Skip to content

Instantly share code, notes, and snippets.

@kshirsagarsiddharth

kshirsagarsiddharth/idioms_in_pandas.ipynb

Created December 28, 2019 18:45
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save kshirsagarsiddharth/bd9e1c97ffa519556e3a3e9543afb11e to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save kshirsagarsiddharth/bd9e1c97ffa519556e3a3e9543afb11e to your computer and use it in GitHub Desktop.
Download ZIP
Created on Cognitive Class Labs
Display the source blob
Display the rendered blob
Raw
idioms_in_pandas.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
" df = pd.DataFrame({'AAA': [4, 5, 6, 7],\n",
" 'BBB': [10, 20, 30, 40],\n",
" 'CCC': [100, 50, -30, -50]})\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 44,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 10 100\n",
"1 5 20 50\n",
"2 6 30 -30\n",
"3 7 40 -50"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [],
"source": [
"df.loc[df.AAA >=5,'BBB'] = -1"
]
},
{
"cell_type": "code",
"execution_count": 46,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>-1</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>-1</td>\n",
" <td>-30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>-1</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 10 100\n",
"1 5 -1 50\n",
"2 6 -1 -30\n",
"3 7 -1 -50"
]
},
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {},
"outputs": [],
"source": [
"df.loc[df.AAA >= 5,['BBB','CCC']] = 555"
]
},
{
"cell_type": "code",
"execution_count": 48,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>555</td>\n",
" <td>555</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>555</td>\n",
" <td>555</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>555</td>\n",
" <td>555</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 10 100\n",
"1 5 555 555\n",
"2 6 555 555\n",
"3 7 555 555"
]
},
"execution_count": 48,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {},
"outputs": [],
"source": [
"df.loc[df.AAA < 5,['BBB','CCC']] = 2000"
]
},
{
"cell_type": "code",
"execution_count": 50,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>2000</td>\n",
" <td>2000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>555</td>\n",
" <td>555</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>555</td>\n",
" <td>555</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>555</td>\n",
" <td>555</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 2000 2000\n",
"1 5 555 555\n",
"2 6 555 555\n",
"3 7 555 555"
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [],
"source": [
"df_mask = pd.DataFrame({'AAA': [True] * 4,\n",
" 'BBB': [False] * 4,\n",
" 'CCC': [True, False] * 2})\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 52,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 True False True\n",
"1 True False False\n",
"2 True False True\n",
"3 True False False"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_mask"
]
},
{
"cell_type": "code",
"execution_count": 53,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>-1000</td>\n",
" <td>2000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>-1000</td>\n",
" <td>-1000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>-1000</td>\n",
" <td>555</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>-1000</td>\n",
" <td>-1000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 -1000 2000\n",
"1 5 -1000 -1000\n",
"2 6 -1000 555\n",
"3 7 -1000 -1000"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.where(df_mask,-1000)"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame({'AAA': [4, 5, 6, 7],\n",
" 'BBB': [10, 20, 30, 40],\n",
" 'CCC': [100, 50, -30, -50]})\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 55,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 10 100\n",
"1 5 20 50\n",
"2 6 30 -30\n",
"3 7 40 -50"
]
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 56,
"metadata": {},
"outputs": [],
"source": [
"df['logic'] = np.where(df['AAA'] > 5,'HIGH','LOW')"
]
},
{
"cell_type": "code",
"execution_count": 57,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" <th>logic</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" <td>LOW</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" <td>LOW</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" <td>HIGH</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" <td>HIGH</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC logic\n",
"0 4 10 100 LOW\n",
"1 5 20 50 LOW\n",
"2 6 30 -30 HIGH\n",
"3 7 40 -50 HIGH"
]
},
"execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 60,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" <th>logic</th>\n",
" <th>vals</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>LOW</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" <td>LOW</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" <td>HIGH</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" <td>HIGH</td>\n",
" <td>4</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC logic vals\n",
"0 4 4 4 LOW 4\n",
"1 5 20 50 LOW 4\n",
"2 6 30 -30 HIGH 4\n",
"3 7 40 -50 HIGH 4"
]
},
"execution_count": 60,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 61,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame({'AAA': [4, 5, 6, 7],\n",
