Feature

class datarobot.models.Feature

A feature from a project’s dataset

These are features either included in the originally uploaded dataset or added to it via feature transformations. In time series projects, these will be distinct from the ModelingFeature s created during partitioning; otherwise, they will correspond to the same features. For more information about input and modeling features, see the time series documentation.

The min, max, mean, median, and std_dev attributes provide information about the distribution of the feature in the EDA sample data. For non-numeric features or features created prior to these summary statistics becoming available, they will be None. For features where the summary statistics are available, they will be in a format compatible with the data type, i.e. date type features will have their summary statistics expressed as ISO-8601 formatted date strings.

Variables:

  • id (int) – the id for the feature - note that name is used to reference the feature instead of id

  • project_id (str) – the id of the project the feature belongs to

  • name (str) – the name of the feature

  • feature_type (str) – the type of the feature, e.g. ‘Categorical’, ‘Text’

  • importance (float or None) – numeric measure of the strength of relationship between the feature and target (independent of any model or other features); may be None for non-modeling features such as partition columns

  • low_information (bool) – whether a feature is considered too uninformative for modeling (e.g. because it has too few values)

  • unique_count (int) – number of unique values

  • na_count (int or None) – number of missing values

  • date_format (str or None) – For Date features, the date format string for how this feature was interpreted, compatible with https://docs.python.org/2/library/time.html#time.strftime . For other feature types, None.

  • min (str, int, float, or None) – The minimum value of the source data in the EDA sample

  • max (str, int, float, or None) – The maximum value of the source data in the EDA sample

  • mean (str, int, or, float) – The arithmetic mean of the source data in the EDA sample

  • median (str, int, float, or None) – The median of the source data in the EDA sample

  • std_dev (str, int, float, or None) – The standard deviation of the source data in the EDA sample

  • time_series_eligible (bool) – Whether this feature can be used as the datetime partition column in a time series project.

  • time_series_eligibility_reason (str) – Why the feature is ineligible for the datetime partition column in a time series project, or ‘suitable’ when it is eligible.

  • time_step (int or None) – For time series eligible features, a positive integer determining the interval at which windows can be specified. If used as the datetime partition column on a time series project, the feature derivation and forecast windows must start and end at an integer multiple of this value. None for features that are not time series eligible.

  • time_unit (str or None) – For time series eligible features, the time unit covered by a single time step, e.g. ‘HOUR’, or None for features that are not time series eligible.

  • target_leakage (str) – Whether a feature is considered to have target leakage or not. A value of ‘SKIPPED_DETECTION’ indicates that target leakage detection was not run on the feature. ‘FALSE’ indicates no leakage, ‘MODERATE’ indicates a moderate risk of target leakage, and ‘HIGH_RISK’ indicates a high risk of target leakage

  • feature_lineage_id (str) – id of a lineage for automatically discovered features or derived time series features.

  • key_summary (list of dict) –

    Statistics for top 50 keys (truncated to 103 characters) of Summarized Categorical column example:

    {‘key’:’DataRobot’, ‘summary’:{‘min’:0, ‘max’:29815.0, ‘stdDev’:6498.029, ‘mean’:1490.75, ‘median’:0.0, ‘pctRows’:5.0}}

    where,
    key: string or None

    name of the key

    summary: dict

    statistics of the key

    max: maximum value of the key. min: minimum value of the key. mean: mean value of the key. median: median value of the key. stdDev: standard deviation of the key. pctRows: percentage occurrence of key in the EDA sample of the feature.

  • multilabel_insights_key (str or None) – For multicategorical columns this will contain a key for multilabel insights. The key is unique for a project, feature and EDA stage combination. This will be the key for the most recent, finished EDA stage.

classmethod get(project_id, feature_name)

Retrieve a single feature

Parameters:

  • project_id (str) – The ID of the project the feature is associated with.

  • feature_name (str) – The name of the feature to retrieve

Returns:

feature – The queried instance

Return type:

Feature

get_multiseries_properties(multiseries_id_columns, max_wait=600)

Retrieve time series properties for a potential multiseries datetime partition column

Multiseries time series projects use multiseries id columns to model multiple distinct series within a single project. This function returns the time series properties (time step and time unit) of this column if it were used as a datetime partition column with the specified multiseries id columns, running multiseries detection automatically if it had not previously been successfully ran.

Parameters:

  • multiseries_id_columns (List[str]) – the name(s) of the multiseries id columns to use with this datetime partition column. Currently only one multiseries id column is supported.

  • max_wait (Optional[int]) – if a multiseries detection task is run, the maximum amount of time to wait for it to complete before giving up

Returns:

properties –

A dict with three keys:

  • time_series_eligible : bool, whether the column can be used as a partition column

  • time_unit : str or null, the inferred time unit if used as a partition column

  • time_step : int or null, the inferred time step if used as a partition column

Return type:

dict

get_cross_series_properties(datetime_partition_column, cross_series_group_by_columns, max_wait=600)

Retrieve cross-series properties for multiseries ID column.

This function returns the cross-series properties (eligibility as group-by column) of this column if it were used with specified datetime partition column and with current multiseries id column, running cross-series group-by validation automatically if it had not previously been successfully ran.

Parameters:

  • datetime_partition_column (datetime partition column)

  • cross_series_group_by_columns (List[str]) – the name(s) of the columns to use with this multiseries ID column. Currently only one cross-series group-by column is supported.

  • max_wait (Optional[int]) – if a multiseries detection task is run, the maximum amount of time to wait for it to complete before giving up

Returns:

properties –

A dict with three keys:

  • name : str, column name

  • eligibility : str, reason for column eligibility

  • isEligible : bool, is column eligible as cross-series group-by

Return type:

dict

get_multicategorical_histogram()

Retrieve multicategorical histogram for this feature

Added in version v2.24.

Return type:

datarobot.models.MulticategoricalHistogram

Raises:
get_pairwise_correlations()

Retrieve pairwise label correlation for multicategorical features

Added in version v2.24.

Return type:

datarobot.models.PairwiseCorrelations

Raises:
get_pairwise_joint_probabilities()

Retrieve pairwise label joint probabilities for multicategorical features

Added in version v2.24.

Return type:

datarobot.models.PairwiseJointProbabilities

Raises:
get_pairwise_conditional_probabilities()

Retrieve pairwise label conditional probabilities for multicategorical features

Added in version v2.24.

Return type:

datarobot.models.PairwiseConditionalProbabilities

Raises:
classmethod from_data(data)

Instantiate an object of this class using a dict.

Parameters:

data (dict) – Correctly snake_cased keys and their values.

Return type:

TypeVar(T, bound= APIObject)

classmethod from_server_data(data, keep_attrs=None)

Instantiate an object of this class using the data directly from the server, meaning that the keys may have the wrong camel casing

Parameters:

  • data (dict) – The directly translated dict of JSON from the server. No casing fixes have taken place

  • keep_attrs (iterable) – List, set or tuple of the dotted namespace notations for attributes to keep within the object structure even if their values are None

Return type:

TypeVar(T, bound= APIObject)

get_histogram(bin_limit=None)

Retrieve a feature histogram

Parameters:

bin_limit (int or None) – Desired max number of histogram bins. If omitted, by default endpoint will use 60.

Returns:

featureHistogram – The requested histogram with desired number or bins

Return type:

FeatureHistogram

class datarobot.models.ModelingFeature

A feature used for modeling

In time series projects, a new set of modeling features is created after setting the partitioning options. These features are automatically derived from those in the project’s dataset and are the features used for modeling. Modeling features are only accessible once the target and partitioning options have been set. In projects that don’t use time series modeling, once the target has been set, ModelingFeatures and Features will behave the same.

For more information about input and modeling features, see the time series documentation.

As with the Feature object, the min, max, `mean, median, and std_dev attributes provide information about the distribution of the feature in the EDA sample data. For non-numeric features, they will be None. For features where the summary statistics are available, they will be in a format compatible with the data type, i.e. date type features will have their summary statistics expressed as ISO-8601 formatted date strings.

Variables:

  • project_id (str) – the id of the project the feature belongs to

  • name (str) – the name of the feature

  • feature_type (str) – the type of the feature, e.g. ‘Categorical’, ‘Text’

  • importance (float or None) – numeric measure of the strength of relationship between the feature and target (independent of any model or other features); may be None for non-modeling features such as partition columns

  • low_information (bool) – whether a feature is considered too uninformative for modeling (e.g. because it has too few values)

  • unique_count (int) – number of unique values

  • na_count (int or None) – number of missing values

  • date_format (str or None) – For Date features, the date format string for how this feature was interpreted, compatible with https://docs.python.org/2/library/time.html#time.strftime . For other feature types, None.

  • min (str, int, float, or None) – The minimum value of the source data in the EDA sample

  • max (str, int, float, or None) – The maximum value of the source data in the EDA sample

  • mean (str, int, or, float) – The arithmetic mean of the source data in the EDA sample

  • median (str, int, float, or None) – The median of the source data in the EDA sample

  • std_dev (str, int, float, or None) – The standard deviation of the source data in the EDA sample

  • parent_feature_names (List[str]) – A list of the names of input features used to derive this modeling feature. In cases where the input features and modeling features are the same, this will simply contain the feature’s name. Note that if a derived feature was used to create this modeling feature, the values here will not necessarily correspond to the features that must be supplied at prediction time.

  • key_summary (list of dict) –

    Statistics for top 50 keys (truncated to 103 characters) of Summarized Categorical column example:

    {‘key’:’DataRobot’, ‘summary’:{‘min’:0, ‘max’:29815.0, ‘stdDev’:6498.029, ‘mean’:1490.75, ‘median’:0.0, ‘pctRows’:5.0}}

    where,
    key: string or None

    name of the key

    summary: dict

    statistics of the key

    max: maximum value of the key. min: minimum value of the key. mean: mean value of the key. median: median value of the key. stdDev: standard deviation of the key. pctRows: percentage occurrence of key in the EDA sample of the feature.

classmethod get(project_id, feature_name)

Retrieve a single modeling feature

Parameters:

  • project_id (str) – The ID of the project the feature is associated with.

  • feature_name (str) – The name of the feature to retrieve

Returns:

feature – The requested feature

Return type:

ModelingFeature

class datarobot.models.DatasetFeature

A feature from a project’s dataset

These are features either included in the originally uploaded dataset or added to it via feature transformations.

The min, max, mean, median, and std_dev attributes provide information about the distribution of the feature in the EDA sample data. For non-numeric features or features created prior to these summary statistics becoming available, they will be None. For features where the summary statistics are available, they will be in a format compatible with the data type, i.e. date type features will have their summary statistics expressed as ISO-8601 formatted date strings.

Variables:

  • id (int) – the id for the feature - note that name is used to reference the feature instead of id

  • dataset_id (str) – the id of the dataset the feature belongs to

  • dataset_version_id (str) – the id of the dataset version the feature belongs to

  • name (str) – the name of the feature

  • feature_type (Optional[str]) – the type of the feature, e.g. ‘Categorical’, ‘Text’

  • low_information (Optional[bool]) – whether a feature is considered too uninformative for modeling (e.g. because it has too few values)

  • unique_count (Optional[int]) – number of unique values

  • na_count (Optional[int]) – number of missing values

  • date_format (Optional[str]) – For Date features, the date format string for how this feature was interpreted, compatible with https://docs.python.org/2/library/time.html#time.strftime . For other feature types, None.

  • min (str, int, Optional[float]) – The minimum value of the source data in the EDA sample

  • max (str, int, Optional[float]) – The maximum value of the source data in the EDA sample

  • mean (str, int, Optional[float]) – The arithmetic mean of the source data in the EDA sample

  • median (str, int, Optional[float]) – The median of the source data in the EDA sample

  • std_dev (str, int, Optional[float]) – The standard deviation of the source data in the EDA sample

  • time_series_eligible (Optional[bool]) – Whether this feature can be used as the datetime partition column in a time series project.

  • time_series_eligibility_reason (Optional[str]) – Why the feature is ineligible for the datetime partition column in a time series project, or ‘suitable’ when it is eligible.

  • time_step (Optional[int]) – For time series eligible features, a positive integer determining the interval at which windows can be specified. If used as the datetime partition column on a time series project, the feature derivation and forecast windows must start and end at an integer multiple of this value. None for features that are not time series eligible.

  • time_unit (Optional[str]) – For time series eligible features, the time unit covered by a single time step, e.g. ‘HOUR’, or None for features that are not time series eligible.

  • target_leakage (Optional[str]) – Whether a feature is considered to have target leakage or not. A value of ‘SKIPPED_DETECTION’ indicates that target leakage detection was not run on the feature. ‘FALSE’ indicates no leakage, ‘MODERATE’ indicates a moderate risk of target leakage, and ‘HIGH_RISK’ indicates a high risk of target leakage

  • target_leakage_reason (string, optional) – The descriptive text explaining the reason for target leakage, if any.

get_histogram(bin_limit=None)

Retrieve a feature histogram

Parameters:

bin_limit (int or None) – Desired max number of histogram bins. If omitted, by default endpoint will use 60.

Returns:

featureHistogram – The requested histogram with desired number or bins

Return type:

DatasetFeatureHistogram

class datarobot.models.DatasetFeatureHistogram
classmethod get(dataset_id, feature_name, bin_limit=None, key_name=None)

Retrieve a single feature histogram

Parameters:

  • dataset_id (str) – The ID of the Dataset the feature is associated with.

  • feature_name (str) – The name of the feature to retrieve

  • bin_limit (int or None) – Desired max number of histogram bins. If omitted, by default the endpoint will use 60.

  • key_name (string or None) – (Only required for summarized categorical feature) Name of the top 50 keys for which plot to be retrieved

Returns:

featureHistogram – The queried instance with plot attribute in it.

Return type:

FeatureHistogram

class datarobot.models.FeatureHistogram
classmethod get(project_id, feature_name, bin_limit=None, key_name=None)

Retrieve a single feature histogram

Parameters:

  • project_id (str) – The ID of the project the feature is associated with.

  • feature_name (str) – The name of the feature to retrieve

  • bin_limit (int or None) – Desired max number of histogram bins. If omitted, by default endpoint will use 60.

  • key_name (string or None) – (Only required for summarized categorical feature) Name of the top 50 keys for which plot to be retrieved

Returns:

featureHistogram – The queried instance with plot attribute in it.

Return type:

FeatureHistogram

class datarobot.models.InteractionFeature

Interaction feature data

Added in version v2.21.

Variables:

  • rows (int) – Total number of rows

  • source_columns (list(str)) – names of two categorical features which were combined into this one

  • bars (list(dict)) – dictionaries representing frequencies of each independent value from the source columns

  • bubbles (list(dict)) – dictionaries representing frequencies of each combined value in the interaction feature.

classmethod get(project_id, feature_name)

Retrieve a single Interaction feature

Parameters:

  • project_id (str) – The id of the project the feature belongs to

  • feature_name (str) – The name of the Interaction feature to retrieve

Returns:

feature – The queried instance

Return type:

InteractionFeature

class datarobot.models.MulticategoricalHistogram

Histogram for Multicategorical feature.

Added in version v2.24.

Notes

HistogramValues contains:

  • values.[].label : string - Label name

  • values.[].plot : list - Histogram for label

  • values.[].plot.[].label_relevance : int - Label relevance value

  • values.[].plot.[].row_count : int - Row count where label has given relevance

  • values.[].plot.[].row_pct : float - Percentage of rows where label has given relevance

Variables:

  • feature_name (str) – Name of the feature

  • values (list(dict)) – List of Histogram values with a schema described as HistogramValues

classmethod get(multilabel_insights_key)

Retrieves multicategorical histogram

You might find it more convenient to use Feature.get_multicategorical_histogram instead.

Parameters:

multilabel_insights_key (string) – Key for multilabel insights, unique for a project, feature and EDA stage combination. The multilabel_insights_key can be retrieved via Feature.multilabel_insights_key.

Returns:

The multicategorical histogram for multilabel_insights_key

Return type:

MulticategoricalHistogram

to_dataframe()

Convenience method to get all the information from this multicategorical_histogram instance in form of a pandas.DataFrame.

Returns:

Histogram information as a multicategorical_histogram. The dataframe will contain these columns: feature_name, label, label_relevance, row_count and row_pct

Return type:

pandas.DataFrame

class datarobot.models.PairwiseCorrelations

Correlation of label pairs for multicategorical feature.

Added in version v2.24.

Notes

CorrelationValues contain:

  • values.[].label_configuration : list of length 2 - Configuration of the label pair

  • values.[].label_configuration.[].label : str – Label name

  • values.[].statistic_value : float – Statistic value

Variables:

  • feature_name (str) – Name of the feature

  • values (list(dict)) – List of correlation values with a schema described as CorrelationValues

  • statistic_dataframe (pandas.DataFrame) – Correlation values for all label pairs as a DataFrame

classmethod get(multilabel_insights_key)

Retrieves pairwise correlations

You might find it more convenient to use Feature.get_pairwise_correlations instead.

Parameters:

multilabel_insights_key (string) – Key for multilabel insights, unique for a project, feature and EDA stage combination. The multilabel_insights_key can be retrieved via Feature.multilabel_insights_key.

Returns:

The pairwise label correlations

Return type:

PairwiseCorrelations

as_dataframe()

The pairwise label correlations as a (num_labels x num_labels) DataFrame.

Returns:

The pairwise label correlations. Index and column names allow the interpretation of the values.

Return type:

pandas.DataFrame

class datarobot.models.PairwiseJointProbabilities

Joint probabilities of label pairs for multicategorical feature.

Added in version v2.24.

Notes

ProbabilityValues contain:

  • values.[].label_configuration : list of length 2 - Configuration of the label pair

  • values.[].label_configuration.[].relevance : int – 0 for absence of the labels, 1 for the presence of labels

  • values.[].label_configuration.[].label : str – Label name

  • values.[].statistic_value : float – Statistic value

Variables:

  • feature_name (str) – Name of the feature

  • values (list(dict)) – List of joint probability values with a schema described as ProbabilityValues

  • statistic_dataframes (dict(pandas.DataFrame)) –

    Joint Probability values as DataFrames for different relevance combinations.

    E.g. The probability P(A=0,B=1) can be retrieved via: pairwise_joint_probabilities.statistic_dataframes[(0,1)].loc['A', 'B']

classmethod get(multilabel_insights_key)

Retrieves pairwise joint probabilities

You might find it more convenient to use Feature.get_pairwise_joint_probabilities instead.

Parameters:

multilabel_insights_key (string) – Key for multilabel insights, unique for a project, feature and EDA stage combination. The multilabel_insights_key can be retrieved via Feature.multilabel_insights_key.

Returns:

The pairwise joint probabilities

Return type:

PairwiseJointProbabilities

as_dataframe(relevance_configuration)

Joint probabilities of label pairs as a (num_labels x num_labels) DataFrame.

Parameters:

relevance_configuration (tuple of length 2) –

Valid options are (0, 0), (0, 1), (1, 0) and (1, 1). Values of 0 indicate absence of labels and 1 indicates presence of labels. The first value describes the presence for the labels in axis=0 and the second value describes the presence for the labels in axis=1.

For example the matrix values for a relevance configuration of (0, 1) describe the probabilities of absent labels in the index axis and present labels in the column axis.

E.g. The probability P(A=0,B=1) can be retrieved via: pairwise_joint_probabilities.as_dataframe((0,1)).loc['A', 'B']

Returns:

The joint probabilities for the requested relevance_configuration. Index and column names allow the interpretation of the values.

Return type:

pandas.DataFrame

class datarobot.models.PairwiseConditionalProbabilities

Conditional probabilities of label pairs for multicategorical feature.

