Skip to content

Instantly share code, notes, and snippets.

@karino2

karino2/RandomForest-interactive2.ipynb

Created January 13, 2016 15:49
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save karino2/e3074f16c54fde6f61ca to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save karino2/e3074f16c54fde6f61ca to your computer and use it in GitHub Desktop.
Download ZIP
Randomforestの実装、インタラクティブに試行錯誤その2
Display the source blob
Display the rendered blob
Raw
RandomForest-interactive2.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"['a b c d']"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"line = \"a b c d\"\n",
"line.split(r\" +\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"['a', 'b', '', '', 'c', 'd']"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"line.split(\" \")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"dt = []\n",
"f = open(\"iris.txt\")\n",
"for line in f:\n",
" arr = line.split(\" \")\n",
" res = [el.strip() for el in arr if el != '']\n",
" dt.append(res)\n",
"f.close()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"[['5.1', '3.5', '1.4', '0.2', '0'],\n",
" ['4.9', '3', '1.4', '0.2', '0'],\n",
" ['4.7', '3.2', '1.3', '0.2', '0'],\n",
" ['4.6', '3.1', '1.5', '0.2', '0'],\n",
" ['5', '3.6', '1.4', '0.2', '0'],\n",
" ['5.4', '3.9', '1.7', '0.4', '0'],\n",
" ['4.6', '3.4', '1.4', '0.3', '0'],\n",
" ['5', '3.4', '1.5', '0.2', '0'],\n",
" ['4.4', '2.9', '1.4', '0.2', '0'],\n",
" ['4.9', '3.1', '1.5', '0.1', '0'],\n",
" ['5.4', '3.7', '1.5', '0.2', '0'],\n",
" ['4.8', '3.4', '1.6', '0.2', '0'],\n",
" ['4.8', '3', '1.4', '0.1', '0'],\n",
" ['4.3', '3', '1.1', '0.1', '0'],\n",
" ['5.8', '4', '1.2', '0.2', '0'],\n",
" ['5.7', '4.4', '1.5', '0.4', '0'],\n",
" ['5.4', '3.9', '1.3', '0.4', '0'],\n",
" ['5.1', '3.5', '1.4', '0.3', '0'],\n",
" ['5.7', '3.8', '1.7', '0.3', '0'],\n",
" ['5.1', '3.8', '1.5', '0.3', '0'],\n",
" ['5.4', '3.4', '1.7', '0.2', '0'],\n",
" ['5.1', '3.7', '1.5', '0.4', '0'],\n",
" ['4.6', '3.6', '1', '0.2', '0'],\n",
" ['5.1', '3.3', '1.7', '0.5', '0'],\n",
" ['4.8', '3.4', '1.9', '0.2', '0'],\n",
" ['5', '3', '1.6', '0.2', '0'],\n",
" ['5', '3.4', '1.6', '0.4', '0'],\n",
" ['5.2', '3.5', '1.5', '0.2', '0'],\n",
" ['5.2', '3.4', '1.4', '0.2', '0'],\n",
" ['4.7', '3.2', '1.6', '0.2', '0'],\n",
" ['4.8', '3.1', '1.6', '0.2', '0'],\n",
" ['5.4', '3.4', '1.5', '0.4', '0'],\n",
" ['5.2', '4.1', '1.5', '0.1', '0'],\n",
" ['5.5', '4.2', '1.4', '0.2', '0'],\n",
" ['4.9', '3.1', '1.5', '0.2', '0'],\n",
" ['5', '3.2', '1.2', '0.2', '0'],\n",
" ['5.5', '3.5', '1.3', '0.2', '0'],\n",
" ['4.9', '3.6', '1.4', '0.1', '0'],\n",
" ['4.4', '3', '1.3', '0.2', '0'],\n",
" ['5.1', '3.4', '1.5', '0.2', '0'],\n",
" ['5', '3.5', '1.3', '0.3', '0'],\n",
" ['4.5', '2.3', '1.3', '0.3', '0'],\n",
" ['4.4', '3.2', '1.3', '0.2', '0'],\n",
" ['5', '3.5', '1.6', '0.6', '0'],\n",
" ['5.1', '3.8', '1.9', '0.4', '0'],\n",
" ['4.8', '3', '1.4', '0.3', '0'],\n",
" ['5.1', '3.8', '1.6', '0.2', '0'],\n",
" ['4.6', '3.2', '1.4', '0.2', '0'],\n",
" ['5.3', '3.7', '1.5', '0.2', '0'],\n",
" ['5', '3.3', '1.4', '0.2', '0'],\n",
" ['7', '3.2', '4.7', '1.4', '1'],\n",
" ['6.4', '3.2', '4.5', '1.5', '1'],\n",
" ['6.9', '3.1', '4.9', '1.5', '1'],\n",
" ['5.5', '2.3', '4', '1.3', '1'],\n",
" ['6.5', '2.8', '4.6', '1.5', '1'],\n",
" ['5.7', '2.8', '4.5', '1.3', '1'],\n",
" ['6.3', '3.3', '4.7', '1.6', '1'],\n",
" ['4.9', '2.4', '3.3', '1', '1'],\n",
" ['6.6', '2.9', '4.6', '1.3', '1'],\n",
" ['5.2', '2.7', '3.9', '1.4', '1'],\n",
" ['5', '2', '3.5', '1', '1'],\n",
" ['5.9', '3', '4.2', '1.5', '1'],\n",
" ['6', '2.2', '4', '1', '1'],\n",
" ['6.1', '2.9', '4.7', '1.4', '1'],\n",
" ['5.6', '2.9', '3.6', '1.3', '1'],\n",
" ['6.7', '3.1', '4.4', '1.4', '1'],\n",
" ['5.6', '3', '4.5', '1.5', '1'],\n",
" ['5.8', '2.7', '4.1', '1', '1'],\n",
" ['6.2', '2.2', '4.5', '1.5', '1'],\n",
" ['5.6', '2.5', '3.9', '1.1', '1'],\n",
" ['5.9', '3.2', '4.8', '1.8', '1'],\n",
" ['6.1', '2.8', '4', '1.3', '1'],\n",
" ['6.3', '2.5', '4.9', '1.5', '1'],\n",
" ['6.1', '2.8', '4.7', '1.2', '1'],\n",
" ['6.4', '2.9', '4.3', '1.3', '1'],\n",
" ['6.6', '3', '4.4', '1.4', '1'],\n",
" ['6.8', '2.8', '4.8', '1.4', '1'],\n",
" ['6.7', '3', '5', '1.7', '1'],\n",
" ['6', '2.9', '4.5', '1.5', '1'],\n",
" ['5.7', '2.6', '3.5', '1', '1'],\n",
" ['5.5', '2.4', '3.8', '1.1', '1'],\n",
" ['5.5', '2.4', '3.7', '1', '1'],\n",
" ['5.8', '2.7', '3.9', '1.2', '1'],\n",
" ['6', '2.7', '5.1', '1.6', '1'],\n",
" ['5.4', '3', '4.5', '1.5', '1'],\n",
" ['6', '3.4', '4.5', '1.6', '1'],\n",
" ['6.7', '3.1', '4.7', '1.5', '1'],\n",
" ['6.3', '2.3', '4.4', '1.3', '1'],\n",
" ['5.6', '3', '4.1', '1.3', '1'],\n",
" ['5.5', '2.5', '4', '1.3', '1'],\n",
" ['5.5', '2.6', '4.4', '1.2', '1'],\n",
" ['6.1', '3', '4.6', '1.4', '1'],\n",
" ['5.8', '2.6', '4', '1.2', '1'],\n",
" ['5', '2.3', '3.3', '1', '1'],\n",
" ['5.6', '2.7', '4.2', '1.3', '1'],\n",
" ['5.7', '3', '4.2', '1.2', '1'],\n",
" ['5.7', '2.9', '4.2', '1.3', '1'],\n",
" ['6.2', '2.9', '4.3', '1.3', '1'],\n",
" ['5.1', '2.5', '3', '1.1', '1'],\n",
" ['5.7', '2.8', '4.1', '1.3', '1'],\n",
" ['6.3', '3.3', '6', '2.5', '2'],\n",
" ['5.8', '2.7', '5.1', '1.9', '2'],\n",
" ['7.1', '3', '5.9', '2.1', '2'],\n",
" ['6.3', '2.9', '5.6', '1.8', '2'],\n",
" ['6.5', '3', '5.8', '2.2', '2'],\n",
" ['7.6', '3', '6.6', '2.1', '2'],\n",
" ['4.9', '2.5', '4.5', '1.7', '2'],\n",
" ['7.3', '2.9', '6.3', '1.8', '2'],\n",
" ['6.7', '2.5', '5.8', '1.8', '2'],\n",
" ['7.2', '3.6', '6.1', '2.5', '2'],\n",
" ['6.5', '3.2', '5.1', '2', '2'],\n",
" ['6.4', '2.7', '5.3', '1.9', '2'],\n",
" ['6.8', '3', '5.5', '2.1', '2'],\n",
" ['5.7', '2.5', '5', '2', '2'],\n",
" ['5.8', '2.8', '5.1', '2.4', '2'],\n",
" ['6.4', '3.2', '5.3', '2.3', '2'],\n",
" ['6.5', '3', '5.5', '1.8', '2'],\n",
" ['7.7', '3.8', '6.7', '2.2', '2'],\n",
" ['7.7', '2.6', '6.9', '2.3', '2'],\n",
" ['6', '2.2', '5', '1.5', '2'],\n",
" ['6.9', '3.2', '5.7', '2.3', '2'],\n",
" ['5.6', '2.8', '4.9', '2', '2'],\n",
" ['7.7', '2.8', '6.7', '2', '2'],\n",
" ['6.3', '2.7', '4.9', '1.8', '2'],\n",
" ['6.7', '3.3', '5.7', '2.1', '2'],\n",
" ['7.2', '3.2', '6', '1.8', '2'],\n",
" ['6.2', '2.8', '4.8', '1.8', '2'],\n",
" ['6.1', '3', '4.9', '1.8', '2'],\n",
" ['6.4', '2.8', '5.6', '2.1', '2'],\n",
" ['7.2', '3', '5.8', '1.6', '2'],\n",
" ['7.4', '2.8', '6.1', '1.9', '2'],\n",
" ['7.9', '3.8', '6.4', '2', '2'],\n",
" ['6.4', '2.8', '5.6', '2.2', '2'],\n",
" ['6.3', '2.8', '5.1', '1.5', '2'],\n",
" ['6.1', '2.6', '5.6', '1.4', '2'],\n",
" ['7.7', '3', '6.1', '2.3', '2'],\n",
" ['6.3', '3.4', '5.6', '2.4', '2'],\n",
" ['6.4', '3.1', '5.5', '1.8', '2'],\n",
" ['6', '3', '4.8', '1.8', '2'],\n",
" ['6.9', '3.1', '5.4', '2.1', '2'],\n",
" ['6.7', '3.1', '5.6', '2.4', '2'],\n",
" ['6.9', '3.1', '5.1', '2.3', '2'],\n",
" ['5.8', '2.7', '5.1', '1.9', '2'],\n",
" ['6.8', '3.2', '5.9', '2.3', '2'],\n",
" ['6.7', '3.3', '5.7', '2.5', '2'],\n",
" ['6.7', '3', '5.2', '2.3', '2'],\n",
" ['6.3', '2.5', '5', '1.9', '2'],\n",
" ['6.5', '3', '5.2', '2', '2'],\n",
" ['6.2', '3.4', '5.4', '2.3', '2'],\n",
" ['5.9', '3', '5.1', '1.8', '2']]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dt"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df = pd.read_table('iris.txt', sep='\\s+')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"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>5.1</th>\n",
" <th>3.5</th>\n",
" <th>1.4</th>\n",
" <th>0.2</th>\n",
" <th>0</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4.9</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.6</td>\n",
" <td>3.1</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5.0</td>\n",
" <td>3.6</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5.4</td>\n",
" <td>3.9</td>\n",
" <td>1.7</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>4.6</td>\n",
" <td>3.4</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>5.0</td>\n",
" <td>3.4</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>4.4</td>\n",
" <td>2.9</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>4.9</td>\n",
" <td>3.1</td>\n",
" <td>1.5</td>\n",
" <td>0.1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>5.4</td>\n",
" <td>3.7</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>4.8</td>\n",
" <td>3.4</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>4.8</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>4.3</td>\n",
" <td>3.0</td>\n",
" <td>1.1</td>\n",
" <td>0.1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>5.8</td>\n",
" <td>4.0</td>\n",
" <td>1.2</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>5.7</td>\n",
" <td>4.4</td>\n",
" <td>1.5</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>5.4</td>\n",
" <td>3.9</td>\n",
" <td>1.3</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>5.7</td>\n",
" <td>3.8</td>\n",
" <td>1.7</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>5.1</td>\n",
" <td>3.8</td>\n",
" <td>1.5</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>5.4</td>\n",
" <td>3.4</td>\n",
" <td>1.7</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>5.1</td>\n",
" <td>3.7</td>\n",
" <td>1.5</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>4.6</td>\n",
" <td>3.6</td>\n",
" <td>1.0</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>5.1</td>\n",
" <td>3.3</td>\n",
" <td>1.7</td>\n",
" <td>0.5</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>4.8</td>\n",
" <td>3.4</td>\n",
" <td>1.9</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>5.0</td>\n",
" <td>3.4</td>\n",
" <td>1.6</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>5.2</td>\n",
" <td>3.5</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>5.2</td>\n",
" <td>3.4</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>4.8</td>\n",
" <td>3.1</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>119</th>\n",
" <td>6.9</td>\n",
" <td>3.2</td>\n",
" <td>5.7</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>120</th>\n",
" <td>5.6</td>\n",
" <td>2.8</td>\n",
" <td>4.9</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>7.7</td>\n",
" <td>2.8</td>\n",
" <td>6.7</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>122</th>\n",
" <td>6.3</td>\n",
" <td>2.7</td>\n",
" <td>4.9</td>\n",
" <td>1.8</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>123</th>\n",
" <td>6.7</td>\n",
" <td>3.3</td>\n",
" <td>5.7</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>124</th>\n",
" <td>7.2</td>\n",
" <td>3.2</td>\n",
" <td>6.0</td>\n",
" <td>1.8</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>125</th>\n",
" <td>6.2</td>\n",
" <td>2.8</td>\n",
" <td>4.8</td>\n",
" <td>1.8</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>126</th>\n",
" <td>6.1</td>\n",
" <td>3.0</td>\n",
" <td>4.9</td>\n",
" <td>1.8</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>127</th>\n",
" <td>6.4</td>\n",
" <td>2.8</td>\n",
" <td>5.6</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>128</th>\n",
" <td>7.2</td>\n",
" <td>3.0</td>\n",
" <td>5.8</td>\n",
" <td>1.6</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>129</th>\n",
" <td>7.4</td>\n",
" <td>2.8</td>\n",
" <td>6.1</td>\n",
" <td>1.9</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>130</th>\n",
" <td>7.9</td>\n",
" <td>3.8</td>\n",
" <td>6.4</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>131</th>\n",
" <td>6.4</td>\n",
" <td>2.8</td>\n",
" <td>5.6</td>\n",
" <td>2.2</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>132</th>\n",
" <td>6.3</td>\n",
" <td>2.8</td>\n",
" <td>5.1</td>\n",
" <td>1.5</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>133</th>\n",
" <td>6.1</td>\n",
" <td>2.6</td>\n",
" <td>5.6</td>\n",
" <td>1.4</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>134</th>\n",
" <td>7.7</td>\n",
" <td>3.0</td>\n",
" <td>6.1</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>135</th>\n",
" <td>6.3</td>\n",
" <td>3.4</td>\n",
" <td>5.6</td>\n",
" <td>2.4</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>136</th>\n",
" <td>6.4</td>\n",
" <td>3.1</td>\n",
" <td>5.5</td>\n",
" <td>1.8</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>137</th>\n",
" <td>6.0</td>\n",
" <td>3.0</td>\n",
" <td>4.8</td>\n",
" <td>1.8</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>138</th>\n",
" <td>6.9</td>\n",
" <td>3.1</td>\n",
" <td>5.4</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>139</th>\n",
" <td>6.7</td>\n",
" <td>3.1</td>\n",
" <td>5.6</td>\n",
" <td>2.4</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>140</th>\n",
" <td>6.9</td>\n",
" <td>3.1</td>\n",
" <td>5.1</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>141</th>\n",
" <td>5.8</td>\n",
" <td>2.7</td>\n",
" <td>5.1</td>\n",
" <td>1.9</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>142</th>\n",
" <td>6.8</td>\n",
" <td>3.2</td>\n",
" <td>5.9</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>143</th>\n",
" <td>6.7</td>\n",
" <td>3.3</td>\n",
" <td>5.7</td>\n",
" <td>2.5</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>144</th>\n",
" <td>6.7</td>\n",
" <td>3.0</td>\n",
" <td>5.2</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>145</th>\n",
" <td>6.3</td>\n",
" <td>2.5</td>\n",
" <td>5.0</td>\n",
" <td>1.9</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>146</th>\n",
" <td>6.5</td>\n",
" <td>3.0</td>\n",
" <td>5.2</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>147</th>\n",
" <td>6.2</td>\n",
" <td>3.4</td>\n",
" <td>5.4</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>148</th>\n",
" <td>5.9</td>\n",
" <td>3.0</td>\n",
" <td>5.1</td>\n",
" <td>1.8</td>\n",
" <td>2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>149 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
" 5.1 3.5 1.4 0.2 0\n",
"0 4.9 3.0 1.4 0.2 0\n",
"1 4.7 3.2 1.3 0.2 0\n",
"2 4.6 3.1 1.5 0.2 0\n",
"3 5.0 3.6 1.4 0.2 0\n",
"4 5.4 3.9 1.7 0.4 0\n",
"5 4.6 3.4 1.4 0.3 0\n",
"6 5.0 3.4 1.5 0.2 0\n",
"7 4.4 2.9 1.4 0.2 0\n",
"8 4.9 3.1 1.5 0.1 0\n",
"9 5.4 3.7 1.5 0.2 0\n",
"10 4.8 3.4 1.6 0.2 0\n",
"11 4.8 3.0 1.4 0.1 0\n",
"12 4.3 3.0 1.1 0.1 0\n",
"13 5.8 4.0 1.2 0.2 0\n",
"14 5.7 4.4 1.5 0.4 0\n",
"15 5.4 3.9 1.3 0.4 0\n",
"16 5.1 3.5 1.4 0.3 0\n",
"17 5.7 3.8 1.7 0.3 0\n",
"18 5.1 3.8 1.5 0.3 0\n",
"19 5.4 3.4 1.7 0.2 0\n",
"20 5.1 3.7 1.5 0.4 0\n",
"21 4.6 3.6 1.0 0.2 0\n",
"22 5.1 3.3 1.7 0.5 0\n",
"23 4.8 3.4 1.9 0.2 0\n",
"24 5.0 3.0 1.6 0.2 0\n",
"25 5.0 3.4 1.6 0.4 0\n",
"26 5.2 3.5 1.5 0.2 0\n",
"27 5.2 3.4 1.4 0.2 0\n",
"28 4.7 3.2 1.6 0.2 0\n",
"29 4.8 3.1 1.6 0.2 0\n",
".. ... ... ... ... ..\n",
"119 6.9 3.2 5.7 2.3 2\n",
"120 5.6 2.8 4.9 2.0 2\n",
"121 7.7 2.8 6.7 2.0 2\n",
"122 6.3 2.7 4.9 1.8 2\n",
"123 6.7 3.3 5.7 2.1 2\n",
"124 7.2 3.2 6.0 1.8 2\n",
"125 6.2 2.8 4.8 1.8 2\n",
"126 6.1 3.0 4.9 1.8 2\n",
"127 6.4 2.8 5.6 2.1 2\n",
"128 7.2 3.0 5.8 1.6 2\n",
"129 7.4 2.8 6.1 1.9 2\n",
"130 7.9 3.8 6.4 2.0 2\n",
"131 6.4 2.8 5.6 2.2 2\n",
"132 6.3 2.8 5.1 1.5 2\n",
"133 6.1 2.6 5.6 1.4 2\n",
"134 7.7 3.0 6.1 2.3 2\n",
"135 6.3 3.4 5.6 2.4 2\n",
"136 6.4 3.1 5.5 1.8 2\n",
"137 6.0 3.0 4.8 1.8 2\n",
"138 6.9 3.1 5.4 2.1 2\n",
"139 6.7 3.1 5.6 2.4 2\n",
"140 6.9 3.1 5.1 2.3 2\n",
"141 5.8 2.7 5.1 1.9 2\n",
"142 6.8 3.2 5.9 2.3 2\n",
"143 6.7 3.3 5.7 2.5 2\n",
"144 6.7 3.0 5.2 2.3 2\n",
"145 6.3 2.5 5.0 1.9 2\n",
"146 6.5 3.0 5.2 2.0 2\n",
"147 6.2 3.4 5.4 2.3 2\n",
"148 5.9 3.0 5.1 1.8 2\n",
"\n",
"[149 rows x 5 columns]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 79,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"df = pd.read_table('iris.txt', sep='\\s+', names=['x1', 'x2', 'x3','x4', 'y'])"
]
},
{
"cell_type": "code",
"execution_count": 82,
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>100</th>\n",
" <td>6.3</td>\n",
" <td>3.3</td>\n",
" <td>6</td>\n",
" <td>2.5</td>\n",
" <td>2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"100 6.3 3.3 6 2.5 2"
]
},
"execution_count": 82,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[100:101]"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"150"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(df)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import numpy as np"
]
},
{
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.9</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.6</td>\n",
" <td>3.1</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5.0</td>\n",
" <td>3.6</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"0 5.1 3.5 1.4 0.2 0\n",
"1 4.9 3.0 1.4 0.2 0\n",
"2 4.7 3.2 1.3 0.2 0\n",
"3 4.6 3.1 1.5 0.2 0\n",
"4 5.0 3.6 1.4 0.2 0"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df[:5]"
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([0, 1, 4, 3, 2])"
]
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sampler = np.random.permutation(5)\n",
"sampler"
]
},
{
"cell_type": "code",
"execution_count": 28,
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5.0</td>\n",
" <td>3.6</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.6</td>\n",
" <td>3.1</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.9</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"4 5.0 3.6 1.4 0.2 0\n",
"0 5.1 3.5 1.4 0.2 0\n",
"3 4.6 3.1 1.5 0.2 0\n",
"1 4.9 3.0 1.4 0.2 0\n",
"2 4.7 3.2 1.3 0.2 0"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.take(sampler)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"sampler = np.random.permutation(len(df))"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([4, 0, 3])"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sampler[0:3]"
]
},
{
"cell_type": "code",
"execution_count": 83,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"randomdf = df.take(sampler)"
]
},
{
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5.0</td>\n",
" <td>3.6</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.6</td>\n",
" <td>3.1</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"4 5.0 3.6 1.4 0.2 0\n",
"0 5.1 3.5 1.4 0.2 0\n",
"3 4.6 3.1 1.5 0.2 0"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"randomdf[:3]"
]
},
{
"cell_type": "code",
"execution_count": 89,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"sampler = np.random.permutation(len(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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>128</th>\n",
" <td>6.4</td>\n",
" <td>2.8</td>\n",
" <td>5.6</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>90</th>\n",
" <td>5.5</td>\n",
" <td>2.6</td>\n",
" <td>4.4</td>\n",
" <td>1.2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>98</th>\n",
" <td>5.1</td>\n",
" <td>2.5</td>\n",
" <td>3.0</td>\n",
" <td>1.1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"128 6.4 2.8 5.6 2.1 2\n",
"90 5.5 2.6 4.4 1.2 1\n",
"98 5.1 2.5 3.0 1.1 1"
]
},
"execution_count": 90,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"randomdf = df.take(sampler)\n",
"randomdf[:3]"
]
},
{
"cell_type": "code",
"execution_count": 91,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"dfTraining = randomdf[0:125]"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"125"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(dfTraining)"
]
},
{
"cell_type": "code",
"execution_count": 92,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"dfTest = randomdf[125:150]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"[{'answerclass': 0,\n",
" 'featureidx': -1,\n",
" 'isleaf': False,\n",
" 'leftidx': -1,\n",
" 'level': -1,\n",
" 'rightidx': -1,\n",
" 'separateval': 0}]"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tnodes = []\n",
"root = {\"isleaf\": False, \"level\": -1, \"featureidx\": -1, \"separateval\":0, \"answerclass\":0, \"leftidx\":-1, \"rightidx\": -1 }\n",
"tnodes.append(root)\n",
"tnodes"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"numdata = len(dfTraining)"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"125"
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"numdata"
]
},
{
"cell_type": "code",
"execution_count": 93,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"{'answerclass': 0,\n",
" 'featureidx': -1,\n",
" 'isleaf': False,\n",
" 'leftidx': -1,\n",
" 'level': -1,\n",
" 'rightidx': -1,\n",
" 'separateval': 0,\n",
" 'valids': array([ 21, 22, 44, 78, 0, 88, 25, 103, 59, 121, 66, 58, 116,\n",
" 122, 116, 38, 19, 46, 93, 114, 113, 43, 12, 42, 48, 64,\n",
" 87, 91, 69, 19, 44, 70, 108, 117, 70, 93, 122, 65, 18,\n",
" 16, 63, 22, 7, 93, 79, 61, 47, 29, 67, 73, 124, 123,\n",
" 40, 1, 8, 60, 60, 19, 27, 95, 58, 101, 90, 97, 60,\n",
" 39, 81, 89, 13, 35, 7, 30, 26, 6, 17, 69, 124, 102,\n",
" 85, 54, 28, 54, 36, 106, 23, 40, 84, 116, 70, 121, 92,\n",
" 4, 77, 53, 46, 77, 121, 15, 66, 123, 66, 13, 121, 115,\n",
" 10, 57, 35, 84, 49, 30, 112, 25, 120, 50, 38, 28, 102,\n",
" 36, 40, 26, 29, 44, 6, 42, 118])}"
]
},
"execution_count": 93,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cur['valids'] = np.random.randint(0, len(dfTraining), size=numdata)\n",
"cur"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"numradfeatures = 2\n",
"numrandpos = 5"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"curidx = 0"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# DT作るループの開始のつもり\n",
"cur = tnodes[curidx]"
]
},
{
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>52</th>\n",
" <td>6.9</td>\n",
" <td>3.1</td>\n",
" <td>4.9</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>4.6</td>\n",
" <td>3.4</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"52 6.9 3.1 4.9 1.5 1\n",
"6 4.6 3.4 1.4 0.3 0"
]
},
"execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dfTraining.take(cur['valids'])[:2]"
]
},
{
"cell_type": "code",
"execution_count": 48,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"52 1\n",
"6 0\n",
"Name: y, dtype: int64"
]
},
"execution_count": 48,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dfTraining.take(cur['valids'])[:2]['y']"
]
},
{
"cell_type": "code",
"execution_count": 49,
"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>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>52</th>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" y\n",
"52 1\n",
"6 0"
]
},
"execution_count": 49,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dfTraining.take(cur['valids'])[:2][['y']]"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"1"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dfTraining.take(cur['valids'])[:2]['y'].values[0]"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0"
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dfTraining.take(cur['valids'])[:2]['y'].values[1]"
]
},
{
"cell_type": "code",
"execution_count": 94,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"curdf = dfTraining.take(cur['valids'])"
]
},
{
"cell_type": "code",
"execution_count": 59,
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"0 5.1 3.5 1.4 0.2 0\n",
"0 5.1 3.5 1.4 0.2 0"
]
},
"execution_count": 59,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf.ix[0]"
]
},
{
"cell_type": "code",
"execution_count": 61,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"52"
]
},
"execution_count": 61,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf.index[0]"
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"125"
]
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(curdf)"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"Int64Index([52, 6], dtype='int64')"
]
},
"execution_count": 65,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf.index[0:2]"
]
},
{
"cell_type": "code",
"execution_count": 66,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"Int64Index([52, 6], dtype='int64')"
]
},
"execution_count": 66,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf.index[:2]"
]
},
{
"cell_type": "code",
"execution_count": 67,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"Int64Index([52, 6, 87], dtype='int64')"
]
},
"execution_count": 67,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf.index[:3]"
]
},
{
"cell_type": "code",
"execution_count": 72,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"1.0"
]
},
"execution_count": 72,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"firsty = curdf.ix[curdf.index[0]]['y']\n",
"firsty"
]
},
{
"cell_type": "code",
"execution_count": 73,
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>52</th>\n",
" <td>6.9</td>\n",
" <td>3.1</td>\n",
" <td>4.9</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>87</th>\n",
" <td>6.3</td>\n",
" <td>2.3</td>\n",
" <td>4.4</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>91</th>\n",
" <td>6.1</td>\n",
" <td>3.0</td>\n",
" <td>4.6</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
" <td>5.7</td>\n",
" <td>2.9</td>\n",
" <td>4.2</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>76</th>\n",
" <td>6.8</td>\n",
" <td>2.8</td>\n",
" <td>4.8</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
" <td>4.9</td>\n",
" <td>2.4</td>\n",
" <td>3.3</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>93</th>\n",
" <td>5.0</td>\n",
" <td>2.3</td>\n",
" <td>3.3</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>85</th>\n",
" <td>6.0</td>\n",
" <td>3.4</td>\n",
" <td>4.5</td>\n",
" <td>1.6</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>60</th>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>3.5</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>91</th>\n",
" <td>6.1</td>\n",
" <td>3.0</td>\n",
" <td>4.6</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
" <td>5.7</td>\n",
" <td>2.9</td>\n",
" <td>4.2</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>77</th>\n",
" <td>6.7</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>1.7</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>80</th>\n",
" <td>5.5</td>\n",
" <td>2.4</td>\n",
" <td>3.8</td>\n",
" <td>1.1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56</th>\n",
" <td>6.3</td>\n",
" <td>3.3</td>\n",
" <td>4.7</td>\n",
" <td>1.6</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>92</th>\n",
" <td>5.8</td>\n",
" <td>2.6</td>\n",
" <td>4.0</td>\n",
" <td>1.2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>80</th>\n",
" <td>5.5</td>\n",
" <td>2.4</td>\n",
" <td>3.8</td>\n",
" <td>1.1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84</th>\n",
" <td>5.4</td>\n",
" <td>3.0</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50</th>\n",
" <td>7.0</td>\n",
" <td>3.2</td>\n",
" <td>4.7</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>92</th>\n",
" <td>5.8</td>\n",
" <td>2.6</td>\n",
" <td>4.0</td>\n",
" <td>1.2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>67</th>\n",
" <td>5.8</td>\n",
" <td>2.7</td>\n",
" <td>4.1</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>97</th>\n",
" <td>6.2</td>\n",
" <td>2.9</td>\n",
" <td>4.3</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>51</th>\n",
" <td>6.4</td>\n",
" <td>3.2</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>79</th>\n",
" <td>5.7</td>\n",
" <td>2.6</td>\n",
" <td>3.5</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>51</th>\n",
" <td>6.4</td>\n",
" <td>3.2</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>72</th>\n",
" <td>6.3</td>\n",
" <td>2.5</td>\n",
" <td>4.9</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>59</th>\n",
" <td>5.2</td>\n",
" <td>2.7</td>\n",
" <td>3.9</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58</th>\n",
" <td>6.6</td>\n",
" <td>2.9</td>\n",
" <td>4.6</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
" <td>4.9</td>\n",
" <td>2.4</td>\n",
" <td>3.3</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>73</th>\n",
" <td>6.1</td>\n",
" <td>2.8</td>\n",
" <td>4.7</td>\n",
" <td>1.2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>89</th>\n",
" <td>5.5</td>\n",
" <td>2.5</td>\n",
" <td>4.0</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>72</th>\n",
" <td>6.3</td>\n",
" <td>2.5</td>\n",
" <td>4.9</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>72</th>\n",
" <td>6.3</td>\n",
" <td>2.5</td>\n",
" <td>4.9</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50</th>\n",
" <td>7.0</td>\n",
" <td>3.2</td>\n",
" <td>4.7</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>87</th>\n",
" <td>6.3</td>\n",
" <td>2.3</td>\n",
" <td>4.4</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>61</th>\n",
" <td>5.9</td>\n",
" <td>3.0</td>\n",
" <td>4.2</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>78</th>\n",
" <td>6.0</td>\n",
" <td>2.9</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>60</th>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>3.5</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>66</th>\n",
" <td>5.6</td>\n",
" <td>3.0</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>68</th>\n",
" <td>6.2</td>\n",
" <td>2.2</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>77</th>\n",
" <td>6.7</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>1.7</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>72</th>\n",
" <td>6.3</td>\n",
" <td>2.5</td>\n",
" <td>4.9</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>82</th>\n",
" <td>5.8</td>\n",
" <td>2.7</td>\n",
" <td>3.9</td>\n",
" <td>1.2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>61</th>\n",
" <td>5.9</td>\n",
" <td>3.0</td>\n",
" <td>4.2</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>97</th>\n",
" <td>6.2</td>\n",
" <td>2.9</td>\n",
" <td>4.3</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>66</th>\n",
" <td>5.6</td>\n",
" <td>3.0</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75</th>\n",
" <td>6.6</td>\n",
" <td>3.0</td>\n",
" <td>4.4</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>97</th>\n",
" <td>6.2</td>\n",
" <td>2.9</td>\n",
" <td>4.3</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
" <td>5.7</td>\n",
" <td>2.9</td>\n",
" <td>4.2</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>74</th>\n",
" <td>6.4</td>\n",
" <td>2.9</td>\n",
" <td>4.3</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>86</th>\n",
" <td>6.7</td>\n",
" <td>3.1</td>\n",
" <td>4.7</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"52 6.9 3.1 4.9 1.5 1\n",
"87 6.3 2.3 4.4 1.3 1\n",
"91 6.1 3.0 4.6 1.4 1\n",
"96 5.7 2.9 4.2 1.3 1\n",
"76 6.8 2.8 4.8 1.4 1\n",
"57 4.9 2.4 3.3 1.0 1\n",
"93 5.0 2.3 3.3 1.0 1\n",
"85 6.0 3.4 4.5 1.6 1\n",
"60 5.0 2.0 3.5 1.0 1\n",
"91 6.1 3.0 4.6 1.4 1\n",
"96 5.7 2.9 4.2 1.3 1\n",
"77 6.7 3.0 5.0 1.7 1\n",
"80 5.5 2.4 3.8 1.1 1\n",
"56 6.3 3.3 4.7 1.6 1\n",
"92 5.8 2.6 4.0 1.2 1\n",
"80 5.5 2.4 3.8 1.1 1\n",
"84 5.4 3.0 4.5 1.5 1\n",
"50 7.0 3.2 4.7 1.4 1\n",
"92 5.8 2.6 4.0 1.2 1\n",
"67 5.8 2.7 4.1 1.0 1\n",
"97 6.2 2.9 4.3 1.3 1\n",
"51 6.4 3.2 4.5 1.5 1\n",
"79 5.7 2.6 3.5 1.0 1\n",
"51 6.4 3.2 4.5 1.5 1\n",
"72 6.3 2.5 4.9 1.5 1\n",
"59 5.2 2.7 3.9 1.4 1\n",
"58 6.6 2.9 4.6 1.3 1\n",
"57 4.9 2.4 3.3 1.0 1\n",
"73 6.1 2.8 4.7 1.2 1\n",
"89 5.5 2.5 4.0 1.3 1\n",
"72 6.3 2.5 4.9 1.5 1\n",
"72 6.3 2.5 4.9 1.5 1\n",
"50 7.0 3.2 4.7 1.4 1\n",
"87 6.3 2.3 4.4 1.3 1\n",
"61 5.9 3.0 4.2 1.5 1\n",
"78 6.0 2.9 4.5 1.5 1\n",
"60 5.0 2.0 3.5 1.0 1\n",
"66 5.6 3.0 4.5 1.5 1\n",
"68 6.2 2.2 4.5 1.5 1\n",
"77 6.7 3.0 5.0 1.7 1\n",
"72 6.3 2.5 4.9 1.5 1\n",
"82 5.8 2.7 3.9 1.2 1\n",
"61 5.9 3.0 4.2 1.5 1\n",
"97 6.2 2.9 4.3 1.3 1\n",
"66 5.6 3.0 4.5 1.5 1\n",
"75 6.6 3.0 4.4 1.4 1\n",
"97 6.2 2.9 4.3 1.3 1\n",
"96 5.7 2.9 4.2 1.3 1\n",
"74 6.4 2.9 4.3 1.3 1\n",
"86 6.7 3.1 4.7 1.5 1"
]
},
"execution_count": 73,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf[curdf['y'] == firsty]"
]
},
{
"cell_type": "code",
"execution_count": 74,
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>4.6</td>\n",
" <td>3.4</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>112</th>\n",
" <td>6.8</td>\n",
" <td>3.0</td>\n",
" <td>5.5</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>5.5</td>\n",
" <td>3.5</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>112</th>\n",
" <td>6.8</td>\n",
" <td>3.0</td>\n",
" <td>5.5</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>4.8</td>\n",
" <td>3.1</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>4.6</td>\n",
" <td>3.6</td>\n",
" <td>1.0</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100</th>\n",
" <td>6.3</td>\n",
" <td>3.3</td>\n",
" <td>6.0</td>\n",
" <td>2.5</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>136</th>\n",
" <td>6.3</td>\n",
" <td>3.4</td>\n",
" <td>5.6</td>\n",
" <td>2.4</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>135</th>\n",
" <td>7.7</td>\n",
" <td>3.0</td>\n",
" <td>6.1</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td>4.4</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>5.1</td>\n",
" <td>3.4</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104</th>\n",
" <td>6.5</td>\n",
" <td>3.0</td>\n",
" <td>5.8</td>\n",
" <td>2.2</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>5.0</td>\n",
" <td>3.4</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>5.7</td>\n",
" <td>4.4</td>\n",
" <td>1.5</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>137</th>\n",
" <td>6.4</td>\n",
" <td>3.1</td>\n",
" <td>5.5</td>\n",
" <td>1.8</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>148</th>\n",
" <td>6.2</td>\n",
" <td>3.4</td>\n",
" <td>5.4</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>130</th>\n",
" <td>7.4</td>\n",
" <td>2.8</td>\n",
" <td>6.1</td>\n",
" <td>1.9</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>5.6</td>\n",
" <td>2.8</td>\n",
" <td>4.9</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>5.4</td>\n",
" <td>3.4</td>\n",
" <td>1.7</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>122</th>\n",
" <td>7.7</td>\n",
" <td>2.8</td>\n",
" <td>6.7</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>43</th>\n",
" <td>5.0</td>\n",
" <td>3.5</td>\n",
" <td>1.6</td>\n",
" <td>0.6</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>148</th>\n",
" <td>6.2</td>\n",
" <td>3.4</td>\n",
" <td>5.4</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>112</th>\n",
" <td>6.8</td>\n",
" <td>3.0</td>\n",
" <td>5.5</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>134</th>\n",
" <td>6.1</td>\n",
" <td>2.6</td>\n",
" <td>5.6</td>\n",
" <td>1.4</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>5.7</td>\n",
" <td>3.8</td>\n",
" <td>1.7</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>140</th>\n",
" <td>6.7</td>\n",
" <td>3.1</td>\n",
" <td>5.6</td>\n",
" <td>2.4</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>47</th>\n",
" <td>4.6</td>\n",
" <td>3.2</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>43</th>\n",
" <td>5.0</td>\n",
" <td>3.5</td>\n",
" <td>1.6</td>\n",
" <td>0.6</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>5.1</td>\n",
" <td>3.4</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>113</th>\n",
" <td>5.7</td>\n",
" <td>2.5</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.9</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>142</th>\n",
" <td>5.8</td>\n",
" <td>2.7</td>\n",
" <td>5.1</td>\n",
" <td>1.9</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>4.8</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>5.4</td>\n",
" <td>3.9</td>\n",
" <td>1.3</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>5.1</td>\n",
" <td>3.4</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>5.2</td>\n",
" <td>3.4</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>5.0</td>\n",
" <td>3.4</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>5.6</td>\n",
" <td>2.8</td>\n",
" <td>4.9</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>128</th>\n",
" <td>6.4</td>\n",
" <td>2.8</td>\n",
" <td>5.6</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>128</th>\n",
" <td>6.4</td>\n",
" <td>2.8</td>\n",
" <td>5.6</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>46</th>\n",
" <td>5.1</td>\n",
" <td>3.8</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>140</th>\n",
" <td>6.7</td>\n",
" <td>3.1</td>\n",
" <td>5.6</td>\n",
" <td>2.4</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>5.6</td>\n",
" <td>2.8</td>\n",
" <td>4.9</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>137</th>\n",
" <td>6.4</td>\n",
" <td>3.1</td>\n",
" <td>5.5</td>\n",
" <td>1.8</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>46</th>\n",
" <td>5.1</td>\n",
" <td>3.8</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>140</th>\n",
" <td>6.7</td>\n",
" <td>3.1</td>\n",
" <td>5.6</td>\n",
" <td>2.4</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>4.8</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>5.7</td>\n",
" <td>4.4</td>\n",
" <td>1.5</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>5.4</td>\n",
" <td>3.4</td>\n",
" <td>1.7</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>136</th>\n",
" <td>6.3</td>\n",
" <td>3.4</td>\n",
" <td>5.6</td>\n",
" <td>2.4</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>5.5</td>\n",
" <td>4.2</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>5.5</td>\n",
" <td>3.5</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>146</th>\n",
" <td>6.3</td>\n",
" <td>2.5</td>\n",
" <td>5.0</td>\n",
" <td>1.9</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
" <td>5.1</td>\n",
" <td>3.8</td>\n",
" <td>1.9</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>75 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"6 4.6 3.4 1.4 0.3 0\n",
"112 6.8 3.0 5.5 2.1 2\n",
"25 5.0 3.0 1.6 0.2 0\n",
"36 5.5 3.5 1.3 0.2 0\n",
"112 6.8 3.0 5.5 2.1 2\n",
"0 5.1 3.5 1.4 0.2 0\n",
"30 4.8 3.1 1.6 0.2 0\n",
"22 4.6 3.6 1.0 0.2 0\n",
"100 6.3 3.3 6.0 2.5 2\n",
"136 6.3 3.4 5.6 2.4 2\n",
"135 7.7 3.0 6.1 2.3 2\n",
"42 4.4 3.2 1.3 0.2 0\n",
"39 5.1 3.4 1.5 0.2 0\n",
"104 6.5 3.0 5.8 2.2 2\n",
"7 5.0 3.4 1.5 0.2 0\n",
"15 5.7 4.4 1.5 0.4 0\n",
"137 6.4 3.1 5.5 1.8 2\n",
"148 6.2 3.4 5.4 2.3 2\n",
"17 5.1 3.5 1.4 0.3 0\n",
"130 7.4 2.8 6.1 1.9 2\n",
"121 5.6 2.8 4.9 2.0 2\n",
"20 5.4 3.4 1.7 0.2 0\n",
"122 7.7 2.8 6.7 2.0 2\n",
"43 5.0 3.5 1.6 0.6 0\n",
"148 6.2 3.4 5.4 2.3 2\n",
"112 6.8 3.0 5.5 2.1 2\n",
"134 6.1 2.6 5.6 1.4 2\n",
"18 5.7 3.8 1.7 0.3 0\n",
"140 6.7 3.1 5.6 2.4 2\n",
"47 4.6 3.2 1.4 0.2 0\n",
".. ... ... ... ... ..\n",
"43 5.0 3.5 1.6 0.6 0\n",
"39 5.1 3.4 1.5 0.2 0\n",
"113 5.7 2.5 5.0 2.0 2\n",
"1 4.9 3.0 1.4 0.2 0\n",
"142 5.8 2.7 5.1 1.9 2\n",
"45 4.8 3.0 1.4 0.3 0\n",
"16 5.4 3.9 1.3 0.4 0\n",
"39 5.1 3.4 1.5 0.2 0\n",
"28 5.2 3.4 1.4 0.2 0\n",
"7 5.0 3.4 1.5 0.2 0\n",
"121 5.6 2.8 4.9 2.0 2\n",
"128 6.4 2.8 5.6 2.1 2\n",
"128 6.4 2.8 5.6 2.1 2\n",
"46 5.1 3.8 1.6 0.2 0\n",
"25 5.0 3.0 1.6 0.2 0\n",