" ....: 'BBB': [10, 20, 30, 40],\n",
" ....: 'CCC': [100, 50, -30, -50]})\n",
" ....: "
]
},
{
"cell_type": "code",
"execution_count": 62,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 10 100\n",
"1 5 20 50\n",
"2 6 30 -30\n",
"3 7 40 -50"
]
},
"execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 63,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 10 100\n",
"1 5 20 50"
]
},
"execution_count": 63,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[df.AAA <= 5]"
]
},
{
"cell_type": "code",
"execution_count": 64,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"2 6 30 -30\n",
"3 7 40 -50"
]
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[df.AAA > 5]"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame({'AAA': [4, 5, 6, 7],\n",
" ....: 'BBB': [10, 20, 30, 40],\n",
" ....: 'CCC': [100, 50, -30, -50]})\n",
" ....: \n"
]
},
{
"cell_type": "code",
"execution_count": 66,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 10 100\n",
"1 5 20 50\n",
"2 6 30 -30\n",
"3 7 40 -50"
]
},
"execution_count": 66,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 67,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 4\n",
"1 5\n",
"Name: AAA, dtype: int64"
]
},
"execution_count": 67,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc[(df['BBB'] < 25) & (df['CCC'] >= -40),'AAA']"
]
},
{
"cell_type": "code",
"execution_count": 68,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 4\n",
"1 5\n",
"2 6\n",
"3 7\n",
"Name: AAA, dtype: int64"
]
},
"execution_count": 68,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc[(df['BBB'] > 25) | (df['CCC'] >= -40),'AAA']"
]
},
{
"cell_type": "code",
"execution_count": 69,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 10 100\n",
"1 5 20 50\n",
"2 6 30 -30\n",
"3 7 40 -50"
]
},
"execution_count": 69,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 70,
"metadata": {},
"outputs": [],
"source": [
"df.loc[(df['BBB'] > 25) | (df['CCC'] >=75),'AAA'] = 0.1"
]
},
{
"cell_type": "code",
"execution_count": 71,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.1</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5.0</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.1</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.1</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 0.1 10 100\n",
"1 5.0 20 50\n",
"2 0.1 30 -30\n",
"3 0.1 40 -50"
]
},
"execution_count": 71,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 72,
"metadata": {},
"outputs": [],
"source": [
"aValue = 43"
]
},
{
"cell_type": "code",
"execution_count": 78,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5.0</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.1</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.1</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.1</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"1 5.0 20 50\n",
"0 0.1 10 100\n",
"2 0.1 30 -30\n",
"3 0.1 40 -50"
]
},
"execution_count": 78,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc[(df.CCC - aValue).abs().argsort()]"
]
},
{
"cell_type": "code",
"execution_count": 79,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.1</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5.0</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.1</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.1</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 0.1 10 100\n",
"1 5.0 20 50\n",
"2 0.1 30 -30\n",
"3 0.1 40 -50"
]
},
"execution_count": 79,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 80,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame({'AAA': [4, 5, 6, 7],\n",
" ....: 'BBB': [10, 20, 30, 40],\n",
" ....: 'CCC': [100, 50, -30, -50]})\n",
" ....: \n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"Crit1 = df.AAA<=5.5\n",
"Crit2 = df.BBB == 10\n",
"Crit3 = df.CCC > -40"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"AllCrit = Crit1 & Crit2 & Crit3"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"import functools\n",
"CritList = [Crit1,Crit2,Crit3]\n",
"AllCrit = functools.reduce(lambda x,y:x&y,CritList)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 10 100"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[AllCrit]"
]
},
{
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 10 100\n",
"1 5 20 50\n",
"2 6 30 -30\n",
"3 7 40 -50"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 13,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"1 5 20 50\n",
"3 7 40 -50"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[~((df.AAA <=6) & (df.index.isin([0,2,4])))]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 10 100\n",
"1 5 20 50\n",
"2 6 30 -30\n",
"3 7 40 -50"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 15,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4</td>\n",
" <td>10</td>\n",
" <td>100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5</td>\n",
" <td>20</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>6</td>\n",
" <td>30</td>\n",
" <td>-30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7</td>\n",
" <td>40</td>\n",
" <td>-50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 4 10 100\n",
"1 5 20 50\n",
"2 6 30 -30\n",
"3 7 40 -50"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame({'AAA': [1, 2, 1, 3],\n",
