{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Групповая статистика" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "tags": [ "remove-cell" ] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Populating the interactive namespace from numpy and matplotlib\n" ] } ], "source": [ "%pylab inline\n", "import pandas as pd" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Загрузим файл, который мы сохранили при подготовке набора данных." ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 48 entries, 0 to 47\n", "Data columns (total 5 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 t 48 non-null float64\n", " 1 v 45 non-null float64\n", " 2 isi 47 non-null float64\n", " 3 mod 48 non-null object \n", " 4 g 48 non-null int64 \n", "dtypes: float64(3), int64(1), object(1)\n", "memory usage: 2.0+ KB\n" ] } ], "source": [ "D = pd.read_csv('rtgotov.csv')\n", "D.info()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Из информации о наборе данных видно, что в нём есть 4 числовых колонки и одна нечисловая." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Для получения базовой статистики по числовым колонкам удобно использовать метод `describe()`." ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
tvisig
count48.00000045.00000047.00000048.000000
mean137.3592920.3948224.8609574.916667
std69.8428280.0850132.5599782.541848
min9.5850000.2820001.6710002.000000
25%85.2040000.3380002.2685002.000000
50%122.8655000.3850004.5080004.000000
75%204.5710000.4310006.9170008.000000
max238.0500000.69800010.5070008.000000
\n", "
" ], "text/plain": [ " t v isi g\n", "count 48.000000 45.000000 47.000000 48.000000\n", "mean 137.359292 0.394822 4.860957 4.916667\n", "std 69.842828 0.085013 2.559978 2.541848\n", "min 9.585000 0.282000 1.671000 2.000000\n", "25% 85.204000 0.338000 2.268500 2.000000\n", "50% 122.865500 0.385000 4.508000 4.000000\n", "75% 204.571000 0.431000 6.917000 8.000000\n", "max 238.050000 0.698000 10.507000 8.000000" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "D.describe()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Зависимая переменная в колонке 'v' - время реакции, с. \n", "Значения зависимой переменной мы хотим сгруппировать по признакам модальность (`mod`) и группа (`g`)." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "mod g\n", "a 2 0.392000\n", " 4 0.456125\n", " 8 0.464143\n", "v 2 0.355143\n", " 4 0.313857\n", " 8 0.382444\n", "Name: v, dtype: float64" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "D.groupby(by=['mod','g'])['v'].mean()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "В полученной серии средних значений индекс сдвоенный в соответствии с нашими группирующими признаками." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Мы можем такой группировочный объект сохранить в переменную, из которой можем получить различные статистические показатели." ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "g = D.groupby(by=['mod','g'])['v']\n", "g" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "xx = arange(len(g))\n", "yy = g.mean()\n", "bar(xx, yy)\n", "errorbar(xx, yy, yerr=g.sem(), color='k', ls='')\n", "xticks(xx, g.groups.keys())\n", "title('Групповые средние ВР, с');" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "В данному случае мы отобразили групповые средние `.mean()` и ошибку средних `.sem()` в виде усов.\n", "Подписи к рисунку взяты из названий получившихся групп." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Фактически группировщик задает списки принадлежности исходных данных к найденным группам по их индексам." ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{('a', 2): [41, 42, 43, 44, 45, 46, 47], ('a', 4): [33, 34, 35, 36, 37, 38, 39, 40], ('a', 8): [24, 25, 26, 27, 28, 29, 30, 31, 32], ('v', 2): [17, 18, 19, 20, 21, 22, 23], ('v', 4): [9, 10, 11, 12, 13, 14, 15, 16], ('v', 8): [0, 1, 2, 3, 4, 5, 6, 7, 8]}" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "g.groups" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Часто при группировке по двум и более факторам удобно получить итоговые значения на пересечениях всех значений факторов. \n", "(В терминологии Excel это называется сводная таблица)." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
g248
mod
a0.3920000.4561250.464143
v0.3551430.3138570.382444
\n", "
" ], "text/plain": [ "g 2 4 8\n", "mod \n", "a 0.392000 0.456125 0.464143\n", "v 0.355143 0.313857 0.382444" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "P = D.pivot_table(index='mod',columns='g', values='v')\n", "P" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "По-умолчанию, в сводной таблице считается среднее, но можно задать и другую агрегирующую функцию." ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# с параметром aggfunc='sem' вычисляем такую же таблицу с ошибками среднего\n", "E = D.pivot_table(index='mod',columns='g', values='v', aggfunc='sem')\n", "P.plot(kind='bar', yerr=E, title='Групповые средние ВР, с');" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Альтернативный способ взглянуть на эти данные - транспонировать сводную таблицу." ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "P.T.plot(kind='bar', yerr=E.T, title='Групповые средние ВР, с');" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "В подписях и легендах к рисункам в пакете `pandas` автоматически отображаются названия группирующих факторов. Это удобно и наглядно при предварительном анализе.\n", "\n", "Для окончательных рисунков можно задать свои подписи с соответствующими параметрами. Или, наоборот, можно задать русские названия факторов и их значений." ] } ], "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": "3.9.0rc1" }, "toc": { "base_numbering": 1, "nav_menu": { "height": "31px", "width": "252px" }, "number_sections": false, "sideBar": true, "skip_h1_title": false, "title_cell": "Table of Contents", "title_sidebar": "Contents", "toc_cell": false, "toc_position": {}, "toc_section_display": "block", "toc_window_display": false } }, "nbformat": 4, "nbformat_minor": 4 }