular models, a pandas DataFrame in split orientation with columns and data.

a Databricks SQL function that calls a Model Serving endpoint from a query, used for batch scoring and in pipelines.

the endpoint setting that lists routes, each pairing a served model name with a traffic percentage.

sending a chosen share of requests to each model behind one endpoint, used for A/B tests and gradual rollouts.