{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "from sklearn.datasets import fetch_20newsgroups\n", "from sklearn.feature_extraction.text import CountVectorizer\n", "from sklearn.preprocessing import Binarizer as skBinarizer" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "class Binarizer():\n", " def fit(self, X):\n", " return self\n", "\n", " def transform(self, X):\n", " Xt = np.zeros_like(X)\n", " Xt[X > 0] = 1\n", " return Xt" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "data = fetch_20newsgroups().data\n", "data = data[:1000]\n", "X = CountVectorizer().fit_transform(data).toarray()\n", "trans1 = Binarizer().fit(X)\n", "trans2 = skBinarizer().fit(X)\n", "Xt1 = trans1.transform(X)\n", "Xt2 = trans2.transform(X)" ] } ], "metadata": { "kernelspec": { "display_name": "dev", "language": "python", "name": "dev" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 2 }