{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "d12d28db-72c9-4f6d-a081-fc7ebb381759", "metadata": {}, "outputs": [], "source": [ "# numeric mising values\n", "\n", "import numpy as np\n", "from sklearn.impute import SimpleImputer" ] }, { "cell_type": "code", "execution_count": 2, "id": "f52e13ea-f7dd-492c-9602-87cc321e6e2b", "metadata": {}, "outputs": [], "source": [ "X = [[10, 2], [20, 4], [np.nan, 6]]" ] }, { "cell_type": "code", "execution_count": 3, "id": "1683e44c-6ce2-4d50-a270-c85b6076e986", "metadata": {}, "outputs": [], "source": [ "imp = SimpleImputer(strategy='mean', add_indicator=True)" ] }, { "cell_type": "code", "execution_count": 4, "id": "4f8de888-7939-4a88-8a7c-bfc21d4470a3", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
SimpleImputer(add_indicator=True)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "SimpleImputer(add_indicator=True)" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "imp.fit(X)" ] }, { "cell_type": "code", "execution_count": 5, "id": "395e65e6-a7e2-4e5a-9867-8f36bc463708", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[10., 2., 0.],\n", " [20., 4., 0.],\n", " [15., 6., 1.]])" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "imp.transform(X)" ] }, { "cell_type": "code", "execution_count": 6, "id": "aa44f214-0be3-442f-a9db-5a5234f510cf", "metadata": {}, "outputs": [], "source": [ "# categorical missing values\n", "\n", "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 7, "id": "9f375dfc-c44a-47c7-813d-bd4024d1e527", "metadata": {}, "outputs": [], "source": [ "X = [['male', 'cat'], ['female', 'dog'], ['male', np.nan]]" ] }, { "cell_type": "code", "execution_count": 8, "id": "be4135a7-26ed-410d-aaed-7b24ab5b643a", "metadata": {}, "outputs": [], "source": [ "imp = SimpleImputer(strategy=\"constant\", fill_value='NA')" ] }, { "cell_type": "code", "execution_count": 9, "id": "d1794791-820a-440b-a189-53e6435ae22c", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
SimpleImputer(fill_value='NA', strategy='constant')
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "SimpleImputer(fill_value='NA', strategy='constant')" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "imp.fit(X)" ] }, { "cell_type": "code", "execution_count": 10, "id": "3dd9abaf-91ad-423d-a36c-ddd0754e4858", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([['male', 'cat'],\n", " ['female', 'dog'],\n", " ['male', 'NA']], dtype=object)" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "imp.transform(X)" ] }, { "cell_type": "code", "execution_count": null, "id": "888ab186-028f-4fbe-b01c-f698dcf1c0f6", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.12.6" } }, "nbformat": 4, "nbformat_minor": 5 }