Skip to content

Instantly share code, notes, and snippets.

@peace098beat

peace098beat/Pandas-first-sandbox.ipynb

Created November 27, 2015 07:56
Show Gist options
  • Save peace098beat/67dcb8a31d7b08d76010 to your computer and use it in GitHub Desktop.
Save peace098beat/67dcb8a31d7b08d76010 to your computer and use it in GitHub Desktop.
Download ZIP
[Pandas] はじめてのPandas
Display the source blob
Display the rendered blob
Raw
Pandas-first-sandbox.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Pandasを使ってみる"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 日時の使い方\n",
"http://sinhrks.hatenablog.com/entry/2014/11/09/183603"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"dt = pd.to_datetime('2014-11-09 10:10')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"Timestamp('2014-11-09 10:10:00')"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dt"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"pandas.tslib.Timestamp"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type(dt)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import datetime"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"isinstance(dt, datetime.datetime)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Python pandas データ選択処理をちょっと詳しく <前編>\n",
"http://sinhrks.hatenablog.com/entry/2014/11/12/233216"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"I1 1\n",
"I2 2\n",
"I3 3\n",
"dtype: int64"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s = pd.Series([1,2,3], index=['I1', 'I2', 'I3'])\n",
"s"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"1"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s[0]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"1"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s['I1']"
]
},
{
"cell_type": "code",
"execution_count": 10,
"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>C1</th>\n",
" <th>C2</th>\n",
" <th>C3</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>I1</th>\n",
" <td>11</td>\n",
" <td>12</td>\n",
" <td>13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I2</th>\n",
" <td>21</td>\n",
" <td>22</td>\n",
" <td>23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I3</th>\n",
" <td>31</td>\n",
" <td>32</td>\n",
" <td>33</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" C1 C2 C3\n",
"I1 11 12 13\n",
"I2 21 22 23\n",
"I3 31 32 33"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.DataFrame({'C1':[11,21,31], 'C2':[12,22,32],'C3':[13,23,33]}, index=['I1','I2','I3'])\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"I1 11\n",
"I2 21\n",
"I3 31\n",
"Name: C1, dtype: int64"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['C1']"
]
},
{
"cell_type": "code",
"execution_count": 12,
"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>C2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>I1</th>\n",
" <td>12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I2</th>\n",
" <td>22</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I3</th>\n",
" <td>32</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" C2\n",
"I1 12\n",
"I2 22\n",
"I3 32"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[[1]]"
]
},
{
"cell_type": "code",
"execution_count": 13,
"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>C1</th>\n",
" <th>C2</th>\n",
" <th>C3</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>I2</th>\n",
" <td>21</td>\n",
" <td>22</td>\n",
" <td>23</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" C1 C2 C3\n",
"I2 21 22 23"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[1:2]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"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>C1</th>\n",
" <th>C2</th>\n",
" <th>C3</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>I1</th>\n",
" <td>11</td>\n",
" <td>12</td>\n",
" <td>13</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I3</th>\n",
" <td>31</td>\n",
" <td>32</td>\n",
" <td>33</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" C1 C2 C3\n",
"I1 11 12 13\n",
"I3 31 32 33"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[[True,False,True]]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"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>C1</th>\n",
" <th>C2</th>\n",
" <th>C3</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>I1</th>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I2</th>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I3</th>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" C1 C2 C3\n",
"I1 False False False\n",
"I2 False True True\n",
"I3 True True True"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df>21"
]
},
{
"cell_type": "code",
"execution_count": 16,
"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>C1</th>\n",
" <th>C2</th>\n",
" <th>C3</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>I1</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I2</th>\n",
" <td>NaN</td>\n",
" <td>22</td>\n",
" <td>23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I3</th>\n",
" <td>31</td>\n",
" <td>32</td>\n",
" <td>33</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" C1 C2 C3\n",
"I1 NaN NaN NaN\n",
"I2 NaN 22 23\n",
"I3 31 32 33"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[df>21]"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"I1 11\n",
"I2 21\n",
"I3 31\n",
"Name: C1, dtype: int64"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['C1'] # 返り値はSeries"
]
},
{
"cell_type": "code",
"execution_count": 18,
"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>C1</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>I1</th>\n",
" <td>11</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I2</th>\n",
" <td>21</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I3</th>\n",
" <td>31</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" C1\n",
"I1 11\n",
"I2 21\n",
"I3 31"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[['C1']] # 返り値はDataFrame"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### index, columnsを元にした選択(ix,loc,iloc)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"22"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.ix['I2', 'C2']"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"22"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.ix[1,1]"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"C1 21\n",
"C2 22\n",
"C3 23\n",
"Name: I2, dtype: int64"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.ix[1,:]"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"I1 12\n",
"I2 22\n",
"I3 32\n",
"Name: C2, dtype: int64"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.ix[:,1]"
]
},
{
"cell_type": "code",
"execution_count": 23,
"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>C1</th>\n",
" <th>C2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>I1</th>\n",
" <td>11</td>\n",
" <td>12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>I3</th>\n",
" <td>31</td>\n",
" <td>32</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" C1 C2\n",
"I1 11 12\n",
"I3 31 32"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.ix[['I1','I3'],['C1','C2']]"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"I2 21\n",
"Name: C1, dtype: int64"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.ix[1:2, \"C1\"]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Python pandas データ選択処理をちょっと詳しく <中編>\n",
"http://sinhrks.hatenablog.com/entry/2014/11/15/230705"
]
},
{
"cell_type": "code",
"execution_count": 25,
"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>N1</th>\n",
" <th>N2</th>\n",
" <th>N3</th>\n",
" <th>F1</th>\n",
" <th>F2</th>\n",
" <th>S1</th>\n",
" <th>S2</th>\n",
" <th>D1</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2014-11-30</th>\n",
" <td>1</td>\n",
" <td>10</td>\n",
" <td>6</td>\n",
" <td>1.1</td>\n",
" <td>1.1</td>\n",
" <td>A</td>\n",
" <td>A</td>\n",
" <td>2014-11-01</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2014-12-31</th>\n",
" <td>2</td>\n",
" <td>20</td>\n",
" <td>5</td>\n",
" <td>2.2</td>\n",
" <td>2.2</td>\n",
" <td>b</td>\n",
" <td>X</td>\n",
" <td>2014-11-02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-01-31</th>\n",
" <td>3</td>\n",
" <td>30</td>\n",
" <td>4</td>\n",
" <td>3.3</td>\n",
" <td>3.3</td>\n",
" <td>C</td>\n",
" <td>X</td>\n",
" <td>2014-11-03</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-02-28</th>\n",
" <td>4</td>\n",
" <td>40</td>\n",
" <td>3</td>\n",
" <td>4.4</td>\n",
" <td>4.4</td>\n",
" <td>D</td>\n",
" <td>X</td>\n",
" <td>2014-11-04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-03-31</th>\n",
" <td>5</td>\n",
" <td>50</td>\n",
" <td>2</td>\n",
" <td>5.5</td>\n",
" <td>5.5</td>\n",
" <td>E</td>\n",
" <td>E</td>\n",
" <td>2014-11-05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-04-30</th>\n",
" <td>6</td>\n",
" <td>60</td>\n",
" <td>1</td>\n",
" <td>6.6</td>\n",
" <td>6.6</td>\n",
" <td>F</td>\n",
" <td>F</td>\n",
" <td>2014-11-06</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" N1 N2 N3 F1 F2 S1 S2 D1\n",
"2014-11-30 1 10 6 1.1 1.1 A A 2014-11-01\n",
"2014-12-31 2 20 5 2.2 2.2 b X 2014-11-02\n",
"2015-01-31 3 30 4 3.3 3.3 C X 2014-11-03\n",
"2015-02-28 4 40 3 4.4 4.4 D X 2014-11-04\n",
"2015-03-31 5 50 2 5.5 5.5 E E 2014-11-05\n",
"2015-04-30 6 60 1 6.6 6.6 F F 2014-11-06"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.DataFrame({\n",
" 'N1':[1,2,3,4,5,6],\n",
" 'N2':[10,20,30,40,50,60],\n",
" 'N3':[6,5,4,3,2,1],\n",
" 'F1': [1.1, 2.2, 3.3, 4.4, 5.5, 6.6],\n",
" 'F2': [1.1, 2.2, 3.3, 4.4, 5.5, 6.6],\n",
" 'S1': ['A', 'b', 'C', 'D', 'E', 'F'],\n",
" 'S2': ['A', 'X', 'X', 'X', 'E', 'F'],\n",
" 'D1':pd.date_range('2014-11-01', freq='D', periods=6)},\n",
" index=pd.date_range('2014-11-01', freq='M', periods=6),\n",
" columns=['N1', 'N2', 'N3', 'F1', 'F2', 'S1', 'S2', 'D1']\n",
" )\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"DatetimeIndex(['2014-11-30', '2014-12-31', '2015-01-31', '2015-02-28',\n",
" '2015-03-31', '2015-04-30'],\n",
" dtype='datetime64[ns]', freq='M')"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.index"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"Index([u'N1', u'N2', u'N3', u'F1', u'F2', u'S1', u'S2', u'D1'], dtype='object')"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"2014-11-30 10\n",
"2014-12-31 20\n",
"2015-01-31 30\n",
"2015-02-28 40\n",
"2015-03-31 50\n",
"2015-04-30 60\n",
"Freq: M, Name: N2, dtype: int64"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.ix[:, 1]"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([ True, True, True, False, False, False, False, False], dtype=bool)"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns.map(lambda x:x.startswith('N'))"
]
},
{
"cell_type": "code",
"execution_count": 30,
"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>N1</th>\n",
" <th>N2</th>\n",
" <th>N3</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2014-11-30</th>\n",
" <td>1</td>\n",
" <td>10</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2014-12-31</th>\n",
" <td>2</td>\n",
" <td>20</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-01-31</th>\n",
" <td>3</td>\n",
" <td>30</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-02-28</th>\n",
" <td>4</td>\n",
" <td>40</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-03-31</th>\n",
" <td>5</td>\n",
" <td>50</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-04-30</th>\n",
" <td>6</td>\n",
" <td>60</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" N1 N2 N3\n",
"2014-11-30 1 10 6\n",
"2014-12-31 2 20 5\n",
"2015-01-31 3 30 4\n",
"2015-02-28 4 40 3\n",
"2015-03-31 5 50 2\n",
"2015-04-30 6 60 1"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.ix[:, df.columns.map(lambda x:x.startswith('N'))]"
]
},
{
"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>N1</th>\n",
" <th>N2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2014-11-30</th>\n",
" <td>1</td>\n",
" <td>10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2014-12-31</th>\n",
" <td>2</td>\n",
" <td>20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-01-31</th>\n",
" <td>3</td>\n",
" <td>30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-02-28</th>\n",
" <td>4</td>\n",
" <td>40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-03-31</th>\n",
" <td>5</td>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-04-30</th>\n",
" <td>6</td>\n",
" <td>60</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" N1 N2\n",
"2014-11-30 1 10\n",
"2014-12-31 2 20\n",
"2015-01-31 3 30\n",
"2015-02-28 4 40\n",
"2015-03-31 5 50\n",
"2015-04-30 6 60"
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.ix[:, df.columns.isin(['N1','N2','N4'])]"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\fifi\\Anaconda\\lib\\site-packages\\ipykernel\\__main__.py:1: FutureWarning: order is deprecated, use sort_values(...)\n",
" if __name__ == '__main__':\n"
]
},
{
"data": {
"text/plain": [
"Index([u'D1', u'F1', u'F2', u'N1', u'N2', u'N3', u'S1', u'S2'], dtype='object')"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns.order()"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\fifi\\Anaconda\\lib\\site-packages\\ipykernel\\__main__.py:1: FutureWarning: order is deprecated, use sort_values(...)\n",
" if __name__ == '__main__':\n"
]
},
{
"data": {
"text/plain": [
"Index([u'D1', u'F1', u'F2'], dtype='object')"
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns.order()[:3]"
]
},
{
"cell_type": "raw",
"metadata": {},
"source": [
"df[df.columns.order()[:5]]"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"N1 int64\n",
"N2 int64\n",
"N3 int64\n",
"F1 float64\n",
"F2 float64\n",
"S1 object\n",
"S2 object\n",
"D1 datetime64[ns]\n",
"dtype: object"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.dtypes"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"N1 False\n",
"N2 False\n",
"N3 False\n",
"F1 True\n",
"F2 True\n",
"S1 False\n",
"S2 False\n",
"D1 False\n",
"dtype: bool"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.dtypes == np.float64"
]
},
{
"cell_type": "code",
"execution_count": 36,
"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>F1</th>\n",
" <th>F2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2014-11-30</th>\n",
" <td>1.1</td>\n",
" <td>1.1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2014-12-31</th>\n",
" <td>2.2</td>\n",
" <td>2.2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-01-31</th>\n",
" <td>3.3</td>\n",
" <td>3.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-02-28</th>\n",
" <td>4.4</td>\n",
" <td>4.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-03-31</th>\n",
" <td>5.5</td>\n",
" <td>5.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-04-30</th>\n",
" <td>6.6</td>\n",
" <td>6.6</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" F1 F2\n",
"2014-11-30 1.1 1.1\n",
"2014-12-31 2.2 2.2\n",
"2015-01-31 3.3 3.3\n",
"2015-02-28 4.4 4.4\n",
"2015-03-31 5.5 5.5\n",
"2015-04-30 6.6 6.6"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.ix[:,df.dtypes == np.float64]"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"N1 21.0\n",
"N2 210.0\n",
"N3 21.0\n",
"F1 23.1\n",
"F2 23.1\n",
"dtype: float64"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.sum()"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"N1 3.50\n",
"N2 35.00\n",
"N3 3.50\n",
"F1 3.85\n",
"F2 3.85\n",
"dtype: float64"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.mean()"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"N1 1.870829\n",
"N2 18.708287\n",
"N3 1.870829\n",
"F1 2.057912\n",
"F2 2.057912\n",
"dtype: float64"
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.std()"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"N1 3.500\n",
"N2 350.000\n",
"N3 3.500\n",
"F1 4.235\n",
"F2 4.235\n",
"dtype: float64"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.var()"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"indexer = df.sum()>50"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"N1 False\n",
"N2 True\n",
"N3 False\n",
"F1 False\n",
"F2 False\n",
"dtype: bool"
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"indexer"
]
},
{
"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>N2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2014-11-30</th>\n",
" <td>10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2014-12-31</th>\n",
" <td>20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-01-31</th>\n",
" <td>30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-02-28</th>\n",
" <td>40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-03-31</th>\n",
" <td>50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-04-30</th>\n",
" <td>60</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" N2\n",
"2014-11-30 10\n",
"2014-12-31 20\n",
"2015-01-31 30\n",
"2015-02-28 40\n",
"2015-03-31 50\n",
"2015-04-30 60"
]
},
"execution_count": 43,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.ix[:,indexer.index[indexer]]"
]
},
{
"cell_type": "code",
"execution_count": 44,
"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>N1</th>\n",
" <th>N2</th>\n",
" <th>N3</th>\n",
" <th>F1</th>\n",
" <th>F2</th>\n",
" <th>S1</th>\n",
" <th>S2</th>\n",
" <th>D1</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2014-11-30</th>\n",
" <td>1</td>\n",
" <td>10</td>\n",
" <td>6</td>\n",
" <td>1.1</td>\n",
" <td>1.1</td>\n",
" <td>A</td>\n",
" <td>A</td>\n",
" <td>2014-11-01</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2014-12-31</th>\n",
" <td>2</td>\n",
" <td>20</td>\n",
" <td>5</td>\n",
" <td>2.2</td>\n",
" <td>2.2</td>\n",
" <td>b</td>\n",
" <td>X</td>\n",
" <td>2014-11-02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-01-31</th>\n",
" <td>3</td>\n",
" <td>30</td>\n",
" <td>4</td>\n",
" <td>3.3</td>\n",
" <td>3.3</td>\n",
" <td>C</td>\n",
" <td>X</td>\n",
" <td>2014-11-03</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-02-28</th>\n",
" <td>4</td>\n",
" <td>40</td>\n",
" <td>3</td>\n",
" <td>4.4</td>\n",
" <td>4.4</td>\n",
" <td>D</td>\n",
" <td>X</td>\n",
" <td>2014-11-04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-03-31</th>\n",
" <td>5</td>\n",
" <td>50</td>\n",
" <td>2</td>\n",
" <td>5.5</td>\n",
" <td>5.5</td>\n",
" <td>E</td>\n",
" <td>E</td>\n",
" <td>2014-11-05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-04-30</th>\n",
" <td>6</td>\n",
" <td>60</td>\n",
" <td>1</td>\n",
" <td>6.6</td>\n",
" <td>6.6</td>\n",
" <td>F</td>\n",
" <td>F</td>\n",
" <td>2014-11-06</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" N1 N2 N3 F1 F2 S1 S2 D1\n",
"2014-11-30 1 10 6 1.1 1.1 A A 2014-11-01\n",
"2014-12-31 2 20 5 2.2 2.2 b X 2014-11-02\n",
"2015-01-31 3 30 4 3.3 3.3 C X 2014-11-03\n",
"2015-02-28 4 40 3 4.4 4.4 D X 2014-11-04\n",
"2015-03-31 5 50 2 5.5 5.5 E E 2014-11-05\n",
"2015-04-30 6 60 1 6.6 6.6 F F 2014-11-06"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"2014-11-30 10\n",
"2014-12-31 40\n",
"2015-01-31 90\n",
"2015-02-28 160\n",
"2015-03-31 250\n",
"2015-04-30 360\n",
"Freq: M, dtype: int64"
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.apply(lambda x: x['N1'] * x['N2'], axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 46,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"2014-11-30 False\n",
"2014-12-31 False\n",
"2015-01-31 False\n",
"2015-02-28 True\n",
"2015-03-31 True\n",
"2015-04-30 True\n",
"Freq: M, dtype: bool"
]
},
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.apply(lambda x: x['N1'] * x['N2'], axis=1) > 100"
]
},
{
"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>N1</th>\n",
" <th>N2</th>\n",
" <th>N3</th>\n",
" <th>F1</th>\n",
" <th>F2</th>\n",
" <th>S1</th>\n",
" <th>S2</th>\n",
" <th>D1</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2015-02-28</th>\n",
" <td>4</td>\n",
" <td>40</td>\n",
" <td>3</td>\n",
" <td>4.4</td>\n",
" <td>4.4</td>\n",
" <td>D</td>\n",
" <td>X</td>\n",
" <td>2014-11-04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-03-31</th>\n",
" <td>5</td>\n",
" <td>50</td>\n",
" <td>2</td>\n",
" <td>5.5</td>\n",
" <td>5.5</td>\n",
" <td>E</td>\n",
" <td>E</td>\n",
" <td>2014-11-05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-04-30</th>\n",
" <td>6</td>\n",
" <td>60</td>\n",
" <td>1</td>\n",
" <td>6.6</td>\n",
" <td>6.6</td>\n",
" <td>F</td>\n",
" <td>F</td>\n",
" <td>2014-11-06</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" N1 N2 N3 F1 F2 S1 S2 D1\n",
"2015-02-28 4 40 3 4.4 4.4 D X 2014-11-04\n",
"2015-03-31 5 50 2 5.5 5.5 E E 2014-11-05\n",
"2015-04-30 6 60 1 6.6 6.6 F F 2014-11-06"
]
},
"execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[df.apply(lambda x: x['N1'] * x['N2'], axis=1) > 100]"
]
},
{
"cell_type": "code",
"execution_count": 48,
"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>N2</th>\n",
" <th>N3</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2014-11-30</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2014-12-31</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-01-31</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-02-28</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-03-31</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2015-04-30</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" N2 N3\n",
"2014-11-30 NaN NaN\n",
"2014-12-31 NaN NaN\n",
"2015-01-31 NaN NaN\n",
"2015-02-28 NaN NaN\n",
"2015-03-31 NaN NaN\n",
"2015-04-30 NaN NaN"
]
},
"execution_count": 48,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[[1]] * df[[2]]"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"2014-11-30 10\n",
"2014-12-31 40\n",
"2015-01-31 90\n",
"2015-02-28 160\n",
"2015-03-31 250\n",
"2015-04-30 360\n",
"Freq: M, dtype: int64"
]
},
"execution_count": 49,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"a = df['N1'] * df['N2']\n",
"a"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"pandas.core.series.Series"
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type(df['N1'])"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"pandas.core.frame.DataFrame"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type(df[[1]])"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\fifi\\Anaconda\\lib\\site-packages\\ipykernel\\__main__.py:1: FutureWarning: The pandas.rpy module is deprecated and will be removed in a future version. We refer to external packages like rpy2. \n",
"See here for a guide on how to port your code to rpy2: http://pandas.pydata.org/pandas-docs/stable/r_interface.html\n",
" if __name__ == '__main__':\n"
]
},
{
"ename": "ImportError",
"evalue": "No module named rpy2.robjects.packages",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mImportError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-52-63ebebefea80>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[1;32mimport\u001b[0m \u001b[0mpandas\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrpy\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcommon\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mcom\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;32mC:\\Users\\fifi\\Anaconda\\lib\\site-packages\\pandas\\rpy\\common.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m 13\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mpandas\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mutil\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtesting\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0m_test\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 14\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 15\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mrpy2\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrobjects\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpackages\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mimportr\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 16\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mrpy2\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrobjects\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mr\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 17\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mrpy2\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrobjects\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mrobj\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mImportError\u001b[0m: No module named rpy2.robjects.packages"
]
}
],
"source": [
"import pandas.rpy.common as com"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 簡単なデータ操作を Python pandas で行う\n",
"http://sinhrks.hatenablog.com/entry/2014/10/11/232951"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"重要!!! pd.options.display.max_rows=5"
]
},
{
"cell_type": "code",
"execution_count": 60,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# 表示する行数を設定\n",
"pd.options.display.max_rows=5"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from sklearn import datasets\n",
"iris = datasets.load_iris()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"irisデータの取得"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"csv から読み込み\n",
"http://aima.cs.berkeley.edu/data/iris.csv"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"names = ['Sepal.Length', 'Sepal.Width', 'Petal.Length', 'Petal.Width', 'Species']\n",
"iris = pd.read_csv('iris.csv', header=None, names=names)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"iris"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"type(iris)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 列操作"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"iris.columns"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"列名変更"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"iris.rename(columns={'Species': 'newcol'})"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"変数名を用いて列選択"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"iris['Species']"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"iris"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"文字列リストを用いて複数列選択"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"clist = ['Petal.Length', 'Petal.Width']\n",
"iris[ clist ]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"真偽値を用いて列選択"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"cols = [False,False,True, True, False]\n",
"iris.loc[:, cols]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"iris.loc[:, iris.dtypes == float]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 列操作"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"値が特定の条件を満たす行を抽出"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"iris[iris['Species'] == 'virginica']"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"iris.loc[[1,2,3]]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"import random\n",
"iris.loc[random.sample(iris.index, 5)]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"iris['Petal.Mult'] = iris['Petal.Width'] * iris['Petal.Length']\n",
"iris"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"iris['Petal.Mean'] = iris['Petal.Width'] + iris['Petal.Length']\n",
"iris"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import matplotlib.pyplot as plt"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from pandas.tools.plotting import scatter_matrix"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"#文字列データの取得のためのFrameDataの取得\n",
"rfilename='pd_data.tsv'\n",
"dialect='tab'\n",
"df0=data_check(rfilename,dialect) \n",
"StartDateTime=pd.Timestamp(df0.ix[2,1]+' '+df0.ix[2,2])\n",
"print(StartDateTime)\n",
"\n",
"#本格的なデータ処理をするためのFrameDataの取得 \n",
"rfilename='pd_data.tsv'\n",
"skiprow=5 #ヘッダを除く、スキップ行数\n",
"head=0 #スキップしたあとの行番号を指定すること 無視する場合はNone\n",
"delimiter='\\t' #区切り文字　：　delimiter=',' or delimiter='\\t'\n",
"df=data_input(rfilename,skiprow,head,delimiter) #データインプット関数\n",
"print(df)"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"source": [
"# 信号処理"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"df = pd.DataFrame({\n",
" 'N1':[1,2,3,4,5,6],\n",
" 'N2':[10,20,30,40,50,60],\n",
" 'N3':[6,5,4,3,2,1],\n",
" 'F1': [1.1, 2.2, 3.3, 4.4, 5.5, 6.6],\n",
" 'F2': [1.1, 2.2, 3.3, 4.4, 5.5, 6.6],\n",
" 'S1': ['A', 'b', 'C', 'D', 'E', 'F'],\n",
" 'S2': ['A', 'X', 'X', 'X', 'E', 'F'],\n",
" 'D1':pd.date_range('2014-11-01', freq='D', periods=6)},\n",
" index=pd.date_range('2014-11-01', freq='M', periods=6),\n",
" columns=['N1', 'N2', 'N3', 'F1', 'F2', 'S1', 'S2', 'D1']\n",
" )\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"Nx = 100\n",
"trange = np.linspace(0,1,Nx)\n",
"S1 = np.sin(np.pi / 10 * trange)\n",
"S2 = S1 ** 2\n",
"S3 = S1 ** (1./2.)\n",
"S4 = S1 + S2\n"
]
},
{
"cell_type": "code",
"execution_count": 68,
"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>S1</th>\n",
" <th>S2</th>\n",
" <th>S3</th>\n",
" <th>S4</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.003173</td>\n",
" <td>0.000010</td>\n",
" <td>0.056332</td>\n",
" <td>0.003183</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>98</th>\n",
" <td>0.305997</td>\n",
" <td>0.093634</td>\n",
" <td>0.553170</td>\n",
" <td>0.399632</td>\n",
" </tr>\n",
" <tr>\n",
" <th>99</th>\n",
" <td>0.309017</td>\n",
" <td>0.095492</td>\n",
" <td>0.555893</td>\n",
" <td>0.404508</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>100 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" S1 S2 S3 S4\n",
"0 0.000000 0.000000 0.000000 0.000000\n",
"1 0.003173 0.000010 0.056332 0.003183\n",
".. ... ... ... ...\n",
"98 0.305997 0.093634 0.553170 0.399632\n",
"99 0.309017 0.095492 0.555893 0.404508\n",
"\n",
"[100 rows x 4 columns]"
]
},
"execution_count": 68,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.DataFrame({\n",
" 'S1':S1,\n",
" 'S2':S2,\n",
" 'S3':S3,\n",
" 'S4': S4,\n",
" 'time': trange},\n",
" index=range(trange.shape[0]),\n",
" columns=['S1', 'S2', 'S3', 'S4']\n",
" )\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 74,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0 0.000000\n",
"1 0.003173\n",
" ... \n",
"98 0.305997\n",
"99 0.309017\n",
"Name: S1, dtype: float64"
]
},
"execution_count": 74,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"s = df['S1']\n",
"s"
]
},
{
"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>S1</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.003173</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>98</th>\n",
" <td>0.305997</td>\n",
" </tr>\n",
" <tr>\n",
" <th>99</th>\n",
" <td>0.309017</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>100 rows × 1 columns</p>\n",
"</div>"
],
"text/plain": [
" S1\n",
"0 0.000000\n",
"1 0.003173\n",
".. ...\n",
"98 0.305997\n",
"99 0.309017\n",
"\n",
"[100 rows x 1 columns]"
]
},
"execution_count": 75,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"d = df[['S1']]\n",
"d"
]
},
{
"cell_type": "code",
"execution_count": 77,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([[ 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
" 0.00000000e+00],\n",
" [ 3.17332059e-03, 1.00699635e-05, 5.63322340e-02,\n",
" 3.18339055e-03],\n",
" [ 6.34660922e-03, 4.02794486e-05, 7.96656088e-02,\n",
" 6.38688867e-03],\n",
" [ 9.51983394e-03, 9.06272382e-05, 9.75696364e-02,\n",
" 9.61046118e-03],\n",
" [ 1.26929628e-02, 1.61111305e-04, 1.12663050e-01,\n",
" 1.28540741e-02],\n",
" [ 1.58659638e-02, 2.51728808e-04, 1.25960168e-01,\n",
" 1.61176926e-02],\n",
" [ 1.90388051e-02, 3.62476100e-04, 1.37981177e-01,\n",
" 1.94012812e-02],\n",
" [ 2.22114547e-02, 4.93348718e-04, 1.49035079e-01,\n",
" 2.27048034e-02],\n",
" [ 2.53838805e-02, 6.44341391e-04, 1.59323195e-01,\n",
" 2.60282219e-02],\n",
" [ 2.85560508e-02, 8.15448037e-04, 1.68985357e-01,\n",
" 2.93714988e-02],\n",
" [ 3.17279335e-02, 1.00666176e-03, 1.78123366e-01,\n",
" 3.27345953e-02],\n",
" [ 3.48994967e-02, 1.21797487e-03, 1.86814070e-01,\n",
" 3.61174716e-02],\n",
" [ 3.80707085e-02, 1.44937884e-03, 1.95117166e-01,\n",
" 3.95200873e-02],\n",
" [ 4.12415369e-02, 1.70086436e-03, 2.03080124e-01,\n",
" 4.29424012e-02],\n",
" [ 4.44119500e-02, 1.97242130e-03, 2.10741429e-01,\n",
" 4.63843713e-02],\n",
" [ 4.75819158e-02, 2.26403871e-03, 2.18132794e-01,\n",
" 4.98459545e-02],\n",
" [ 5.07514025e-02, 2.57570486e-03, 2.25280719e-01,\n",
" 5.33271074e-02],\n",
" [ 5.39203782e-02, 2.90740718e-03, 2.32207619e-01,\n",
" 5.68277854e-02],\n",
" [ 5.70888109e-02, 3.25913233e-03, 2.38932649e-01,\n",
" 6.03479432e-02],\n",
" [ 6.02566687e-02, 3.63086612e-03, 2.45472338e-01,\n",
" 6.38875348e-02],\n",
" [ 6.34239197e-02, 4.02259358e-03, 2.51841060e-01,\n",
" 6.74465132e-02],\n",
" [ 6.65905320e-02, 4.43429895e-03, 2.58051413e-01,\n",
" 7.10248309e-02],\n",
" [ 6.97564737e-02, 4.86596563e-03, 2.64114509e-01,\n",
" 7.46224394e-02],\n",
" [ 7.29217131e-02, 5.31757624e-03, 2.70040206e-01,\n",
" 7.82392893e-02],\n",
" [ 7.60862181e-02, 5.78911258e-03, 2.75837304e-01,\n",
" 8.18753306e-02],\n",
" [ 7.92499569e-02, 6.28055566e-03, 2.81513689e-01,\n",
" 8.55305125e-02],\n",
" [ 8.24128976e-02, 6.79188569e-03, 2.87076466e-01,\n",
" 8.92047833e-02],\n",
" [ 8.55750085e-02, 7.32308208e-03, 2.92532064e-01,\n",
" 9.28980906e-02],\n",
" [ 8.87362576e-02, 7.87412341e-03, 2.97886317e-01,\n",
" 9.66103810e-02],\n",
" [ 9.18966132e-02, 8.44498751e-03, 3.03144542e-01,\n",
" 1.00341601e-01],\n",
" [ 9.50560433e-02, 9.03565137e-03, 3.08311601e-01,\n",
" 1.04091695e-01],\n",
" [ 9.82145162e-02, 9.64609120e-03, 3.13391953e-01,\n",
" 1.07860607e-01],\n",
" [ 1.01372000e-01, 1.02762824e-02, 3.18389699e-01,\n",
" 1.11648283e-01],\n",
" [ 1.04528463e-01, 1.09261996e-02, 3.23308619e-01,\n",
" 1.15454663e-01],\n",
" [ 1.07683874e-01, 1.15958167e-02, 3.28152211e-01,\n",
" 1.19279690e-01],\n",
" [ 1.10838200e-01, 1.22851066e-02, 3.32923715e-01,\n",
" 1.23123306e-01],\n",
" [ 1.13991410e-01, 1.29940415e-02, 3.37626139e-01,\n",
" 1.26985451e-01],\n",
" [ 1.17143472e-01, 1.37225930e-02, 3.42262285e-01,\n",
" 1.30866065e-01],\n",
" [ 1.20294354e-01, 1.44707317e-02, 3.46834765e-01,\n",
" 1.34765086e-01],\n",
" [ 1.23444026e-01, 1.52384274e-02, 3.51346020e-01,\n",
" 1.38682453e-01],\n",
" [ 1.26592454e-01, 1.60256493e-02, 3.55798333e-01,\n",
" 1.42618103e-01],\n",
" [ 1.29739607e-01, 1.68323656e-02, 3.60193846e-01,\n",
" 1.46571972e-01],\n",
" [ 1.32885454e-01, 1.76585438e-02, 3.64534571e-01,\n",
" 1.50543997e-01],\n",
" [ 1.36029962e-01, 1.85041506e-02, 3.68822399e-01,\n",
" 1.54534113e-01],\n",
" [ 1.39173101e-01, 1.93691520e-02, 3.73059112e-01,\n",
" 1.58542253e-01],\n",
" [ 1.42314838e-01, 2.02535132e-02, 3.77246389e-01,\n",
" 1.62568351e-01],\n",
" [ 1.45455142e-01, 2.11571985e-02, 3.81385818e-01,\n",
" 1.66612341e-01],\n",
" [ 1.48593982e-01, 2.20801715e-02, 3.85478899e-01,\n",
" 1.70674153e-01],\n",
" [ 1.51731325e-01, 2.30223950e-02, 3.89527053e-01,\n",
" 1.74753720e-01],\n",
" [ 1.54867140e-01, 2.39838311e-02, 3.93531626e-01,\n",
" 1.78850971e-01],\n",
" [ 1.58001396e-01, 2.49644411e-02, 3.97493894e-01,\n",
" 1.82965837e-01],\n",
" [ 1.61134061e-01, 2.59641855e-02, 4.01415073e-01,\n",
" 1.87098246e-01],\n",
" [ 1.64265103e-01, 2.69830239e-02, 4.05296315e-01,\n",
" 1.91248127e-01],\n",
" [ 1.67394490e-01, 2.80209154e-02, 4.09138718e-01,\n",
" 1.95415406e-01],\n",
" [ 1.70522193e-01, 2.90778182e-02, 4.12943329e-01,\n",
" 1.99600011e-01],\n",
" [ 1.73648178e-01, 3.01536896e-02, 4.16711144e-01,\n",
" 2.03801867e-01],\n",
" [ 1.76772414e-01, 3.12484864e-02, 4.20443116e-01,\n",
" 2.08020900e-01],\n",
" [ 1.79894870e-01, 3.23621644e-02, 4.24140154e-01,\n",
" 2.12257035e-01],\n",
" [ 1.83015515e-01, 3.34946788e-02, 4.27803127e-01,\n",
" 2.16510194e-01],\n",
" [ 1.86134317e-01, 3.46459839e-02, 4.31432865e-01,\n",
" 2.20780301e-01],\n",
" [ 1.89251244e-01, 3.58160335e-02, 4.35030165e-01,\n",
" 2.25067278e-01],\n",
" [ 1.92366266e-01, 3.70047803e-02, 4.38595789e-01,\n",
" 2.29371046e-01],\n",
" [ 1.95479351e-01, 3.82121765e-02, 4.42130468e-01,\n",
" 2.33691527e-01],\n",
" [ 1.98590467e-01, 3.94381734e-02, 4.45634903e-01,\n",
" 2.38028640e-01],\n",
" [ 2.01699583e-01, 4.06827217e-02, 4.49109767e-01,\n",
" 2.42382305e-01],\n",
" [ 2.04806668e-01, 4.19457713e-02, 4.52555707e-01,\n",
" 2.46752439e-01],\n",
" [ 2.07911691e-01, 4.32272712e-02, 4.55973344e-01,\n",
" 2.51138962e-01],\n",
" [ 2.11014620e-01, 4.45271698e-02, 4.59363277e-01,\n",
" 2.55541790e-01],\n",
" [ 2.14115424e-01, 4.58454148e-02, 4.62726079e-01,\n",
" 2.59960839e-01],\n",
" [ 2.17214072e-01, 4.71819531e-02, 4.66062305e-01,\n",
" 2.64396025e-01],\n",
" [ 2.20310533e-01, 4.85367309e-02, 4.69372488e-01,\n",
" 2.68847264e-01],\n",
" [ 2.23404775e-01, 4.99096935e-02, 4.72657143e-01,\n",
" 2.73314468e-01],\n",
" [ 2.26496767e-01, 5.13007857e-02, 4.75916765e-01,\n",
" 2.77797553e-01],\n",
" [ 2.29586479e-01, 5.27099514e-02, 4.79151833e-01,\n",
" 2.82296430e-01],\n",
" [ 2.32673879e-01, 5.41371339e-02, 4.82362808e-01,\n",
" 2.86811013e-01],\n",
" [ 2.35758936e-01, 5.55822757e-02, 4.85550137e-01,\n",
" 2.91341211e-01],\n",
" [ 2.38841618e-01, 5.70453185e-02, 4.88714250e-01,\n",
" 2.95886937e-01],\n",
" [ 2.41921896e-01, 5.85262036e-02, 4.91855564e-01,\n",
" 3.00448099e-01],\n",
" [ 2.44999737e-01, 6.00248711e-02, 4.94974481e-01,\n",
" 3.05024608e-01],\n",
" [ 2.48075111e-01, 6.15412608e-02, 4.98071392e-01,\n",
" 3.09616372e-01],\n",
" [ 2.51147987e-01, 6.30753115e-02, 5.01146672e-01,\n",
" 3.14223299e-01],\n",
" [ 2.54218334e-01, 6.46269614e-02, 5.04200688e-01,\n",
" 3.18845296e-01],\n",
" [ 2.57286121e-01, 6.61961482e-02, 5.07233793e-01,\n",
" 3.23482269e-01],\n",
" [ 2.60351317e-01, 6.77828085e-02, 5.10246330e-01,\n",
" 3.28134126e-01],\n",
" [ 2.63413892e-01, 6.93868784e-02, 5.13238630e-01,\n",
" 3.32800770e-01],\n",
" [ 2.66473814e-01, 7.10082934e-02, 5.16211017e-01,\n",
" 3.37482107e-01],\n",
" [ 2.69531052e-01, 7.26469881e-02, 5.19163801e-01,\n",
" 3.42178040e-01],\n",
" [ 2.72585576e-01, 7.43028965e-02, 5.22097286e-01,\n",
" 3.46888473e-01],\n",
" [ 2.75637356e-01, 7.59759519e-02, 5.25011767e-01,\n",
" 3.51613308e-01],\n",
" [ 2.78686360e-01, 7.76660870e-02, 5.27907529e-01,\n",
" 3.56352446e-01],\n",
" [ 2.81732557e-01, 7.93732336e-02, 5.30784850e-01,\n",
" 3.61105790e-01],\n",
" [ 2.84775917e-01, 8.10973230e-02, 5.33643998e-01,\n",
" 3.65873240e-01],\n",
" [ 2.87816410e-01, 8.28382857e-02, 5.36485237e-01,\n",
" 3.70654695e-01],\n",
" [ 2.90854004e-01, 8.45960516e-02, 5.39308821e-01,\n",
" 3.75450056e-01],\n",
" [ 2.93888669e-01, 8.63705500e-02, 5.42114996e-01,\n",
" 3.80259219e-01],\n",
" [ 2.96920375e-01, 8.81617093e-02, 5.44904006e-01,\n",
" 3.85082085e-01],\n",
" [ 2.99949091e-01, 8.99694574e-02, 5.47676082e-01,\n",
" 3.89918549e-01],\n",
" [ 3.02974787e-01, 9.17937214e-02, 5.50431455e-01,\n",
" 3.94768508e-01],\n",
" [ 3.05997431e-01, 9.36344279e-02, 5.53170346e-01,\n",
" 3.99631859e-01],\n",
" [ 3.09016994e-01, 9.54915028e-02, 5.55892970e-01,\n",
" 4.04508497e-01]])"
]
},
"execution_count": 77,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ary = np.array(df.values)\n",
"ary\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df.values"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# pandasの基礎"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 79,
"metadata": {
"collapsed": false
},
"outputs": [
{
"ename": "AttributeError",
"evalue": "'list' object has no attribute 'shape'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-79-1a88fe294431>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mlist\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mflatten\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;31mAttributeError\u001b[0m: 'list' object has no attribute 'shape'"
]
}
],
"source": [
"list(df.values.flatten())"
]
},
{
"cell_type": "code",
"execution_count": 82,
"metadata": {
"collapsed": false
},
"outputs": [
{
"ename": "TypeError",
"evalue": "'numpy.ndarray' object is not callable",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-82-a5a86ec19353>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0marray\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;31mTypeError\u001b[0m: 'numpy.ndarray' object is not callable"
]
}
],
"source": [
"np.array(df.values()).shape"
]
},
{
"cell_type": "code",
"execution_count": 83,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([[ 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
" 0.00000000e+00],\n",
" [ 3.17332059e-03, 1.00699635e-05, 5.63322340e-02,\n",
" 3.18339055e-03],\n",
" [ 6.34660922e-03, 4.02794486e-05, 7.96656088e-02,\n",
" 6.38688867e-03],\n",
" [ 9.51983394e-03, 9.06272382e-05, 9.75696364e-02,\n",
" 9.61046118e-03],\n",
" [ 1.26929628e-02, 1.61111305e-04, 1.12663050e-01,\n",
" 1.28540741e-02],\n",
" [ 1.58659638e-02, 2.51728808e-04, 1.25960168e-01,\n",
" 1.61176926e-02],\n",
" [ 1.90388051e-02, 3.62476100e-04, 1.37981177e-01,\n",
" 1.94012812e-02],\n",
" [ 2.22114547e-02, 4.93348718e-04, 1.49035079e-01,\n",
" 2.27048034e-02],\n",
" [ 2.53838805e-02, 6.44341391e-04, 1.59323195e-01,\n",
" 2.60282219e-02],\n",
" [ 2.85560508e-02, 8.15448037e-04, 1.68985357e-01,\n",
" 2.93714988e-02],\n",
" [ 3.17279335e-02, 1.00666176e-03, 1.78123366e-01,\n",
" 3.27345953e-02],\n",
" [ 3.48994967e-02, 1.21797487e-03, 1.86814070e-01,\n",
" 3.61174716e-02],\n",
" [ 3.80707085e-02, 1.44937884e-03, 1.95117166e-01,\n",
" 3.95200873e-02],\n",
" [ 4.12415369e-02, 1.70086436e-03, 2.03080124e-01,\n",
" 4.29424012e-02],\n",
" [ 4.44119500e-02, 1.97242130e-03, 2.10741429e-01,\n",
" 4.63843713e-02],\n",
" [ 4.75819158e-02, 2.26403871e-03, 2.18132794e-01,\n",
" 4.98459545e-02],\n",
" [ 5.07514025e-02, 2.57570486e-03, 2.25280719e-01,\n",
" 5.33271074e-02],\n",
" [ 5.39203782e-02, 2.90740718e-03, 2.32207619e-01,\n",
" 5.68277854e-02],\n",
" [ 5.70888109e-02, 3.25913233e-03, 2.38932649e-01,\n",
" 6.03479432e-02],\n",
" [ 6.02566687e-02, 3.63086612e-03, 2.45472338e-01,\n",
" 6.38875348e-02],\n",
" [ 6.34239197e-02, 4.02259358e-03, 2.51841060e-01,\n",
" 6.74465132e-02],\n",
" [ 6.65905320e-02, 4.43429895e-03, 2.58051413e-01,\n",
" 7.10248309e-02],\n",
" [ 6.97564737e-02, 4.86596563e-03, 2.64114509e-01,\n",
" 7.46224394e-02],\n",
" [ 7.29217131e-02, 5.31757624e-03, 2.70040206e-01,\n",
" 7.82392893e-02],\n",
" [ 7.60862181e-02, 5.78911258e-03, 2.75837304e-01,\n",
" 8.18753306e-02],\n",
" [ 7.92499569e-02, 6.28055566e-03, 2.81513689e-01,\n",
" 8.55305125e-02],\n",
" [ 8.24128976e-02, 6.79188569e-03, 2.87076466e-01,\n",
" 8.92047833e-02],\n",
" [ 8.55750085e-02, 7.32308208e-03, 2.92532064e-01,\n",
" 9.28980906e-02],\n",
" [ 8.87362576e-02, 7.87412341e-03, 2.97886317e-01,\n",
" 9.66103810e-02],\n",
" [ 9.18966132e-02, 8.44498751e-03, 3.03144542e-01,\n",
" 1.00341601e-01],\n",
" [ 9.50560433e-02, 9.03565137e-03, 3.08311601e-01,\n",
" 1.04091695e-01],\n",
" [ 9.82145162e-02, 9.64609120e-03, 3.13391953e-01,\n",
" 1.07860607e-01],\n",
" [ 1.01372000e-01, 1.02762824e-02, 3.18389699e-01,\n",
" 1.11648283e-01],\n",
" [ 1.04528463e-01, 1.09261996e-02, 3.23308619e-01,\n",
" 1.15454663e-01],\n",
" [ 1.07683874e-01, 1.15958167e-02, 3.28152211e-01,\n",
" 1.19279690e-01],\n",
" [ 1.10838200e-01, 1.22851066e-02, 3.32923715e-01,\n",
" 1.23123306e-01],\n",
" [ 1.13991410e-01, 1.29940415e-02, 3.37626139e-01,\n",
" 1.26985451e-01],\n",
" [ 1.17143472e-01, 1.37225930e-02, 3.42262285e-01,\n",
" 1.30866065e-01],\n",
" [ 1.20294354e-01, 1.44707317e-02, 3.46834765e-01,\n",
" 1.34765086e-01],\n",
" [ 1.23444026e-01, 1.52384274e-02, 3.51346020e-01,\n",
" 1.38682453e-01],\n",
" [ 1.26592454e-01, 1.60256493e-02, 3.55798333e-01,\n",
" 1.42618103e-01],\n",
" [ 1.29739607e-01, 1.68323656e-02, 3.60193846e-01,\n",
" 1.46571972e-01],\n",
" [ 1.32885454e-01, 1.76585438e-02, 3.64534571e-01,\n",
" 1.50543997e-01],\n",
" [ 1.36029962e-01, 1.85041506e-02, 3.68822399e-01,\n",
" 1.54534113e-01],\n",
" [ 1.39173101e-01, 1.93691520e-02, 3.73059112e-01,\n",
" 1.58542253e-01],\n",
" [ 1.42314838e-01, 2.02535132e-02, 3.77246389e-01,\n",
" 1.62568351e-01],\n",
" [ 1.45455142e-01, 2.11571985e-02, 3.81385818e-01,\n",
" 1.66612341e-01],\n",
" [ 1.48593982e-01, 2.20801715e-02, 3.85478899e-01,\n",
" 1.70674153e-01],\n",
" [ 1.51731325e-01, 2.30223950e-02, 3.89527053e-01,\n",
" 1.74753720e-01],\n",
" [ 1.54867140e-01, 2.39838311e-02, 3.93531626e-01,\n",
" 1.78850971e-01],\n",
" [ 1.58001396e-01, 2.49644411e-02, 3.97493894e-01,\n",
" 1.82965837e-01],\n",
" [ 1.61134061e-01, 2.59641855e-02, 4.01415073e-01,\n",
" 1.87098246e-01],\n",
" [ 1.64265103e-01, 2.69830239e-02, 4.05296315e-01,\n",
" 1.91248127e-01],\n",
" [ 1.67394490e-01, 2.80209154e-02, 4.09138718e-01,\n",
" 1.95415406e-01],\n",
" [ 1.70522193e-01, 2.90778182e-02, 4.12943329e-01,\n",
" 1.99600011e-01],\n",
" [ 1.73648178e-01, 3.01536896e-02, 4.16711144e-01,\n",
" 2.03801867e-01],\n",
" [ 1.76772414e-01, 3.12484864e-02, 4.20443116e-01,\n",
" 2.08020900e-01],\n",
" [ 1.79894870e-01, 3.23621644e-02, 4.24140154e-01,\n",
" 2.12257035e-01],\n",
" [ 1.83015515e-01, 3.34946788e-02, 4.27803127e-01,\n",
" 2.16510194e-01],\n",
" [ 1.86134317e-01, 3.46459839e-02, 4.31432865e-01,\n",
" 2.20780301e-01],\n",
" [ 1.89251244e-01, 3.58160335e-02, 4.35030165e-01,\n",
" 2.25067278e-01],\n",
" [ 1.92366266e-01, 3.70047803e-02, 4.38595789e-01,\n",
" 2.29371046e-01],\n",
" [ 1.95479351e-01, 3.82121765e-02, 4.42130468e-01,\n",
" 2.33691527e-01],\n",
" [ 1.98590467e-01, 3.94381734e-02, 4.45634903e-01,\n",
" 2.38028640e-01],\n",
" [ 2.01699583e-01, 4.06827217e-02, 4.49109767e-01,\n",
" 2.42382305e-01],\n",
" [ 2.04806668e-01, 4.19457713e-02, 4.52555707e-01,\n",
" 2.46752439e-01],\n",
" [ 2.07911691e-01, 4.32272712e-02, 4.55973344e-01,\n",
" 2.51138962e-01],\n",
" [ 2.11014620e-01, 4.45271698e-02, 4.59363277e-01,\n",
" 2.55541790e-01],\n",
" [ 2.14115424e-01, 4.58454148e-02, 4.62726079e-01,\n",
" 2.59960839e-01],\n",
" [ 2.17214072e-01, 4.71819531e-02, 4.66062305e-01,\n",
" 2.64396025e-01],\n",
" [ 2.20310533e-01, 4.85367309e-02, 4.69372488e-01,\n",
" 2.68847264e-01],\n",
" [ 2.23404775e-01, 4.99096935e-02, 4.72657143e-01,\n",
" 2.73314468e-01],\n",
" [ 2.26496767e-01, 5.13007857e-02, 4.75916765e-01,\n",
" 2.77797553e-01],\n",
" [ 2.29586479e-01, 5.27099514e-02, 4.79151833e-01,\n",
" 2.82296430e-01],\n",
" [ 2.32673879e-01, 5.41371339e-02, 4.82362808e-01,\n",
" 2.86811013e-01],\n",
" [ 2.35758936e-01, 5.55822757e-02, 4.85550137e-01,\n",
" 2.91341211e-01],\n",
" [ 2.38841618e-01, 5.70453185e-02, 4.88714250e-01,\n",
" 2.95886937e-01],\n",
" [ 2.41921896e-01, 5.85262036e-02, 4.91855564e-01,\n",
" 3.00448099e-01],\n",
" [ 2.44999737e-01, 6.00248711e-02, 4.94974481e-01,\n",
" 3.05024608e-01],\n",
" [ 2.48075111e-01, 6.15412608e-02, 4.98071392e-01,\n",
" 3.09616372e-01],\n",
" [ 2.51147987e-01, 6.30753115e-02, 5.01146672e-01,\n",
" 3.14223299e-01],\n",
" [ 2.54218334e-01, 6.46269614e-02, 5.04200688e-01,\n",
" 3.18845296e-01],\n",
" [ 2.57286121e-01, 6.61961482e-02, 5.07233793e-01,\n",
" 3.23482269e-01],\n",
" [ 2.60351317e-01, 6.77828085e-02, 5.10246330e-01,\n",
" 3.28134126e-01],\n",
" [ 2.63413892e-01, 6.93868784e-02, 5.13238630e-01,\n",
" 3.32800770e-01],\n",
" [ 2.66473814e-01, 7.10082934e-02, 5.16211017e-01,\n",
" 3.37482107e-01],\n",
" [ 2.69531052e-01, 7.26469881e-02, 5.19163801e-01,\n",
" 3.42178040e-01],\n",
" [ 2.72585576e-01, 7.43028965e-02, 5.22097286e-01,\n",
" 3.46888473e-01],\n",
" [ 2.75637356e-01, 7.59759519e-02, 5.25011767e-01,\n",
" 3.51613308e-01],\n",
" [ 2.78686360e-01, 7.76660870e-02, 5.27907529e-01,\n",
" 3.56352446e-01],\n",
" [ 2.81732557e-01, 7.93732336e-02, 5.30784850e-01,\n",
" 3.61105790e-01],\n",
" [ 2.84775917e-01, 8.10973230e-02, 5.33643998e-01,\n",
" 3.65873240e-01],\n",
" [ 2.87816410e-01, 8.28382857e-02, 5.36485237e-01,\n",
" 3.70654695e-01],\n",
" [ 2.90854004e-01, 8.45960516e-02, 5.39308821e-01,\n",
" 3.75450056e-01],\n",
" [ 2.93888669e-01, 8.63705500e-02, 5.42114996e-01,\n",
" 3.80259219e-01],\n",
" [ 2.96920375e-01, 8.81617093e-02, 5.44904006e-01,\n",
" 3.85082085e-01],\n",
" [ 2.99949091e-01, 8.99694574e-02, 5.47676082e-01,\n",
" 3.89918549e-01],\n",
" [ 3.02974787e-01, 9.17937214e-02, 5.50431455e-01,\n",
" 3.94768508e-01],\n",
" [ 3.05997431e-01, 9.36344279e-02, 5.53170346e-01,\n",
" 3.99631859e-01],\n",
" [ 3.09016994e-01, 9.54915028e-02, 5.55892970e-01,\n",
" 4.04508497e-01]])"
]
},
"execution_count": 83,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.values"
]
},
{
"cell_type": "code",
"execution_count": 88,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"(4L, 100L)"
]
},
"execution_count": 88,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.values.T.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"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": "2.7.10"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment