Skip to content

Instantly share code, notes, and snippets.

@Rogeman

Rogeman/Learning Pandas.ipynb

Last active October 18, 2016 21:31
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 Rogeman/1b292b6d6e7c729406c1843c71bfc0cc to your computer and use it in GitHub Desktop.
Save Rogeman/1b292b6d6e7c729406c1843c71bfc0cc to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
Learning Pandas.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Learning Pandas #\n",
"http://pandas.pydata.org/pandas-docs/stable/10min.html#min\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Object Creation ##"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Series ###"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"0 1.0\n",
"1 3.0\n",
"2 5.0\n",
"3 NaN\n",
"4 6.0\n",
"5 8.0\n",
"dtype: float64"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#import the pandas, numpy and matplotlib libraries\n",
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"s=pd.Series([1,3,5,np.nan,6,8])\n",
"s\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### date_range ###"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',\n",
" '2013-01-05', '2013-01-06'],\n",
" dtype='datetime64[ns]', freq='D')"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Create a date range\n",
"dates=pd.date_range('20130101',periods=6)\n",
"dates"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### DataFrame ###\n",
"This is pandas strenght, managing big tables of data easily"
]
},
{
"cell_type": "code",
"execution_count": 54,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-01</th>\n",
" <td>0.790777</td>\n",
" <td>-0.645811</td>\n",
" <td>1.121823</td>\n",
" <td>-0.758688</td>\n",
" <td>-0.765090</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>-0.187210</td>\n",
" <td>-1.329730</td>\n",
" <td>-0.031925</td>\n",
" <td>1.492296</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-03</th>\n",
" <td>1.111047</td>\n",
" <td>-0.083611</td>\n",
" <td>0.799030</td>\n",
" <td>-0.980553</td>\n",
" <td>-0.088336</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.112443</td>\n",
" <td>0.313526</td>\n",
" <td>0.394046</td>\n",
" <td>0.228101</td>\n",
" <td>0.393986</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-05</th>\n",
" <td>0.637097</td>\n",
" <td>1.015037</td>\n",
" <td>-1.006203</td>\n",
" <td>0.119320</td>\n",
" <td>-0.662282</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-06</th>\n",
" <td>-0.175692</td>\n",
" <td>0.894900</td>\n",
" <td>0.206329</td>\n",
" <td>1.441154</td>\n",
" <td>0.231754</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"2013-01-01 0.790777 -0.645811 1.121823 -0.758688 -0.765090\n",
"2013-01-02 0.594159 -0.187210 -1.329730 -0.031925 1.492296\n",
"2013-01-03 1.111047 -0.083611 0.799030 -0.980553 -0.088336\n",
"2013-01-04 -0.112443 0.313526 0.394046 0.228101 0.393986\n",
"2013-01-05 0.637097 1.015037 -1.006203 0.119320 -0.662282\n",
"2013-01-06 -0.175692 0.894900 0.206329 1.441154 0.231754"
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Create a Data Frame, this is pandas strenght. Managing big tables of data easily\n",
"\n",
"df = pd.DataFrame(np.random.randn(6,5),index=dates,columns=list('ABCDE'))\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 26,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" <th>F</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.0</td>\n",
" <td>2013-01-02</td>\n",
" <td>1.0</td>\n",
" <td>3</td>\n",
" <td>test</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.0</td>\n",
" <td>2013-01-02</td>\n",
" <td>1.0</td>\n",
" <td>3</td>\n",
" <td>train</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.0</td>\n",
" <td>2013-01-02</td>\n",
" <td>1.0</td>\n",
" <td>3</td>\n",
" <td>test</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1.0</td>\n",
" <td>2013-01-02</td>\n",
" <td>1.0</td>\n",
" <td>3</td>\n",
" <td>train</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E F\n",
"0 1.0 2013-01-02 1.0 3 test foo\n",
"1 1.0 2013-01-02 1.0 3 train foo\n",
"2 1.0 2013-01-02 1.0 3 test foo\n",
"3 1.0 2013-01-02 1.0 3 train foo"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2 = pd.DataFrame({'A' : 1.,\n",
" 'B' : pd.Timestamp('20130102'),\n",
" 'C' : pd.Series(1,index=list(range(4)),dtype='float32'),\n",
" 'D' : np.array([3] * 4,dtype='int32'),\n",
" 'E' : pd.Categorical([\"test\",\"train\",\"test\",\"train\"]),\n",
" 'F' : 'foo'})\n",
"df2"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"A float64\n",
"B datetime64[ns]\n",
"C float32\n",
"D int32\n",
"E category\n",
"F object\n",
"dtype: object"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2.dtypes"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Viewing Data ##"
]
},
{
"cell_type": "code",
"execution_count": 31,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" <th>F</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1.0</td>\n",
" <td>2013-01-02</td>\n",
" <td>1.0</td>\n",
" <td>3</td>\n",
" <td>test</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.0</td>\n",
" <td>2013-01-02</td>\n",
" <td>1.0</td>\n",
" <td>3</td>\n",
" <td>train</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1.0</td>\n",
" <td>2013-01-02</td>\n",
" <td>1.0</td>\n",
" <td>3</td>\n",
" <td>test</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1.0</td>\n",
" <td>2013-01-02</td>\n",
" <td>1.0</td>\n",
" <td>3</td>\n",
" <td>train</td>\n",
" <td>foo</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E F\n",
"0 1.0 2013-01-02 1.0 3 test foo\n",
"1 1.0 2013-01-02 1.0 3 train foo\n",
"2 1.0 2013-01-02 1.0 3 test foo\n",
"3 1.0 2013-01-02 1.0 3 train foo"
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2.head()"
]
},
{
"cell_type": "code",
"execution_count": 32,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.066932</td>\n",
" <td>0.814831</td>\n",
" <td>-0.530873</td>\n",
" <td>0.420534</td>\n",
" <td>-0.283383</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-05</th>\n",
" <td>-0.381570</td>\n",
" <td>-1.459545</td>\n",
" <td>-1.118827</td>\n",
" <td>-0.441326</td>\n",
" <td>-0.496440</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-06</th>\n",
" <td>0.305037</td>\n",
" <td>0.200597</td>\n",
" <td>0.677120</td>\n",
" <td>-2.301574</td>\n",
" <td>1.084699</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"2013-01-04 -0.066932 0.814831 -0.530873 0.420534 -0.283383\n",
"2013-01-05 -0.381570 -1.459545 -1.118827 -0.441326 -0.496440\n",
"2013-01-06 0.305037 0.200597 0.677120 -2.301574 1.084699"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.tail(3)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',\n",
" '2013-01-05', '2013-01-06'],\n",
" dtype='datetime64[ns]', freq='D')"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.index"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"Index([u'A', u'B', u'C', u'D', u'E'], dtype='object')"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([[ 0.8627033 , 1.79973521, 0.46620713, 0.2763234 , 0.99238605],\n",
" [ 0.73438583, 0.73733965, -0.46265282, -0.05800679, 0.66008374],\n",
" [ 0.82690887, 0.66882248, -0.29789657, 0.66296849, -0.60098529],\n",
" [-0.06693225, 0.81483134, -0.53087295, 0.42053426, -0.28338318],\n",
" [-0.38156979, -1.4595453 , -1.11882718, -0.44132608, -0.49644037],\n",
" [ 0.30503654, 0.20059724, 0.67712008, -2.30157356, 1.08469931]])"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.values"
]
},
{
"cell_type": "code",
"execution_count": 37,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>6.000000</td>\n",
" <td>6.000000</td>\n",
" <td>6.000000</td>\n",
" <td>6.000000</td>\n",
" <td>6.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>0.380089</td>\n",
" <td>0.460297</td>\n",
" <td>-0.211154</td>\n",
" <td>-0.240180</td>\n",
" <td>0.226060</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>0.518397</td>\n",
" <td>1.076407</td>\n",
" <td>0.670032</td>\n",
" <td>1.080924</td>\n",
" <td>0.771808</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>-0.381570</td>\n",
" <td>-1.459545</td>\n",
" <td>-1.118827</td>\n",
" <td>-2.301574</td>\n",
" <td>-0.600985</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>0.026060</td>\n",
" <td>0.317654</td>\n",
" <td>-0.513818</td>\n",
" <td>-0.345496</td>\n",
" <td>-0.443176</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>0.519711</td>\n",
" <td>0.703081</td>\n",
" <td>-0.380275</td>\n",
" <td>0.109158</td>\n",
" <td>0.188350</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>0.803778</td>\n",
" <td>0.795458</td>\n",
" <td>0.275181</td>\n",
" <td>0.384482</td>\n",
" <td>0.909310</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>0.862703</td>\n",
" <td>1.799735</td>\n",
" <td>0.677120</td>\n",
" <td>0.662968</td>\n",
" <td>1.084699</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"count 6.000000 6.000000 6.000000 6.000000 6.000000\n",
"mean 0.380089 0.460297 -0.211154 -0.240180 0.226060\n",
"std 0.518397 1.076407 0.670032 1.080924 0.771808\n",
"min -0.381570 -1.459545 -1.118827 -2.301574 -0.600985\n",
"25% 0.026060 0.317654 -0.513818 -0.345496 -0.443176\n",
"50% 0.519711 0.703081 -0.380275 0.109158 0.188350\n",
"75% 0.803778 0.795458 0.275181 0.384482 0.909310\n",
"max 0.862703 1.799735 0.677120 0.662968 1.084699"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.describe()"
]
},
{
"cell_type": "code",
"execution_count": 40,
"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>2013-01-01 00:00:00</th>\n",
" <th>2013-01-02 00:00:00</th>\n",
" <th>2013-01-03 00:00:00</th>\n",
" <th>2013-01-04 00:00:00</th>\n",
" <th>2013-01-05 00:00:00</th>\n",
" <th>2013-01-06 00:00:00</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
" <td>0.862703</td>\n",
" <td>0.734386</td>\n",
" <td>0.826909</td>\n",
" <td>-0.066932</td>\n",
" <td>-0.381570</td>\n",
" <td>0.305037</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
" <td>1.799735</td>\n",
" <td>0.737340</td>\n",
" <td>0.668822</td>\n",
" <td>0.814831</td>\n",
" <td>-1.459545</td>\n",
" <td>0.200597</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
" <td>0.466207</td>\n",
" <td>-0.462653</td>\n",
" <td>-0.297897</td>\n",
" <td>-0.530873</td>\n",
" <td>-1.118827</td>\n",
" <td>0.677120</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
" <td>0.276323</td>\n",
" <td>-0.058007</td>\n",
" <td>0.662968</td>\n",
" <td>0.420534</td>\n",
" <td>-0.441326</td>\n",
" <td>-2.301574</td>\n",
" </tr>\n",
" <tr>\n",
" <th>E</th>\n",
" <td>0.992386</td>\n",
" <td>0.660084</td>\n",
" <td>-0.600985</td>\n",
" <td>-0.283383</td>\n",
" <td>-0.496440</td>\n",
" <td>1.084699</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 2013-01-01 2013-01-02 2013-01-03 2013-01-04 2013-01-05 2013-01-06\n",
"A 0.862703 0.734386 0.826909 -0.066932 -0.381570 0.305037\n",
"B 1.799735 0.737340 0.668822 0.814831 -1.459545 0.200597\n",
"C 0.466207 -0.462653 -0.297897 -0.530873 -1.118827 0.677120\n",
"D 0.276323 -0.058007 0.662968 0.420534 -0.441326 -2.301574\n",
"E 0.992386 0.660084 -0.600985 -0.283383 -0.496440 1.084699"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Transpose the data\n",
"df.T"
]
},
{
"cell_type": "code",
"execution_count": 43,
"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>E</th>\n",
" <th>D</th>\n",
" <th>C</th>\n",
" <th>B</th>\n",
" <th>A</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-01</th>\n",
" <td>0.992386</td>\n",
" <td>0.276323</td>\n",
" <td>0.466207</td>\n",
" <td>1.799735</td>\n",
" <td>0.862703</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.660084</td>\n",
" <td>-0.058007</td>\n",
" <td>-0.462653</td>\n",
" <td>0.737340</td>\n",
" <td>0.734386</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-03</th>\n",
" <td>-0.600985</td>\n",
" <td>0.662968</td>\n",
" <td>-0.297897</td>\n",
" <td>0.668822</td>\n",
" <td>0.826909</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.283383</td>\n",
" <td>0.420534</td>\n",
" <td>-0.530873</td>\n",
" <td>0.814831</td>\n",
" <td>-0.066932</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-05</th>\n",
" <td>-0.496440</td>\n",
" <td>-0.441326</td>\n",
" <td>-1.118827</td>\n",
" <td>-1.459545</td>\n",
" <td>-0.381570</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-06</th>\n",
" <td>1.084699</td>\n",
" <td>-2.301574</td>\n",
" <td>0.677120</td>\n",
" <td>0.200597</td>\n",
" <td>0.305037</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" E D C B A\n",
"2013-01-01 0.992386 0.276323 0.466207 1.799735 0.862703\n",
"2013-01-02 0.660084 -0.058007 -0.462653 0.737340 0.734386\n",
"2013-01-03 -0.600985 0.662968 -0.297897 0.668822 0.826909\n",
"2013-01-04 -0.283383 0.420534 -0.530873 0.814831 -0.066932\n",
"2013-01-05 -0.496440 -0.441326 -1.118827 -1.459545 -0.381570\n",
"2013-01-06 1.084699 -2.301574 0.677120 0.200597 0.305037"
]
},
"execution_count": 43,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#sort by an axis\n",
"#this seems to order the columns \n",
"df.sort_index(axis=1,ascending=False)"
]
},
{
"cell_type": "code",
"execution_count": 47,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-01</th>\n",
" <td>0.862703</td>\n",
" <td>1.799735</td>\n",
" <td>0.466207</td>\n",
" <td>0.276323</td>\n",
" <td>0.992386</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.734386</td>\n",
" <td>0.737340</td>\n",
" <td>-0.462653</td>\n",
" <td>-0.058007</td>\n",
" <td>0.660084</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-03</th>\n",
" <td>0.826909</td>\n",
" <td>0.668822</td>\n",
" <td>-0.297897</td>\n",
" <td>0.662968</td>\n",
" <td>-0.600985</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.066932</td>\n",
" <td>0.814831</td>\n",
" <td>-0.530873</td>\n",
" <td>0.420534</td>\n",
" <td>-0.283383</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-05</th>\n",
" <td>-0.381570</td>\n",
" <td>-1.459545</td>\n",
" <td>-1.118827</td>\n",
" <td>-0.441326</td>\n",
" <td>-0.496440</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-06</th>\n",
" <td>0.305037</td>\n",
" <td>0.200597</td>\n",
" <td>0.677120</td>\n",
" <td>-2.301574</td>\n",
" <td>1.084699</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"2013-01-01 0.862703 1.799735 0.466207 0.276323 0.992386\n",
"2013-01-02 0.734386 0.737340 -0.462653 -0.058007 0.660084\n",
"2013-01-03 0.826909 0.668822 -0.297897 0.662968 -0.600985\n",
"2013-01-04 -0.066932 0.814831 -0.530873 0.420534 -0.283383\n",
"2013-01-05 -0.381570 -1.459545 -1.118827 -0.441326 -0.496440\n",
"2013-01-06 0.305037 0.200597 0.677120 -2.301574 1.084699"
]
},
"execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#sort by an axis\n",
"#this seems to order the columns \n",
"df.sort_index(axis=1,ascending=True)"
]
},
{
"cell_type": "code",
"execution_count": 57,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"#Order the table by column B in descending order\n",
"# inplace=True modifies df\n",
"df.sort_values(by='B',ascending=False, inplace=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Selection"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Getting ###"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"2013-01-05 0.637097\n",
"2013-01-06 -0.175692\n",
"2013-01-04 -0.112443\n",
"2013-01-03 1.111047\n",
"2013-01-02 0.594159\n",
"2013-01-01 0.790777\n",
"Name: A, dtype: float64"
]
},
"execution_count": 59,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Show me column A\n",
"df['A']"
]
},
{
"cell_type": "code",
"execution_count": 66,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-05</th>\n",
" <td>0.637097</td>\n",
" <td>1.015037</td>\n",
" <td>-1.006203</td>\n",
" <td>0.119320</td>\n",
" <td>-0.662282</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-06</th>\n",
" <td>-0.175692</td>\n",
" <td>0.894900</td>\n",
" <td>0.206329</td>\n",
" <td>1.441154</td>\n",
" <td>0.231754</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.112443</td>\n",
" <td>0.313526</td>\n",
" <td>0.394046</td>\n",
" <td>0.228101</td>\n",
" <td>0.393986</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"2013-01-05 0.637097 1.015037 -1.006203 0.119320 -0.662282\n",
"2013-01-06 -0.175692 0.894900 0.206329 1.441154 0.231754\n",
"2013-01-04 -0.112443 0.313526 0.394046 0.228101 0.393986"
]
},
"execution_count": 66,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[0:3]"
]
},
{
"cell_type": "code",
"execution_count": 67,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.112443</td>\n",
" <td>0.313526</td>\n",
" <td>0.394046</td>\n",
" <td>0.228101</td>\n",
" <td>0.393986</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-03</th>\n",
" <td>1.111047</td>\n",
" <td>-0.083611</td>\n",
" <td>0.799030</td>\n",
" <td>-0.980553</td>\n",
" <td>-0.088336</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>-0.187210</td>\n",
" <td>-1.329730</td>\n",
" <td>-0.031925</td>\n",
" <td>1.492296</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"2013-01-04 -0.112443 0.313526 0.394046 0.228101 0.393986\n",
"2013-01-03 1.111047 -0.083611 0.799030 -0.980553 -0.088336\n",
"2013-01-02 0.594159 -0.187210 -1.329730 -0.031925 1.492296"
]
},
"execution_count": 67,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['20130102':'20130104']"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Selection by Label ###"
]
},
{
"cell_type": "code",
"execution_count": 60,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"A 0.790777\n",
"B -0.645811\n",
"C 1.121823\n",
"D -0.758688\n",
"E -0.765090\n",
"Name: 2013-01-01 00:00:00, dtype: float64"
]
},
"execution_count": 60,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# loc selects by label\n",
"df.loc[dates[0]]"
]
},
{
"cell_type": "code",
"execution_count": 61,
"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>A</th>\n",
" <th>B</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-05</th>\n",
" <td>0.637097</td>\n",
" <td>1.015037</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-06</th>\n",
" <td>-0.175692</td>\n",
" <td>0.894900</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.112443</td>\n",
" <td>0.313526</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-03</th>\n",
" <td>1.111047</td>\n",
" <td>-0.083611</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>-0.187210</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-01</th>\n",
" <td>0.790777</td>\n",
" <td>-0.645811</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B\n",
"2013-01-05 0.637097 1.015037\n",
"2013-01-06 -0.175692 0.894900\n",
"2013-01-04 -0.112443 0.313526\n",
"2013-01-03 1.111047 -0.083611\n",
"2013-01-02 0.594159 -0.187210\n",
"2013-01-01 0.790777 -0.645811"
]
},
"execution_count": 61,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc[:,['A','B']]"
]
},
{
"cell_type": "code",
"execution_count": 62,
"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>A</th>\n",
" <th>B</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.112443</td>\n",
" <td>0.313526</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-03</th>\n",
" <td>1.111047</td>\n",
" <td>-0.083611</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>-0.187210</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B\n",
"2013-01-04 -0.112443 0.313526\n",
"2013-01-03 1.111047 -0.083611\n",
"2013-01-02 0.594159 -0.187210"
]
},
"execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc['20130102':'20130104',['A','B']]"
]
},
{
"cell_type": "code",
"execution_count": 63,
"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>A</th>\n",
" <th>B</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>-0.18721</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B\n",
"2013-01-02 0.594159 -0.18721"
]
},
"execution_count": 63,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc['20130102',['A','B']]"
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0.79077723243443043"
]
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc[dates[0],'A']"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0.79077723243443043"
]
},
"execution_count": 65,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.at[dates[0],'A']"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Selection by Position ###\n"
]
},
{
"cell_type": "code",
"execution_count": 68,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"A 1.111047\n",
"B -0.083611\n",
"C 0.799030\n",
"D -0.980553\n",
"E -0.088336\n",
"Name: 2013-01-03 00:00:00, dtype: float64"
]
},
"execution_count": 68,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[3]"
]
},
{
"cell_type": "code",
"execution_count": 69,
"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>A</th>\n",
" <th>B</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-03</th>\n",
" <td>1.111047</td>\n",
" <td>-0.083611</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>-0.187210</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B\n",
"2013-01-03 1.111047 -0.083611\n",
"2013-01-02 0.594159 -0.187210"
]
},
"execution_count": 69,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[3:5,0:2]"
]
},
{
"cell_type": "code",
"execution_count": 71,
"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>A</th>\n",
" <th>C</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-06</th>\n",
" <td>-0.175692</td>\n",
" <td>0.206329</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.112443</td>\n",
" <td>0.394046</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>-1.329730</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A C\n",
"2013-01-06 -0.175692 0.206329\n",
"2013-01-04 -0.112443 0.394046\n",
"2013-01-02 0.594159 -1.329730"
]
},
"execution_count": 71,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[[1,2,4],[0,2]]"
]
},
{
"cell_type": "code",
"execution_count": 72,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-06</th>\n",
" <td>-0.175692</td>\n",
" <td>0.894900</td>\n",
" <td>0.206329</td>\n",
" <td>1.441154</td>\n",
" <td>0.231754</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.112443</td>\n",
" <td>0.313526</td>\n",
" <td>0.394046</td>\n",
" <td>0.228101</td>\n",
" <td>0.393986</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"2013-01-06 -0.175692 0.894900 0.206329 1.441154 0.231754\n",
"2013-01-04 -0.112443 0.313526 0.394046 0.228101 0.393986"
]
},
"execution_count": 72,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[1:3,:]"
]
},
{
"cell_type": "code",
"execution_count": 73,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0.89489983355669811"
]
},
"execution_count": 73,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[1,1]"
]
},
{
"cell_type": "code",
"execution_count": 74,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0.89489983355669811"
]
},
"execution_count": 74,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iat[1,1]"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"source": [
"### Boolean Indexing"
]
},
{
"cell_type": "code",
"execution_count": 75,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-05</th>\n",
" <td>0.637097</td>\n",
" <td>1.015037</td>\n",
" <td>-1.006203</td>\n",
" <td>0.119320</td>\n",
" <td>-0.662282</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-03</th>\n",
" <td>1.111047</td>\n",
" <td>-0.083611</td>\n",
" <td>0.799030</td>\n",
" <td>-0.980553</td>\n",
" <td>-0.088336</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>-0.187210</td>\n",
" <td>-1.329730</td>\n",
" <td>-0.031925</td>\n",
" <td>1.492296</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-01</th>\n",
" <td>0.790777</td>\n",
" <td>-0.645811</td>\n",
" <td>1.121823</td>\n",
" <td>-0.758688</td>\n",
" <td>-0.765090</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"2013-01-05 0.637097 1.015037 -1.006203 0.119320 -0.662282\n",
"2013-01-03 1.111047 -0.083611 0.799030 -0.980553 -0.088336\n",
"2013-01-02 0.594159 -0.187210 -1.329730 -0.031925 1.492296\n",
"2013-01-01 0.790777 -0.645811 1.121823 -0.758688 -0.765090"
]
},
"execution_count": 75,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[df.A>0]"
]
},
{
"cell_type": "code",
"execution_count": 76,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-05</th>\n",
" <td>0.637097</td>\n",
" <td>1.015037</td>\n",
" <td>NaN</td>\n",
" <td>0.119320</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-06</th>\n",
" <td>NaN</td>\n",
" <td>0.894900</td>\n",
" <td>0.206329</td>\n",
" <td>1.441154</td>\n",
" <td>0.231754</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>NaN</td>\n",
" <td>0.313526</td>\n",
" <td>0.394046</td>\n",
" <td>0.228101</td>\n",
" <td>0.393986</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-03</th>\n",
" <td>1.111047</td>\n",
" <td>NaN</td>\n",
" <td>0.799030</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.492296</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-01</th>\n",
" <td>0.790777</td>\n",
" <td>NaN</td>\n",
" <td>1.121823</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"2013-01-05 0.637097 1.015037 NaN 0.119320 NaN\n",
"2013-01-06 NaN 0.894900 0.206329 1.441154 0.231754\n",
"2013-01-04 NaN 0.313526 0.394046 0.228101 0.393986\n",
"2013-01-03 1.111047 NaN 0.799030 NaN NaN\n",
"2013-01-02 0.594159 NaN NaN NaN 1.492296\n",
"2013-01-01 0.790777 NaN 1.121823 NaN NaN"
]
},
"execution_count": 76,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[df>0]"
]
},
{
"cell_type": "code",
"execution_count": 78,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-05</th>\n",
" <td>0.637097</td>\n",
" <td>1.015037</td>\n",
" <td>-1.006203</td>\n",
" <td>0.119320</td>\n",
" <td>one</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-06</th>\n",
" <td>-0.175692</td>\n",
" <td>0.894900</td>\n",
" <td>0.206329</td>\n",
" <td>1.441154</td>\n",
" <td>one</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.112443</td>\n",
" <td>0.313526</td>\n",
" <td>0.394046</td>\n",
" <td>0.228101</td>\n",
" <td>two</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-03</th>\n",
" <td>1.111047</td>\n",
" <td>-0.083611</td>\n",
" <td>0.799030</td>\n",
" <td>-0.980553</td>\n",
" <td>three</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>-0.187210</td>\n",
" <td>-1.329730</td>\n",
" <td>-0.031925</td>\n",
" <td>four</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-01</th>\n",
" <td>0.790777</td>\n",
" <td>-0.645811</td>\n",
" <td>1.121823</td>\n",
" <td>-0.758688</td>\n",
" <td>three</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"2013-01-05 0.637097 1.015037 -1.006203 0.119320 one\n",
"2013-01-06 -0.175692 0.894900 0.206329 1.441154 one\n",
"2013-01-04 -0.112443 0.313526 0.394046 0.228101 two\n",
"2013-01-03 1.111047 -0.083611 0.799030 -0.980553 three\n",
"2013-01-02 0.594159 -0.187210 -1.329730 -0.031925 four\n",
"2013-01-01 0.790777 -0.645811 1.121823 -0.758688 three"
]
},
"execution_count": 78,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2=df.copy()\n",
"df2['E']=['one','one','two','three','four','three']\n",
"df2\n"
]
},
{
"cell_type": "code",
"execution_count": 80,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.112443</td>\n",
" <td>0.313526</td>\n",
" <td>0.394046</td>\n",
" <td>0.228101</td>\n",
" <td>two</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>-0.187210</td>\n",
" <td>-1.329730</td>\n",
" <td>-0.031925</td>\n",
" <td>four</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E\n",
"2013-01-04 -0.112443 0.313526 0.394046 0.228101 two\n",
"2013-01-02 0.594159 -0.187210 -1.329730 -0.031925 four"
]
},
"execution_count": 80,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#isin returns a Series of booleans, true if the parameter element matches the item in the Series in the particular position\n",
"#Series.isin(values)\n",
"df2[df2['E'].isin(['two','four'])]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Setting ###"
]
},
{
"cell_type": "code",
"execution_count": 86,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2013-01-02 1\n",
"2013-01-03 2\n",
"2013-01-04 3\n",
"2013-01-05 4\n",
"2013-01-06 5\n",
"2013-01-07 6\n",
"Freq: D, dtype: int64\n"
]
}
],
"source": [
"s1=pd.Series([1,2,3,4,5,6], index=pd.date_range('20130102',periods=6))\n",
"print s1\n",
"df['F']=s1"
]
},
{
"cell_type": "code",
"execution_count": 88,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" <th>F</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-05</th>\n",
" <td>0.637097</td>\n",
" <td>1.015037</td>\n",
" <td>-1.006203</td>\n",
" <td>0.119320</td>\n",
" <td>-0.662282</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-06</th>\n",
" <td>-0.175692</td>\n",
" <td>0.894900</td>\n",
" <td>0.206329</td>\n",
" <td>1.441154</td>\n",
" <td>0.231754</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.112443</td>\n",
" <td>0.313526</td>\n",
" <td>0.394046</td>\n",
" <td>0.228101</td>\n",
" <td>0.393986</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-03</th>\n",
" <td>1.111047</td>\n",
" <td>-0.083611</td>\n",
" <td>0.799030</td>\n",
" <td>-0.980553</td>\n",
" <td>-0.088336</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>-0.187210</td>\n",
" <td>-1.329730</td>\n",
" <td>-0.031925</td>\n",
" <td>1.492296</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-01</th>\n",
" <td>0.000000</td>\n",
" <td>-0.645811</td>\n",
" <td>1.121823</td>\n",
" <td>-0.758688</td>\n",
