Usage
The following example shows how the step can be used in a recipe.Examples
Examples
- Example 1
- Signature
To automatically select the a model (classifier vs regressor) based on the kind of target
variable (numeric or categorical), simply use:
Inputs & Outputs
The following are the inputs expected by the step and the outputs it produces. These are generally columns (ds.first_name), datasets (ds or ds[["first_name", "last_name"]]) or models (referenced
by name e.g. "churn-clf").
Inputs
Inputs
dataset
required
A dataset containing the column to be imputed as well as any other column to use as predictors in the model.
Outputs
Outputs
column
required
A column containing the predicted values for all rows.
Configuration
The following parameters can be used to configure the behaviour of the step by including them in a json object as the last “input” to the step, i.e.step(..., {"param": "value", ...}) -> (output).
Parameters
Parameters
string (ds.column:category|number)
required
Name of the column to impute.
The step will predict the missing values for this column, using rows in the dataset where the values are not missing to train the prediction model.
boolean
default:"false"
Predict non-missing values.
When set to true, all values are predicted. Set this param to false to maintain original values when they are not missing.
number
default:"0"
Confidence threshold.
Every prediction with probability strictly below this threshold will be set to NaN (missing).Values must be in the following range:
object
CatBoost configuration parameters.
You can check the official documentation for more details about Catboost’s parameters here.
Properties
Properties
integer
default:"6"
The maximum depth of the tree.Values must be in the following range:
[integer, null]
default:"1000"
Number of iterations.
The maximum number of trees that can be built when solving machine learning problems. When using other parameters that limit the number of iterations, the final number of trees may be less than the number specified in this parameter.Values must be in the following range:
integer
default:"10"
Maximum cardinality of variables to be one-hot encoded.
Use one-hot encoding for all categorical features with a number of different values less than or equal to this value. Other variables will be target-encoded. Note that one-hot encoding is faster than the alternatives, so decreasing this value makes it more likely slower methods will be used. See CatBoost details for further information.Values must be in the following range:
number
default:"2"
The maximum number of features that can be combined when transforming categorical variables.
Each resulting combination consists of one or more categorical features and can optionally contain binary features in the following form: “numeric feature > value”.Values must be in the following range:
number
default:"3.0"
Coefficient at the L2 regularization term of the cost function.Values must be in the following range:
integer
default:"254"
The number of splits for numerical features.Values must be in the following range:
number
default:"1.0"
The amount of randomness to use for scoring splits.
Use this parameter to avoid overfitting the model. The value multiplies the variance of a random variable (with
zero mean) that is added to the score used to select splits when a tree is grown.Values must be in the following range:
string
default:"Min"
The method for processing missing values in the input dataset.
Possible values:
- “Forbidden”: Missing values are not supported, their presence is interpreted as an error.
- “Min”: Missing values are processed as the minimum value (less than all other values) for the feature. It is guaranteed that a split that separates missing values from all other values is considered when selecting trees.
- “Max”: Missing values are processed as the maximum value (greater than all other values) for the feature. It is guaranteed that a split that separates missing values from all other values is considered when selecting trees.
ForbiddenMinMax
string
default:"Plain"
Boosting type.
Boosting scheme. Possible values are
- Ordered: Usually provides better quality on small datasets, but it may be slower than the Plain scheme.
- Plain: The classic gradient boosting scheme.
OrderedPlain
[number, null]
Random subspace method.
The percentage of features to use at each split selection, when features are selected over again at random. The value
null is equivalent to 1.0 (all features). You can set this to values < 1.0 when the dataset has many features (e.g. > 20) to speed up training.Values must be in the following range:integer
default:"0"
The random seed used for training.
[string, null]
Whether and how to limit memory usage.
Select the maximum Ram used using strings like “2GB” or “100mb” (non case_sensitive).
boolean
default:"true"
Toggle encoding of feature columns.
When enabled, Graphext will auto-convert any column types to the numeric type before
fitting the model. How this conversion is done can be configured using the
feature_encoder
option below.[null, object]
Configures encoding of feature columns.
By default (
null), Graphext chooses automatically how to convert any column types the model
may not understand natively to a numeric type.A configuration object can be passed instead to overwrite specific parameter values with respect
to their default values.Properties
Properties
object
Numeric encoder.
Configures encoding of numeric features.
Properties
Properties
boolean
Toggle the addition of a column using 0s and 1s to indicate where an input column contained missing values.
[null, string]
Whether and how to impute (replace/fill) missing values.Values must be one of the following:
MeanMedianMostFrequentConstNone
[null, string]
Whether and how to scale the final numerical values (across a single column).Values must be one of the following:
StandardRobustKNNNone
object
Further parameters passed to the
scaler function.
Details depend no the particular scaler used.object
Boolean encoder.
Configures encoding of boolean features.
object
Ordinal encoder.
Configures encoding of categorical features that have a natural order.
[object, object]
Category encoder.
May contain either a single configuration for all categorical variables, or two different configurations
for low- and high-cardinality variables. For further details pick one of the two options below.
Options
Options
- Simple category encoder
- Conditional category encoder
boolean
Toggle the addition of a column using 0s and 1s to indicate where an input column contained missing values.
[null, string]
Whether and how to impute (replace/fill) missing values.Values must be one of the following:
MostFrequentConstNone
[null, integer]
Maximum number of unique categories to encode.
Only the N-1 most common categories will be encoded, and the rest will be grouped into a single
“Others” category.Values must be in the following range:
[null, string]
How to encode categories.Values must be one of the following:
OneHot Label Ordinal Binary Frequency None[null, string]
Whether and how to scale the final numerical values (across a single column).Values must be one of the following:
StandardRobustKNNNone
[object, object]
Multilabel encoder.
Configures encoding of multivalued categorical features (variable length lists of categories,
or the semantic type
list[category] for short). May contain either a single configuration for
all multilabel variables, or two different configurations for low- and high-cardinality variables.
For further details pick one of the two options below.Options
Options
- Simple multilabel encoder
- Conditional multilabel encoder
boolean
Toggle the addition of a column using 0s and 1s to indicate where an input column contained missing values.
[null, string]
How to encode categories/labels in multilabel (list[category]) columns.Values must be one of the following:
BinarizerTfIdfNone
[null, integer]
Maximum number of categories/labels to encode.
If a number is provided, the result of the encoding will be reduced to these many dimensions (columns)
using scikit-learn’s truncated SVD.
When applied together with (after a) Tf-Idf encoding, this performs a kind of
latent semantic analysis.Values must be in the following range:
[null, string]
How to scale the encoded (numerical columns).Values must be one of the following:
EuclideanKNNNormNone
object
Datetime encoder.
Configures encoding of datetime (timestamp) features.
Properties
Properties
boolean
Toggle the addition of a column using 0s and 1s to indicate where an input column contained missing values.
array[string]
A list of numerical components to extract.
Will create one numeric column for each component.
Array items
Array items
string
Each item in array.Values must be one of the following:
day dayofweek dayofyear hour minute month quarter season second week weekday weekofyear yeararray[string]
A list of cyclical time features to extract.
“Cycles” are numerical transformations of features that should be represented on a circle. E.g. months,
ranging from 1 to 12, should be arranged such that 12 and 1 are next to each other, rather than on
opposite ends of a linear scale. We represent such cyclical time features on a circle by creating two
columns for each original feature: the sin and cos of the numerical feature after appropriate scaling.
Array items
Array items
string
Each item in array.Values must be one of the following:
daydayofweekdayofyearhourmonth
[null, boolean]
Whether to include the epoch as new feature (seconds since 01/01/1970).
[null, string]
Whether and how to impute (replace/fill) missing values.Values must be one of the following:
MeanMedianMostFrequentConstNone
[null, string]
Whether and how to scale the final numerical values (across a single column).Values must be one of the following:
StandardRobustKNNNone
[null, string]
How to scale the encoded (numerical columns).Values must be one of the following:
EuclideanKNNNormNone
object
Embedding/vector encoder.
Configures encoding of multivalued numerical features (variable length lists of numbers, i.e. vectors, or the semantic type
list[number] for short).object
Text encoder.
Configures encoding of text (natural language) features. Currently only allows
Tf-Idf embeddings to represent texts. If you wish
to use other embeddings, e.g. semantic, Word2Vec etc., transform your text column first using
another step, and then use that result instead of the original texts.
Properties
Properties
boolean
Toggle the addition of a column using 0s and 1s to indicate where an input column contained missing values.
object
Parameters to be passed to the text encoder (Tf-Idf parameters only for now).
See scikit-learn’s documentation
for detailed parameters and their explanation.
integer
How many output features to generate.
The resulting Tf-Idf vectors will be reduced to these many dimensions (columns) using scikit-learn’s
truncated SVD.
This performs a kind of latent semantic analysis.
By default we will reduce to 200 components.Values must be in the following range:
[null, string]
How to scale the encoded (numerical columns).Values must be one of the following:
EuclideanKNNNormNone
boolean
default:"false"
Whether to include or ignore text columns during the processing of input data.
Enabling this will convert texts to their TfIdf representation. Each text will be
converted to an N-dimensional vector in which each component measures the relative
“over-representation” of a specific word (or n-gram) relative to its overall
frequency in the whole dataset. This is disabled by default because it will
often be better to convert texts explicitly using a previous step, such as
embed_text or embed_text_with_model.[object, null]
Configure model validation.
Allows evaluation of model performance via cross-validation with custom metrics. If not
specified, will by default perform 5-fold cross-validation with automatically selected
metrics.
Properties
Properties
[integer, null]
default:"5"
Number of train-test splits to evaluate the model on.
Will split the dataset into training and test set
n_splits times, train on the former
and evaluate on the latter using specified or automatically selected metrics.[number, null]
What proportion of the data to use for testing in each split.
If
null or not provided, will use cross-validation to split the dataset. E.g. if n_splits
is 5, the dataset will be split into 5 equal-sized parts. For five iterations four parts will then
be used for training and the remaining part for testing. If test_size is a number between 0 and 1,
in contrast, validation is done using a shuffle-split approach. Here, instead of splitting the data into
n_splits equal parts up front, in each iteration we randomize the data and sample a proportion equal
to test_size to use for evaluation and the remaining rows for training.Values must be in the following range:[null, array]
One or more metrics/scoring functions to evaluate the model with.
When none is provided, will measure default metrics appropriate for the prediction task
(classification vs. regression determined from model or type of target column). See
sklearn model evaluation
for further details.
Options
Options
- null
- array
null
null.
object
Configure hypertuning.
Configures the optimization of model hyper-parameters via cross-validated grid- or randomized search.
Properties
Properties
object
The parameter values to explore.
Allows tuning of any and all of the parameters that can be set also as constants in the
“params” attribute.Keys in this object should be strings identifying parameter names, and values should be
lists of values to explore for that parameter. E.g.
"depth": [3, 5, 7].Properties
Properties
array[integer]
List of depths values to explore.
Array items
Array items
integer
default:"6"
The maximum depth of the tree.Values must be in the following range:
array[['integer', 'null']]
List of iterations values to explore.
Array items
Array items
[integer, null]
default:"1000"
Number of iterations.
The maximum number of trees that can be built when solving machine learning problems. When using other parameters that limit the number of iterations, the final number of trees may be less than the number specified in this parameter.Values must be in the following range:
array[integer]
List of values configuring max cardinality for one-hot encoding.
Array items
Array items
integer
default:"10"
Maximum cardinality of variables to be one-hot encoded.
Use one-hot encoding for all categorical features with a number of different values less than or equal to this value. Other variables will be target-encoded. Note that one-hot encoding is faster than the alternatives, so decreasing this value makes it more likely slower methods will be used. See CatBoost details for further information.Values must be in the following range:
array[number]
List of values configuring variable combination complexity.
Array items
Array items
number
default:"2"
The maximum number of features that can be combined when transforming categorical variables.
Each resulting combination consists of one or more categorical features and can optionally contain binary features in the following form: “numeric feature > value”.Values must be in the following range:
array[number]
List of leaf regularization strengths.
Array items
Array items
number
default:"3.0"
Coefficient at the L2 regularization term of the cost function.Values must be in the following range:
array[integer]
List of border counts.
Array items
Array items
integer
default:"254"
The number of splits for numerical features.Values must be in the following range:
array[number]
List of random strengths.
Array items
Array items
number
default:"1.0"
The amount of randomness to use for scoring splits.
Use this parameter to avoid overfitting the model. The value multiplies the variance of a random variable (with
zero mean) that is added to the score used to select splits when a tree is grown.Values must be in the following range:
string
default:"grid"
Which search strategy to use for optimization.
Grid search explores all possible combinations of parameters specified in
params.
Randomized search, on the other hand, randomly samples iterations parameter combinations
from the distributions specified in params.Values must be one of the following:gridrandom
integer
default:"10"
How many randomly sampled parameter combinations to test in randomized search.Values must be in the following range:
[object, null]
Configure model validation.
Allows evaluation of model performance via cross-validation with custom metrics. If not
specified, will by default perform 5-fold cross-validation with automatically selected
metrics.
Properties
Properties
[integer, null]
default:"5"
Number of train-test splits to evaluate the model on.
Will split the dataset into training and test set
n_splits times, train on the former
and evaluate on the latter using specified or automatically selected metrics.[number, null]
What proportion of the data to use for testing in each split.
If
null or not provided, will use cross-validation to split the dataset. E.g. if n_splits
is 5, the dataset will be split into 5 equal-sized parts. For five iterations four parts will then
be used for training and the remaining part for testing. If test_size is a number between 0 and 1,
in contrast, validation is done using a shuffle-split approach. Here, instead of splitting the data into
n_splits equal parts up front, in each iteration we randomize the data and sample a proportion equal
to test_size to use for evaluation and the remaining rows for training.Values must be in the following range:[null, array]
One or more metrics/scoring functions to evaluate the model with.
When none is provided, will measure default metrics appropriate for the prediction task
(classification vs. regression determined from model or type of target column). See
sklearn model evaluation
for further details.
Options
Options
- null
- array
null
null.
string
Each item in array.Values must be one of the following:
accuracy balanced_accuracy explained_variance f1_micro f1_macro f1_samples f1_weighted neg_mean_squared_error neg_median_absolute_error neg_root_mean_squared_error precision_micro precision_macro precision_samples precision_weighted recall_micro recall_macro recall_samples recall_weighted r2integer
Seed for random number generator ensuring reproducibility.Values must be in the following range: