Skip to content

Instantly share code, notes, and snippets.

@jbencook

jbencook/pandas-melt.ipynb Secret

Created Dec 22, 2020
Embed
What would you like to do?
Create a long format dummy dataset and pivot/unpivot it
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import datetime as dt\n",
"import random"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>date</th>\n",
" <th>region</th>\n",
" <th>revenue</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>1999-01-03</td>\n",
" <td>EMEA</td>\n",
" <td>306</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>1999-01-04</td>\n",
" <td>EMEA</td>\n",
" <td>236</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1999-01-05</td>\n",
" <td>AMER</td>\n",
" <td>835</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>1999-01-09</td>\n",
" <td>AMER</td>\n",
" <td>225</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1999-01-10</td>\n",
" <td>AMER</td>\n",
" <td>684</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" date region revenue\n",
"25 1999-01-03 EMEA 306\n",
"18 1999-01-04 EMEA 236\n",
"4 1999-01-05 AMER 835\n",
"8 1999-01-09 AMER 225\n",
"0 1999-01-10 AMER 684"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Create a DataFrame with fake sales data for Q1 1999\n",
"dates = []\n",
"regions = []\n",
"revenues = []\n",
"\n",
"days = {1:31, 2:28, 3:31}\n",
"for i in range(30):\n",
" month = random.choice([1, 2, 3])\n",
" dates.append(dt.date(1999, month, random.randint(1, days[month])))\n",
" regions.append(random.choice([\"AMER\", \"EMEA\", \"APAC\"]))\n",
" revenues.append(random.randint(100, 999))\n",
"\n",
"df = pd.DataFrame({\n",
" 'date': dates,\n",
" 'region': regions,\n",
" 'revenue': revenues\n",
"}).sort_values(['date', 'region'])\n",
"\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>region</th>\n",
" <th>AMER</th>\n",
" <th>APAC</th>\n",
" <th>EMEA</th>\n",
" </tr>\n",
" <tr>\n",
" <th>date</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1999-01-03</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>306</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1999-01-04</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>236</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1999-01-05</th>\n",
" <td>835</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1999-01-09</th>\n",
" <td>225</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1999-01-10</th>\n",
" <td>684</td>\n",
" <td>0</td>\n",
" <td>257</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"region AMER APAC EMEA\n",
"date \n",
"1999-01-03 0 0 306\n",
"1999-01-04 0 0 236\n",
"1999-01-05 835 0 0\n",
"1999-01-09 225 0 0\n",
"1999-01-10 684 0 257"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Pivot to get total daily revenue per region\n",
"wide_df = df.pivot_table(\n",
" values='revenue',\n",
" index='date',\n",
" columns='region',\n",
" aggfunc='sum',\n",
" fill_value=0,\n",
")\n",
"\n",
"wide_df.head()"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>date</th>\n",
" <th>region</th>\n",
" <th>total_revenue</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1999-01-03</td>\n",
" <td>AMER</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1999-01-04</td>\n",
" <td>AMER</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1999-01-05</td>\n",
" <td>AMER</td>\n",
" <td>835</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1999-01-09</td>\n",
" <td>AMER</td>\n",
" <td>225</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1999-01-10</td>\n",
" <td>AMER</td>\n",
" <td>684</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" date region total_revenue\n",
"0 1999-01-03 AMER 0\n",
"1 1999-01-04 AMER 0\n",
"2 1999-01-05 AMER 835\n",
"3 1999-01-09 AMER 225\n",
"4 1999-01-10 AMER 684"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"wide_df = wide_df.reset_index()\n",
"long_df = wide_df.melt(\n",
" id_vars='date',\n",
" value_vars=['AMER', 'APAC', 'EMEA'],\n",
" value_name='total_revenue',\n",
")\n",
"\n",
"long_df.head()"
]
}
],
"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": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment