Assemble structured custom models¶

DataRobot provides built-in support for a variety of libraries to create models that use conventional target types. If your model is based on one of these libraries, DataRobot expects your model artifact to have a matching file extension:

If your model doesn't use one of the following libraries, you must create an unstructured custom model.

Compare the characteristics and capabilities of the two types of custom models below:

Structured custom model requirements¶

If your custom model uses one of the supported libraries, make sure it meets the following requirements:

• Data sent to a model must be usable for predictions without additional pre-processing.
• Regression models must return a single floating point per row of prediction data.
• Binary classification models must return one floating point value <= 1.0 or two floating point values that sum to 1.0 per row of prediction data.
  • Single-value output is assumed to be the positive class probability.
  • For multi-value, it is assumed that the first value is the negative class probability and the second is the positive class probability.
• There must be a single pkl/pth/h5 file present.

Structured custom model hooks¶

To define a custom model using DataRobot’s framework, your artifact file should contain hooks (or functions) to define how a model is trained and how it scores new data. DataRobot automatically calls each hook and passes the parameters based on the project and blueprint configuration. However, you have full flexibility to define the logic that runs inside each hook. If necessary, you can include these hooks alongside your model artifacts in your model folder in a file called custom.py for Python models or custom.R for R models.

The following sections describe each hook, with examples.

init()¶

The init hook is executed only once at the beginning of the run to allow the model to load libraries and additional files for use in other hooks.

init(**kwargs) -> None

init() input¶

init() example¶

The following provides a brief code snippet using init(); see a more complete example here.

def init(code_dir):
    global g_code_dir
    g_code_dir = code_dir

init <- function(...) {
    library(brnn)
    library(glmnet)
}

init() output¶

The init() hook does not return anything.

load_model()¶

The load_model() hook is executed only once at the beginning of the run to load one or more trained objects from multiple artifacts. It is only required when a trained object is stored in an artifact that uses an unsupported format or when multiple artifacts are used. The load_model() hook is not required when there is a single artifact in one of the supported formats:

• Python: .pkl, .pth, .h5, .joblib
• Java: .mojo
• R: .rds

load_model(code_dir: str) -> Any

load_model() input¶

load_model() example¶

The following provides a brief code snippet using load_model(); see a more complete example here.

def load_model(code_dir):
    model_path = "model.pkl"
    model = joblib.load(os.path.join(code_dir, model_path))

load_model <- function(input_dir) {
    readRDS(file.path(input_dir, "model_name.rds"))
}

load_model() output¶

The load_model() hook returns a trained object (of any type).

read_input_data()¶

The read_input_data hook customizes how the model reads data; for example, with encoding and missing value handling.

read_input_data(input_binary_data: bytes) -> Any

read_input_data() input¶

read_input_data() example¶

def read_input_data(input_binary_data):
    global prediction_value
    prediction_value += 1
    return pd.read_csv(io.BytesIO(input_binary_data))

read_input_data <- function(input_binary_data) {
    input_text_data <- stri_conv(input_binary_data, "utf8")
    read.csv(text=gsub("\r","", input_text_data, fixed=TRUE))
}

read_input_data() output¶

The read_input_data() hook must return a pandas DataFrame or R data.frame; otherwise, you must write your own score method.

transform()¶

The transform() hook defines the output of a custom transform and returns transformed data. Do not use this hook for estimator models. This hook can be used in both transformer and estimator tasks:

• For transformers, this hook applies transformations to the data provided and passes it to downstream tasks.

• For estimators, this hook applies transformations to the prediction data before making predictions.

transform(data: DataFrame, model: Any) -> DataFrame

transform() input¶

transform() example¶

The following provides a brief code snippet using transform(); see a more complete example here.

def transform(data, model):
    data = data.fillna(0)
    return data

transform <- function(data, model) {
    data[is.na(data)] <- 0
    data
}

transform() output¶

The transform() hook returns a pandas DataFrame or R data.frame with transformed data.

score()¶

The score() hook defines the output of a custom estimator and returns predictions on input data. Do not use this hook for transform models.

score(data: DataFrame, model: Any, **kwargs: Dict[str, Any]) -> DataFrame

score() input¶

score() examples¶

The following provides a brief code snippet using score(); see a more complete example here.

def score(data: pd.DataFrame, model: Any, **kwargs: Dict[str, Any]) -> pd.DataFrame:
    predictions = model.predict(data)
    predictions_df = pd.DataFrame(predictions, columns=[kwargs["positive_class_label"]])
    predictions_df[kwargs["negative_class_label"]] = (
        1 - predictions_df[kwargs["positive_class_label"]]
    )

    return predictions_df

score <- function(data, model, ...){
    scores <- predict(model, newdata = data, type = "prob")
    names(scores) <- c('0', '1')
    return(scores)
}

score() output¶

The score() hook should return a pandas DataFrame (or R data.frame or tibble) of the following format:

• For regression or anomaly detection projects, the output must have a single numeric column named Predictions.

• For binary or multiclass projects, the output must have one column per class, with class names used as column names. Each cell must contain the probability of the respective class, and each row must sum up to 1.0.

post_process()¶

The post_process hook formats the prediction data returned by DataRobot or the score hook when it doesn't match the output format expectations.

post_process(predictions: DataFrame, model: Any) -> DataFrame

post_process() input¶

post_process() example¶

def post_process(predictions, model):
    return predictions + 1

post_process <- function(predictions, model) {
    names(predictions) <- c('0', '1')
}

post_process() output¶

The post_process hook returns a pandas DataFrame (or R data.frame or tibble) of the following format:

• For regression or anomaly detection projects, the output must have a single numeric column named Predictions.

• For binary or multiclass projects, the output must have one column per class, with class names used as column names. Each cell must contain the probability of the respective class, and each row must sum up to 1.0.