Skip to content

Instantly share code, notes, and snippets.

@sergiks

sergiks/pandas filtering playground.ipynb

Created February 21, 2018 15:14
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save sergiks/0eb381fb59f7546a59e9fd66343008e4 to your computer and use it in GitHub Desktop.
Save sergiks/0eb381fb59f7546a59e9fd66343008e4 to your computer and use it in GitHub Desktop.
Download ZIP
Filering rows with similar values within pandas DataSet
Display the source blob
Display the rendered blob
Raw
pandas filtering playground.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Pandas play\n",
"Toster question https://toster.ru/q/507710"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd, numpy as np"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df = pd.DataFrame(\n",
" [\n",
" ['bar', 1, 'foo'],\n",
" ['foo', 999, 'bar'],\n",
" ['foo', 15, 'foo'],\n",
" ['smth', 4, 'foo'],\n",
" ['smth', 23, 'bar'],\n",
" ['foo', -19, 'foo'],\n",
" ['bar', 0, 'bar'],\n",
" ['smth', 88, 'bar'],\n",
" ['foo', 10500, 'foo'],\n",
" ['foo', 12, 'bar'],\n",
" ], columns=('co11', 'co12', 'co13')\n",
")\n"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>co11</th>\n",
" <th>co12</th>\n",
" <th>co13</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>bar</td>\n",
" <td>1</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>foo</td>\n",
" <td>999</td>\n",
" <td>bar</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>foo</td>\n",
" <td>15</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>smth</td>\n",
" <td>4</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>smth</td>\n",
" <td>23</td>\n",
" <td>bar</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>foo</td>\n",
" <td>-19</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>bar</td>\n",
" <td>0</td>\n",
" <td>bar</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>smth</td>\n",
" <td>88</td>\n",
" <td>bar</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>foo</td>\n",
" <td>10500</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>foo</td>\n",
" <td>12</td>\n",
" <td>bar</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" co11 co12 co13\n",
"0 bar 1 foo\n",
"1 foo 999 bar\n",
"2 foo 15 foo\n",
"3 smth 4 foo\n",
"4 smth 23 bar\n",
"5 foo -19 foo\n",
"6 bar 0 bar\n",
"7 smth 88 bar\n",
"8 foo 10500 foo\n",
"9 foo 12 bar"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>co11</th>\n",
" <th>co12</th>\n",
" <th>co13</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>foo</td>\n",
" <td>15</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>foo</td>\n",
" <td>-19</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>bar</td>\n",
" <td>0</td>\n",
" <td>bar</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>foo</td>\n",
" <td>10500</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" co11 co12 co13\n",
"2 foo 15 foo\n",
"5 foo -19 foo\n",
"6 bar 0 bar\n",
"8 foo 10500 foo"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[df[['co11','co13']].nunique(axis=1) == 1]"
]
},
{
"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": "3.6.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment