Created
November 12, 2019 21:00
-
-
Save amueller/fbef5030f729d07a5261fcfdbbd54c03 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "cells": [ | |
| { | |
| "cell_type": "code", | |
| "execution_count": 1, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "from sklearn.datasets import fetch_openml\n", | |
| "import numpy as np\n" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 2, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "cc18 = np.array([3, 6, 11, 12, 14, 15, 16, 18, 22, 23, 28, 29, 31, 32, 37, 38, 44, 46, 50, 54, 151, 182, 188, 300, 307, 458, 469, 554, 1049, 1050,\n", | |
| " 1053, 1063, 1067, 1068, 1461, 1462, 1464, 1468, 1475, 1478, 1480, 1485, 1486, 1487, 1489, 1494, 1497, 1501, 1510, 1590, 4134, 4534,\n", | |
| " 4538, 6332, 23381, 23517, 40499, 40668, 40670, 40701, 40923, 40927, 40966, 40975, 40978, 40979, 40982, 40983, 40984, 40994, 40996, 41027])" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 6, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "from sklearn.compose import make_column_transformer, make_column_selector\n", | |
| "from sklearn.linear_model import LogisticRegression\n", | |
| "from sklearn.preprocessing import OneHotEncoder\n", | |
| "from sklearn.impute import SimpleImputer\n", | |
| "from sklearn.pipeline import make_pipeline\n", | |
| "from time import time" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 7, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "# todo: add scaled results, add cross-validation accuracy" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 8, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| } | |
| ], | |
| "source": [ | |
| "no_scale_no_pre = []\n", | |
| "no_scale_pre = []\n", | |
| "time_no_scale_no_pre = []\n", | |
| "time_no_scale_pre = []\n", | |
| "for did in cc18:\n", | |
| " print(did)\n", | |
| " X, y = fetch_openml(data_id=did, as_frame=True, return_X_y=True)\n", | |
| " selector = make_column_selector(dtype_include='category')\n", | |
| " ct = make_column_transformer((make_pipeline(SimpleImputer(strategy='most_frequent'), OneHotEncoder()), selector), remainder=SimpleImputer())\n", | |
| " # check objective\n", | |
| " X_trans = ct.fit_transform(X)\n", | |
| " tick = time()\n", | |
| " lr = LogisticRegression(precondition=False).fit(X_trans, y)\n", | |
| " time_no_scale_no_pre.append(time() - tick)\n", | |
| " no_scale_no_pre.append(lr.loss_values_)\n", | |
| " tick = time()\n", | |
| " lr_pre = LogisticRegression(precondition=True).fit(X_trans, y)\n", | |
| " time_no_scale_pre.append(time() - tick)\n", | |
| " no_scale_pre.append(lr_pre.loss_values_)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 9, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "import matplotlib.pyplot as plt\n", | |
| "import numpy as np\n", | |
| "%matplotlib inline\n", | |
| "no_scale_no_pre = np.array(no_scale_no_pre)\n", | |
| "no_scale_pre = np.array(no_scale_pre)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 26, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "[<matplotlib.lines.Line2D at 0x7ffaa121c4e0>]" | |
| ] | |
| }, | |
| "execution_count": 26, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| }, | |
| { | |
| "data": { | |
| "image/png": "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\n", | |
| "text/plain": [ | |
| "<Figure size 432x288 with 1 Axes>" | |
| ] | |
| }, | |
| "metadata": { | |
| "needs_background": "light" | |
| }, | |
| "output_type": "display_data" | |
| } | |
| ], | |
| "source": [ | |
| "plt.title(\"Objective on unscaled data\")\n", | |
| "plt.plot(no_scale_no_pre, no_scale_pre, 'o')\n", | |
| "plt.xlabel(\"no pre\")\n", | |
| "plt.yscale(\"log\")\n", | |
| "plt.xscale(\"log\")\n", | |
| "plt.ylabel(\"pre\")\n", | |
| "ax = plt.gca()\n", | |
| "ax.set_aspect('equal')\n", | |
| "plt.plot([1, 1e5], [1, 1e5])" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 27, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "[<matplotlib.lines.Line2D at 0x7ffaa197e4a8>]" | |
| ] | |
| }, | |
| "execution_count": 27, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| }, | |
| { | |
| "data": { | |
| "image/png": "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\n", | |
| "text/plain": [ | |
| "<Figure size 432x288 with 1 Axes>" | |
| ] | |
| }, | |
| "metadata": { | |
| "needs_background": "light" | |
| }, | |
| "output_type": "display_data" | |
| } | |
| ], | |
| "source": [ | |
| "plt.title(\"Relative Objective on unscaled data\")\n", | |
| "\n", | |
| "plt.plot(no_scale_no_pre, (no_scale_no_pre - no_scale_pre)/no_scale_no_pre, 'o')\n", | |
| "plt.xlabel(\"no pre\")\n", | |
| "#plt.yscale(\"log\")\n", | |
| "plt.xscale(\"log\")\n", | |
| "plt.ylabel(\"(no pre - pre)/no pre\")\n", | |
| "ax = plt.gca()\n", | |
| "#ax.set_aspect('equal')\n", | |
| "plt.plot([0, 1e5], [0, 0])" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 28, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "[<matplotlib.lines.Line2D at 0x7ffaa1732f98>]" | |
| ] | |
| }, | |
| "execution_count": 28, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| }, | |
| { | |
| "data": { | |
| "image/png": "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\n", | |
| "text/plain": [ | |
| "<Figure size 432x288 with 1 Axes>" | |
| ] | |
| }, | |
| "metadata": { | |
| "needs_background": "light" | |
| }, | |
| "output_type": "display_data" | |
| } | |
| ], | |
| "source": [ | |
| "plt.title(\"Time on unscaled data\")\n", | |
| "\n", | |
| "plt.plot(time_no_scale_no_pre, time_no_scale_pre, 'o')\n", | |
| "plt.xlabel(\"no pre\")\n", | |
| "plt.yscale(\"log\")\n", | |
| "plt.xscale(\"log\")\n", | |
| "plt.ylabel(\"pre\")\n", | |
| "ax = plt.gca()\n", | |
| "ax.set_aspect('equal')\n", | |
| "plt.plot([1e-2, 1e2], [1e-2, 1e2])" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 19, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "3\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "6\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "11\n", | |
| "12\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "14\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "15\n", | |
| "16\n", | |
| "18\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "22\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "23\n", | |
| "28\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "29\n", | |
| "31\n", | |
| "32\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "37\n", | |
| "38\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "44\n", | |
| "46\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "50\n", | |
| "54\n", | |
| "151\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "182\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "188\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "300\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "307\n", | |
| "458\n", | |
| "469\n", | |
| "554\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "1049\n", | |
| "1050\n", | |
| "1053\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "1063\n", | |
| "1067\n", | |
| "1068\n", | |
| "1461\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "1462\n", | |
| "1464\n", | |
| "1468\n", | |
| "1475\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "1478\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "1480\n", | |
| "1485\n", | |
| "1486\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "1487\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "1489\n", | |
| "1494\n", | |
| "1497\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "1501\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "1510\n", | |
| "1590\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "4134\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "4534\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "4538\n", | |
| "6332\n", | |
| "23381\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "23517\n", | |
| "40499\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "40668\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "40670\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "40701\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "40923\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "40927\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "40966\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "40975\n", | |
| "40978\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "40979\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "40982\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "40983\n", | |
| "40984\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "40994\n", | |
| "40996\n" | |
| ] | |
| }, | |
| { | |
| "name": "stderr", | |
| "output_type": "stream", | |
| "text": [ | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n", | |
| "/home/andy/checkout/scikit-learn/sklearn/linear_model/_logistic.py:1004: ConvergenceWarning: lbfgs failed to converge (status=1): b'STOP: TOTAL NO. of ITERATIONS REACHED LIMIT'. Increase the number of iterations.\n", | |
| " n_iter_i = _check_optimize_result(solver, opt_res, max_iter)\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "41027\n" | |
| ] | |
| } | |
| ], | |
| "source": [ | |
| "from sklearn.preprocessing import StandardScaler\n", | |
| "\n", | |
| "time_scale_no_pre = []\n", | |
| "time_scale_pre = []\n", | |
| "scale_no_pre = []\n", | |
| "scale_pre = []\n", | |
| "for did in cc18:\n", | |
| " print(did)\n", | |
| " X, y = fetch_openml(data_id=did, as_frame=True, return_X_y=True)\n", | |
| " selector = make_column_selector(dtype_include='category')\n", | |
| " ct = make_column_transformer((make_pipeline(SimpleImputer(strategy='most_frequent'), OneHotEncoder()), selector),\n", | |
| " remainder=make_pipeline(SimpleImputer(), StandardScaler()))\n", | |
| " # check objective\n", | |
| " X_trans = ct.fit_transform(X)\n", | |
| " tick = time()\n", | |
| " lr = LogisticRegression(precondition=False).fit(X_trans, y)\n", | |
| " time_scale_no_pre.append(time() - tick)\n", | |
| " scale_no_pre.append(lr.loss_values_)\n", | |
| " tick = time()\n", | |
| " lr_pre = LogisticRegression(precondition=True).fit(X_trans, y)\n", | |
| " time_scale_pre.append(time() - tick)\n", | |
| " scale_pre.append(lr_pre.loss_values_)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 20, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "scale_no_pre = np.array(scale_no_pre)\n", | |
| "scale_pre = np.array(scale_pre)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 29, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "[<matplotlib.lines.Line2D at 0x7ffaa1759b00>]" | |
| ] | |
| }, | |
| "execution_count": 29, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| }, | |
| { | |
| "data": { | |
| "image/png": "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\n", | |
| "text/plain": [ | |
| "<Figure size 432x288 with 1 Axes>" | |
| ] | |
| }, | |
| "metadata": { | |
| "needs_background": "light" | |
| }, | |
| "output_type": "display_data" | |
| } | |
| ], | |
| "source": [ | |
| "plt.title(\"Objective on scaled data\")\n", | |
| "\n", | |
| "plt.title(\"With scaling\")\n", | |
| "plt.plot(scale_no_pre, scale_pre, 'o')\n", | |
| "plt.xlabel(\"no pre\")\n", | |
| "plt.yscale(\"log\")\n", | |
| "plt.xscale(\"log\")\n", | |
| "plt.ylabel(\"pre\")\n", | |
| "ax = plt.gca()\n", | |
| "ax.set_aspect('equal')\n", | |
| "plt.plot([1, 1e5], [1, 1e5])" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 32, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "[<matplotlib.lines.Line2D at 0x7ffaa0eec8d0>]" | |
| ] | |
| }, | |
| "execution_count": 32, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| }, | |
| { | |
| "data": { | |
| "image/png": "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\n", | |
| "text/plain": [ | |
| "<Figure size 432x288 with 1 Axes>" | |
| ] | |
| }, | |
| "metadata": { | |
| "needs_background": "light" | |
| }, | |
| "output_type": "display_data" | |
| } | |
| ], | |
| "source": [ | |
| "plt.title(\"Relative objective on scaled data\")\n", | |
| "\n", | |
| "plt.plot(no_scale_no_pre, (scale_no_pre - scale_pre)/scale_no_pre, 'o')\n", | |
| "plt.xlabel(\"no pre\")\n", | |
| "#plt.yscale(\"log\")\n", | |
| "plt.xscale(\"log\")\n", | |
| "plt.ylabel(\"no pre - pre / no pre\")\n", | |
| "ax = plt.gca()\n", | |
| "#ax.set_aspect('equal')\n", | |
| "plt.plot([0, 1e5], [0, 0])" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 31, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "data": { | |
| "text/plain": [ | |
| "[<matplotlib.lines.Line2D at 0x7ffaa1171160>]" | |
| ] | |
| }, | |
| "execution_count": 31, | |
| "metadata": {}, | |
| "output_type": "execute_result" | |
| }, | |
| { | |
| "data": { | |
| "image/png": "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\n", | |
| "text/plain": [ | |
| "<Figure size 432x288 with 1 Axes>" | |
| ] | |
| }, | |
| "metadata": { | |
| "needs_background": "light" | |
| }, | |
| "output_type": "display_data" | |
| } | |
| ], | |
| "source": [ | |
| "plt.title(\"Time on scaled data\")\n", | |
| "\n", | |
| "plt.plot(no_scale_no_pre, no_scale_pre, 'o')\n", | |
| "plt.xlabel(\"no pre\")\n", | |
| "plt.yscale(\"log\")\n", | |
| "plt.xscale(\"log\")\n", | |
| "plt.ylabel(\"pre\")\n", | |
| "ax = plt.gca()\n", | |
| "ax.set_aspect('equal')\n", | |
| "plt.plot([1e-1, 1e2], [1e-1, 1e2])" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": null, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [] | |
| } | |
| ], | |
| "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": "3.7.3" | |
| } | |
| }, | |
| "nbformat": 4, | |
| "nbformat_minor": 2 | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment