my_feature_vect.py

# so far basically just copied from 
#https://github.com/scikit-learn/scikit-learn/blob/14031f6/sklearn/feature_extraction/text.py#L511
# the idea is to use this as a stub to create our own feature extractor
from __future__ import unicode_literals

import array
from collections import Mapping, defaultdict
import numbers
from operator import itemgetter
import re
import unicodedata

import numpy as np
import scipy.sparse as sp
import six
from sklearn.base import BaseEstimator
from sklearn.feature_extraction.text import VectorizerMixin
from sklearn.preprocessing import normalize
from sklearn.feature_extraction.hashing import FeatureHasher
from sklearn.feature_extraction.stop_words import ENGLISH_STOP_WORDS
from sklearn.utils import deprecated
from sklearn.utils.fixes import frombuffer_empty, bincount
from sklearn.utils.validation import check_is_fitted
def _document_frequency(X):
    """Count the number of non-zero values for each feature in sparse X."""
    if sp.isspmatrix_csr(X):
        return bincount(X.indices, minlength=X.shape[1])
    else:
        return np.diff(sp.csc_matrix(X, copy=False).indptr)


class StanceVectorizer(BaseEstimator, VectorizerMixin):
    def __init__(self, input='content', encoding='utf-8',
                 decode_error='strict', strip_accents=None,
                 lowercase=True, preprocessor=None, tokenizer=None,
                 stop_words=None, token_pattern=r"(?u)\b\w\w+\b",
                 ngram_range=(1, 1), analyzer='word',
                 max_df=1.0, min_df=1, max_features=None,
                 vocabulary=None, binary=False, dtype=np.int64):
        self.input = input
        self.encoding = encoding
        self.decode_error = decode_error
        self.strip_accents = strip_accents
        self.preprocessor = preprocessor
        self.tokenizer = tokenizer
        self.analyzer = analyzer
        self.lowercase = lowercase
        self.token_pattern = token_pattern
        self.stop_words = stop_words
        self.max_df = max_df
        self.min_df = min_df
        if max_df < 0 or min_df < 0:
            raise ValueError("negative value for max_df or min_df")
        self.max_features = max_features
        if max_features is not None:
            if (not isinstance(max_features, numbers.Integral) or
                    max_features <= 0):
                raise ValueError(
                    "max_features=%r, neither a positive integer nor None"
                    % max_features)
        self.ngram_range = ngram_range
        self.vocabulary = vocabulary
        self.binary = binary
        self.dtype = dtype

    def fit(self, raw_documents, y=None):
        """Learn a vocabulary dictionary of all tokens in the raw documents.
        Parameters
        ----------
        raw_documents : iterable
            An iterable which yields either str, unicode or file objects.
        Returns
        -------
        self
        """
        self.fit_transform(raw_documents)
        return self


    def fit_transform(self, raw_documents, y=None):
        """Learn the vocabulary dictionary and return term-document matrix.
        Each document is a tuple of headline,body
        This is equivalent to fit followed by transform, but more efficiently
        implemented.
        Parameters
        ----------
        raw_documents : iterable
            An iterable which yields either str, unicode or file objects.
        Returns
        -------
        X : array, [n_samples, n_features]
            Document-term matrix.
        """
        vocabulary, X = self._extract_features(raw_documents)
        self.vocabulary_ = vocabulary
        return X

    def transform(self, raw_documents):
        """Transform documents to document-term matrix.
        Extract token counts out of raw text documents using the vocabulary
        fitted with fit or the one provided to the constructor.
        Parameters
        ----------
        raw_documents : iterable
            An iterable which yields either str, unicode or file objects.
        Returns
        -------
        X : sparse matrix, [n_samples, n_features]
            Document-term matrix.
        """
        if isinstance(raw_documents, six.string_types):
            raise ValueError(
                "Iterable over raw text documents expected, "
                "string object received.")

        if not hasattr(self, 'vocabulary_'):
            self._validate_vocabulary()

        self._check_vocabulary()

        # use the same matrix-building strategy as fit_transform
        _, X = self._extract_features(raw_documents)
        if self.binary:
            X.data.fill(1)
        return X

    def _extract_features(self,raw_documents):
        j_indices = []
        indptr = _make_int_array()
        values = _make_int_array()
        indptr.append(0)
        vocabulary = defaultdict(int)
        for doc in raw_documents:
            feature_counter = {}
            #for feature,feature_idx in contains_keywords(doc).items():
            for feature,feature_idx in self.body_words_in_headline(doc).items():
                vocabulary[feature]+=1
                try:
                    if feature_idx not in feature_counter:
                        feature_counter[feature_idx] = 1
                    else:
                        feature_counter[feature_idx] += 1
                except KeyError:
                    # Ignore out-of-vocabulary items for fixed_vocab=True
                    continue

            j_indices.extend(feature_counter.keys())
            values.extend(feature_counter.values())
            indptr.append(len(j_indices))


        j_indices = np.asarray(j_indices, dtype=np.intc)
        indptr = np.frombuffer(indptr, dtype=np.intc)
        values = frombuffer_empty(values, dtype=np.intc)

        X = sp.csr_matrix((values, j_indices, indptr),
                          shape=(len(indptr) - 1, len(vocabulary)),
                          dtype=self.dtype)
        X.sort_indices()
        return vocabulary, X

    def get_feature_names(self):
        """Array mapping from feature integer indices to feature name"""
        self._check_vocabulary()

        return [t for t, i in sorted(six.iteritems(self.vocabulary_),
                                     key=itemgetter(1))]

    def body_words_in_headline(self,doc):
        """ For each word in the headline, create a feature. The value of the
        feature will be the number of times that word appears in the body"""
        features = defaultdict(int)
        analyze = self.build_analyzer()
        headline_tokens=analyze(doc[0])
        body_tokens=analyze(doc[1])
        #headline_token_counts=defaultdict(int)
        body_token_counts=defaultdict(int)
        for token in body_tokens:
            body_token_counts[token]+=1
        for token in headline_tokens:
            if token in body_token_counts:
                features[token] +=1
        return features

class CountVectorizer(BaseEstimator, VectorizerMixin):
    """Convert a collection of text documents to a matrix of token counts
    This implementation produces a sparse representation of the counts using
    scipy.sparse.coo_matrix.
    If you do not provide an a-priori dictionary and you do not use an analyzer
    that does some kind of feature selection then the number of features will
    be equal to the vocabulary size found by analyzing the data.
    Read more in the :ref:`User Guide <text_feature_extraction>`.
    Parameters
    ----------
    input : string {'filename', 'file', 'content'}
        If 'filename', the sequence passed as an argument to fit is
        expected to be a list of filenames that need reading to fetch
        the raw content to analyze.
        If 'file', the sequence items must have a 'read' method (file-like
        object) that is called to fetch the bytes in memory.
        Otherwise the input is expected to be the sequence strings or
        bytes items are expected to be analyzed directly.
    encoding : string, 'utf-8' by default.
        If bytes or files are given to analyze, this encoding is used to
        decode.
    decode_error : {'strict', 'ignore', 'replace'}
        Instruction on what to do if a byte sequence is given to analyze that
        contains characters not of the given `encoding`. By default, it is
        'strict', meaning that a UnicodeDecodeError will be raised. Other
        values are 'ignore' and 'replace'.
    strip_accents : {'ascii', 'unicode', None}
        Remove accents during the preprocessing step.
        'ascii' is a fast method that only works on characters that have
        an direct ASCII mapping.
        'unicode' is a slightly slower method that works on any characters.
        None (default) does nothing.
    analyzer : string, {'word', 'char', 'char_wb'} or callable
        Whether the feature should be made of word or character n-grams.
        Option 'char_wb' creates character n-grams only from text inside
        word boundaries.
        If a callable is passed it is used to extract the sequence of features
        out of the raw, unprocessed input.
    preprocessor : callable or None (default)
        Override the preprocessing (string transformation) stage while
        preserving the tokenizing and n-grams generation steps.
    tokenizer : callable or None (default)
        Override the string tokenization step while preserving the
        preprocessing and n-grams generation steps.
        Only applies if ``analyzer == 'word'``.
    ngram_range : tuple (min_n, max_n)
        The lower and upper boundary of the range of n-values for different
        n-grams to be extracted. All values of n such that min_n <= n <= max_n
        will be used.
    stop_words : string {'english'}, list, or None (default)
        If 'english', a built-in stop word list for English is used.
        If a list, that list is assumed to contain stop words, all of which
        will be removed from the resulting tokens.
        Only applies if ``analyzer == 'word'``.
        If None, no stop words will be used. max_df can be set to a value
        in the range [0.7, 1.0) to automatically detect and filter stop
        words based on intra corpus document frequency of terms.
    lowercase : boolean, True by default
        Convert all characters to lowercase before tokenizing.
    token_pattern : string
        Regular expression denoting what constitutes a "token", only used
        if ``analyzer == 'word'``. The default regexp select tokens of 2
        or more alphanumeric characters (punctuation is completely ignored
        and always treated as a token separator).
    max_df : float in range [0.0, 1.0] or int, default=1.0
        When building the vocabulary ignore terms that have a document
        frequency strictly higher than the given threshold (corpus-specific
        stop words).
        If float, the parameter represents a proportion of documents, integer
        absolute counts.
        This parameter is ignored if vocabulary is not None.
    min_df : float in range [0.0, 1.0] or int, default=1
        When building the vocabulary ignore terms that have a document
        frequency strictly lower than the given threshold. This value is also
        called cut-off in the literature.
        If float, the parameter represents a proportion of documents, integer
        absolute counts.
        This parameter is ignored if vocabulary is not None.
    max_features : int or None, default=None
        If not None, build a vocabulary that only consider the top
        max_features ordered by term frequency across the corpus.
        This parameter is ignored if vocabulary is not None.
    vocabulary : Mapping or iterable, optional
        Either a Mapping (e.g., a dict) where keys are terms and values are
        indices in the feature matrix, or an iterable over terms. If not
        given, a vocabulary is determined from the input documents. Indices
        in the mapping should not be repeated and should not have any gap
        between 0 and the largest index.
    binary : boolean, default=False
        If True, all non zero counts are set to 1. This is useful for discrete
        probabilistic models that model binary events rather than integer
        counts.
    dtype : type, optional
        Type of the matrix returned by fit_transform() or transform().
    Attributes
    ----------
    vocabulary_ : dict
        A mapping of terms to feature indices.
    stop_words_ : set
        Terms that were ignored because they either:
          - occurred in too many documents (`max_df`)
          - occurred in too few documents (`min_df`)
          - were cut off by feature selection (`max_features`).
        This is only available if no vocabulary was given.
    See also
    --------
    HashingVectorizer, TfidfVectorizer
    Notes
    -----
    The ``stop_words_`` attribute can get large and increase the model size
    when pickling. This attribute is provided only for introspection and can
    be safely removed using delattr or set to None before pickling.
    """

    def __init__(self, input='content', encoding='utf-8',
                 decode_error='strict', strip_accents=None,
                 lowercase=True, preprocessor=None, tokenizer=None,
                 stop_words=None, token_pattern=r"(?u)\b\w\w+\b",
                 ngram_range=(1, 1), analyzer='word',
                 max_df=1.0, min_df=1, max_features=None,
                 vocabulary=None, binary=False, dtype=np.int64):
        self.input = input
        self.encoding = encoding
        self.decode_error = decode_error
        self.strip_accents = strip_accents
        self.preprocessor = preprocessor
        self.tokenizer = tokenizer
        self.analyzer = analyzer
        self.lowercase = lowercase
        self.token_pattern = token_pattern
        self.stop_words = stop_words
        self.max_df = max_df
        self.min_df = min_df
        if max_df < 0 or min_df < 0:
            raise ValueError("negative value for max_df or min_df")
        self.max_features = max_features
        if max_features is not None:
            if (not isinstance(max_features, numbers.Integral) or
                    max_features <= 0):
                raise ValueError(
                    "max_features=%r, neither a positive integer nor None"
                    % max_features)
        self.ngram_range = ngram_range
        self.vocabulary = vocabulary
        self.binary = binary
        self.dtype = dtype

    def _sort_features(self, X, vocabulary):
        """Sort features by name
        Returns a reordered matrix and modifies the vocabulary in place
        """
        sorted_features = sorted(six.iteritems(vocabulary))
        map_index = np.empty(len(sorted_features), dtype=np.int32)
        for new_val, (term, old_val) in enumerate(sorted_features):
            vocabulary[term] = new_val
            map_index[old_val] = new_val

        X.indices = map_index.take(X.indices, mode='clip')
        return X

    def _limit_features(self, X, vocabulary, high=None, low=None,
                        limit=None):
        """Remove too rare or too common features.
        Prune features that are non zero in more samples than high or less
        documents than low, modifying the vocabulary, and restricting it to
        at most the limit most frequent.
        This does not prune samples with zero features.
        """
        if high is None and low is None and limit is None:
            return X, set()

        # Calculate a mask based on document frequencies
        dfs = _document_frequency(X)
        tfs = np.asarray(X.sum(axis=0)).ravel()
        mask = np.ones(len(dfs), dtype=bool)
        if high is not None:
            mask &= dfs <= high
        if low is not None:
            mask &= dfs >= low
        if limit is not None and mask.sum() > limit:
            mask_inds = (-tfs[mask]).argsort()[:limit]
            new_mask = np.zeros(len(dfs), dtype=bool)
            new_mask[np.where(mask)[0][mask_inds]] = True
            mask = new_mask

        new_indices = np.cumsum(mask) - 1  # maps old indices to new
        removed_terms = set()
        for term, old_index in list(six.iteritems(vocabulary)):
            if mask[old_index]:
                vocabulary[term] = new_indices[old_index]
            else:
                del vocabulary[term]
                removed_terms.add(term)
        kept_indices = np.where(mask)[0]
        if len(kept_indices) == 0:
            raise ValueError("After pruning, no terms remain. Try a lower"
                             " min_df or a higher max_df.")
        return X[:, kept_indices], removed_terms

    def _count_vocab(self, raw_documents, fixed_vocab):
        """Create sparse feature matrix, and vocabulary where fixed_vocab=False
        """
        if fixed_vocab:
            vocabulary = self.vocabulary_
        else:
            # Add a new value when a new vocabulary item is seen
            vocabulary = defaultdict()
            vocabulary.default_factory = vocabulary.__len__

        analyze = self.build_analyzer()
        j_indices = []
        indptr = _make_int_array()
        values = _make_int_array()
        indptr.append(0)
        for doc in raw_documents:
            feature_counter = {}
            for feature in analyze(doc):
                try:
                    feature_idx = vocabulary[feature]
                    if feature_idx not in feature_counter:
                        feature_counter[feature_idx] = 1
                    else:
                        feature_counter[feature_idx] += 1
                except KeyError:
                    # Ignore out-of-vocabulary items for fixed_vocab=True
                    continue

            j_indices.extend(feature_counter.keys())
            values.extend(feature_counter.values())
            indptr.append(len(j_indices))

        if not fixed_vocab:
            # disable defaultdict behaviour
            vocabulary = dict(vocabulary)
            if not vocabulary:
                raise ValueError("empty vocabulary; perhaps the documents only"
                                 " contain stop words")

        j_indices = np.asarray(j_indices, dtype=np.intc)
        indptr = np.frombuffer(indptr, dtype=np.intc)
        values = frombuffer_empty(values, dtype=np.intc)

        X = sp.csr_matrix((values, j_indices, indptr),
                          shape=(len(indptr) - 1, len(vocabulary)),
                          dtype=self.dtype)
        X.sort_indices()
        return vocabulary, X

    def fit(self, raw_documents, y=None):
        """Learn a vocabulary dictionary of all tokens in the raw documents.
        Parameters
        ----------
        raw_documents : iterable
            An iterable which yields either str, unicode or file objects.
        Returns
        -------
        self
        """
        self.fit_transform(raw_documents)
        return self

    def fit_transform(self, raw_documents, y=None):
        """Learn the vocabulary dictionary and return term-document matrix.
        This is equivalent to fit followed by transform, but more efficiently
        implemented.
        Parameters
        ----------
        raw_documents : iterable
            An iterable which yields either str, unicode or file objects.
        Returns
        -------
        X : array, [n_samples, n_features]
            Document-term matrix.
        """
        # We intentionally don't call the transform method to make
        # fit_transform overridable without unwanted side effects in
        # TfidfVectorizer.
        if isinstance(raw_documents, six.string_types):
            raise ValueError(
                "Iterable over raw text documents expected, "
                "string object received.")

        self._validate_vocabulary()
        max_df = self.max_df
        min_df = self.min_df
        max_features = self.max_features

        vocabulary, X = self._count_vocab(raw_documents,
                                          self.fixed_vocabulary_)

        if self.binary:
            X.data.fill(1)

        if not self.fixed_vocabulary_:
            X = self._sort_features(X, vocabulary)

            n_doc = X.shape[0]
            max_doc_count = (max_df
                             if isinstance(max_df, numbers.Integral)
                             else max_df * n_doc)
            min_doc_count = (min_df
                             if isinstance(min_df, numbers.Integral)
                             else min_df * n_doc)
            if max_doc_count < min_doc_count:
                raise ValueError(
                    "max_df corresponds to < documents than min_df")
            X, self.stop_words_ = self._limit_features(X, vocabulary,
                                                       max_doc_count,
                                                       min_doc_count,
                                                       max_features)

            self.vocabulary_ = vocabulary

        return X

    def transform(self, raw_documents):
        """Transform documents to document-term matrix.
        Extract token counts out of raw text documents using the vocabulary
        fitted with fit or the one provided to the constructor.
        Parameters
        ----------
        raw_documents : iterable
            An iterable which yields either str, unicode or file objects.
        Returns
        -------
        X : sparse matrix, [n_samples, n_features]
            Document-term matrix.
        """
        if isinstance(raw_documents, six.string_types):
            raise ValueError(
                "Iterable over raw text documents expected, "
                "string object received.")

        if not hasattr(self, 'vocabulary_'):
            self._validate_vocabulary()

        self._check_vocabulary()

        # use the same matrix-building strategy as fit_transform
        _, X = self._count_vocab(raw_documents, fixed_vocab=True)
        if self.binary:
            X.data.fill(1)
        return X

    def inverse_transform(self, X):
        """Return terms per document with nonzero entries in X.
        Parameters
        ----------
        X : {array, sparse matrix}, shape = [n_samples, n_features]
        Returns
        -------
        X_inv : list of arrays, len = n_samples
            List of arrays of terms.
        """
        self._check_vocabulary()

        if sp.issparse(X):
            # We need CSR format for fast row manipulations.
            X = X.tocsr()
        else:
            # We need to convert X to a matrix, so that the indexing
            # returns 2D objects
            X = np.asmatrix(X)
        n_samples = X.shape[0]

        terms = np.array(list(self.vocabulary_.keys()))
        indices = np.array(list(self.vocabulary_.values()))
        inverse_vocabulary = terms[np.argsort(indices)]

        return [inverse_vocabulary[X[i, :].nonzero()[1]].ravel()
                for i in range(n_samples)]

    def get_feature_names(self):
        """Array mapping from feature integer indices to feature name"""
        self._check_vocabulary()

        return [t for t, i in sorted(six.iteritems(self.vocabulary_),
                                     key=itemgetter(1))]

def _make_int_array():
    """Construct an array.array of a type suitable for scipy.sparse indices."""
    return array.array(str("i"))


def contains_keywords(doc):
    features={}
    keywords = set(['good', 'bad', 'ugly'])
    for keyword in keywords:
        if keyword in doc:
            features[keyword] = 1
        else:
            features[keyword] = 0
    return features