"140 6.7 3.1 5.6 2.4 2\n",
"121 5.6 2.8 4.9 2.0 2\n",
"137 6.4 3.1 5.5 1.8 2\n",
"0 5.1 3.5 1.4 0.2 0\n",
"46 5.1 3.8 1.6 0.2 0\n",
"140 6.7 3.1 5.6 2.4 2\n",
"45 4.8 3.0 1.4 0.3 0\n",
"29 4.7 3.2 1.6 0.2 0\n",
"15 5.7 4.4 1.5 0.4 0\n",
"20 5.4 3.4 1.7 0.2 0\n",
"136 6.3 3.4 5.6 2.4 2\n",
"33 5.5 4.2 1.4 0.2 0\n",
"36 5.5 3.5 1.3 0.2 0\n",
"146 6.3 2.5 5.0 1.9 2\n",
"44 5.1 3.8 1.9 0.4 0\n",
"\n",
"[75 rows x 5 columns]"
]
},
"execution_count": 74,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf[curdf['y'] != firsty]"
]
},
{
"cell_type": "code",
"execution_count": 75,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"75"
]
},
"execution_count": 75,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#これが0ならツリーの葉になる\n",
"len(curdf[curdf['y'] != firsty])"
]
},
{
"cell_type": "code",
"execution_count": 76,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"125"
]
},
"execution_count": 76,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# これがminnodesize以下なら葉になる\n",
"# あとはcur['level']がmaxlevel以上か\n",
"len(curdf)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"featurenum = 4"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([3, 2])"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tryfeatureids = np.random.randint(0, featurenum, size=numradfeatures)\n",
"tryfeatureids"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# for tryfid in tryfeatureids:\n",
"tryfid = tryfeatureids[0]"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([ 47, 21, 104, 91, 61])"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tryposes = np.random.randint(0, len(curdf), size=numrandpos)\n",
"tryposes"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# for trypos in tryposes\n",
"trypos = tryposes[0]"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"trydf = curdf.iloc[trypos]"
]
},
{
"cell_type": "code",
"execution_count": 119,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"x1 6.7\n",
"x2 3.0\n",
"x3 5.0\n",
"x4 1.7\n",
"y 1.0\n",
"Name: 77, dtype: float64"
]
},
"execution_count": 119,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"trydf"
]
},
{
"cell_type": "code",
"execution_count": 120,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"5.0"
]
},
"execution_count": 120,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"trydf[tryfid]"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"tryfval = trydf[tryfid]"
]
},
{
"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>0.2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>63</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>99</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>77</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>134</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>46</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>67</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>116</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>109</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>137</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>82</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>117</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>127</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>125</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>52</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>90</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>99</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>98</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>117</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>98</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>146</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>103</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>59</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>108</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>127</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>111</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>147</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>120</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>52</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>48</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>123</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>74</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>123</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>116</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>76</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>101</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>123</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>123</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>87</th>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>60</th>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>125 rows × 1 columns</p>\n",
"</div>"
],
"text/plain": [
" 0.2\n",
"63 False\n",
"99 False\n",
"77 False\n",
"22 True\n",
"134 False\n",
"31 True\n",
"46 True\n",
"67 False\n",
"116 False\n",
"109 False\n",
"2 True\n",
"13 True\n",
"137 False\n",
"82 False\n",
"117 False\n",
"127 False\n",
"125 False\n",
"52 False\n",
"9 True\n",
"7 True\n",
"90 False\n",
"99 False\n",
"98 False\n",
"13 True\n",
"117 False\n",
"21 True\n",
"98 False\n",
"146 False\n",
"103 False\n",
"10 True\n",
".. ...\n",
"6 True\n",
"31 True\n",
"59 False\n",
"108 False\n",
"41 True\n",
"104 False\n",
"127 False\n",
"20 True\n",
"45 True\n",
"111 False\n",
"147 False\n",
"1 True\n",
"44 True\n",
"120 False\n",
"52 False\n",
"45 True\n",
"48 True\n",
"123 False\n",
"74 False\n",
"123 False\n",
"5 True\n",
"121 False\n",
"116 False\n",
"76 False\n",
"101 False\n",
"84 False\n",
"123 False\n",
"123 False\n",
"87 False\n",
"60 False\n",
"\n",
"[125 rows x 1 columns]"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf[[tryfid]] < tryfval"
]
},
{
"cell_type": "code",
"execution_count": 126,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"issmaller = curdf[[tryfid]] < tryfval"
]
},
{
"cell_type": "code",
"execution_count": 127,
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>52</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.9</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.4</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>87</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.4</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>112</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>91</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.2</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>76</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.3</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>112</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.4</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>3.3</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>136</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>135</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>93</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>3.3</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.3</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>85</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.5</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.5</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.5</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>60</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>3.5</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.5</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>137</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>91</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>148</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.4</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>130</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>140</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>78</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.5</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>60</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>3.5</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>66</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.5</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.9</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>137</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>68</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.5</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>77</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.4</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>46</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>140</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.4</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>72</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.9</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.6</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.5</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.7</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>136</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.4</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>82</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>3.9</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>61</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.2</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.3</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>97</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.3</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>66</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.5</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.4</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>146</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>97</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.3</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.9</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.2</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>74</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.3</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>86</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.7</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>125 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"52 NaN NaN 4.9 NaN NaN\n",
"6 NaN NaN 1.4 NaN NaN\n",
"87 NaN NaN 4.4 NaN NaN\n",
"112 NaN NaN NaN NaN NaN\n",
"91 NaN NaN 4.6 NaN NaN\n",
"96 NaN NaN 4.2 NaN NaN\n",
"76 NaN NaN 4.8 NaN NaN\n",
"25 NaN NaN 1.6 NaN NaN\n",
"36 NaN NaN 1.3 NaN NaN\n",
"112 NaN NaN NaN NaN NaN\n",
"0 NaN NaN 1.4 NaN NaN\n",
"57 NaN NaN 3.3 NaN NaN\n",
"30 NaN NaN 1.6 NaN NaN\n",
"22 NaN NaN 1.0 NaN NaN\n",
"100 NaN NaN NaN NaN NaN\n",
"136 NaN NaN NaN NaN NaN\n",
"135 NaN NaN NaN NaN NaN\n",
"93 NaN NaN 3.3 NaN NaN\n",
"42 NaN NaN 1.3 NaN NaN\n",
"85 NaN NaN 4.5 NaN NaN\n",
"39 NaN NaN 1.5 NaN NaN\n",
"104 NaN NaN NaN NaN NaN\n",
"7 NaN NaN 1.5 NaN NaN\n",
"60 NaN NaN 3.5 NaN NaN\n",
"15 NaN NaN 1.5 NaN NaN\n",
"137 NaN NaN NaN NaN NaN\n",
"91 NaN NaN 4.6 NaN NaN\n",
"148 NaN NaN NaN NaN NaN\n",
"17 NaN NaN 1.4 NaN NaN\n",
"130 NaN NaN NaN NaN NaN\n",
".. .. .. ... .. ..\n",
"140 NaN NaN NaN NaN NaN\n",
"78 NaN NaN 4.5 NaN NaN\n",
"60 NaN NaN 3.5 NaN NaN\n",
"66 NaN NaN 4.5 NaN NaN\n",
"121 NaN NaN 4.9 NaN NaN\n",
"137 NaN NaN NaN NaN NaN\n",
"68 NaN NaN 4.5 NaN NaN\n",
"77 NaN NaN NaN NaN NaN\n",
"0 NaN NaN 1.4 NaN NaN\n",
"46 NaN NaN 1.6 NaN NaN\n",
"140 NaN NaN NaN NaN NaN\n",
"45 NaN NaN 1.4 NaN NaN\n",
"72 NaN NaN 4.9 NaN NaN\n",
"29 NaN NaN 1.6 NaN NaN\n",
"15 NaN NaN 1.5 NaN NaN\n",
"20 NaN NaN 1.7 NaN NaN\n",
"136 NaN NaN NaN NaN NaN\n",
"33 NaN NaN 1.4 NaN NaN\n",
"82 NaN NaN 3.9 NaN NaN\n",
"61 NaN NaN 4.2 NaN NaN\n",
"36 NaN NaN 1.3 NaN NaN\n",
"97 NaN NaN 4.3 NaN NaN\n",
"66 NaN NaN 4.5 NaN NaN\n",
"75 NaN NaN 4.4 NaN NaN\n",
"146 NaN NaN NaN NaN NaN\n",
"97 NaN NaN 4.3 NaN NaN\n",
"44 NaN NaN 1.9 NaN NaN\n",
"96 NaN NaN 4.2 NaN NaN\n",
"74 NaN NaN 4.3 NaN NaN\n",
"86 NaN NaN 4.7 NaN NaN\n",
"\n",
"[125 rows x 5 columns]"
]
},
"execution_count": 127,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf[issmaller]"
]
},
{
"cell_type": "code",
"execution_count": 129,
"metadata": {
"collapsed": false
},
"outputs": [
{
"ename": "KeyError",
"evalue": "2",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-129-621f4cd171ef>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mcurdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mcurdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mtryfid\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m<\u001b[0m \u001b[0mtryfval\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;32mC:\\Users\\_\\Anaconda2\\lib\\site-packages\\pandas\\core\\frame.pyc\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 1912\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_getitem_multilevel\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1913\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1914\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_getitem_column\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1915\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1916\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_getitem_column\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mC:\\Users\\_\\Anaconda2\\lib\\site-packages\\pandas\\core\\frame.pyc\u001b[0m in \u001b[0;36m_getitem_column\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 1919\u001b[0m \u001b[1;31m# get column\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1920\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mis_unique\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1921\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_item_cache\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1922\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1923\u001b[0m \u001b[1;31m# duplicate columns & possible reduce dimensionaility\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mC:\\Users\\_\\Anaconda2\\lib\\site-packages\\pandas\\core\\generic.pyc\u001b[0m in \u001b[0;36m_get_item_cache\u001b[1;34m(self, item)\u001b[0m\n\u001b[0;32m 1088\u001b[0m \u001b[0mres\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcache\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1089\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mres\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1090\u001b[1;33m \u001b[0mvalues\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_data\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1091\u001b[0m \u001b[0mres\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_box_item_values\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalues\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1092\u001b[0m \u001b[0mcache\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mitem\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mres\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mC:\\Users\\_\\Anaconda2\\lib\\site-packages\\pandas\\core\\internals.pyc\u001b[0m in \u001b[0;36mget\u001b[1;34m(self, item, fastpath)\u001b[0m\n\u001b[0;32m 3100\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3101\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0misnull\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3102\u001b[1;33m \u001b[0mloc\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 3103\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3104\u001b[0m \u001b[0mindexer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0marange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0misnull\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mC:\\Users\\_\\Anaconda2\\lib\\site-packages\\pandas\\core\\index.pyc\u001b[0m in \u001b[0;36mget_loc\u001b[1;34m(self, key, method, tolerance)\u001b[0m\n\u001b[0;32m 1690\u001b[0m raise ValueError('tolerance argument only valid if using pad, '\n\u001b[0;32m 1691\u001b[0m 'backfill or nearest lookups')\n\u001b[1;32m-> 1692\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m_values_from_object\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1693\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1694\u001b[0m indexer = self.get_indexer([key], method=method,\n",
"\u001b[1;32mpandas\\index.pyx\u001b[0m in \u001b[0;36mpandas.index.IndexEngine.get_loc (pandas\\index.c:3979)\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\index.pyx\u001b[0m in \u001b[0;36mpandas.index.IndexEngine.get_loc (pandas\\index.c:3843)\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\hashtable.pyx\u001b[0m in \u001b[0;36mpandas.hashtable.PyObjectHashTable.get_item (pandas\\hashtable.c:12265)\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\hashtable.pyx\u001b[0m in \u001b[0;36mpandas.hashtable.PyObjectHashTable.get_item (pandas\\hashtable.c:12216)\u001b[1;34m()\u001b[0m\n",
"\u001b[1;31mKeyError\u001b[0m: 2"
]
}
],
"source": [
"curdf[curdf[tryfid] < tryfval]"
]
},
{
"cell_type": "code",
"execution_count": 130,
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>52</th>\n",
" <td>6.9</td>\n",
" <td>3.1</td>\n",
" <td>4.9</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"52 6.9 3.1 4.9 1.5 1"
]
},
"execution_count": 130,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf[0:1]"
]
},
{
"cell_type": "code",
"execution_count": 131,
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>4.6</td>\n",
" <td>3.4</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
" <td>4.9</td>\n",
" <td>2.4</td>\n",
" <td>3.3</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>4.8</td>\n",
" <td>3.1</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>4.6</td>\n",
" <td>3.6</td>\n",
" <td>1.0</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td>4.4</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>47</th>\n",
" <td>4.6</td>\n",
" <td>3.2</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>4.8</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>47</th>\n",
" <td>4.6</td>\n",
" <td>3.2</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.9</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
" <td>4.9</td>\n",
" <td>2.4</td>\n",
" <td>3.3</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>4.8</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>4.8</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"6 4.6 3.4 1.4 0.3 0\n",
"57 4.9 2.4 3.3 1.0 1\n",
"30 4.8 3.1 1.6 0.2 0\n",
"22 4.6 3.6 1.0 0.2 0\n",
"42 4.4 3.2 1.3 0.2 0\n",
"47 4.6 3.2 1.4 0.2 0\n",
"12 4.8 3.0 1.4 0.1 0\n",
"47 4.6 3.2 1.4 0.2 0\n",
"1 4.9 3.0 1.4 0.2 0\n",
"57 4.9 2.4 3.3 1.0 1\n",
"45 4.8 3.0 1.4 0.3 0\n",
"45 4.8 3.0 1.4 0.3 0\n",
"29 4.7 3.2 1.6 0.2 0"
]
},
"execution_count": 131,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf[curdf['x1'] < 5]"
]
},
{
"cell_type": "code",
"execution_count": 132,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"2"
]
},
"execution_count": 132,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tryfid"
]
},
{
"cell_type": "code",
"execution_count": 133,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'x3'"
]
},
"execution_count": 133,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf.columns[tryfid]"
]
},
{
"cell_type": "code",
"execution_count": 72,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"tryfname = curdf.columns[tryfid]"
]
},
{
"cell_type": "code",
"execution_count": 135,
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>52</th>\n",
" <td>6.9</td>\n",
" <td>3.1</td>\n",
" <td>4.9</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>4.6</td>\n",
" <td>3.4</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>87</th>\n",
" <td>6.3</td>\n",
" <td>2.3</td>\n",
" <td>4.4</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>91</th>\n",
" <td>6.1</td>\n",
" <td>3.0</td>\n",
" <td>4.6</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
" <td>5.7</td>\n",
" <td>2.9</td>\n",
" <td>4.2</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>76</th>\n",
" <td>6.8</td>\n",
" <td>2.8</td>\n",
" <td>4.8</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>5.5</td>\n",
" <td>3.5</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
" <td>4.9</td>\n",
" <td>2.4</td>\n",
" <td>3.3</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>4.8</td>\n",
" <td>3.1</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>4.6</td>\n",
" <td>3.6</td>\n",
" <td>1.0</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>93</th>\n",
" <td>5.0</td>\n",
" <td>2.3</td>\n",
" <td>3.3</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td>4.4</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>85</th>\n",
" <td>6.0</td>\n",
" <td>3.4</td>\n",
" <td>4.5</td>\n",
" <td>1.6</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>5.1</td>\n",
" <td>3.4</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>5.0</td>\n",
" <td>3.4</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>60</th>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>3.5</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>5.7</td>\n",
" <td>4.4</td>\n",
" <td>1.5</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>91</th>\n",
" <td>6.1</td>\n",
" <td>3.0</td>\n",
" <td>4.6</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
" <td>5.7</td>\n",
" <td>2.9</td>\n",
" <td>4.2</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>5.6</td>\n",
" <td>2.8</td>\n",
" <td>4.9</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>5.4</td>\n",
" <td>3.4</td>\n",
" <td>1.7</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>43</th>\n",
" <td>5.0</td>\n",
" <td>3.5</td>\n",
" <td>1.6</td>\n",
" <td>0.6</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>5.7</td>\n",
" <td>3.8</td>\n",
" <td>1.7</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>47</th>\n",
" <td>4.6</td>\n",
" <td>3.2</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>5.6</td>\n",
" <td>2.8</td>\n",
" <td>4.9</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>80</th>\n",
" <td>5.5</td>\n",
" <td>2.4</td>\n",
" <td>3.8</td>\n",
" <td>1.1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>56</th>\n",
" <td>6.3</td>\n",
" <td>3.3</td>\n",
" <td>4.7</td>\n",
" <td>1.6</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>5.2</td>\n",
" <td>3.4</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>5.0</td>\n",
" <td>3.4</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>5.6</td>\n",
" <td>2.8</td>\n",
" <td>4.9</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>61</th>\n",
" <td>5.9</td>\n",
" <td>3.0</td>\n",
" <td>4.2</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>46</th>\n",
" <td>5.1</td>\n",
" <td>3.8</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>78</th>\n",
" <td>6.0</td>\n",
" <td>2.9</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>60</th>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>3.5</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>66</th>\n",
" <td>5.6</td>\n",
" <td>3.0</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>5.6</td>\n",
" <td>2.8</td>\n",
" <td>4.9</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>68</th>\n",
" <td>6.2</td>\n",
" <td>2.2</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>46</th>\n",
" <td>5.1</td>\n",
" <td>3.8</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>4.8</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>72</th>\n",
" <td>6.3</td>\n",
" <td>2.5</td>\n",
" <td>4.9</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>5.7</td>\n",
" <td>4.4</td>\n",
" <td>1.5</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>5.4</td>\n",
" <td>3.4</td>\n",
" <td>1.7</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>5.5</td>\n",
" <td>4.2</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>82</th>\n",
" <td>5.8</td>\n",
" <td>2.7</td>\n",
" <td>3.9</td>\n",
" <td>1.2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>61</th>\n",
" <td>5.9</td>\n",
" <td>3.0</td>\n",
" <td>4.2</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>5.5</td>\n",
" <td>3.5</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>97</th>\n",
" <td>6.2</td>\n",
" <td>2.9</td>\n",
" <td>4.3</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>66</th>\n",
" <td>5.6</td>\n",
" <td>3.0</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75</th>\n",
" <td>6.6</td>\n",
" <td>3.0</td>\n",
" <td>4.4</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>97</th>\n",
" <td>6.2</td>\n",
" <td>2.9</td>\n",
" <td>4.3</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
" <td>5.1</td>\n",
" <td>3.8</td>\n",
" <td>1.9</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
" <td>5.7</td>\n",
" <td>2.9</td>\n",
" <td>4.2</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>74</th>\n",
" <td>6.4</td>\n",
" <td>2.9</td>\n",
" <td>4.3</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>86</th>\n",
" <td>6.7</td>\n",
" <td>3.1</td>\n",
" <td>4.7</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>92 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"52 6.9 3.1 4.9 1.5 1\n",
"6 4.6 3.4 1.4 0.3 0\n",
"87 6.3 2.3 4.4 1.3 1\n",
"91 6.1 3.0 4.6 1.4 1\n",
"96 5.7 2.9 4.2 1.3 1\n",
"76 6.8 2.8 4.8 1.4 1\n",
"25 5.0 3.0 1.6 0.2 0\n",
"36 5.5 3.5 1.3 0.2 0\n",
"0 5.1 3.5 1.4 0.2 0\n",
"57 4.9 2.4 3.3 1.0 1\n",
"30 4.8 3.1 1.6 0.2 0\n",
"22 4.6 3.6 1.0 0.2 0\n",
"93 5.0 2.3 3.3 1.0 1\n",
"42 4.4 3.2 1.3 0.2 0\n",
"85 6.0 3.4 4.5 1.6 1\n",
"39 5.1 3.4 1.5 0.2 0\n",
"7 5.0 3.4 1.5 0.2 0\n",
"60 5.0 2.0 3.5 1.0 1\n",
"15 5.7 4.4 1.5 0.4 0\n",
"91 6.1 3.0 4.6 1.4 1\n",
"17 5.1 3.5 1.4 0.3 0\n",
"96 5.7 2.9 4.2 1.3 1\n",
