{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "from copy import deepcopy\n", "from scipy.spatial.distance import cdist\n", "from scipy.special import expit\n", "from scipy.optimize import minimize\n", "from sklearn.datasets import load_iris\n", "from sklearn.linear_model import LogisticRegression as skLogisticRegression\n", "from sklearn.multiclass import OutputCodeClassifier as skOutputCodeClassifier" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "class OutputCodeClassifier():\n", " def __init__(self, estimator,\n", " code_size=1.5, random_state=0):\n", " self.estimator = estimator\n", " self.code_size = code_size\n", " self.random_state = random_state\n", "\n", " def fit(self, X, y):\n", " self.classes_, y_enc = np.unique(y, return_inverse=True)\n", " code_size_ = int(len(self.classes_) * self.code_size)\n", " rng = np.random.RandomState(self.random_state)\n", " self.code_book_ = rng.random_sample((len(self.classes_), code_size_))\n", " self.code_book_[self.code_book_ > 0.5] = 1\n", " self.code_book_[self.code_book_ != 1] = -1\n", " y_train = self.code_book_[y_enc]\n", " self.estimators_ = []\n", " for i in range(y_train.shape[1]):\n", " cur_y = y_train[:, i]\n", " clf = deepcopy(self.estimator)\n", " clf.fit(X, cur_y)\n", " self.estimators_.append(clf)\n", " return self\n", "\n", " def predict(self, X):\n", " scores = np.zeros((X.shape[0], len(self.estimators_)))\n", " for i, est in enumerate(self.estimators_):\n", " scores[:, i] = est.decision_function(X)\n", " pred = cdist(scores, self.code_book_).argmin(axis=1)\n", " return self.classes_[pred]" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "# Simplified version of LogisticRegression, only work for binary classification\n", "class BinaryLogisticRegression():\n", " def __init__(self, C=1.0):\n", " self.C = C\n", "\n", " @staticmethod\n", " def _cost_grad(w, X, y, alpha):\n", " def _log_logistic(x):\n", " if x > 0:\n", " return -np.log(1 + np.exp(-x))\n", " else:\n", " return x - np.log(1 + np.exp(x))\n", " yz = y * (np.dot(X, w[:-1]) + w[-1])\n", " cost = -np.sum(np.vectorize(_log_logistic)(yz)) + 0.5 * alpha * np.dot(w[:-1], w[:-1])\n", " grad = np.zeros(len(w))\n", " t = (expit(yz) - 1) * y\n", " grad[:-1] = np.dot(X.T, t) + alpha * w[:-1]\n", " grad[-1] = np.sum(t)\n", " return cost, grad\n", "\n", " def _solve_lbfgs(self, X, y):\n", " y_train = np.full(X.shape[0], -1)\n", " y_train[y == 1] = 1\n", " w0 = np.zeros(X.shape[1] + 1)\n", " res = minimize(fun=self._cost_grad, jac=True, x0=w0,\n", " args=(X, y_train, 1 / self.C), method='L-BFGS-B')\n", " return res.x[:-1], res.x[-1]\n", "\n", " def fit(self, X, y):\n", " self.coef_, self.intercept_ = self._solve_lbfgs(X, y)\n", " return self\n", "\n", " def decision_function(self, X):\n", " scores = np.dot(X, self.coef_) + self.intercept_\n", " return scores\n", "\n", " def predict(self, X):\n", " scores = self.decision_function(X)\n", " indices = (scores > 0).astype(int)\n", " return indices" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "for C in [0.1, 1, 10, np.inf]:\n", " X, y = load_iris(return_X_y=True)\n", " clf1 = OutputCodeClassifier(BinaryLogisticRegression(C=C)).fit(X, y)\n", " clf2 = skOutputCodeClassifier(skLogisticRegression(C=C, multi_class=\"ovr\", solver=\"lbfgs\",\n", " # keep consisent with scipy default\n", " tol=1e-5, max_iter=15000),\n", " random_state=0).fit(X, y)\n", " pred1 = clf1.predict(X)\n", " pred2 = clf2.predict(X)\n", " assert np.array_equal(pred1, pred2)" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.8" } }, "nbformat": 4, "nbformat_minor": 2 }