" ....: 'BBB': [1, 1, 2, 2],\n",
" ....: 'CCC': [2, 1, 3, 1]})\n",
" ....: \n"
]
},
{
"cell_type": "code",
"execution_count": 17,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC\n",
"0 1 1 2\n",
"1 2 1 1\n",
"2 1 2 3\n",
"3 3 2 1"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"source_cols = df.columns\n",
"new_cols = [str(x)+'_cat' for x in source_cols]\n",
"categories = {1:'Alpha',2:'Beta',3:'Gamma'}\n",
"df[new_cols] = df[source_cols].applymap(categories.get)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"ename": "TypeError",
"evalue": "'builtin_function_or_method' object is not iterable",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-29-a60decdae68b>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mfor\u001b[0m \u001b[0mval\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mcategories\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mval\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mTypeError\u001b[0m: 'builtin_function_or_method' object is not iterable"
]
}
],
"source": []
},
{
"cell_type": "code",
"execution_count": 30,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" <th>AAA_cat</th>\n",
" <th>BBB_cat</th>\n",
" <th>CCC_cat</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>Alpha</td>\n",
" <td>Alpha</td>\n",
" <td>Beta</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Beta</td>\n",
" <td>Alpha</td>\n",
" <td>Alpha</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>Alpha</td>\n",
" <td>Beta</td>\n",
" <td>Gamma</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>Gamma</td>\n",
" <td>Beta</td>\n",
" <td>Alpha</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC AAA_cat BBB_cat CCC_cat\n",
"0 1 1 2 Alpha Alpha Beta\n",
"1 2 1 1 Beta Alpha Alpha\n",
"2 1 2 3 Alpha Beta Gamma\n",
"3 3 2 1 Gamma Beta Alpha"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"source_cols = df.columns\n",
"new_cols = [str(x)+\"_cat\" for x in source_cols]\n",
"categories = {1:'alpha',2:'beta',3:'gamma'}\n",
"df[new_cols] = df[source_cols].applymap(categories.get)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" <th>CCC</th>\n",
" <th>AAA_cat</th>\n",
" <th>BBB_cat</th>\n",
" <th>CCC_cat</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>alpha</td>\n",
" <td>alpha</td>\n",
" <td>beta</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>beta</td>\n",
" <td>alpha</td>\n",
" <td>alpha</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>alpha</td>\n",
" <td>beta</td>\n",
" <td>gamma</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>gamma</td>\n",
" <td>beta</td>\n",
" <td>alpha</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB CCC AAA_cat BBB_cat CCC_cat\n",
"0 1 1 2 alpha alpha beta\n",
"1 2 1 1 beta alpha alpha\n",
"2 1 2 3 alpha beta gamma\n",
"3 3 2 1 gamma beta alpha"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame({'AAA': [1, 1, 1, 2, 2, 2, 3, 3],\n",
" ....: 'BBB': [2, 1, 3, 4, 5, 1, 2, 3]})\n",
" ....: \n"
]
},
{
"cell_type": "code",
"execution_count": 36,
"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>AAA</th>\n",
" <th>BBB</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" AAA BBB\n",
"0 1 2\n",
"1 1 1\n",
"2 1 3\n",
"3 2 4\n",
"4 2 5\n",
"5 2 1\n",
"6 3 2\n",
"7 3 3"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame({'row': [0, 1, 2],\n",
" ....: 'One_X': [1.1, 1.1, 1.1],\n",
" ....: 'One_Y': [1.2, 1.2, 1.2],\n",
" ....: 'Two_X': [1.11, 1.11, 1.11],\n",
" ....: 'Two_Y': [1.22, 1.22, 1.22]})\n",
" ....: "
]
},
{
"cell_type": "code",
"execution_count": 38,
"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>row</th>\n",
" <th>One_X</th>\n",
" <th>One_Y</th>\n",
" <th>Two_X</th>\n",
" <th>Two_Y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>1.1</td>\n",
" <td>1.2</td>\n",
" <td>1.11</td>\n",
" <td>1.22</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>1.1</td>\n",
" <td>1.2</td>\n",
" <td>1.11</td>\n",
" <td>1.22</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>1.1</td>\n",
" <td>1.2</td>\n",
" <td>1.11</td>\n",
" <td>1.22</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" row One_X One_Y Two_X Two_Y\n",
"0 0 1.1 1.2 1.11 1.22\n",
"1 1 1.1 1.2 1.11 1.22\n",
"2 2 1.1 1.2 1.11 1.22"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 39,
"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>One_X</th>\n",
" <th>One_Y</th>\n",
" <th>Two_X</th>\n",
" <th>Two_Y</th>\n",
" </tr>\n",
" <tr>\n",
" <th>row</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.1</td>\n",
" <td>1.2</td>\n",
" <td>1.11</td>\n",
" <td>1.22</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.1</td>\n",
" <td>1.2</td>\n",
" <td>1.11</td>\n",
" <td>1.22</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.1</td>\n",
" <td>1.2</td>\n",
" <td>1.11</td>\n",
" <td>1.22</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" One_X One_Y Two_X Two_Y\n",
"row \n",
"0 1.1 1.2 1.11 1.22\n",
"1 1.1 1.2 1.11 1.22\n",
"2 1.1 1.2 1.11 1.22"
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.set_index('row')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python",
"language": "python",
"name": "conda-env-python-py"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.7"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment