preprocessing¶
Submodules¶
Package Contents¶
Classes Summary¶
Transformer that can automatically extract features from datetime columns. |
|
Transformer that delays input features and target variable for time series problems. |
|
Featuretools DFS component that generates features for the input features. |
|
Transformer to drop features whose percentage of NaN values exceeds a specified threshold. |
|
Transformer that can automatically extract features from emails. |
|
Applies a log transformation to the target data. |
|
Transformer to calculate the Latent Semantic Analysis Values of text input. |
|
Removes trends from time series by fitting a polynomial to the data. |
|
Transformer that can automatically featurize text columns using featuretools’ nlp_primitives. |
|
Base class for all transformers working with text features. |
|
Transformer that can automatically extract features from URL. |
Contents¶
-
class
evalml.pipelines.components.transformers.preprocessing.DateTimeFeaturizer(features_to_extract=None, encode_as_categories=False, date_index=None, random_seed=0, **kwargs)[source]¶ Transformer that can automatically extract features from datetime columns.
- Parameters
features_to_extract (list) – List of features to extract. Valid options include “year”, “month”, “day_of_week”, “hour”. Defaults to None.
encode_as_categories (bool) – Whether day-of-week and month features should be encoded as pandas “category” dtype. This allows OneHotEncoders to encode these features. Defaults to False.
date_index (str) – Name of the column containing the datetime information used to order the data. Ignored.
random_seed (int) – Seed for the random number generator. Defaults to 0.
Attributes
hyperparameter_ranges
{}
model_family
ModelFamily.NONE
modifies_features
True
modifies_target
False
name
DateTime Featurization Component
Methods
Constructs a new component with the same parameters and random state.
Returns the default parameters for this component.
Describe a component and its parameters
Fits component to data
Fits on X and transforms X
Gets the categories of each datetime feature.
Loads component at file path
Returns boolean determining if component needs fitting before
Returns the parameters which were used to initialize the component
Saves component at file path
Transforms data X by creating new features using existing DateTime columns, and then dropping those DateTime columns
-
clone(self)¶ Constructs a new component with the same parameters and random state.
- Returns
A new instance of this component with identical parameters and random state.
-
default_parameters(cls)¶ Returns the default parameters for this component.
Our convention is that Component.default_parameters == Component().parameters.
- Returns
default parameters for this component.
- Return type
dict
-
describe(self, print_name=False, return_dict=False)¶ Describe a component and its parameters
- Parameters
print_name (bool, optional) – whether to print name of component
return_dict (bool, optional) – whether to return description as dictionary in the format {“name”: name, “parameters”: parameters}
- Returns
prints and returns dictionary
- Return type
None or dict
-
fit(self, X, y=None)[source]¶ Fits component to data
- Parameters
X (list, pd.DataFrame or np.ndarray) – The input training data of shape [n_samples, n_features]
y (list, pd.Series, np.ndarray, optional) – The target training data of length [n_samples]
- Returns
self
-
fit_transform(self, X, y=None)¶ Fits on X and transforms X
- Parameters
X (pd.DataFrame) – Data to fit and transform
y (pd.Series) – Target data
- Returns
Transformed X
- Return type
pd.DataFrame
-
get_feature_names(self)[source]¶ Gets the categories of each datetime feature.
- Returns
Dictionary, where each key-value pair is a column name and a dictionary mapping the unique feature values to their integer encoding.
-
static
load(file_path)¶ Loads component at file path
- Parameters
file_path (str) – Location to load file
- Returns
ComponentBase object
-
needs_fitting(self)¶ Returns boolean determining if component needs fitting before calling predict, predict_proba, transform, or feature_importances. This can be overridden to False for components that do not need to be fit or whose fit methods do nothing.
-
property
parameters(self)¶ Returns the parameters which were used to initialize the component
-
save(self, file_path, pickle_protocol=cloudpickle.DEFAULT_PROTOCOL)¶ Saves component at file path
- Parameters
file_path (str) – Location to save file
pickle_protocol (int) – The pickle data stream format.
- Returns
None
-
class
evalml.pipelines.components.transformers.preprocessing.DelayedFeatureTransformer(date_index=None, max_delay=2, delay_features=True, delay_target=True, gap=1, random_seed=0, **kwargs)[source]¶ Transformer that delays input features and target variable for time series problems.
- Parameters
date_index (str) – Name of the column containing the datetime information used to order the data. Ignored.
max_delay (int) – Maximum number of time units to delay each feature. Defaults to 2.
delay_features (bool) – Whether to delay the input features. Defaults to True.
delay_target (bool) – Whether to delay the target. Defaults to True.
gap (int) – The number of time units between when the features are collected and when the target is collected. For example, if you are predicting the next time step’s target, gap=1. This is only needed because when gap=0, we need to be sure to start the lagging of the target variable at 1. Defaults to 1.
random_seed (int) – Seed for the random number generator. This transformer performs the same regardless of the random seed provided.
Attributes
hyperparameter_ranges
{}
model_family
ModelFamily.NONE
modifies_features
True
modifies_target
False
name
Delayed Feature Transformer
needs_fitting
False
Methods
Constructs a new component with the same parameters and random state.
Returns the default parameters for this component.
Describe a component and its parameters
Fits the DelayFeatureTransformer.
Fits on X and transforms X
Loads component at file path
Returns the parameters which were used to initialize the component
Saves component at file path
Computes the delayed features for all features in X and y.
-
clone(self)¶ Constructs a new component with the same parameters and random state.
- Returns
A new instance of this component with identical parameters and random state.
-
default_parameters(cls)¶ Returns the default parameters for this component.
Our convention is that Component.default_parameters == Component().parameters.
- Returns
default parameters for this component.
- Return type
dict
-
describe(self, print_name=False, return_dict=False)¶ Describe a component and its parameters
- Parameters
print_name (bool, optional) – whether to print name of component
return_dict (bool, optional) – whether to return description as dictionary in the format {“name”: name, “parameters”: parameters}
- Returns
prints and returns dictionary
- Return type
None or dict
-
fit(self, X, y=None)[source]¶ Fits the DelayFeatureTransformer.
- Parameters
X (pd.DataFrame or np.ndarray) – The input training data of shape [n_samples, n_features]
y (pd.Series, optional) – The target training data of length [n_samples]
- Returns
self
-
fit_transform(self, X, y)[source]¶ Fits on X and transforms X
- Parameters
X (pd.DataFrame) – Data to fit and transform
y (pd.Series) – Target data
- Returns
Transformed X
- Return type
pd.DataFrame
-
static
load(file_path)¶ Loads component at file path
- Parameters
file_path (str) – Location to load file
- Returns
ComponentBase object
-
property
parameters(self)¶ Returns the parameters which were used to initialize the component
-
save(self, file_path, pickle_protocol=cloudpickle.DEFAULT_PROTOCOL)¶ Saves component at file path
- Parameters
file_path (str) – Location to save file
pickle_protocol (int) – The pickle data stream format.
- Returns
None
-
transform(self, X, y=None)[source]¶ Computes the delayed features for all features in X and y.
For each feature in X, it will add a column to the output dataframe for each delay in the (inclusive) range [1, max_delay]. The values of each delayed feature are simply the original feature shifted forward in time by the delay amount. For example, a delay of 3 units means that the feature value at row n will be taken from the n-3rd row of that feature
If y is not None, it will also compute the delayed values for the target variable.
- Parameters
X (pd.DataFrame or None) – Data to transform. None is expected when only the target variable is being used.
y (pd.Series, or None) – Target.
- Returns
Transformed X.
- Return type
pd.DataFrame
-
class
evalml.pipelines.components.transformers.preprocessing.DFSTransformer(index='index', random_seed=0, **kwargs)[source]¶ Featuretools DFS component that generates features for the input features.
- Parameters
index (string) – The name of the column that contains the indices. If no column with this name exists, then featuretools.EntitySet() creates a column with this name to serve as the index column. Defaults to ‘index’.
random_seed (int) – Seed for the random number generator. Defaults to 0.
Attributes
hyperparameter_ranges
{}
model_family
ModelFamily.NONE
modifies_features
True
modifies_target
False
name
DFS Transformer
Methods
Constructs a new component with the same parameters and random state.
Returns the default parameters for this component.
Describe a component and its parameters
Fits the DFSTransformer Transformer component.
Fits on X and transforms X
Loads component at file path
Returns boolean determining if component needs fitting before
Returns the parameters which were used to initialize the component
Saves component at file path
Computes the feature matrix for the input X using featuretools’ dfs algorithm.
-
clone(self)¶ Constructs a new component with the same parameters and random state.
- Returns
A new instance of this component with identical parameters and random state.
-
default_parameters(cls)¶ Returns the default parameters for this component.
Our convention is that Component.default_parameters == Component().parameters.
- Returns
default parameters for this component.
- Return type
dict
-
describe(self, print_name=False, return_dict=False)¶ Describe a component and its parameters
- Parameters
print_name (bool, optional) – whether to print name of component
return_dict (bool, optional) – whether to return description as dictionary in the format {“name”: name, “parameters”: parameters}
- Returns
prints and returns dictionary
- Return type
None or dict
-
fit(self, X, y=None)[source]¶ Fits the DFSTransformer Transformer component.
- Parameters
X (pd.DataFrame, np.array) – The input data to transform, of shape [n_samples, n_features]
y (pd.Series, np.ndarray, optional) – The target training data of length [n_samples]
- Returns
self
-
fit_transform(self, X, y=None)¶ Fits on X and transforms X
- Parameters
X (pd.DataFrame) – Data to fit and transform
y (pd.Series) – Target data
- Returns
Transformed X
- Return type
pd.DataFrame
-
static
load(file_path)¶ Loads component at file path
- Parameters
file_path (str) – Location to load file
- Returns
ComponentBase object
-
needs_fitting(self)¶ Returns boolean determining if component needs fitting before calling predict, predict_proba, transform, or feature_importances. This can be overridden to False for components that do not need to be fit or whose fit methods do nothing.
-
property
parameters(self)¶ Returns the parameters which were used to initialize the component
-
save(self, file_path, pickle_protocol=cloudpickle.DEFAULT_PROTOCOL)¶ Saves component at file path
- Parameters
file_path (str) – Location to save file
pickle_protocol (int) – The pickle data stream format.
- Returns
None
-
transform(self, X, y=None)[source]¶ Computes the feature matrix for the input X using featuretools’ dfs algorithm.
- Parameters
X (pd.DataFrame or np.ndarray) – The input training data to transform. Has shape [n_samples, n_features]
y (pd.Series, optional) – Ignored.
- Returns
Feature matrix
- Return type
pd.DataFrame
-
class
evalml.pipelines.components.transformers.preprocessing.DropNullColumns(pct_null_threshold=1.0, random_seed=0, **kwargs)[source]¶ Transformer to drop features whose percentage of NaN values exceeds a specified threshold.
- Parameters
pct_null_threshold (float) – The percentage of NaN values in an input feature to drop. Must be a value between [0, 1] inclusive. If equal to 0.0, will drop columns with any null values. If equal to 1.0, will drop columns with all null values. Defaults to 0.95.
random_seed (int) – Seed for the random number generator. Defaults to 0.
Attributes
hyperparameter_ranges
{}
model_family
ModelFamily.NONE
modifies_features
True
modifies_target
False
name
Drop Null Columns Transformer
Methods
Constructs a new component with the same parameters and random state.
Returns the default parameters for this component.
Describe a component and its parameters
Fits component to data
Fits on X and transforms X
Loads component at file path
Returns boolean determining if component needs fitting before
Returns the parameters which were used to initialize the component
Saves component at file path
Transforms data X by dropping columns that exceed the threshold of null values.
-
clone(self)¶ Constructs a new component with the same parameters and random state.
- Returns
A new instance of this component with identical parameters and random state.
-
default_parameters(cls)¶ Returns the default parameters for this component.
Our convention is that Component.default_parameters == Component().parameters.
- Returns
default parameters for this component.
- Return type
dict
-
describe(self, print_name=False, return_dict=False)¶ Describe a component and its parameters
- Parameters
print_name (bool, optional) – whether to print name of component
return_dict (bool, optional) – whether to return description as dictionary in the format {“name”: name, “parameters”: parameters}
- Returns
prints and returns dictionary
- Return type
None or dict
-
fit(self, X, y=None)[source]¶ Fits component to data
- Parameters
X (list, pd.DataFrame or np.ndarray) – The input training data of shape [n_samples, n_features]
y (list, pd.Series, np.ndarray, optional) – The target training data of length [n_samples]
- Returns
self
-
fit_transform(self, X, y=None)¶ Fits on X and transforms X
- Parameters
X (pd.DataFrame) – Data to fit and transform
y (pd.Series) – Target data
- Returns
Transformed X
- Return type
pd.DataFrame
-
static
load(file_path)¶ Loads component at file path
- Parameters
file_path (str) – Location to load file
- Returns
ComponentBase object
-
needs_fitting(self)¶ Returns boolean determining if component needs fitting before calling predict, predict_proba, transform, or feature_importances. This can be overridden to False for components that do not need to be fit or whose fit methods do nothing.
-
property
parameters(self)¶ Returns the parameters which were used to initialize the component
-
save(self, file_path, pickle_protocol=cloudpickle.DEFAULT_PROTOCOL)¶ Saves component at file path
- Parameters
file_path (str) – Location to save file
pickle_protocol (int) – The pickle data stream format.
- Returns
None
-
class
evalml.pipelines.components.transformers.preprocessing.EmailFeaturizer(random_seed=0, **kwargs)[source]¶ Transformer that can automatically extract features from emails.
- Parameters
random_seed (int) – Seed for the random number generator. Defaults to 0.
Attributes
hyperparameter_ranges
{}
model_family
ModelFamily.NONE
modifies_features
True
modifies_target
False
name
Email Featurizer
Methods
Constructs a new component with the same parameters and random state.
Returns the default parameters for this component.
Describe a component and its parameters
Fits component to data
Fits on X and transforms X
Loads component at file path
Returns boolean determining if component needs fitting before
Returns the parameters which were used to initialize the component
Saves component at file path
Transforms data X.
-
clone(self)¶ Constructs a new component with the same parameters and random state.
- Returns
A new instance of this component with identical parameters and random state.
-
default_parameters(cls)¶ Returns the default parameters for this component.
Our convention is that Component.default_parameters == Component().parameters.
- Returns
default parameters for this component.
- Return type
dict
-
describe(self, print_name=False, return_dict=False)¶ Describe a component and its parameters
- Parameters
print_name (bool, optional) – whether to print name of component
return_dict (bool, optional) – whether to return description as dictionary in the format {“name”: name, “parameters”: parameters}
- Returns
prints and returns dictionary
- Return type
None or dict
-
fit(self, X, y=None)¶ Fits component to data
- Parameters
X (list, pd.DataFrame or np.ndarray) – The input training data of shape [n_samples, n_features]
y (list, pd.Series, np.ndarray, optional) – The target training data of length [n_samples]
- Returns
self
-
fit_transform(self, X, y=None)¶ Fits on X and transforms X
- Parameters
X (pd.DataFrame) – Data to fit and transform
y (pd.Series) – Target data
- Returns
Transformed X
- Return type
pd.DataFrame
-
static
load(file_path)¶ Loads component at file path
- Parameters
file_path (str) – Location to load file
- Returns
ComponentBase object
-
needs_fitting(self)¶ Returns boolean determining if component needs fitting before calling predict, predict_proba, transform, or feature_importances. This can be overridden to False for components that do not need to be fit or whose fit methods do nothing.
-
property
parameters(self)¶ Returns the parameters which were used to initialize the component
-
save(self, file_path, pickle_protocol=cloudpickle.DEFAULT_PROTOCOL)¶ Saves component at file path
- Parameters
file_path (str) – Location to save file
pickle_protocol (int) – The pickle data stream format.
- Returns
None
-
transform(self, X, y=None)¶ Transforms data X.
- Parameters
X (pd.DataFrame) – Data to transform.
y (pd.Series, optional) – Target data.
- Returns
Transformed X
- Return type
pd.DataFrame
-
class
evalml.pipelines.components.transformers.preprocessing.LogTransformer(random_seed=0)[source]¶ Applies a log transformation to the target data.
Attributes
hyperparameter_ranges
{}
model_family
ModelFamily.NONE
modifies_features
False
modifies_target
True
name
Log Transformer
Methods
Constructs a new component with the same parameters and random state.
Returns the default parameters for this component.
Describe a component and its parameters
Fits the LogTransformer.
Log transforms the target variable.
Inverts the transformation done by the transform method.
Loads component at file path
Returns boolean determining if component needs fitting before
Returns the parameters which were used to initialize the component
Saves component at file path
Log transforms the target variable.
-
clone(self)¶ Constructs a new component with the same parameters and random state.
- Returns
A new instance of this component with identical parameters and random state.
-
default_parameters(cls)¶ Returns the default parameters for this component.
Our convention is that Component.default_parameters == Component().parameters.
- Returns
default parameters for this component.
- Return type
dict
-
describe(self, print_name=False, return_dict=False)¶ Describe a component and its parameters
- Parameters
print_name (bool, optional) – whether to print name of component
return_dict (bool, optional) – whether to return description as dictionary in the format {“name”: name, “parameters”: parameters}
- Returns
prints and returns dictionary
- Return type
None or dict
-
fit(self, X, y=None)[source]¶ Fits the LogTransformer.
- Parameters
X (pd.DataFrame or np.ndarray) – Ignored.
y (pd.Series, optional) – Ignored.
- Returns
self
-
fit_transform(self, X, y=None)[source]¶ Log transforms the target variable.
- Parameters
X (pd.DataFrame, optional) – Ignored.
y (pd.Series) – Target variable to log transform.
- Returns
- The input features are returned without modification. The target
variable y is log transformed.
- Return type
tuple of pd.DataFrame, pd.Series
-
inverse_transform(self, y)[source]¶ Inverts the transformation done by the transform method.
- Arguments:
y (pd.Series): Target transformed by this component.
- Returns
Target without the transformation.
- Return type
pd.Seriesø
-
static
load(file_path)¶ Loads component at file path
- Parameters
file_path (str) – Location to load file
- Returns
ComponentBase object
-
needs_fitting(self)¶ Returns boolean determining if component needs fitting before calling predict, predict_proba, transform, or feature_importances. This can be overridden to False for components that do not need to be fit or whose fit methods do nothing.
-
property
parameters(self)¶ Returns the parameters which were used to initialize the component
-
save(self, file_path, pickle_protocol=cloudpickle.DEFAULT_PROTOCOL)¶ Saves component at file path
- Parameters
file_path (str) – Location to save file
pickle_protocol (int) – The pickle data stream format.
- Returns
None
-
transform(self, X, y=None)[source]¶ Log transforms the target variable.
- Parameters
X (pd.DataFrame, optional) – Ignored.
y (pd.Series) – Target data to log transform.
- Returns
- The input features are returned without modification. The target
variable y is log transformed.
- Return type
tuple of pd.DataFrame, pd.Series
-
-
class
evalml.pipelines.components.transformers.preprocessing.LSA(random_seed=0, **kwargs)[source]¶ Transformer to calculate the Latent Semantic Analysis Values of text input.
- Parameters
random_seed (int) – Seed for the random number generator. Defaults to 0.
Attributes
hyperparameter_ranges
{}
model_family
ModelFamily.NONE
modifies_features
True
modifies_target
False
name
LSA Transformer
Methods
Constructs a new component with the same parameters and random state.
Returns the default parameters for this component.
Describe a component and its parameters
Fits component to data
Fits on X and transforms X
Loads component at file path
Returns boolean determining if component needs fitting before
Returns the parameters which were used to initialize the component
Saves component at file path
Transforms data X by applying the LSA pipeline.
-
clone(self)¶ Constructs a new component with the same parameters and random state.
- Returns
A new instance of this component with identical parameters and random state.
-
default_parameters(cls)¶ Returns the default parameters for this component.
Our convention is that Component.default_parameters == Component().parameters.
- Returns
default parameters for this component.
- Return type
dict
-
describe(self, print_name=False, return_dict=False)¶ Describe a component and its parameters
- Parameters
print_name (bool, optional) – whether to print name of component
return_dict (bool, optional) – whether to return description as dictionary in the format {“name”: name, “parameters”: parameters}
- Returns
prints and returns dictionary
- Return type
None or dict
-
fit(self, X, y=None)[source]¶ Fits component to data
- Parameters
X (list, pd.DataFrame or np.ndarray) – The input training data of shape [n_samples, n_features]
y (list, pd.Series, np.ndarray, optional) – The target training data of length [n_samples]
- Returns
self
-
fit_transform(self, X, y=None)¶ Fits on X and transforms X
- Parameters
X (pd.DataFrame) – Data to fit and transform
y (pd.Series) – Target data
- Returns
Transformed X
- Return type
pd.DataFrame
-
static
load(file_path)¶ Loads component at file path
- Parameters
file_path (str) – Location to load file
- Returns
ComponentBase object
-
needs_fitting(self)¶ Returns boolean determining if component needs fitting before calling predict, predict_proba, transform, or feature_importances. This can be overridden to False for components that do not need to be fit or whose fit methods do nothing.
-
property
parameters(self)¶ Returns the parameters which were used to initialize the component
-
save(self, file_path, pickle_protocol=cloudpickle.DEFAULT_PROTOCOL)¶ Saves component at file path
- Parameters
file_path (str) – Location to save file
pickle_protocol (int) – The pickle data stream format.
- Returns
None
-
transform(self, X, y=None)[source]¶ Transforms data X by applying the LSA pipeline.
- Parameters
X (pd.DataFrame) – The data to transform.
y (pd.Series, optional) – Ignored.
- Returns
- Transformed X. The original column is removed and replaced with two columns of the
format LSA(original_column_name)[feature_number], where feature_number is 0 or 1.
- Return type
pd.DataFrame
-
class
evalml.pipelines.components.transformers.preprocessing.PolynomialDetrender(degree=1, random_seed=0, **kwargs)[source]¶ Removes trends from time series by fitting a polynomial to the data.
- Parameters
degree (int) – Degree for the polynomial. If 1, linear model is fit to the data. If 2, quadratic model is fit, etc. Defaults to 1.
random_seed (int) – Seed for the random number generator. Defaults to 0.
Attributes
hyperparameter_ranges
{ “degree”: Integer(1, 3)}
model_family
ModelFamily.NONE
modifies_features
False
modifies_target
True
name
Polynomial Detrender
Methods
Constructs a new component with the same parameters and random state.
Returns the default parameters for this component.
Describe a component and its parameters
Fits the PolynomialDetrender.
Removes fitted trend from target variable.
Adds back fitted trend to target variable.
Loads component at file path
Returns boolean determining if component needs fitting before
Returns the parameters which were used to initialize the component
Saves component at file path
Removes fitted trend from target variable.
-
clone(self)¶ Constructs a new component with the same parameters and random state.
- Returns
A new instance of this component with identical parameters and random state.
-
default_parameters(cls)¶ Returns the default parameters for this component.
Our convention is that Component.default_parameters == Component().parameters.
- Returns
default parameters for this component.
- Return type
dict
-
describe(self, print_name=False, return_dict=False)¶ Describe a component and its parameters
- Parameters
print_name (bool, optional) – whether to print name of component
return_dict (bool, optional) – whether to return description as dictionary in the format {“name”: name, “parameters”: parameters}
- Returns
prints and returns dictionary
- Return type
None or dict
-
fit(self, X, y=None)[source]¶ Fits the PolynomialDetrender.
- Parameters
X (pd.DataFrame, optional) – Ignored.
y (pd.Series) – Target variable to detrend.
- Returns
self
-
fit_transform(self, X, y=None)[source]¶ Removes fitted trend from target variable.
- Parameters
X (pd.DataFrame, optional) – Ignored.
y (pd.Series) – Target variable to detrend.
- Returns
- The first element are the input features returned without modification.
The second element is the target variable y with the fitted trend removed.
- Return type
tuple of pd.DataFrame, pd.Series
-
inverse_transform(self, y)[source]¶ Adds back fitted trend to target variable.
- Parameters
X (pd.DataFrame, optional) – Ignored.
y (pd.Series) – Target variable.
- Returns
- The first element are the input features returned without modification.
The second element is the target variable y with the trend added back.
- Return type
tuple of pd.DataFrame, pd.Series
-
static
load(file_path)¶ Loads component at file path
- Parameters
file_path (str) – Location to load file
- Returns
ComponentBase object
-
needs_fitting(self)¶ Returns boolean determining if component needs fitting before calling predict, predict_proba, transform, or feature_importances. This can be overridden to False for components that do not need to be fit or whose fit methods do nothing.
-
property
parameters(self)¶ Returns the parameters which were used to initialize the component
-
save(self, file_path, pickle_protocol=cloudpickle.DEFAULT_PROTOCOL)¶ Saves component at file path
- Parameters
file_path (str) – Location to save file
pickle_protocol (int) – The pickle data stream format.
- Returns
None
-
transform(self, X, y=None)[source]¶ Removes fitted trend from target variable.
- Parameters
X (pd.DataFrame, optional) – Ignored.
y (pd.Series) – Target variable to detrend.
- Returns
- The input features are returned without modification. The target
variable y is detrended
- Return type
tuple of pd.DataFrame, pd.Series
-
class
evalml.pipelines.components.transformers.preprocessing.TextFeaturizer(random_seed=0, **kwargs)[source]¶ Transformer that can automatically featurize text columns using featuretools’ nlp_primitives.
Since models cannot handle non-numeric data, any text must be broken down into features that provide useful information about that text. This component splits each text column into several informative features: Diversity Score, Mean Characters per Word, Polarity Score, and LSA (Latent Semantic Analysis). Calling transform on this component will replace any text columns in the given dataset with these numeric columns.
- Parameters
random_seed (int) – Seed for the random number generator. Defaults to 0.
Attributes
hyperparameter_ranges
{}
model_family
ModelFamily.NONE
modifies_features
True
modifies_target
False
name
Text Featurization Component
Methods
Constructs a new component with the same parameters and random state.
Returns the default parameters for this component.
Describe a component and its parameters
Fits component to data
Fits on X and transforms X
Loads component at file path
Returns boolean determining if component needs fitting before
Returns the parameters which were used to initialize the component
Saves component at file path
Transforms data X by creating new features using existing text columns
-
clone(self)¶ Constructs a new component with the same parameters and random state.
- Returns
A new instance of this component with identical parameters and random state.
-
default_parameters(cls)¶ Returns the default parameters for this component.
Our convention is that Component.default_parameters == Component().parameters.
- Returns
default parameters for this component.
- Return type
dict
-
describe(self, print_name=False, return_dict=False)¶ Describe a component and its parameters
- Parameters
print_name (bool, optional) – whether to print name of component
return_dict (bool, optional) – whether to return description as dictionary in the format {“name”: name, “parameters”: parameters}
- Returns
prints and returns dictionary
- Return type
None or dict
-
fit(self, X, y=None)[source]¶ Fits component to data
- Parameters
X (pd.DataFrame or np.ndarray) – The input training data of shape [n_samples, n_features]
y (pd.Series, np.ndarray, optional) – The target training data of length [n_samples]
- Returns
self
-
fit_transform(self, X, y=None)¶ Fits on X and transforms X
- Parameters
X (pd.DataFrame) – Data to fit and transform
y (pd.Series) – Target data
- Returns
Transformed X
- Return type
pd.DataFrame
-
static
load(file_path)¶ Loads component at file path
- Parameters
file_path (str) – Location to load file
- Returns
ComponentBase object
-
needs_fitting(self)¶ Returns boolean determining if component needs fitting before calling predict, predict_proba, transform, or feature_importances. This can be overridden to False for components that do not need to be fit or whose fit methods do nothing.
-
property
parameters(self)¶ Returns the parameters which were used to initialize the component
-
save(self, file_path, pickle_protocol=cloudpickle.DEFAULT_PROTOCOL)¶ Saves component at file path
- Parameters
file_path (str) – Location to save file
pickle_protocol (int) – The pickle data stream format.
- Returns
None
-
class
evalml.pipelines.components.transformers.preprocessing.TextTransformer(component_obj=None, random_seed=0, **kwargs)[source]¶ Base class for all transformers working with text features.
- Parameters
component_obj (obj) – Third-party objects useful in component implementation. Defaults to None.
random_seed (int) – Seed for the random number generator. Defaults to 0.
Attributes
model_family
ModelFamily.NONE
modifies_features
True
modifies_target
False
Methods
Constructs a new component with the same parameters and random state.
Returns the default parameters for this component.
Describe a component and its parameters
Fits component to data
Fits on X and transforms X
Loads component at file path
Returns string name of this component
Returns boolean determining if component needs fitting before
Returns the parameters which were used to initialize the component
Saves component at file path
Transforms data X.
-
clone(self)¶ Constructs a new component with the same parameters and random state.
- Returns
A new instance of this component with identical parameters and random state.
-
default_parameters(cls)¶ Returns the default parameters for this component.
Our convention is that Component.default_parameters == Component().parameters.
- Returns
default parameters for this component.
- Return type
dict
-
describe(self, print_name=False, return_dict=False)¶ Describe a component and its parameters
- Parameters
print_name (bool, optional) – whether to print name of component
return_dict (bool, optional) – whether to return description as dictionary in the format {“name”: name, “parameters”: parameters}
- Returns
prints and returns dictionary
- Return type
None or dict
-
fit(self, X, y=None)¶ Fits component to data
- Parameters
X (list, pd.DataFrame or np.ndarray) – The input training data of shape [n_samples, n_features]
y (list, pd.Series, np.ndarray, optional) – The target training data of length [n_samples]
- Returns
self
-
fit_transform(self, X, y=None)¶ Fits on X and transforms X
- Parameters
X (pd.DataFrame) – Data to fit and transform
y (pd.Series) – Target data
- Returns
Transformed X
- Return type
pd.DataFrame
-
static
load(file_path)¶ Loads component at file path
- Parameters
file_path (str) – Location to load file
- Returns
ComponentBase object
-
property
name(cls)¶ Returns string name of this component
-
needs_fitting(self)¶ Returns boolean determining if component needs fitting before calling predict, predict_proba, transform, or feature_importances. This can be overridden to False for components that do not need to be fit or whose fit methods do nothing.
-
property
parameters(self)¶ Returns the parameters which were used to initialize the component
-
save(self, file_path, pickle_protocol=cloudpickle.DEFAULT_PROTOCOL)¶ Saves component at file path
- Parameters
file_path (str) – Location to save file
pickle_protocol (int) – The pickle data stream format.
- Returns
None
-
transform(self, X, y=None)¶ Transforms data X.
- Parameters
X (pd.DataFrame) – Data to transform.
y (pd.Series, optional) – Target data.
- Returns
Transformed X
- Return type
pd.DataFrame
-
class
evalml.pipelines.components.transformers.preprocessing.URLFeaturizer(random_seed=0, **kwargs)[source]¶ Transformer that can automatically extract features from URL.
- Parameters
random_seed (int) – Seed for the random number generator. Defaults to 0.
Attributes
hyperparameter_ranges
{}
model_family
ModelFamily.NONE
modifies_features
True
modifies_target
False
name
URL Featurizer
Methods
Constructs a new component with the same parameters and random state.
Returns the default parameters for this component.
Describe a component and its parameters
Fits component to data
Fits on X and transforms X
Loads component at file path
Returns boolean determining if component needs fitting before
Returns the parameters which were used to initialize the component
Saves component at file path
Transforms data X.
-
clone(self)¶ Constructs a new component with the same parameters and random state.
- Returns
A new instance of this component with identical parameters and random state.
-
default_parameters(cls)¶ Returns the default parameters for this component.
Our convention is that Component.default_parameters == Component().parameters.
- Returns
default parameters for this component.
- Return type
dict
-
describe(self, print_name=False, return_dict=False)¶ Describe a component and its parameters
- Parameters
print_name (bool, optional) – whether to print name of component
return_dict (bool, optional) – whether to return description as dictionary in the format {“name”: name, “parameters”: parameters}
- Returns
prints and returns dictionary
- Return type
None or dict
-
fit(self, X, y=None)¶ Fits component to data
- Parameters
X (list, pd.DataFrame or np.ndarray) – The input training data of shape [n_samples, n_features]
y (list, pd.Series, np.ndarray, optional) – The target training data of length [n_samples]
- Returns
self
-
fit_transform(self, X, y=None)¶ Fits on X and transforms X
- Parameters
X (pd.DataFrame) – Data to fit and transform
y (pd.Series) – Target data
- Returns
Transformed X
- Return type
pd.DataFrame
-
static
load(file_path)¶ Loads component at file path
- Parameters
file_path (str) – Location to load file
- Returns
ComponentBase object
-
needs_fitting(self)¶ Returns boolean determining if component needs fitting before calling predict, predict_proba, transform, or feature_importances. This can be overridden to False for components that do not need to be fit or whose fit methods do nothing.
-
property
parameters(self)¶ Returns the parameters which were used to initialize the component
-
save(self, file_path, pickle_protocol=cloudpickle.DEFAULT_PROTOCOL)¶ Saves component at file path
- Parameters
file_path (str) – Location to save file
pickle_protocol (int) – The pickle data stream format.
- Returns
None
-
transform(self, X, y=None)¶ Transforms data X.
- Parameters
X (pd.DataFrame) – Data to transform.
y (pd.Series, optional) – Target data.
- Returns
Transformed X
- Return type
pd.DataFrame