"121 5.6 2.8 4.9 2.0 2\n",
"20 5.4 3.4 1.7 0.2 0\n",
"43 5.0 3.5 1.6 0.6 0\n",
"18 5.7 3.8 1.7 0.3 0\n",
"47 4.6 3.2 1.4 0.2 0\n",
"121 5.6 2.8 4.9 2.0 2\n",
"80 5.5 2.4 3.8 1.1 1\n",
"56 6.3 3.3 4.7 1.6 1\n",
".. ... ... ... ... ..\n",
"28 5.2 3.4 1.4 0.2 0\n",
"7 5.0 3.4 1.5 0.2 0\n",
"121 5.6 2.8 4.9 2.0 2\n",
"61 5.9 3.0 4.2 1.5 1\n",
"46 5.1 3.8 1.6 0.2 0\n",
"25 5.0 3.0 1.6 0.2 0\n",
"78 6.0 2.9 4.5 1.5 1\n",
"60 5.0 2.0 3.5 1.0 1\n",
"66 5.6 3.0 4.5 1.5 1\n",
"121 5.6 2.8 4.9 2.0 2\n",
"68 6.2 2.2 4.5 1.5 1\n",
"0 5.1 3.5 1.4 0.2 0\n",
"46 5.1 3.8 1.6 0.2 0\n",
"45 4.8 3.0 1.4 0.3 0\n",
"72 6.3 2.5 4.9 1.5 1\n",
"29 4.7 3.2 1.6 0.2 0\n",
"15 5.7 4.4 1.5 0.4 0\n",
"20 5.4 3.4 1.7 0.2 0\n",
"33 5.5 4.2 1.4 0.2 0\n",
"82 5.8 2.7 3.9 1.2 1\n",
"61 5.9 3.0 4.2 1.5 1\n",
"36 5.5 3.5 1.3 0.2 0\n",
"97 6.2 2.9 4.3 1.3 1\n",
"66 5.6 3.0 4.5 1.5 1\n",
"75 6.6 3.0 4.4 1.4 1\n",
"97 6.2 2.9 4.3 1.3 1\n",
"44 5.1 3.8 1.9 0.4 0\n",
"96 5.7 2.9 4.2 1.3 1\n",
"74 6.4 2.9 4.3 1.3 1\n",
"86 6.7 3.1 4.7 1.5 1\n",
"\n",
"[92 rows x 5 columns]"
]
},
"execution_count": 135,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf[curdf[tryfname] < tryfval]"
]
},
{
"cell_type": "code",
"execution_count": 136,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"52 True\n",
"6 True\n",
"87 True\n",
"112 False\n",
"91 True\n",
"96 True\n",
"76 True\n",
"25 True\n",
"36 True\n",
"112 False\n",
"0 True\n",
"57 True\n",
"30 True\n",
"22 True\n",
"100 False\n",
"136 False\n",
"135 False\n",
"93 True\n",
"42 True\n",
"85 True\n",
"39 True\n",
"104 False\n",
"7 True\n",
"60 True\n",
"15 True\n",
"137 False\n",
"91 True\n",
"148 False\n",
"17 True\n",
"130 False\n",
" ... \n",
"140 False\n",
"78 True\n",
"60 True\n",
"66 True\n",
"121 True\n",
"137 False\n",
"68 True\n",
"77 False\n",
"0 True\n",
"46 True\n",
"140 False\n",
"45 True\n",
"72 True\n",
"29 True\n",
"15 True\n",
"20 True\n",
"136 False\n",
"33 True\n",
"82 True\n",
"61 True\n",
"36 True\n",
"97 True\n",
"66 True\n",
"75 True\n",
"146 False\n",
"97 True\n",
"44 True\n",
"96 True\n",
"74 True\n",
"86 True\n",
"Name: x3, dtype: bool"
]
},
"execution_count": 136,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf[tryfname] < tryfval"
]
},
{
"cell_type": "code",
"execution_count": 73,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"curdf[\"isleft\"] = curdf[tryfname] < tryfval"
]
},
{
"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>5.1</th>\n",
" <th>3.5</th>\n",
" <th>1.4</th>\n",
" <th>0.2</th>\n",
" <th>0</th>\n",
" <th>isleft</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>63</th>\n",
" <td>5.6</td>\n",
" <td>2.9</td>\n",
" <td>3.6</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>99</th>\n",
" <td>6.3</td>\n",
" <td>3.3</td>\n",
" <td>6.0</td>\n",
" <td>2.5</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>77</th>\n",
" <td>6.0</td>\n",
" <td>2.9</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>5.1</td>\n",
" <td>3.3</td>\n",
" <td>1.7</td>\n",
" <td>0.5</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>134</th>\n",
" <td>7.7</td>\n",
" <td>3.0</td>\n",
" <td>6.1</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>5.2</td>\n",
" <td>4.1</td>\n",
" <td>1.5</td>\n",
" <td>0.1</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>46</th>\n",
" <td>4.6</td>\n",
" <td>3.2</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>67</th>\n",
" <td>6.2</td>\n",
" <td>2.2</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>116</th>\n",
" <td>7.7</td>\n",
" <td>3.8</td>\n",
" <td>6.7</td>\n",
" <td>2.2</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>109</th>\n",
" <td>6.5</td>\n",
" <td>3.2</td>\n",
" <td>5.1</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.6</td>\n",
" <td>3.1</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>5.8</td>\n",
" <td>4.0</td>\n",
" <td>1.2</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>137</th>\n",
" <td>6.0</td>\n",
" <td>3.0</td>\n",
" <td>4.8</td>\n",
" <td>1.8</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>82</th>\n",
" <td>6.0</td>\n",
" <td>2.7</td>\n",
" <td>5.1</td>\n",
" <td>1.6</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>117</th>\n",
" <td>7.7</td>\n",
" <td>2.6</td>\n",
" <td>6.9</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>127</th>\n",
" <td>6.4</td>\n",
" <td>2.8</td>\n",
" <td>5.6</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>125</th>\n",
" <td>6.2</td>\n",
" <td>2.8</td>\n",
" <td>4.8</td>\n",
" <td>1.8</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>52</th>\n",
" <td>5.5</td>\n",
" <td>2.3</td>\n",
" <td>4.0</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>5.4</td>\n",
" <td>3.7</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>4.4</td>\n",
" <td>2.9</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>90</th>\n",
" <td>6.1</td>\n",
" <td>3.0</td>\n",
" <td>4.6</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>99</th>\n",
" <td>6.3</td>\n",
" <td>3.3</td>\n",
" <td>6.0</td>\n",
" <td>2.5</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>98</th>\n",
" <td>5.7</td>\n",
" <td>2.8</td>\n",
" <td>4.1</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>5.8</td>\n",
" <td>4.0</td>\n",
" <td>1.2</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>117</th>\n",
" <td>7.7</td>\n",
" <td>2.6</td>\n",
" <td>6.9</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>4.6</td>\n",
" <td>3.6</td>\n",
" <td>1.0</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>98</th>\n",
" <td>5.7</td>\n",
" <td>2.8</td>\n",
" <td>4.1</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>146</th>\n",
" <td>6.5</td>\n",
" <td>3.0</td>\n",
" <td>5.2</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>103</th>\n",
" <td>6.5</td>\n",
" <td>3.0</td>\n",
" <td>5.8</td>\n",
" <td>2.2</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>4.8</td>\n",
" <td>3.4</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>5.0</td>\n",
" <td>3.4</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>5.2</td>\n",
" <td>4.1</td>\n",
" <td>1.5</td>\n",
" <td>0.1</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>59</th>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>3.5</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>108</th>\n",
" <td>7.2</td>\n",
" <td>3.6</td>\n",
" <td>6.1</td>\n",
" <td>2.5</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>41</th>\n",
" <td>4.4</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104</th>\n",
" <td>7.6</td>\n",
" <td>3.0</td>\n",
" <td>6.6</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>127</th>\n",
" <td>6.4</td>\n",
" <td>2.8</td>\n",
" <td>5.6</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>5.1</td>\n",
" <td>3.7</td>\n",
" <td>1.5</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>5.1</td>\n",
" <td>3.8</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>111</th>\n",
" <td>6.8</td>\n",
" <td>3.0</td>\n",
" <td>5.5</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>147</th>\n",
" <td>6.2</td>\n",
" <td>3.4</td>\n",
" <td>5.4</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
" <td>4.8</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>120</th>\n",
" <td>5.6</td>\n",
" <td>2.8</td>\n",
" <td>4.9</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>52</th>\n",
" <td>5.5</td>\n",
" <td>2.3</td>\n",
" <td>4.0</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>5.1</td>\n",
" <td>3.8</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>48</th>\n",
" <td>5.0</td>\n",
" <td>3.3</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>123</th>\n",
" <td>6.7</td>\n",
" <td>3.3</td>\n",
" <td>5.7</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>74</th>\n",
" <td>6.6</td>\n",
" <td>3.0</td>\n",
" <td>4.4</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>123</th>\n",
" <td>6.7</td>\n",
" <td>3.3</td>\n",
" <td>5.7</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>4.6</td>\n",
" <td>3.4</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>7.7</td>\n",
" <td>2.8</td>\n",
" <td>6.7</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>116</th>\n",
" <td>7.7</td>\n",
" <td>3.8</td>\n",
" <td>6.7</td>\n",
" <td>2.2</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>76</th>\n",
" <td>6.7</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>1.7</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>101</th>\n",
" <td>7.1</td>\n",
" <td>3.0</td>\n",
" <td>5.9</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84</th>\n",
" <td>6.0</td>\n",
" <td>3.4</td>\n",
" <td>4.5</td>\n",
" <td>1.6</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>123</th>\n",
" <td>6.7</td>\n",
" <td>3.3</td>\n",
" <td>5.7</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>123</th>\n",
" <td>6.7</td>\n",
" <td>3.3</td>\n",
" <td>5.7</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>87</th>\n",
" <td>5.6</td>\n",
" <td>3.0</td>\n",
" <td>4.1</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>60</th>\n",
" <td>5.9</td>\n",
" <td>3.0</td>\n",
" <td>4.2</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>125 rows × 6 columns</p>\n",
"</div>"
],
"text/plain": [
" 5.1 3.5 1.4 0.2 0 isleft\n",
"63 5.6 2.9 3.6 1.3 1 False\n",
"99 6.3 3.3 6.0 2.5 2 False\n",
"77 6.0 2.9 4.5 1.5 1 False\n",
"22 5.1 3.3 1.7 0.5 0 True\n",
"134 7.7 3.0 6.1 2.3 2 False\n",
"31 5.2 4.1 1.5 0.1 0 True\n",
"46 4.6 3.2 1.4 0.2 0 True\n",
"67 6.2 2.2 4.5 1.5 1 False\n",
"116 7.7 3.8 6.7 2.2 2 False\n",
"109 6.5 3.2 5.1 2.0 2 False\n",
"2 4.6 3.1 1.5 0.2 0 True\n",
"13 5.8 4.0 1.2 0.2 0 True\n",
"137 6.0 3.0 4.8 1.8 2 False\n",
"82 6.0 2.7 5.1 1.6 1 False\n",
"117 7.7 2.6 6.9 2.3 2 False\n",
"127 6.4 2.8 5.6 2.1 2 False\n",
"125 6.2 2.8 4.8 1.8 2 False\n",
"52 5.5 2.3 4.0 1.3 1 False\n",
"9 5.4 3.7 1.5 0.2 0 True\n",
"7 4.4 2.9 1.4 0.2 0 True\n",
"90 6.1 3.0 4.6 1.4 1 False\n",
"99 6.3 3.3 6.0 2.5 2 False\n",
"98 5.7 2.8 4.1 1.3 1 False\n",
"13 5.8 4.0 1.2 0.2 0 True\n",
"117 7.7 2.6 6.9 2.3 2 False\n",
"21 4.6 3.6 1.0 0.2 0 True\n",
"98 5.7 2.8 4.1 1.3 1 False\n",
"146 6.5 3.0 5.2 2.0 2 False\n",
"103 6.5 3.0 5.8 2.2 2 False\n",
"10 4.8 3.4 1.6 0.2 0 True\n",
".. ... ... ... ... .. ...\n",
"6 5.0 3.4 1.5 0.2 0 True\n",
"31 5.2 4.1 1.5 0.1 0 True\n",
"59 5.0 2.0 3.5 1.0 1 False\n",
"108 7.2 3.6 6.1 2.5 2 False\n",
"41 4.4 3.2 1.3 0.2 0 True\n",
"104 7.6 3.0 6.6 2.1 2 False\n",
"127 6.4 2.8 5.6 2.1 2 False\n",
"20 5.1 3.7 1.5 0.4 0 True\n",
"45 5.1 3.8 1.6 0.2 0 True\n",
"111 6.8 3.0 5.5 2.1 2 False\n",
"147 6.2 3.4 5.4 2.3 2 False\n",
"1 4.7 3.2 1.3 0.2 0 True\n",
"44 4.8 3.0 1.4 0.3 0 True\n",
"120 5.6 2.8 4.9 2.0 2 False\n",
"52 5.5 2.3 4.0 1.3 1 False\n",
"45 5.1 3.8 1.6 0.2 0 True\n",
"48 5.0 3.3 1.4 0.2 0 True\n",
"123 6.7 3.3 5.7 2.1 2 False\n",
"74 6.6 3.0 4.4 1.4 1 False\n",
"123 6.7 3.3 5.7 2.1 2 False\n",
"5 4.6 3.4 1.4 0.3 0 True\n",
"121 7.7 2.8 6.7 2.0 2 False\n",
"116 7.7 3.8 6.7 2.2 2 False\n",
"76 6.7 3.0 5.0 1.7 1 False\n",
"101 7.1 3.0 5.9 2.1 2 False\n",
"84 6.0 3.4 4.5 1.6 1 False\n",
"123 6.7 3.3 5.7 2.1 2 False\n",
"123 6.7 3.3 5.7 2.1 2 False\n",
"87 5.6 3.0 4.1 1.3 1 False\n",
"60 5.9 3.0 4.2 1.5 1 False\n",
"\n",
"[125 rows x 6 columns]"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf.copy()"
]
},
{
"cell_type": "code",
"execution_count": 140,
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" <th>isleft</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>52</th>\n",
" <td>6.9</td>\n",
" <td>3.1</td>\n",
" <td>4.9</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>4.6</td>\n",
" <td>3.4</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>87</th>\n",
" <td>6.3</td>\n",
" <td>2.3</td>\n",
" <td>4.4</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>112</th>\n",
" <td>6.8</td>\n",
" <td>3.0</td>\n",
" <td>5.5</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>91</th>\n",
" <td>6.1</td>\n",
" <td>3.0</td>\n",
" <td>4.6</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
" <td>5.7</td>\n",
" <td>2.9</td>\n",
" <td>4.2</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>76</th>\n",
" <td>6.8</td>\n",
" <td>2.8</td>\n",
" <td>4.8</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>5.5</td>\n",
" <td>3.5</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>112</th>\n",
" <td>6.8</td>\n",
" <td>3.0</td>\n",
" <td>5.5</td>\n",
" <td>2.1</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>57</th>\n",
" <td>4.9</td>\n",
" <td>2.4</td>\n",
" <td>3.3</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>4.8</td>\n",
" <td>3.1</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>4.6</td>\n",
" <td>3.6</td>\n",
" <td>1.0</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100</th>\n",
" <td>6.3</td>\n",
" <td>3.3</td>\n",
" <td>6.0</td>\n",
" <td>2.5</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>136</th>\n",
" <td>6.3</td>\n",
" <td>3.4</td>\n",
" <td>5.6</td>\n",
" <td>2.4</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>135</th>\n",
" <td>7.7</td>\n",
" <td>3.0</td>\n",
" <td>6.1</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>93</th>\n",
" <td>5.0</td>\n",
" <td>2.3</td>\n",
" <td>3.3</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>42</th>\n",
" <td>4.4</td>\n",
" <td>3.2</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>85</th>\n",
" <td>6.0</td>\n",
" <td>3.4</td>\n",
" <td>4.5</td>\n",
" <td>1.6</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>39</th>\n",
" <td>5.1</td>\n",
" <td>3.4</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>104</th>\n",
" <td>6.5</td>\n",
" <td>3.0</td>\n",
" <td>5.8</td>\n",
" <td>2.2</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>5.0</td>\n",
" <td>3.4</td>\n",
" <td>1.5</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>60</th>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>3.5</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>5.7</td>\n",
" <td>4.4</td>\n",
" <td>1.5</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>137</th>\n",
" <td>6.4</td>\n",
" <td>3.1</td>\n",
" <td>5.5</td>\n",
" <td>1.8</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>91</th>\n",
" <td>6.1</td>\n",
" <td>3.0</td>\n",
" <td>4.6</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>148</th>\n",
" <td>6.2</td>\n",
" <td>3.4</td>\n",
" <td>5.4</td>\n",
" <td>2.3</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>130</th>\n",
" <td>7.4</td>\n",
" <td>2.8</td>\n",
" <td>6.1</td>\n",
" <td>1.9</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>140</th>\n",
" <td>6.7</td>\n",
" <td>3.1</td>\n",
" <td>5.6</td>\n",
" <td>2.4</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>78</th>\n",
" <td>6.0</td>\n",
" <td>2.9</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>60</th>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>3.5</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>66</th>\n",
" <td>5.6</td>\n",
" <td>3.0</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>5.6</td>\n",
" <td>2.8</td>\n",
" <td>4.9</td>\n",
" <td>2.0</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>137</th>\n",
" <td>6.4</td>\n",
" <td>3.1</td>\n",
" <td>5.5</td>\n",
" <td>1.8</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>68</th>\n",
" <td>6.2</td>\n",
" <td>2.2</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>77</th>\n",
" <td>6.7</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>1.7</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5.1</td>\n",
" <td>3.5</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>46</th>\n",
" <td>5.1</td>\n",
" <td>3.8</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>140</th>\n",
" <td>6.7</td>\n",
" <td>3.1</td>\n",
" <td>5.6</td>\n",
" <td>2.4</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>45</th>\n",
" <td>4.8</td>\n",
" <td>3.0</td>\n",
" <td>1.4</td>\n",
" <td>0.3</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>72</th>\n",
" <td>6.3</td>\n",
" <td>2.5</td>\n",
" <td>4.9</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>4.7</td>\n",
" <td>3.2</td>\n",
" <td>1.6</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>5.7</td>\n",
" <td>4.4</td>\n",
" <td>1.5</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>5.4</td>\n",
" <td>3.4</td>\n",
" <td>1.7</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>136</th>\n",
" <td>6.3</td>\n",
" <td>3.4</td>\n",
" <td>5.6</td>\n",
" <td>2.4</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>5.5</td>\n",
" <td>4.2</td>\n",
" <td>1.4</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>82</th>\n",
" <td>5.8</td>\n",
" <td>2.7</td>\n",
" <td>3.9</td>\n",
" <td>1.2</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>61</th>\n",
" <td>5.9</td>\n",
" <td>3.0</td>\n",
" <td>4.2</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>5.5</td>\n",
" <td>3.5</td>\n",
" <td>1.3</td>\n",
" <td>0.2</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>97</th>\n",
" <td>6.2</td>\n",
" <td>2.9</td>\n",
" <td>4.3</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>66</th>\n",
" <td>5.6</td>\n",
" <td>3.0</td>\n",
" <td>4.5</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75</th>\n",
" <td>6.6</td>\n",
" <td>3.0</td>\n",
" <td>4.4</td>\n",
" <td>1.4</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>146</th>\n",
" <td>6.3</td>\n",
" <td>2.5</td>\n",
" <td>5.0</td>\n",
" <td>1.9</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>97</th>\n",
" <td>6.2</td>\n",
" <td>2.9</td>\n",
" <td>4.3</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>44</th>\n",
" <td>5.1</td>\n",
" <td>3.8</td>\n",
" <td>1.9</td>\n",
" <td>0.4</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
" <td>5.7</td>\n",
" <td>2.9</td>\n",
" <td>4.2</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>74</th>\n",
" <td>6.4</td>\n",
" <td>2.9</td>\n",
" <td>4.3</td>\n",
" <td>1.3</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>86</th>\n",
" <td>6.7</td>\n",
" <td>3.1</td>\n",
" <td>4.7</td>\n",
" <td>1.5</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>125 rows × 6 columns</p>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y isleft\n",
"52 6.9 3.1 4.9 1.5 1 True\n",
"6 4.6 3.4 1.4 0.3 0 True\n",
"87 6.3 2.3 4.4 1.3 1 True\n",
"112 6.8 3.0 5.5 2.1 2 False\n",
"91 6.1 3.0 4.6 1.4 1 True\n",
"96 5.7 2.9 4.2 1.3 1 True\n",
"76 6.8 2.8 4.8 1.4 1 True\n",
"25 5.0 3.0 1.6 0.2 0 True\n",
"36 5.5 3.5 1.3 0.2 0 True\n",
"112 6.8 3.0 5.5 2.1 2 False\n",
"0 5.1 3.5 1.4 0.2 0 True\n",
"57 4.9 2.4 3.3 1.0 1 True\n",
"30 4.8 3.1 1.6 0.2 0 True\n",
"22 4.6 3.6 1.0 0.2 0 True\n",
"100 6.3 3.3 6.0 2.5 2 False\n",
"136 6.3 3.4 5.6 2.4 2 False\n",
"135 7.7 3.0 6.1 2.3 2 False\n",
"93 5.0 2.3 3.3 1.0 1 True\n",
"42 4.4 3.2 1.3 0.2 0 True\n",
"85 6.0 3.4 4.5 1.6 1 True\n",
"39 5.1 3.4 1.5 0.2 0 True\n",
"104 6.5 3.0 5.8 2.2 2 False\n",
"7 5.0 3.4 1.5 0.2 0 True\n",
"60 5.0 2.0 3.5 1.0 1 True\n",
"15 5.7 4.4 1.5 0.4 0 True\n",
"137 6.4 3.1 5.5 1.8 2 False\n",
"91 6.1 3.0 4.6 1.4 1 True\n",
"148 6.2 3.4 5.4 2.3 2 False\n",
"17 5.1 3.5 1.4 0.3 0 True\n",
"130 7.4 2.8 6.1 1.9 2 False\n",
".. ... ... ... ... .. ...\n",
"140 6.7 3.1 5.6 2.4 2 False\n",
"78 6.0 2.9 4.5 1.5 1 True\n",
"60 5.0 2.0 3.5 1.0 1 True\n",
"66 5.6 3.0 4.5 1.5 1 True\n",
"121 5.6 2.8 4.9 2.0 2 True\n",
"137 6.4 3.1 5.5 1.8 2 False\n",
"68 6.2 2.2 4.5 1.5 1 True\n",
"77 6.7 3.0 5.0 1.7 1 False\n",
"0 5.1 3.5 1.4 0.2 0 True\n",
"46 5.1 3.8 1.6 0.2 0 True\n",
"140 6.7 3.1 5.6 2.4 2 False\n",
"45 4.8 3.0 1.4 0.3 0 True\n",
"72 6.3 2.5 4.9 1.5 1 True\n",
"29 4.7 3.2 1.6 0.2 0 True\n",
"15 5.7 4.4 1.5 0.4 0 True\n",
"20 5.4 3.4 1.7 0.2 0 True\n",
"136 6.3 3.4 5.6 2.4 2 False\n",
"33 5.5 4.2 1.4 0.2 0 True\n",
"82 5.8 2.7 3.9 1.2 1 True\n",
"61 5.9 3.0 4.2 1.5 1 True\n",
"36 5.5 3.5 1.3 0.2 0 True\n",
"97 6.2 2.9 4.3 1.3 1 True\n",
"66 5.6 3.0 4.5 1.5 1 True\n",
"75 6.6 3.0 4.4 1.4 1 True\n",
"146 6.3 2.5 5.0 1.9 2 False\n",
"97 6.2 2.9 4.3 1.3 1 True\n",
"44 5.1 3.8 1.9 0.4 0 True\n",
"96 5.7 2.9 4.2 1.3 1 True\n",
"74 6.4 2.9 4.3 1.3 1 True\n",
"86 6.7 3.1 4.7 1.5 1 True\n",
"\n",
"[125 rows x 6 columns]"
]
},
"execution_count": 140,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf"
]
},
{
"cell_type": "code",
"execution_count": 74,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"isleft = curdf['isleft'].copy()"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"63 False\n",
"99 False\n",
"77 False\n",
"22 True\n",
"134 False\n",
"31 True\n",
"46 True\n",
"67 False\n",
"116 False\n",
"109 False\n",
"2 True\n",
"13 True\n",
"137 False\n",
"82 False\n",
"117 False\n",
"127 False\n",
"125 False\n",
"52 False\n",
"9 True\n",
"7 True\n",
"90 False\n",
"99 False\n",
"98 False\n",
"13 True\n",
"117 False\n",
"21 True\n",
"98 False\n",
"146 False\n",
"103 False\n",
"10 True\n",
" ... \n",
"6 True\n",
"31 True\n",
"59 False\n",
"108 False\n",
"41 True\n",
"104 False\n",
"127 False\n",
"20 True\n",
"45 True\n",
"111 False\n",
"147 False\n",
"1 True\n",
"44 True\n",
"120 False\n",
"52 False\n",
"45 True\n",
"48 True\n",
"123 False\n",
"74 False\n",
"123 False\n",
"5 True\n",
"121 False\n",
"116 False\n",
"76 False\n",
"101 False\n",
"84 False\n",
"123 False\n",
"123 False\n",
"87 False\n",
"60 False\n",
"Name: isleft, dtype: bool"
]
},
"execution_count": 59,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"isleft"
]
},
{
"cell_type": "code",
"execution_count": 70,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"curdf = curdf.copy()"
]
},
{
"cell_type": "code",
"execution_count": 58,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"curdf['isleft'] = True"
]
},
{
"cell_type": "code",
"execution_count": 142,
"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>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" <th>y</th>\n",
" </tr>\n",
" <tr>\n",
" <th>isleft</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>False</th>\n",
" <td>33</td>\n",
" <td>33</td>\n",
" <td>33</td>\n",
" <td>33</td>\n",
" <td>33</td>\n",
" </tr>\n",
" <tr>\n",
" <th>True</th>\n",
" <td>92</td>\n",
" <td>92</td>\n",
" <td>92</td>\n",
" <td>92</td>\n",
" <td>92</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4 y\n",
"isleft \n",
"False 33 33 33 33 33\n",
"True 92 92 92 92 92"
]
},
"execution_count": 142,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf.groupby('isleft').count()"
]
},
{
"cell_type": "code",
"execution_count": 146,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"isleft\n",
"False 33\n",
"True 92\n",
"dtype: int64"
]
},
"execution_count": 146,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf[tryfname].groupby(curdf['isleft']).count()"
]
},
{
"cell_type": "code",
"execution_count": 148,
"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></th>\n",
" <th>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" </tr>\n",
" <tr>\n",
" <th>isleft</th>\n",
" <th>y</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">False</th>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>31</td>\n",
" <td>31</td>\n",
" <td>31</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"3\" valign=\"top\">True</th>\n",
" <th>0</th>\n",
" <td>40</td>\n",
" <td>40</td>\n",
" <td>40</td>\n",
" <td>40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>48</td>\n",
" <td>48</td>\n",
" <td>48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4\n",
"isleft y \n",
"False 1 2 2 2 2\n",
" 2 31 31 31 31\n",
"True 0 40 40 40 40\n",
" 1 48 48 48 48\n",
" 2 4 4 4 4"
]
},
"execution_count": 148,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf.groupby(['isleft', 'y']).count()"
]
},
{
"cell_type": "code",
"execution_count": 149,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"isleft y\n",
"False 1 2\n",
" 2 31\n",
"True 0 40\n",
" 1 48\n",
" 2 4\n",
"Name: x1, dtype: int64"
]
},
"execution_count": 149,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf.groupby(['isleft', 'y'])['x1'].count()"
]
},
{
"cell_type": "code",
"execution_count": 150,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"isleft y\n",
"False 1 2\n",
" 2 31\n",
"True 0 40\n",
" 1 48\n",
" 2 4\n",
"Name: y, dtype: int64"
]
},
"execution_count": 150,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf.groupby(['isleft', 'y'])['y'].count()"
]
},
{
"cell_type": "code",
"execution_count": 155,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"res = curdf.groupby(['isleft', 'y']).count()"
]
},
{
"cell_type": "code",
"execution_count": 156,
"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></th>\n",
" <th>x1</th>\n",
" <th>x2</th>\n",
" <th>x3</th>\n",
" <th>x4</th>\n",
" </tr>\n",
" <tr>\n",
" <th>isleft</th>\n",
" <th>y</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">False</th>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>31</td>\n",
" <td>31</td>\n",
" <td>31</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"3\" valign=\"top\">True</th>\n",
" <th>0</th>\n",
" <td>40</td>\n",
" <td>40</td>\n",
" <td>40</td>\n",
" <td>40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>48</td>\n",
" <td>48</td>\n",
" <td>48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2 x3 x4\n",
"isleft y \n",
"False 1 2 2 2 2\n",
" 2 31 31 31 31\n",
"True 0 40 40 40 40\n",
" 1 48 48 48 48\n",
" 2 4 4 4 4"
]
},
"execution_count": 156,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"res"
]
},
{
"cell_type": "code",
"execution_count": 157,
"metadata": {
"collapsed": false
},
"outputs": [
{
"ename": "KeyError",
"evalue": "True",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-157-2fb828fc8adf>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mres\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mTrue\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;32mC:\\Users\\_\\Anaconda2\\lib\\site-packages\\pandas\\core\\frame.pyc\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 1912\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_getitem_multilevel\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1913\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1914\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_getitem_column\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1915\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1916\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_getitem_column\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mC:\\Users\\_\\Anaconda2\\lib\\site-packages\\pandas\\core\\frame.pyc\u001b[0m in \u001b[0;36m_getitem_column\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 1919\u001b[0m \u001b[1;31m# get column\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1920\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mis_unique\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1921\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_item_cache\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1922\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1923\u001b[0m \u001b[1;31m# duplicate columns & possible reduce dimensionaility\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mC:\\Users\\_\\Anaconda2\\lib\\site-packages\\pandas\\core\\generic.pyc\u001b[0m in \u001b[0;36m_get_item_cache\u001b[1;34m(self, item)\u001b[0m\n\u001b[0;32m 1088\u001b[0m \u001b[0mres\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcache\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1089\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mres\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1090\u001b[1;33m \u001b[0mvalues\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_data\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1091\u001b[0m \u001b[0mres\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_box_item_values\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalues\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1092\u001b[0m \u001b[0mcache\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mitem\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mres\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mC:\\Users\\_\\Anaconda2\\lib\\site-packages\\pandas\\core\\internals.pyc\u001b[0m in \u001b[0;36mget\u001b[1;34m(self, item, fastpath)\u001b[0m\n\u001b[0;32m 3100\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3101\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0misnull\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3102\u001b[1;33m \u001b[0mloc\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 3103\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3104\u001b[0m \u001b[0mindexer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0marange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0misnull\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mC:\\Users\\_\\Anaconda2\\lib\\site-packages\\pandas\\core\\index.pyc\u001b[0m in \u001b[0;36mget_loc\u001b[1;34m(self, key, method, tolerance)\u001b[0m\n\u001b[0;32m 1690\u001b[0m raise ValueError('tolerance argument only valid if using pad, '\n\u001b[0;32m 1691\u001b[0m 'backfill or nearest lookups')\n\u001b[1;32m-> 1692\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m_values_from_object\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1693\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1694\u001b[0m indexer = self.get_indexer([key], method=method,\n",
"\u001b[1;32mpandas\\index.pyx\u001b[0m in \u001b[0;36mpandas.index.IndexEngine.get_loc (pandas\\index.c:3979)\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\index.pyx\u001b[0m in \u001b[0;36mpandas.index.IndexEngine.get_loc (pandas\\index.c:3843)\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\hashtable.pyx\u001b[0m in \u001b[0;36mpandas.hashtable.PyObjectHashTable.get_item (pandas\\hashtable.c:12265)\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mpandas\\hashtable.pyx\u001b[0m in \u001b[0;36mpandas.hashtable.PyObjectHashTable.get_item (pandas\\hashtable.c:12216)\u001b[1;34m()\u001b[0m\n",
"\u001b[1;31mKeyError\u001b[0m: True"
]
}
],
"source": [
"res[True]"
]
},
{
"cell_type": "code",
"execution_count": 158,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"MultiIndex(levels=[[False, True], [0, 1, 2]],\n",
" labels=[[0, 0, 1, 1, 1], [1, 2, 0, 1, 2]],\n",
" names=[u'isleft', u'y'])"
]
},
"execution_count": 158,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"res.index"
]
},
{
"cell_type": "code",
"execution_count": 160,
"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></th>\n",
" <th>x1</th>\n",
" <th>x2</th>\n",
" </tr>\n",
" <tr>\n",
" <th>isleft</th>\n",
" <th>y</th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">False</th>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>31</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"3\" valign=\"top\">True</th>\n",
" <th>0</th>\n",
" <td>40</td>\n",
" <td>40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>48</td>\n",
" <td>48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" x1 x2\n",
"isleft y \n",
"False 1 2 2\n",
" 2 31 31\n",
"True 0 40 40\n",
" 1 48 48\n",
" 2 4 4"
]
},
"execution_count": 160,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"res[[False, 1]]"
]
},
{
"cell_type": "code",
"execution_count": 162,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"y\n",
"1 2\n",
"2 31\n",
"Name: y, dtype: int64"
]
},
"execution_count": 162,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf.groupby(['isleft', 'y'])['y'].count()[False]"
]
},
{
"cell_type": "code",
"execution_count": 163,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"y\n",
"0 40\n",
"1 48\n",
"2 4\n",
"Name: y, dtype: int64"
]
},
"execution_count": 163,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"curdf.groupby(['isleft', 'y'])['y'].count()[True]"
]
},
{
"cell_type": "code",
"execution_count": 164,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"righttotal = curdf[tryfname].groupby(curdf['isleft']).count()[False]"
]
},
{
"cell_type": "code",
"execution_count": 165,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"33"
]
},
"execution_count": 165,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"righttotal"
]
},
{
"cell_type": "code",
"execution_count": 166,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"rightcountbyclass = curdf.groupby(['isleft', 'y'])['y'].count()[False]"
]
},
{
"cell_type": "code",
"execution_count": 167,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"y\n",
"1 2\n",
"2 31\n",
"Name: y, dtype: int64"
]
},
"execution_count": 167,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rightcountbyclass"
]
},
{
"cell_type": "code",
"execution_count": 168,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"2"
]
},
"execution_count": 168,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rightcountbyclass[1]"
]
},
{
"cell_type": "code",
"execution_count": 169,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"Int64Index([1, 2], dtype='int64', name=u'y')"
]
},
"execution_count": 169,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rightcountbyclass.index"
]
},
{
"cell_type": "code",
"execution_count": 170,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"1"
]
},
"execution_count": 170,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rightcountbyclass.index[0]"
]
},
{
"cell_type": "code",
"execution_count": 171,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"2"
]
},
"execution_count": 171,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(rightcountbyclass.index)"
]
},
{
"cell_type": "code",
"execution_count": 172,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0"
]
},
"execution_count": 172,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rightcountbyclass[1]/righttotal"
]
},
{
"cell_type": "code",
"execution_count": 173,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"2"
]
},
"execution_count": 173,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rightcountbyclass[1]"
]
},
{
"cell_type": "code",
"execution_count": 174,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"33"
]
},
"execution_count": 174,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"righttotal"
]
},
{
"cell_type": "code",
"execution_count": 175,
"metadata": {
"collapsed": false
},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'double' is not defined",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-175-38e67e31767a>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdouble\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m2\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;31mNameError\u001b[0m: name 'double' is not defined"
]
}
],
"source": [
"double(2)"
]
},
{
"cell_type": "code",
"execution_count": 176,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"2.0"
]
},
"execution_count": 176,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"float(2)"
]
},
{
"cell_type": "code",
"execution_count": 177,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0.060606060606060608"
]
},
"execution_count": 177,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"float(rightcountbyclass[1])/righttotal"
]
},
{
"cell_type": "code",
"execution_count": 178,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"[0.060606060606060608, 0.93939393939393945]"
]
},
"execution_count": 178,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"[float(rightcountbyclass[index])/righttotal for index in rightcountbyclass.index]"
]
},
{
"cell_type": "code",
"execution_count": 179,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"rightgini = 1.0"
]
},
{
"cell_type": "code",
"execution_count": 181,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"rightgini = 1.0 - sum([(float(rightcountbyclass[index])/righttotal)**2 for index in rightcountbyclass.index])"
]
},
{
"cell_type": "code",
"execution_count": 184,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"lefttotal = curdf[tryfname].groupby(curdf['isleft']).count()[True]"
]
},
{
"cell_type": "code",
"execution_count": 185,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"leftcountbyclass = curdf.groupby(['isleft', 'y'])['y'].count()[True]"
]
},
{
"cell_type": "code",
"execution_count": 186,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"leftgini = 1.0 - sum([(float(leftcountbyclass[index])/lefttotal)**2 for index in leftcountbyclass.index])"
]
},
{
"cell_type": "code",
"execution_count": 187,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0.53686200378071836"
]
},
"execution_count": 187,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"leftgini"
]
},
{
"cell_type": "code",
"execution_count": 188,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0.1138659320477502"
]
},
"execution_count": 188,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rightgini"
]
},
{
"cell_type": "code",
"execution_count": 189,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"125"
]
},
"execution_count": 189,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sum(curdf[tryfname].groupby(curdf['isleft']).count())"
]
},
{
"cell_type": "code",
"execution_count": 190,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# これが最小のfeatureと値がツリーとなる。\n",
"totalgini = leftgini*float(lefttotal)/(lefttotal+righttotal) + rightgini*float(righttotal)/(righttotal+lefttotal)"
]
},
{
"cell_type": "code",
"execution_count": 191,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0.42519104084321474"
]
},
"execution_count": 191,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"totalgini"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false
},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'curdf' is not defined",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-1-1632a6cd491a>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mcurdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'isleft'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;31mNameError\u001b[0m: name 'curdf' is not defined"
]
}
],
"source": [
"curdf['isleft']"
]
},
{
"cell_type": "code",
"execution_count": 106,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"ysize = curdf.groupby('y').size()"
]
},
{
"cell_type": "code",
"execution_count": 120,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"2"
]
},
"execution_count": 120,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ysize.index[ysize == max(ysize)][0]"
]
},
{
"cell_type": "code",
"execution_count": 119,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"y\n",
"0 43\n",
"1 36\n",
"2 46\n",
"dtype: int64"
]
},
"execution_count": 119,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ysize"
]
},
{
"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