Module imodelsx.linear_ngram

Simple scikit-learn interface for finetuning a single linear layer on top of LLM embeddings.

Expand source code 
"""
Simple scikit-learn interface for finetuning a single linear layer on top of LLM embeddings.
"""
from numpy.typing import ArrayLike
import numpy as np
from scipy.special import softmax
from sklearn.base import BaseEstimator, ClassifierMixin, RegressorMixin
from sklearn.linear_model import LogisticRegressionCV, RidgeCV
from sklearn.utils.multiclass import unique_labels
from sklearn.utils.validation import check_is_fitted
# from spacy.lang.en import English
from scipy.sparse import issparse
from sklearn.preprocessing import StandardScaler
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
import transformers
from tqdm import tqdm
import os
import os.path
import warnings
import pickle as pkl
import torch
from sklearn.exceptions import ConvergenceWarning

device = "cuda" if torch.cuda.is_available() else "cpu"


class LinearNgram(BaseEstimator):
    def __init__(
        self,
        checkpoint: str = "tfidfvectorizer",
        tokenizer=None,
        ngrams=2,
        all_ngrams=True,
        random_state=None,
    ):
        """LinearNgram Class - use either LinearNgramClassifier or LinearNgramRegressor rather than initializing this class directly.

        Parameters
        ----------
        checkpoint: str
            Name of vectorizer checkpoint: "countvectorizer" or "tfidfvectorizer"
        ngrams
            Order of ngrams to extract. 1 for unigrams, 2 for bigrams, etc.
        all_ngrams
            Whether to use all order ngrams <= ngrams argument
        random_state
            random seed for fitting

        Example
        -------
        ```
        from imodelsx import LinearNgramClassifier
        import datasets
        import numpy as np

        # load data
        dset = datasets.load_dataset('rotten_tomatoes')['train']
        dset = dset.select(np.random.choice(len(dset), size=300, replace=False))
        dset_val = datasets.load_dataset('rotten_tomatoes')['validation']
        dset_val = dset_val.select(np.random.choice(len(dset_val), size=300, replace=False))


        # fit a simple ngram model
        m = LinearNgramClassifier()
        m.fit(dset['text'], dset['label'])
        preds = m.predict(dset_val['text'])
        acc = (preds == dset_val['label']).mean()
        print('validation acc', acc)
        ```
        """
        assert checkpoint in ["countvectorizer", "tfidfvectorizer"]
        self.checkpoint = checkpoint
        self.tokenizer = tokenizer
        self.ngrams = ngrams
        self.all_ngrams = all_ngrams
        self.random_state = random_state

    def fit(
        self,
        X_text: ArrayLike,
        y: ArrayLike,
        verbose=True,
    ):
        """Extract embeddings then fit linear model

        Parameters
        ----------
        X_text: ArrayLike[str]
        y: ArrayLike[str]
        """

        # metadata
        if isinstance(self, ClassifierMixin):
            self.classes_ = unique_labels(y)
        if self.random_state is not None:
            np.random.seed(self.random_state)

        # set up model
        if verbose:
            print("initializing model...")

        # get embs
        if verbose:
            print("calculating embeddings...")
        if self.all_ngrams:
            lower_ngram = 1
        else:
            lower_ngram = self.ngrams

        # get vectorizer
        if self.checkpoint == "countvectorizer":
            self.vectorizer = CountVectorizer(
                tokenizer=self.tokenizer, ngram_range=(
                    lower_ngram, self.ngrams)
            )
        elif self.checkpoint == "tfidfvectorizer":
            self.vectorizer = TfidfVectorizer(
                tokenizer=self.tokenizer, ngram_range=(
                    lower_ngram, self.ngrams)
            )

        # get embs
        embs = self.vectorizer.fit_transform(X_text)

        # train linear
        warnings.filterwarnings("ignore", category=ConvergenceWarning)
        if verbose:
            print("training linear model...")
        if isinstance(self, ClassifierMixin):
            self.linear = LogisticRegressionCV()
        elif isinstance(self, RegressorMixin):
            self.linear = RidgeCV()
        self.linear.fit(embs, y)

        return self

    def predict(self, X_text):
        """For regression returns continuous output.
        For classification, returns discrete output.
        """
        check_is_fitted(self)
        embs = self.vectorizer.transform(X_text)
        return self.linear.predict(embs)

    def predict_proba(self, X_text):
        check_is_fitted(self)
        embs = self.vectorizer.transform(X_text)
        return self.linear.predict_proba(embs)


class LinearNgramRegressor(LinearNgram, RegressorMixin):
    ...


class LinearNgramClassifier(LinearNgram, ClassifierMixin):
    ...


if __name__ == "__main__":
    import imodelsx.data

    dset, k = imodelsx.data.load_huggingface_dataset(
        "rotten_tomatoes", binary_classification=False, subsample_frac=0.1
    )
    print(dset)
    print(dset["train"])
    print(np.unique(dset["train"]["label"]))

    clf = LinearNgramClassifier()
    clf.fit(dset["train"]["text"], dset["train"]["label"])

    print("predicting")
    preds = clf.predict(dset["test"]["text"])
    print(preds.shape)

    print("predicting proba")
    preds_proba = clf.predict_proba(dset["test"]["text"])
    print(preds_proba.shape)

    assert preds_proba.shape[0] == preds.shape[0]
    print(
        "acc_train",
        np.mean(clf.predict(dset["train"]["text"]) == dset["train"]["label"]),
    )
    print("acc_test", np.mean(preds == dset["test"]["label"]))

Classes

class LinearNgram (checkpoint: str = 'tfidfvectorizer', tokenizer=None, ngrams=2, all_ngrams=True, random_state=None)

Base class for all estimators in scikit-learn.

Inheriting from this class provides default implementations of:

  • setting and getting parameters used by GridSearchCV and friends;
  • textual and HTML representation displayed in terminals and IDEs;
  • estimator serialization;
  • parameters validation;
  • data validation;
  • feature names validation.

Read more in the :ref:User Guide <rolling_your_own_estimator>.

Notes

All estimators should specify all the parameters that can be set at the class level in their __init__ as explicit keyword arguments (no *args or **kwargs).

Examples

>>> import numpy as np
>>> from sklearn.base import BaseEstimator
>>> class MyEstimator(BaseEstimator):
...     def __init__(self, *, param=1):
...         self.param = param
...     def fit(self, X, y=None):
...         self.is_fitted_ = True
...         return self
...     def predict(self, X):
...         return np.full(shape=X.shape[0], fill_value=self.param)
>>> estimator = MyEstimator(param=2)
>>> estimator.get_params()
{'param': 2}
>>> X = np.array([[1, 2], [2, 3], [3, 4]])
>>> y = np.array([1, 0, 1])
>>> estimator.fit(X, y).predict(X)
array([2, 2, 2])
>>> estimator.set_params(param=3).fit(X, y).predict(X)
array([3, 3, 3])

LinearNgram Class - use either LinearNgramClassifier or LinearNgramRegressor rather than initializing this class directly.

Parameters

checkpoint : str
Name of vectorizer checkpoint: "countvectorizer" or "tfidfvectorizer"
ngrams
Order of ngrams to extract. 1 for unigrams, 2 for bigrams, etc.
all_ngrams
Whether to use all order ngrams <= ngrams argument
random_state
random seed for fitting

Example

from imodelsx import LinearNgramClassifier
import datasets
import numpy as np

# load data
dset = datasets.load_dataset('rotten_tomatoes')['train']
dset = dset.select(np.random.choice(len(dset), size=300, replace=False))
dset_val = datasets.load_dataset('rotten_tomatoes')['validation']
dset_val = dset_val.select(np.random.choice(len(dset_val), size=300, replace=False))


# fit a simple ngram model
m = LinearNgramClassifier()
m.fit(dset['text'], dset['label'])
preds = m.predict(dset_val['text'])
acc = (preds == dset_val['label']).mean()
print('validation acc', acc)
Expand source code 
class LinearNgram(BaseEstimator):
    def __init__(
        self,
        checkpoint: str = "tfidfvectorizer",
        tokenizer=None,
        ngrams=2,
        all_ngrams=True,
        random_state=None,
    ):
        """LinearNgram Class - use either LinearNgramClassifier or LinearNgramRegressor rather than initializing this class directly.

        Parameters
        ----------
        checkpoint: str
            Name of vectorizer checkpoint: "countvectorizer" or "tfidfvectorizer"
        ngrams
            Order of ngrams to extract. 1 for unigrams, 2 for bigrams, etc.
        all_ngrams
            Whether to use all order ngrams <= ngrams argument
        random_state
            random seed for fitting

        Example
        -------
        ```
        from imodelsx import LinearNgramClassifier
        import datasets
        import numpy as np

        # load data
        dset = datasets.load_dataset('rotten_tomatoes')['train']
        dset = dset.select(np.random.choice(len(dset), size=300, replace=False))
        dset_val = datasets.load_dataset('rotten_tomatoes')['validation']
        dset_val = dset_val.select(np.random.choice(len(dset_val), size=300, replace=False))


        # fit a simple ngram model
        m = LinearNgramClassifier()
        m.fit(dset['text'], dset['label'])
        preds = m.predict(dset_val['text'])
        acc = (preds == dset_val['label']).mean()
        print('validation acc', acc)
        ```
        """
        assert checkpoint in ["countvectorizer", "tfidfvectorizer"]
        self.checkpoint = checkpoint
        self.tokenizer = tokenizer
        self.ngrams = ngrams
        self.all_ngrams = all_ngrams
        self.random_state = random_state

    def fit(
        self,
        X_text: ArrayLike,
        y: ArrayLike,
        verbose=True,
    ):
        """Extract embeddings then fit linear model

        Parameters
        ----------
        X_text: ArrayLike[str]
        y: ArrayLike[str]
        """

        # metadata
        if isinstance(self, ClassifierMixin):
            self.classes_ = unique_labels(y)
        if self.random_state is not None:
            np.random.seed(self.random_state)

        # set up model
        if verbose:
            print("initializing model...")

        # get embs
        if verbose:
            print("calculating embeddings...")
        if self.all_ngrams:
            lower_ngram = 1
        else:
            lower_ngram = self.ngrams

        # get vectorizer
        if self.checkpoint == "countvectorizer":
            self.vectorizer = CountVectorizer(
                tokenizer=self.tokenizer, ngram_range=(
                    lower_ngram, self.ngrams)
            )
        elif self.checkpoint == "tfidfvectorizer":
            self.vectorizer = TfidfVectorizer(
                tokenizer=self.tokenizer, ngram_range=(
                    lower_ngram, self.ngrams)
            )

        # get embs
        embs = self.vectorizer.fit_transform(X_text)

        # train linear
        warnings.filterwarnings("ignore", category=ConvergenceWarning)
        if verbose:
            print("training linear model...")
        if isinstance(self, ClassifierMixin):
            self.linear = LogisticRegressionCV()
        elif isinstance(self, RegressorMixin):
            self.linear = RidgeCV()
        self.linear.fit(embs, y)

        return self

    def predict(self, X_text):
        """For regression returns continuous output.
        For classification, returns discrete output.
        """
        check_is_fitted(self)
        embs = self.vectorizer.transform(X_text)
        return self.linear.predict(embs)

    def predict_proba(self, X_text):
        check_is_fitted(self)
        embs = self.vectorizer.transform(X_text)
        return self.linear.predict_proba(embs)

Ancestors

  • sklearn.base.BaseEstimator
  • sklearn.utils._estimator_html_repr._HTMLDocumentationLinkMixin
  • sklearn.utils._metadata_requests._MetadataRequester

Subclasses

Methods

def fit(self, X_text: Union[numpy._typing._array_like._SupportsArray[numpy.dtype[Any]], numpy._typing._nested_sequence._NestedSequence[numpy._typing._array_like._SupportsArray[numpy.dtype[Any]]], bool, int, float, complex, str, bytes, numpy._typing._nested_sequence._NestedSequence[Union[bool, int, float, complex, str, bytes]]], y: Union[numpy._typing._array_like._SupportsArray[numpy.dtype[Any]], numpy._typing._nested_sequence._NestedSequence[numpy._typing._array_like._SupportsArray[numpy.dtype[Any]]], bool, int, float, complex, str, bytes, numpy._typing._nested_sequence._NestedSequence[Union[bool, int, float, complex, str, bytes]]], verbose=True)

Extract embeddings then fit linear model

Parameters

X_text : ArrayLike[str]
 
y : ArrayLike[str]
 
Expand source code 
def fit(
    self,
    X_text: ArrayLike,
    y: ArrayLike,
    verbose=True,
):
    """Extract embeddings then fit linear model

    Parameters
    ----------
    X_text: ArrayLike[str]
    y: ArrayLike[str]
    """

    # metadata
    if isinstance(self, ClassifierMixin):
        self.classes_ = unique_labels(y)
    if self.random_state is not None:
        np.random.seed(self.random_state)

    # set up model
    if verbose:
        print("initializing model...")

    # get embs
    if verbose:
        print("calculating embeddings...")
    if self.all_ngrams:
        lower_ngram = 1
    else:
        lower_ngram = self.ngrams

    # get vectorizer
    if self.checkpoint == "countvectorizer":
        self.vectorizer = CountVectorizer(
            tokenizer=self.tokenizer, ngram_range=(
                lower_ngram, self.ngrams)
        )
    elif self.checkpoint == "tfidfvectorizer":
        self.vectorizer = TfidfVectorizer(
            tokenizer=self.tokenizer, ngram_range=(
                lower_ngram, self.ngrams)
        )

    # get embs
    embs = self.vectorizer.fit_transform(X_text)

    # train linear
    warnings.filterwarnings("ignore", category=ConvergenceWarning)
    if verbose:
        print("training linear model...")
    if isinstance(self, ClassifierMixin):
        self.linear = LogisticRegressionCV()
    elif isinstance(self, RegressorMixin):
        self.linear = RidgeCV()
    self.linear.fit(embs, y)

    return self
def predict(self, X_text)

For regression returns continuous output. For classification, returns discrete output.

Expand source code 
def predict(self, X_text):
    """For regression returns continuous output.
    For classification, returns discrete output.
    """
    check_is_fitted(self)
    embs = self.vectorizer.transform(X_text)
    return self.linear.predict(embs)
def predict_proba(self, X_text)
Expand source code 
def predict_proba(self, X_text):
    check_is_fitted(self)
    embs = self.vectorizer.transform(X_text)
    return self.linear.predict_proba(embs)
def set_fit_request(self: LinearNgram, *, X_text: Union[bool, ForwardRef(None), str] = '$UNCHANGED$', verbose: Union[bool, ForwardRef(None), str] = '$UNCHANGED$') ‑> LinearNgram

Request metadata passed to the fit method.

Note that this method is only relevant if enable_metadata_routing=True (see :func:sklearn.set_config). Please see :ref:User Guide <metadata_routing> on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to fit.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version: 1.3

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a :class:~sklearn.pipeline.Pipeline. Otherwise it has no effect.

Parameters

X_text : str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED
Metadata routing for X_text parameter in fit.
verbose : str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED
Metadata routing for verbose parameter in fit.

Returns

self : object
The updated object.
Expand source code 
def func(**kw):
    """Updates the request for provided parameters

    This docstring is overwritten below.
    See REQUESTER_DOC for expected functionality
    """
    if not _routing_enabled():
        raise RuntimeError(
            "This method is only available when metadata routing is enabled."
            " You can enable it using"
            " sklearn.set_config(enable_metadata_routing=True)."
        )

    if self.validate_keys and (set(kw) - set(self.keys)):
        raise TypeError(
            f"Unexpected args: {set(kw) - set(self.keys)}. Accepted arguments"
            f" are: {set(self.keys)}"
        )

    requests = instance._get_metadata_request()
    method_metadata_request = getattr(requests, self.name)

    for prop, alias in kw.items():
        if alias is not UNCHANGED:
            method_metadata_request.add_request(param=prop, alias=alias)
    instance._metadata_request = requests

    return instance
def set_predict_proba_request(self: LinearNgram, *, X_text: Union[bool, ForwardRef(None), str] = '$UNCHANGED$') ‑> LinearNgram

Request metadata passed to the predict_proba method.

Note that this method is only relevant if enable_metadata_routing=True (see :func:sklearn.set_config). Please see :ref:User Guide <metadata_routing> on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to predict_proba if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to predict_proba.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version: 1.3

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a :class:~sklearn.pipeline.Pipeline. Otherwise it has no effect.

Parameters

X_text : str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED
Metadata routing for X_text parameter in predict_proba.

Returns

self : object
The updated object.
Expand source code 
def func(**kw):
    """Updates the request for provided parameters

    This docstring is overwritten below.
    See REQUESTER_DOC for expected functionality
    """
    if not _routing_enabled():
        raise RuntimeError(
            "This method is only available when metadata routing is enabled."
            " You can enable it using"
            " sklearn.set_config(enable_metadata_routing=True)."
        )

    if self.validate_keys and (set(kw) - set(self.keys)):
        raise TypeError(
            f"Unexpected args: {set(kw) - set(self.keys)}. Accepted arguments"
            f" are: {set(self.keys)}"
        )

    requests = instance._get_metadata_request()
    method_metadata_request = getattr(requests, self.name)

    for prop, alias in kw.items():
        if alias is not UNCHANGED:
            method_metadata_request.add_request(param=prop, alias=alias)
    instance._metadata_request = requests

    return instance
def set_predict_request(self: LinearNgram, *, X_text: Union[bool, ForwardRef(None), str] = '$UNCHANGED$') ‑> LinearNgram

Request metadata passed to the predict method.

Note that this method is only relevant if enable_metadata_routing=True (see :func:sklearn.set_config). Please see :ref:User Guide <metadata_routing> on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to predict.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version: 1.3

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a :class:~sklearn.pipeline.Pipeline. Otherwise it has no effect.

Parameters

X_text : str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED
Metadata routing for X_text parameter in predict.

Returns

self : object
The updated object.
Expand source code 
def func(**kw):
    """Updates the request for provided parameters

    This docstring is overwritten below.
    See REQUESTER_DOC for expected functionality
    """
    if not _routing_enabled():
        raise RuntimeError(
            "This method is only available when metadata routing is enabled."
            " You can enable it using"
            " sklearn.set_config(enable_metadata_routing=True)."
        )

    if self.validate_keys and (set(kw) - set(self.keys)):
        raise TypeError(
            f"Unexpected args: {set(kw) - set(self.keys)}. Accepted arguments"
            f" are: {set(self.keys)}"
        )

    requests = instance._get_metadata_request()
    method_metadata_request = getattr(requests, self.name)

    for prop, alias in kw.items():
        if alias is not UNCHANGED:
            method_metadata_request.add_request(param=prop, alias=alias)
    instance._metadata_request = requests

    return instance
class LinearNgramClassifier (checkpoint: str = 'tfidfvectorizer', tokenizer=None, ngrams=2, all_ngrams=True, random_state=None)

Base class for all estimators in scikit-learn.

Inheriting from this class provides default implementations of:

  • setting and getting parameters used by GridSearchCV and friends;
  • textual and HTML representation displayed in terminals and IDEs;
  • estimator serialization;
  • parameters validation;
  • data validation;
  • feature names validation.

Read more in the :ref:User Guide <rolling_your_own_estimator>.

Notes

All estimators should specify all the parameters that can be set at the class level in their __init__ as explicit keyword arguments (no *args or **kwargs).

Examples

>>> import numpy as np
>>> from sklearn.base import BaseEstimator
>>> class MyEstimator(BaseEstimator):
...     def __init__(self, *, param=1):
...         self.param = param
...     def fit(self, X, y=None):
...         self.is_fitted_ = True
...         return self
...     def predict(self, X):
...         return np.full(shape=X.shape[0], fill_value=self.param)
>>> estimator = MyEstimator(param=2)
>>> estimator.get_params()
{'param': 2}
>>> X = np.array([[1, 2], [2, 3], [3, 4]])
>>> y = np.array([1, 0, 1])
>>> estimator.fit(X, y).predict(X)
array([2, 2, 2])
>>> estimator.set_params(param=3).fit(X, y).predict(X)
array([3, 3, 3])

LinearNgram Class - use either LinearNgramClassifier or LinearNgramRegressor rather than initializing this class directly.

Parameters

checkpoint : str
Name of vectorizer checkpoint: "countvectorizer" or "tfidfvectorizer"
ngrams
Order of ngrams to extract. 1 for unigrams, 2 for bigrams, etc.
all_ngrams
Whether to use all order ngrams <= ngrams argument
random_state
random seed for fitting

Example

from imodelsx import LinearNgramClassifier
import datasets
import numpy as np

# load data
dset = datasets.load_dataset('rotten_tomatoes')['train']
dset = dset.select(np.random.choice(len(dset), size=300, replace=False))
dset_val = datasets.load_dataset('rotten_tomatoes')['validation']
dset_val = dset_val.select(np.random.choice(len(dset_val), size=300, replace=False))


# fit a simple ngram model
m = LinearNgramClassifier()
m.fit(dset['text'], dset['label'])
preds = m.predict(dset_val['text'])
acc = (preds == dset_val['label']).mean()
print('validation acc', acc)
Expand source code 
class LinearNgramClassifier(LinearNgram, ClassifierMixin):
    ...

Ancestors

  • LinearNgram
  • sklearn.base.BaseEstimator
  • sklearn.utils._estimator_html_repr._HTMLDocumentationLinkMixin
  • sklearn.utils._metadata_requests._MetadataRequester
  • sklearn.base.ClassifierMixin

Methods

def set_score_request(self: LinearNgramClassifier, *, sample_weight: Union[bool, ForwardRef(None), str] = '$UNCHANGED$') ‑> LinearNgramClassifier

Request metadata passed to the score method.

Note that this method is only relevant if enable_metadata_routing=True (see :func:sklearn.set_config). Please see :ref:User Guide <metadata_routing> on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to score if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to score.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version: 1.3

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a :class:~sklearn.pipeline.Pipeline. Otherwise it has no effect.

Parameters

sample_weight : str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED
Metadata routing for sample_weight parameter in score.

Returns

self : object
The updated object.
Expand source code 
def func(**kw):
    """Updates the request for provided parameters

    This docstring is overwritten below.
    See REQUESTER_DOC for expected functionality
    """
    if not _routing_enabled():
        raise RuntimeError(
            "This method is only available when metadata routing is enabled."
            " You can enable it using"
            " sklearn.set_config(enable_metadata_routing=True)."
        )

    if self.validate_keys and (set(kw) - set(self.keys)):
        raise TypeError(
            f"Unexpected args: {set(kw) - set(self.keys)}. Accepted arguments"
            f" are: {set(self.keys)}"
        )

    requests = instance._get_metadata_request()
    method_metadata_request = getattr(requests, self.name)

    for prop, alias in kw.items():
        if alias is not UNCHANGED:
            method_metadata_request.add_request(param=prop, alias=alias)
    instance._metadata_request = requests

    return instance

Inherited members

class LinearNgramRegressor (checkpoint: str = 'tfidfvectorizer', tokenizer=None, ngrams=2, all_ngrams=True, random_state=None)

Base class for all estimators in scikit-learn.

Inheriting from this class provides default implementations of:

  • setting and getting parameters used by GridSearchCV and friends;
  • textual and HTML representation displayed in terminals and IDEs;
  • estimator serialization;
  • parameters validation;
  • data validation;
  • feature names validation.

Read more in the :ref:User Guide <rolling_your_own_estimator>.

Notes

All estimators should specify all the parameters that can be set at the class level in their __init__ as explicit keyword arguments (no *args or **kwargs).

Examples

>>> import numpy as np
>>> from sklearn.base import BaseEstimator
>>> class MyEstimator(BaseEstimator):
...     def __init__(self, *, param=1):
...         self.param = param
...     def fit(self, X, y=None):
...         self.is_fitted_ = True
...         return self
...     def predict(self, X):
...         return np.full(shape=X.shape[0], fill_value=self.param)
>>> estimator = MyEstimator(param=2)
>>> estimator.get_params()
{'param': 2}
>>> X = np.array([[1, 2], [2, 3], [3, 4]])
>>> y = np.array([1, 0, 1])
>>> estimator.fit(X, y).predict(X)
array([2, 2, 2])
>>> estimator.set_params(param=3).fit(X, y).predict(X)
array([3, 3, 3])

LinearNgram Class - use either LinearNgramClassifier or LinearNgramRegressor rather than initializing this class directly.

Parameters

checkpoint : str
Name of vectorizer checkpoint: "countvectorizer" or "tfidfvectorizer"
ngrams
Order of ngrams to extract. 1 for unigrams, 2 for bigrams, etc.
all_ngrams
Whether to use all order ngrams <= ngrams argument
random_state
random seed for fitting

Example

from imodelsx import LinearNgramClassifier
import datasets
import numpy as np

# load data
dset = datasets.load_dataset('rotten_tomatoes')['train']
dset = dset.select(np.random.choice(len(dset), size=300, replace=False))
dset_val = datasets.load_dataset('rotten_tomatoes')['validation']
dset_val = dset_val.select(np.random.choice(len(dset_val), size=300, replace=False))


# fit a simple ngram model
m = LinearNgramClassifier()
m.fit(dset['text'], dset['label'])
preds = m.predict(dset_val['text'])
acc = (preds == dset_val['label']).mean()
print('validation acc', acc)
Expand source code 
class LinearNgramRegressor(LinearNgram, RegressorMixin):
    ...

Ancestors

  • LinearNgram
  • sklearn.base.BaseEstimator
  • sklearn.utils._estimator_html_repr._HTMLDocumentationLinkMixin
  • sklearn.utils._metadata_requests._MetadataRequester
  • sklearn.base.RegressorMixin

Methods

def set_score_request(self: LinearNgramRegressor, *, sample_weight: Union[bool, ForwardRef(None), str] = '$UNCHANGED$') ‑> LinearNgramRegressor

Request metadata passed to the score method.

Note that this method is only relevant if enable_metadata_routing=True (see :func:sklearn.set_config). Please see :ref:User Guide <metadata_routing> on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to score if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to score.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version: 1.3

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a :class:~sklearn.pipeline.Pipeline. Otherwise it has no effect.

Parameters

sample_weight : str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED
Metadata routing for sample_weight parameter in score.

Returns

self : object
The updated object.
Expand source code 
def func(**kw):
    """Updates the request for provided parameters

    This docstring is overwritten below.
    See REQUESTER_DOC for expected functionality
    """
    if not _routing_enabled():
        raise RuntimeError(
            "This method is only available when metadata routing is enabled."
            " You can enable it using"
            " sklearn.set_config(enable_metadata_routing=True)."
        )

    if self.validate_keys and (set(kw) - set(self.keys)):
        raise TypeError(
            f"Unexpected args: {set(kw) - set(self.keys)}. Accepted arguments"
            f" are: {set(self.keys)}"
        )

    requests = instance._get_metadata_request()
    method_metadata_request = getattr(requests, self.name)

    for prop, alias in kw.items():
        if alias is not UNCHANGED:
            method_metadata_request.add_request(param=prop, alias=alias)
    instance._metadata_request = requests

    return instance

Inherited members