{
"metadata": {
"name": "",
"signature": "sha256:c482b50e820d7d0ce9954ab777285f2c8db83155fd43d727d4d3dffe75db3321"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "code",
"collapsed": false,
"input": [
"#Create DataFrame\n",
"import pandas as pd\n",
"import numpy as np\n",
"from pandas import DataFrame, Series\n",
"df = DataFrame(\n",
" {'integer':[1,2,3,6,7,23,8,3],\n",
" 'float':[2,3.4,5,6,2,4.7,4,8],\n",
" 'string':['saya',None,'aku','cinta','kamu','a','b','jika']}\n",
")\n",
"df"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"
\n",
"
\n",
" \n",
" \n",
" | \n",
" float | \n",
" integer | \n",
" string | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 2.0 | \n",
" 1 | \n",
" saya | \n",
"
\n",
" \n",
" 1 | \n",
" 3.4 | \n",
" 2 | \n",
" None | \n",
"
\n",
" \n",
" 2 | \n",
" 5.0 | \n",
" 3 | \n",
" aku | \n",
"
\n",
" \n",
" 3 | \n",
" 6.0 | \n",
" 6 | \n",
" cinta | \n",
"
\n",
" \n",
" 4 | \n",
" 2.0 | \n",
" 7 | \n",
" kamu | \n",
"
\n",
" \n",
" 5 | \n",
" 4.7 | \n",
" 23 | \n",
" a | \n",
"
\n",
" \n",
" 6 | \n",
" 4.0 | \n",
" 8 | \n",
" b | \n",
"
\n",
" \n",
" 7 | \n",
" 8.0 | \n",
" 3 | \n",
" jika | \n",
"
\n",
" \n",
"
\n",
"
"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 2,
"text": [
" float integer string\n",
"0 2.0 1 saya\n",
"1 3.4 2 None\n",
"2 5.0 3 aku\n",
"3 6.0 6 cinta\n",
"4 2.0 7 kamu\n",
"5 4.7 23 a\n",
"6 4.0 8 b\n",
"7 8.0 3 jika"
]
}
],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"#Change value by index\n",
"df.ix[6,'string']='a'\n",
"df.ix[7,'string']='a'\n",
"df"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"\n",
"
\n",
" \n",
" \n",
" | \n",
" float | \n",
" integer | \n",
" string | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 2.0 | \n",
" 1 | \n",
" saya | \n",
"
\n",
" \n",
" 1 | \n",
" 3.4 | \n",
" 2 | \n",
" None | \n",
"
\n",
" \n",
" 2 | \n",
" 5.0 | \n",
" 3 | \n",
" aku | \n",
"
\n",
" \n",
" 3 | \n",
" 6.0 | \n",
" 6 | \n",
" cinta | \n",
"
\n",
" \n",
" 4 | \n",
" 2.0 | \n",
" 7 | \n",
" kamu | \n",
"
\n",
" \n",
" 5 | \n",
" 4.7 | \n",
" 23 | \n",
" a | \n",
"
\n",
" \n",
" 6 | \n",
" 4.0 | \n",
" 8 | \n",
" a | \n",
"
\n",
" \n",
" 7 | \n",
" 8.0 | \n",
" 3 | \n",
" a | \n",
"
\n",
" \n",
"
\n",
"
"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 5,
"text": [
" float integer string\n",
"0 2.0 1 saya\n",
"1 3.4 2 None\n",
"2 5.0 3 aku\n",
"3 6.0 6 cinta\n",
"4 2.0 7 kamu\n",
"5 4.7 23 a\n",
"6 4.0 8 a\n",
"7 8.0 3 a"
]
}
],
"prompt_number": 5
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"#Grouping data in DataFrame\n",
"grouped = df['float'].groupby(df['string'])\n",
"grouped.mean()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 6,
"text": [
"string\n",
"a 5.566667\n",
"aku 5.000000\n",
"cinta 6.000000\n",
"kamu 2.000000\n",
"saya 2.000000\n",
"Name: float, dtype: float64"
]
}
],