" <td>-0.765090</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E F\n",
"2013-01-05 0.637097 1.015037 -1.006203 0.119320 -0.662282 4.0\n",
"2013-01-06 -0.175692 0.894900 0.206329 1.441154 0.231754 5.0\n",
"2013-01-04 -0.112443 0.313526 0.394046 0.228101 0.393986 3.0\n",
"2013-01-03 1.111047 -0.083611 0.799030 -0.980553 -0.088336 2.0\n",
"2013-01-02 0.594159 -0.187210 -1.329730 -0.031925 1.492296 1.0\n",
"2013-01-01 0.000000 -0.645811 1.121823 -0.758688 -0.765090 NaN"
]
},
"execution_count": 88,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.at[dates[0],'A']=0\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 90,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" <th>F</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-05</th>\n",
" <td>0.637097</td>\n",
" <td>0.000000</td>\n",
" <td>-1.006203</td>\n",
" <td>0.119320</td>\n",
" <td>-0.662282</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-06</th>\n",
" <td>-0.175692</td>\n",
" <td>0.894900</td>\n",
" <td>0.206329</td>\n",
" <td>1.441154</td>\n",
" <td>0.231754</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.112443</td>\n",
" <td>0.313526</td>\n",
" <td>0.394046</td>\n",
" <td>0.228101</td>\n",
" <td>0.393986</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-03</th>\n",
" <td>1.111047</td>\n",
" <td>-0.083611</td>\n",
" <td>0.799030</td>\n",
" <td>-0.980553</td>\n",
" <td>-0.088336</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>-0.187210</td>\n",
" <td>-1.329730</td>\n",
" <td>-0.031925</td>\n",
" <td>1.492296</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-01</th>\n",
" <td>0.000000</td>\n",
" <td>-0.645811</td>\n",
" <td>1.121823</td>\n",
" <td>-0.758688</td>\n",
" <td>-0.765090</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E F\n",
"2013-01-05 0.637097 0.000000 -1.006203 0.119320 -0.662282 4.0\n",
"2013-01-06 -0.175692 0.894900 0.206329 1.441154 0.231754 5.0\n",
"2013-01-04 -0.112443 0.313526 0.394046 0.228101 0.393986 3.0\n",
"2013-01-03 1.111047 -0.083611 0.799030 -0.980553 -0.088336 2.0\n",
"2013-01-02 0.594159 -0.187210 -1.329730 -0.031925 1.492296 1.0\n",
"2013-01-01 0.000000 -0.645811 1.121823 -0.758688 -0.765090 NaN"
]
},
"execution_count": 90,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iat[0,1]=0\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 92,
"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>A</th>\n",
" <th>B</th>\n",
" <th>C</th>\n",
" <th>D</th>\n",
" <th>E</th>\n",
" <th>F</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2013-01-05</th>\n",
" <td>0.637097</td>\n",
" <td>0.000000</td>\n",
" <td>-1.006203</td>\n",
" <td>5</td>\n",
" <td>-0.662282</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-06</th>\n",
" <td>-0.175692</td>\n",
" <td>0.894900</td>\n",
" <td>0.206329</td>\n",
" <td>5</td>\n",
" <td>0.231754</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-04</th>\n",
" <td>-0.112443</td>\n",
" <td>0.313526</td>\n",
" <td>0.394046</td>\n",
" <td>5</td>\n",
" <td>0.393986</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-03</th>\n",
" <td>1.111047</td>\n",
" <td>-0.083611</td>\n",
" <td>0.799030</td>\n",
" <td>5</td>\n",
" <td>-0.088336</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-02</th>\n",
" <td>0.594159</td>\n",
" <td>-0.187210</td>\n",
" <td>-1.329730</td>\n",
" <td>5</td>\n",
" <td>1.492296</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2013-01-01</th>\n",
" <td>0.000000</td>\n",
" <td>-0.645811</td>\n",
" <td>1.121823</td>\n",
" <td>5</td>\n",
" <td>-0.765090</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" A B C D E F\n",
"2013-01-05 0.637097 0.000000 -1.006203 5 -0.662282 4.0\n",
"2013-01-06 -0.175692 0.894900 0.206329 5 0.231754 5.0\n",
"2013-01-04 -0.112443 0.313526 0.394046 5 0.393986 3.0\n",
"2013-01-03 1.111047 -0.083611 0.799030 5 -0.088336 2.0\n",
"2013-01-02 0.594159 -0.187210 -1.329730 5 1.492296 1.0\n",
"2013-01-01 0.000000 -0.645811 1.121823 5 -0.765090 NaN"
]
},
"execution_count": 92,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.loc[:,'D']=np.array([5]*len(df))\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.12"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment