{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## 第3章 pandasでデータを処理しよう\n", "\n", "### 3-4: DataFrame" ] }, { "cell_type": "code", "execution_count": 1, "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", "
c1c2c3
r1110100
r2220200
r3330300
\n", "
" ], "text/plain": [ " c1 c2 c3\n", "r1 1 10 100\n", "r2 2 20 200\n", "r3 3 30 300" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# リスト3.4.1：DataFrameの作成\n", "import pandas as pd\n", "\n", "df = pd.DataFrame(\n", " [[1, 10, 100], [2, 20, 200], [3, 30, 300]],\n", " index=[\"r1\", \"r2\", \"r3\"],\n", " columns=[\"c1\", \"c2\", \"c3\"],\n", ")\n", "df" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "20" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# リスト3.4.3：ラベル指定\n", "df.loc[\"r2\", \"c2\"]" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "c1 2\n", "c2 20\n", "c3 200\n", "Name: r2, dtype: int64" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# リスト3.4.5：すべての列ラベルを指定\n", "df.loc[\"r2\", :]" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "r1 10\n", "r2 20\n", "r3 30\n", "Name: c2, dtype: int64" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# リスト3.4.7：すべての行ラベルを指定\n", "df.loc[:, \"c2\"]" ] }, { "cell_type": "code", "execution_count": 5, "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", "
c2c3
r110100
r330300
\n", "
" ], "text/plain": [ " c2 c3\n", "r1 10 100\n", "r3 30 300" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# リスト3.4.9：行ラベルをリストで指定し列ラベルをスライスで指定した抽出\n", "# 行ラベルをリストで指定、 列ラベルをスライスで指定\n", "df.loc[[\"r1\", \"r3\"], \"c2\":\"c3\"]" ] }, { "cell_type": "code", "execution_count": 6, "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", "
c1c3
r22200
r33300
\n", "
" ], "text/plain": [ " c1 c3\n", "r2 2 200\n", "r3 3 300" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# リスト3.4.11：行の位置をスライスで指定し、 列の位置をリストで指定した抽出\n", "df.iloc[1:3, [0, 2]]" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "r1 10\n", "r2 20\n", "r3 30\n", "Name: c2, dtype: int64" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# リスト3.4.13：[]による指定\n", "df[\"c2\"]" ] }, { "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", "
c1c2c3
r1FalseFalseTrue
r2FalseTrueTrue
r3FalseTrueTrue
\n", "
" ], "text/plain": [ " c1 c2 c3\n", "r1 False False True\n", "r2 False True True\n", "r3 False True True" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# リスト3.4.15：DataFrameに対する比較演算\n", "df > 10" ] }, { "cell_type": "code", "execution_count": 9, "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", "
c1c2c3
r2220200
r3330300
\n", "
" ], "text/plain": [ " c1 c2 c3\n", "r2 2 20 200\n", "r3 3 30 300" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# リスト3.4.17：比較演算を利用したデータの抽出\n", "# c2列の値が10より大きいデータ\n", "df.loc[df[\"c2\"] > 10]" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
c1c2c3
r2220200
\n", "
" ], "text/plain": [ " c1 c2 c3\n", "r2 2 20 200" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# リスト3.4.19：複数条件を組み合わせたデータの抽出\n", "# c1列が1より大きくかつ、c3列が300より小さいデータ\n", "df.loc[(df[\"c1\"] > 1) & (df[\"c3\"] < 300)]" ] }, { "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": "3.6.2" } }, "nbformat": 4, "nbformat_minor": 2 }