"prompt_number": 6
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"df2 = df.copy()\n",
"def operation_more_than_one_columns(x):\n",
" return x*2, x*3\n",
"\n",
"df2['star_by_2'], df2['star_by_3'] = zip(*df2['integer'].map(operation_more_than_one_columns))\n",
"df2"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"\n",
"
\n",
" \n",
" \n",
" | \n",
" float | \n",
" integer | \n",
" string | \n",
" star_by_2 | \n",
" star_by_3 | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 2.0 | \n",
" 1 | \n",
" saya | \n",
" 2 | \n",
" 3 | \n",
"
\n",
" \n",
" 1 | \n",
" 3.4 | \n",
" 2 | \n",
" None | \n",
" 4 | \n",
" 6 | \n",
"
\n",
" \n",
" 2 | \n",
" 5.0 | \n",
" 3 | \n",
" aku | \n",
" 6 | \n",
" 9 | \n",
"
\n",
" \n",
" 3 | \n",
" 6.0 | \n",
" 6 | \n",
" cinta | \n",
" 12 | \n",
" 18 | \n",
"
\n",
" \n",
" 4 | \n",
" 2.0 | \n",
" 7 | \n",
" kamu | \n",
" 14 | \n",
" 21 | \n",
"
\n",
" \n",
" 5 | \n",
" 4.7 | \n",
" 23 | \n",
" a | \n",
" 46 | \n",
" 69 | \n",
"
\n",
" \n",
" 6 | \n",
" 4.0 | \n",
" 8 | \n",
" a | \n",
" 16 | \n",
" 24 | \n",
"
\n",
" \n",
" 7 | \n",
" 8.0 | \n",
" 3 | \n",
" a | \n",
" 6 | \n",
" 9 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 15,
"text": [
" float integer string star_by_2 star_by_3\n",
"0 2.0 1 saya 2 3\n",
"1 3.4 2 None 4 6\n",
"2 5.0 3 aku 6 9\n",
"3 6.0 6 cinta 12 18\n",
"4 2.0 7 kamu 14 21\n",
"5 4.7 23 a 46 69\n",
"6 4.0 8 a 16 24\n",
"7 8.0 3 a 6 9"
]
}
],
"prompt_number": 15
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"df3 = df.copy()\n",
"def sum_two_columns(series):\n",
" return series['integer'] + series['float']\n",
"\n",
"df3['sum_int_float'] = df3.apply(sum_two_columns,axis=1)\n",
"df3"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"\n",
"
\n",
" \n",
" \n",
" | \n",
" float | \n",
" integer | \n",
" string | \n",
" sum_int_float | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 2.0 | \n",
" 1 | \n",
" saya | \n",
" 3.0 | \n",
"
\n",
" \n",
" 1 | \n",
" 3.4 | \n",
" 2 | \n",
" None | \n",
" 5.4 | \n",
"
\n",
" \n",
" 2 | \n",
" 5.0 | \n",
" 3 | \n",
" aku | \n",
" 8.0 | \n",
"
\n",
" \n",
" 3 | \n",
" 6.0 | \n",
" 6 | \n",
" cinta | \n",
" 12.0 | \n",
"
\n",
" \n",
" 4 | \n",
" 2.0 | \n",
" 7 | \n",
" kamu | \n",
" 9.0 | \n",
"
\n",
" \n",
" 5 | \n",
" 4.7 | \n",
" 23 | \n",
" a | \n",
" 27.7 | \n",
"
\n",
" \n",
" 6 | \n",
" 4.0 | \n",
" 8 | \n",
" a | \n",
" 12.0 | \n",
"
\n",
" \n",
" 7 | \n",
" 8.0 | \n",
" 3 | \n",
" a | \n",
" 11.0 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 22,
"text": [
" float integer string sum_int_float\n",
"0 2.0 1 saya 3.0\n",
"1 3.4 2 None 5.4\n",
"2 5.0 3 aku 8.0\n",
"3 6.0 6 cinta 12.0\n",
"4 2.0 7 kamu 9.0\n",
"5 4.7 23 a 27.7\n",
"6 4.0 8 a 12.0\n",
"7 8.0 3 a 11.0"
]
}
],
"prompt_number": 22
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
}
],
"metadata": {}
}
]
}