Added in version v2.24.

Notes

ProbabilityValues contain:

  • values.[].label_configuration : list of length 2 - Configuration of the label pair

  • values.[].label_configuration.[].relevance : int – 0 for absence of the labels, 1 for the presence of labels

  • values.[].label_configuration.[].label : str – Label name

  • values.[].statistic_value : float – Statistic value

Variables:

  • feature_name (str) – Name of the feature

  • values (list(dict)) – List of conditional probability values with a schema described as ProbabilityValues

  • statistic_dataframes (dict(pandas.DataFrame)) –

    Conditional Probability values as DataFrames for different relevance combinations. The label names in the columns are the events, on which we condition. The label names in the index are the events whose conditional probability given the indexes is in the dataframe.

    E.g. The probability P(A=0|B=1) can be retrieved via: pairwise_conditional_probabilities.statistic_dataframes[(0,1)].loc['A', 'B']

classmethod get(multilabel_insights_key)

Retrieves pairwise conditional probabilities

You might find it more convenient to use Feature.get_pairwise_conditional_probabilities instead.

Parameters:

multilabel_insights_key (string) – Key for multilabel insights, unique for a project, feature and EDA stage combination. The multilabel_insights_key can be retrieved via Feature.multilabel_insights_key.

Returns:

The pairwise conditional probabilities

Return type:

PairwiseConditionalProbabilities

as_dataframe(relevance_configuration)

Conditional probabilities of label pairs as a (num_labels x num_labels) DataFrame. The label names in the columns are the events, on which we condition. The label names in the index are the events whose conditional probability given the indexes is in the dataframe.

E.g. The probability P(A=0|B=1) can be retrieved via: pairwise_conditional_probabilities.as_dataframe((0, 1)).loc['A', 'B']

Parameters:

relevance_configuration (tuple of length 2) –

Valid options are (0, 0), (0, 1), (1, 0) and (1, 1). Values of 0 indicate absence of labels and 1 indicates presence of labels. The first value describes the presence for the labels in axis=0 and the second value describes the presence for the labels in axis=1.

For example the matrix values for a relevance configuration of (0, 1) describe the probabilities of absent labels in the index axis given the presence of labels in the column axis.

Returns:

The conditional probabilities for the requested relevance_configuration. Index and column names allow the interpretation of the values.

Return type:

pandas.DataFrame

Restoring Discarded Features

class datarobot.models.restore_discarded_features.DiscardedFeaturesInfo

An object containing information about time series features which were reduced during time series feature generation process. These features can be restored back to the project. They will be included into All Time Series Features and can be used to create new feature lists.

Added in version v2.27.

Variables:

  • total_restore_limit (int) – The total limit indicating how many features can be restored in this project.

  • remaining_restore_limit (int) – The remaining available number of the features which can be restored in this project.

  • features (list of strings) – Discarded features which can be restored.

  • count (int) – Discarded features count.

classmethod restore(project_id, features_to_restore, max_wait=600)

Restore discarded during time series feature generation process features back to the project. After restoration features will be included into All Time Series Features.

Added in version v2.27.

Parameters:

  • project_id (string)

  • features_to_restore (list of strings) – List of the feature names to restore

  • max_wait (Optional[int]) – max time to wait for features to be restored. Defaults to 10 min

Returns:

status – information about features which were restored and which were not.

Return type:

FeatureRestorationStatus

classmethod retrieve(project_id)

Retrieve the discarded features information for a given project.

Added in version v2.27.

Parameters:

project_id (string)

Returns:

info – information about features which were discarded during feature generation process and limits how many features can be restored.

Return type:

DiscardedFeaturesInfo

class datarobot.models.restore_discarded_features.FeatureRestorationStatus

Status of the feature restoration process.

Added in version v2.27.

Variables:

  • warnings (list of strings) – Warnings generated for those features which failed to restore

  • remaining_restore_limit (int) – The remaining available number of the features which can be restored in this project.

  • restored_features (list of strings) – Features which were restored