{
"cells": [
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"from platform import python_version"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"('3.6.9', '1.0.5', '1.19.0')"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"python_version(), pd.__version__, np.__version__"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## loc\n",
"\n",
"> locate by label"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" john | \n",
" 22 | \n",
" AK | \n",
"
\n",
" \n",
" 1 | \n",
" mary | \n",
" 33 | \n",
" DC | \n",
"
\n",
" \n",
" 2 | \n",
" peter | \n",
" 27 | \n",
" CA | \n",
"
\n",
" \n",
" 3 | \n",
" nancy | \n",
" 22 | \n",
" CA | \n",
"
\n",
" \n",
" 4 | \n",
" gary | \n",
" 31 | \n",
" NY | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name age state\n",
"0 john 22 AK\n",
"1 mary 33 DC\n",
"2 peter 27 CA\n",
"3 nancy 22 CA\n",
"4 gary 31 NY"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_default_index = pd.DataFrame({\n",
" 'name':['john','mary','peter','nancy','gary'],\n",
" 'age':[22,33,27,22,31],\n",
" 'state':['AK','DC','CA','CA','NY']\n",
"})\n",
"df_default_index"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" john | \n",
" 22 | \n",
" AK | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name age state\n",
"0 john 22 AK"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_default_index.loc[[0]]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" 2 | \n",
" peter | \n",
" 27 | \n",
" CA | \n",
"
\n",
" \n",
" 3 | \n",
" nancy | \n",
" 22 | \n",
" CA | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name age state\n",
"2 peter 27 CA\n",
"3 nancy 22 CA"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_default_index.loc[[2,3]]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"df_name_index = pd.DataFrame(\n",
" index=['john','mary','peter','nancy','gary'],\n",
" data={\n",
" 'age':[22,33,27,22,31],\n",
" 'state':['AK','DC','CA','CA','NY']\n",
" }\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" john | \n",
" 22 | \n",
" AK | \n",
"
\n",
" \n",
" mary | \n",
" 33 | \n",
" DC | \n",
"
\n",
" \n",
" peter | \n",
" 27 | \n",
" CA | \n",
"
\n",
" \n",
" nancy | \n",
" 22 | \n",
" CA | \n",
"
\n",
" \n",
" gary | \n",
" 31 | \n",
" NY | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" age state\n",
"john 22 AK\n",
"mary 33 DC\n",
"peter 27 CA\n",
"nancy 22 CA\n",
"gary 31 NY"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_name_index"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" peter | \n",
" 27 | \n",
" CA | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" age state\n",
"peter 27 CA"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_name_index.loc[['peter']]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" john | \n",
" 22 | \n",
" AK | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" age state\n",
"john 22 AK"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_name_index.loc[['john']]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## iloc\n",
"\n",
"> locate by position"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" john | \n",
" 22 | \n",
" AK | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" age state\n",
"john 22 AK"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_name_index.iloc[[0]]"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" peter | \n",
" 27 | \n",
" CA | \n",
"
\n",
" \n",
" nancy | \n",
" 22 | \n",
" CA | \n",
"
\n",
" \n",
" gary | \n",
" 31 | \n",
" NY | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" age state\n",
"peter 27 CA\n",
"nancy 22 CA\n",
"gary 31 NY"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_name_index.iloc[[2,3,4]]"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" john | \n",
" 22 | \n",
" AK | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name age state\n",
"0 john 22 AK"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_default_index.iloc[[0]]"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" 2 | \n",
" peter | \n",
" 27 | \n",
" CA | \n",
"
\n",
" \n",
" 3 | \n",
" nancy | \n",
" 22 | \n",
" CA | \n",
"
\n",
" \n",
" 4 | \n",
" gary | \n",
" 31 | \n",
" NY | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name age state\n",
"2 peter 27 CA\n",
"3 nancy 22 CA\n",
"4 gary 31 NY"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_default_index.iloc[[2,3,4]]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## set value to individual cell\n",
"\n",
"> must use `loc`"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" john | \n",
" 22 | \n",
" AK | \n",
"
\n",
" \n",
" 1 | \n",
" mary | \n",
" 33 | \n",
" DC | \n",
"
\n",
" \n",
" 2 | \n",
" peter | \n",
" 27 | \n",
" CA | \n",
"
\n",
" \n",
" 3 | \n",
" nancy | \n",
" 22 | \n",
" CA | \n",
"
\n",
" \n",
" 4 | \n",
" gary | \n",
" 31 | \n",
" NY | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name age state\n",
"0 john 22 AK\n",
"1 mary 33 DC\n",
"2 peter 27 CA\n",
"3 nancy 22 CA\n",
"4 gary 31 NY"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_set = pd.DataFrame({\n",
" 'name':['john','mary','peter','nancy','gary'],\n",
" 'age':[22,33,27,22,31],\n",
" 'state':['AK','DC','CA','CA','NY']\n",
"})\n",
"df_set"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" bartholomew | \n",
" 22 | \n",
" AK | \n",
"
\n",
" \n",
" 1 | \n",
" mary | \n",
" 33 | \n",
" DC | \n",
"
\n",
" \n",
" 2 | \n",
" peter | \n",
" 27 | \n",
" CA | \n",
"
\n",
" \n",
" 3 | \n",
" nancy | \n",
" 39 | \n",
" CA | \n",
"
\n",
" \n",
" 4 | \n",
" gary | \n",
" 31 | \n",
" NY | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name age state\n",
"0 bartholomew 22 AK\n",
"1 mary 33 DC\n",
"2 peter 27 CA\n",
"3 nancy 39 CA\n",
"4 gary 31 NY"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_set.loc[0,'name'] = 'bartholomew'\n",
"\n",
"df_set.loc[3, 'age'] = 39\n",
"\n",
"df_set"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" john | \n",
" 99 | \n",
" AK | \n",
"
\n",
" \n",
" mary | \n",
" 33 | \n",
" DC | \n",
"
\n",
" \n",
" peter | \n",
" 27 | \n",
" CA | \n",
"
\n",
" \n",
" nancy | \n",
" 22 | \n",
" CA | \n",
"
\n",
" \n",
" gary | \n",
" 31 | \n",
" NY | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" age state\n",
"john 99 AK\n",
"mary 33 DC\n",
"peter 27 CA\n",
"nancy 22 CA\n",
"gary 31 NY"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_name_index.loc['john','age'] = 99\n",
"df_name_index"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Use column as index"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" john | \n",
" 22 | \n",
" AK | \n",
"
\n",
" \n",
" 1 | \n",
" mary | \n",
" 33 | \n",
" DC | \n",
"
\n",
" \n",
" 2 | \n",
" peter | \n",
" 27 | \n",
" CA | \n",
"
\n",
" \n",
" 3 | \n",
" nancy | \n",
" 22 | \n",
" CA | \n",
"
\n",
" \n",
" 4 | \n",
" gary | \n",
" 31 | \n",
" NY | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name age state\n",
"0 john 22 AK\n",
"1 mary 33 DC\n",
"2 peter 27 CA\n",
"3 nancy 22 CA\n",
"4 gary 31 NY"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.DataFrame({\n",
" 'name':['john','mary','peter','nancy','gary'],\n",
" 'age':[22,33,27,22,31],\n",
" 'state':['AK','DC','CA','CA','NY']\n",
"})\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" name | \n",
" | \n",
" | \n",
"
\n",
" \n",
" \n",
" \n",
" john | \n",
" 22 | \n",
" AK | \n",
"
\n",
" \n",
" mary | \n",
" 33 | \n",
" DC | \n",
"
\n",
" \n",
" peter | \n",
" 27 | \n",
" CA | \n",
"
\n",
" \n",
" nancy | \n",
" 22 | \n",
" CA | \n",
"
\n",
" \n",
" gary | \n",
" 31 | \n",
" NY | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" age state\n",
"name \n",
"john 22 AK\n",
"mary 33 DC\n",
"peter 27 CA\n",
"nancy 22 CA\n",
"gary 31 NY"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.set_index('name', verify_integrity=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Set multiple values"
]
},
{
"cell_type": "code",
"execution_count": 63,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" age | \n",
" state | \n",
" lives_in_ca | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" john | \n",
" 22 | \n",
" AK | \n",
" False | \n",
"
\n",
" \n",
" 1 | \n",
" mary | \n",
" 33 | \n",
" DC | \n",
" False | \n",
"
\n",
" \n",
" 2 | \n",
" peter | \n",
" 27 | \n",
" CA | \n",
" False | \n",
"
\n",
" \n",
" 3 | \n",
" nancy | \n",
" 22 | \n",
" CA | \n",
" False | \n",
"
\n",
" \n",
" 4 | \n",
" gary | \n",
" 31 | \n",
" NY | \n",
" False | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name age state lives_in_ca\n",
"0 john 22 AK False\n",
"1 mary 33 DC False\n",
"2 peter 27 CA False\n",
"3 nancy 22 CA False\n",
"4 gary 31 NY False"
]
},
"execution_count": 63,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.DataFrame({\n",
" 'name':['john','mary','peter','nancy','gary'],\n",
" 'age':[22,33,27,22,31],\n",
" 'state':['AK','DC','CA','CA','NY'],\n",
" 'lives_in_ca': [False,False,False,False,False]\n",
"})\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {},
"outputs": [],
"source": [
"index = df[df['state']=='CA'].index"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" age | \n",
" state | \n",
" lives_in_ca | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" john | \n",
" 22 | \n",
" AK | \n",
" False | \n",
"
\n",
" \n",
" 1 | \n",
" mary | \n",
" 33 | \n",
" DC | \n",
" False | \n",
"
\n",
" \n",
" 2 | \n",
" peter | \n",
" 27 | \n",
" CA | \n",
" True | \n",
"
\n",
" \n",
" 3 | \n",
" nancy | \n",
" 22 | \n",
" CA | \n",
" True | \n",
"
\n",
" \n",
" 4 | \n",
" gary | \n",
" 31 | \n",
" NY | \n",
" False | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name age state lives_in_ca\n",
"0 john 22 AK False\n",
"1 mary 33 DC False\n",
"2 peter 27 CA True\n",
"3 nancy 22 CA True\n",
"4 gary 31 NY False"
]
},
"execution_count": 65,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc[index,'lives_in_ca'] = True\n",
"df"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## settingwithcopywarning"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame({\n",
" 'name':['john','mary','peter','nancy','gary'],\n",
" 'age':[22,33,27,22,31],\n",
" 'state':['AK','DC','CA','CA','NY']\n",
"})"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### bad:"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" 1 | \n",
" mary | \n",
" 33 | \n",
" DC | \n",
"
\n",
" \n",
" 4 | \n",
" gary | \n",
" 31 | \n",
" NY | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name age state\n",
"1 mary 33 DC\n",
"4 gary 31 NY"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_over_30_years = df[df['age']>30]\n",
"df_over_30_years"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/felipe/jekyll-utils/jekyll-venv/lib/python3.6/site-packages/ipykernel_launcher.py:1: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" \"\"\"Entry point for launching an IPython kernel.\n"
]
}
],
"source": [
"df_over_30_years['new_column'] = 'some_value'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### good:"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" age | \n",
" state | \n",
"
\n",
" \n",
" \n",
" \n",
" 1 | \n",
" mary | \n",
" 33 | \n",
" DC | \n",
"
\n",
" \n",
" 4 | \n",
" gary | \n",
" 31 | \n",
" NY | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name age state\n",
"1 mary 33 DC\n",
"4 gary 31 NY"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_over_30_years = df.copy()[df['age']>30]\n",
"df_over_30_years"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"df_over_30_years['new_column'] = 'some_value'"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" name | \n",
" age | \n",
" state | \n",
" new_column | \n",
"
\n",
" \n",
" \n",
" \n",
" 1 | \n",
" mary | \n",
" 33 | \n",
" DC | \n",
" some_value | \n",
"
\n",
" \n",
" 4 | \n",
" gary | \n",
" 31 | \n",
" NY | \n",
" some_value | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" name age state new_column\n",
"1 mary 33 DC some_value\n",
"4 gary 31 NY some_value"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_over_30_years"
]
},
{
"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": "3.6.9"
},
"toc": {
"base_numbering": 1,
"nav_menu": {},
"number_sections": true,
"sideBar": true,
"skip_h1_title": false,
"title_cell": "Table of Contents",
"title_sidebar": "Contents",
"toc_cell": false,
"toc_position": {},
"toc_section_display": true,
"toc_window_display": false
}
},
"nbformat": 4,
"nbformat_minor": 2
}