o Ni @s&ddlZddlmZGdddZdS)N)sparsec@s"eZdZdZddZdddZdS) OneHotEncoderaTransforms categorical features to continuous numeric features. Examples -------- >>> from one_hot_encoder import OneHotEncoder >>> enc = OneHotEncoder() >>> sequences = [list('bat'), list('cat'), list('rat')] >>> enc.fit(sequences) >>> enc.transform(sequences, sparse=False).astype(int) array([[0, 1, 0, 1, 1], [1, 0, 0, 1, 1], [0, 0, 1, 1, 1]]) >>> enc.transform(list('cat'), sparse=False).astype(int) array([[1, 0, 0, 1, 1]]) >>> enc.transform(list('bat'), sparse=True) <1x5 sparse matrix of type '' with 3 stored elements in Compressed Sparse Row format> cspt|}g}dt|jdD]"}t|dd|f}fddt|D}||t|7q||_|S)zFit OneHotEncoder to X. Parameters ---------- X : array-like, shape [n_samples, n_feature] Input array of type int. Returns ------- self rNcsi|] \}}||qSr).0ivaloffsetrU/home/ubuntu/.local/lib/python3.10/site-packages/indictrans/_utils/one_hot_encoder.py 1sz%OneHotEncoder.fit..) npasarrayrangeshapeset enumerateappendlen unique_feats)selfXdatarr feat_set_idrr r fits  zOneHotEncoder.fitTcCst|}|rtt|tdd|jDf}ntt|tdd|jDft}t |D]\}}t |D]\}}||j|vrMd|||j||f<q7q/|rVt |S|S)aTransform X using one-hot encoding. Parameters ---------- X : array-like, shape [n_samples, n_features] Input array of categorical features. sparse : bool, default: True Return sparse matrix if set True else return an array. Returns ------- X_out : sparse matrix if sparse=True else a 2-d array, dtype=int Transformed input. cs|]}t|VqdSNrrrrrr Lz*OneHotEncoder.transform..csrrrrrrr r Or!g?) r atleast_2dsp lil_matrixrsumrzerosboolr csr_matrix)rrrone_hot_matrixrvecjrrrr transform8s zOneHotEncoder.transformN)T)__name__ __module__ __qualname____doc__rr,rrrr r sr)numpyr scipyrr#rrrrr s