Sparse Interaction Terms for scikit-learn

SparseInteractions.py

from sklearn.base import BaseEstimator, TransformerMixin
from scipy import sparse
from itertools import combinations


class SparseInteractions(BaseEstimator, TransformerMixin):
    def __init__(self, degree=2, feature_name_separator="_"):
        self.degree = degree
        self.feature_name_separator = feature_name_separator
    
    def fit(self, X, y=None):
        return self
        
    def transform(self, X):
        if not sparse.isspmatrix_csc(X):
            X = sparse.csc_matrix(X)
            
        if hasattr(X, "columns"):
            self.orig_col_names = X.columns
        else:
            self.orig_col_names = np.array([str(i) for i in range(X.shape[1])])
            
        spi = self._create_sparse_interactions(X)
        return spi
    
    
    def get_feature_names(self):
        return self.feature_names
    
    def _create_sparse_interactions(self, X):
        out_mat = []
        self.feature_names = self.orig_col_names.tolist()
        
        for sub_degree in range(2, self.degree + 1):
            for col_ixs in combinations(range(X.shape[1]), sub_degree):
                # add name for new column
                name = self.feature_name_separator.join(self.orig_col_names[list(col_ixs)])
                self.feature_names.append(name)
                
                # get column multiplications value
                out = X[:, col_ixs[0]]    
                for j in col_ixs[1:]:
                    out = out.multiply(X[:, j])

                out_mat.append(out)

        return sparse.hstack([X] + out_mat)
    

• Just does unique interactions, not all polynomial features (i.e., uses combinations)
• For degree > 2 includes smaller order degrees. (i.e., degree=3 includes (x1 * x2), (x1 * x3), (x2 * x3) in addition to (x1 * x2 * x3))
• Does not add bias term
• Uses CSC, which is fastest for column selection & supports arithmetic operations.
• Maintains feature names if DataFrame is passed in.

Example usage:

pl = Pipeline([
        ('vec', CountVectorizer(ngram_range=(1, 2))),
        ('int', SparseInteractions(degree=2)),
        ('clf', LogisticRegression())
    ])

pl.fit(X_train, y_train)

Thanks for the code.

The script errors due to missing import numpy as np. Other than that the class has run fine in my Pipeline.