Skip to content

Instantly share code, notes, and snippets.

@sinhrks

sinhrks/group_key.ipynb

Created July 12, 2016 23:44
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save sinhrks/104b831cbb680f9c1beb76534c742fdf to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save sinhrks/104b831cbb680f9c1beb76534c742fdf to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
group_key.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Q. 指定したキーが変わる度にナンバリングしたい\n",
"\n",
"groupbyで分けたグループにナンバリングするようなイメージ\n",
"\n",
"```\n",
"result:\n",
"-------\n",
"\tc1\tc2\tc3\tgroup\n",
"0\ta\ta\ta\t0\n",
"1\ta\ta\ta\t0\n",
"2\ta\ta\tb\t1\n",
"3\ta\tb\tb\t2\n",
"4\ta\tb\tb\t2\n",
"5\tb\tb\tc\t3\n",
"6\tb\tc\tc\t4\n",
"7\tb\tc\tc\t4\n",
"8\tb\tc\tc\t4\n",
"```\n",
"\n",
"https://gist.github.com/KazukiOnodera/ed158c161ede48067c475b6406bef330\n",
"\n",
"## A"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df = pd.DataFrame([['a', 'a', 'a'],\n",
" ['a', 'a', 'a'],\n",
" ['a', 'a', 'b'],\n",
" ['a', 'b', 'b'],\n",
" ['a', 'b', 'b'],\n",
" ['b', 'b', 'c'],\n",
" ['b', 'c', 'c'],\n",
" ['b', 'c', 'c'],\n",
" ['b', 'c', 'c']],\n",
" columns=['c1','c2','c3'])"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>c1</th>\n",
" <th>c2</th>\n",
" <th>c3</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" <td>b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>a</td>\n",
" <td>b</td>\n",
" <td>b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>a</td>\n",
" <td>b</td>\n",
" <td>b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>b</td>\n",
" <td>b</td>\n",
" <td>c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>b</td>\n",
" <td>c</td>\n",
" <td>c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>b</td>\n",
" <td>c</td>\n",
" <td>c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>b</td>\n",
" <td>c</td>\n",
" <td>c</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" c1 c2 c3\n",
"0 a a a\n",
"1 a a a\n",
"2 a a b\n",
"3 a b b\n",
"4 a b b\n",
"5 b b c\n",
"6 b c c\n",
"7 b c c\n",
"8 b c c"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>c1</th>\n",
" <th>c2</th>\n",
" <th>c3</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" <td>b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>a</td>\n",
" <td>b</td>\n",
" <td>b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>a</td>\n",
" <td>b</td>\n",
" <td>b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>b</td>\n",
" <td>b</td>\n",
" <td>c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>b</td>\n",
" <td>c</td>\n",
" <td>c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>b</td>\n",
" <td>c</td>\n",
" <td>c</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" c1 c2 c3\n",
"0 NaN NaN NaN\n",
"1 a a a\n",
"2 a a a\n",
"3 a a b\n",
"4 a b b\n",
"5 a b b\n",
"6 b b c\n",
"7 b c c\n",
"8 b c c"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shift(1)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>c1</th>\n",
" <th>c2</th>\n",
" <th>c3</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" c1 c2 c3\n",
"0 True True True\n",
"1 False False False\n",
"2 False False True\n",
"3 False True False\n",
"4 False False False\n",
"5 True False True\n",
"6 False True False\n",
"7 False False False\n",
"8 False False False"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df != df.shift(1)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0 True\n",
"1 False\n",
"2 True\n",
"3 True\n",
"4 False\n",
"5 True\n",
"6 True\n",
"7 False\n",
"8 False\n",
"dtype: bool"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"(df != df.shift(1)).any(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0 0\n",
"1 0\n",
"2 1\n",
"3 2\n",
"4 2\n",
"5 3\n",
"6 4\n",
"7 4\n",
"8 4\n",
"dtype: int32"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"(df != df.shift(1)).any(axis=1).cumsum() - 1"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>c1</th>\n",
" <th>c2</th>\n",
" <th>c3</th>\n",
" <th>group</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>a</td>\n",
" <td>a</td>\n",
" <td>b</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>a</td>\n",
" <td>b</td>\n",
" <td>b</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>a</td>\n",
" <td>b</td>\n",
" <td>b</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>b</td>\n",
" <td>b</td>\n",
" <td>c</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>b</td>\n",
" <td>c</td>\n",
" <td>c</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>b</td>\n",
" <td>c</td>\n",
" <td>c</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>b</td>\n",
" <td>c</td>\n",
" <td>c</td>\n",
" <td>4</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" c1 c2 c3 group\n",
"0 a a a 0\n",
"1 a a a 0\n",
"2 a a b 1\n",
"3 a b b 2\n",
"4 a b b 2\n",
"5 b b c 3\n",
"6 b c c 4\n",
"7 b c c 4\n",
"8 b c c 4"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['group'] = (df != df.shift(1)).any(axis=1).cumsum() - 1\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"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": "3.5.1"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment