Skip to content

Instantly share code, notes, and snippets.

@decisionstats

decisionstats/py data transforms

Created December 24, 2016 15:58
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save decisionstats/b818917b37807fa0ded41522928f26af to your computer and use it in GitHub Desktop.
Save decisionstats/b818917b37807fa0ded41522928f26af to your computer and use it in GitHub Desktop.
Download ZIP
Raw
py data transforms
{
"cells": [
{
"cell_type": "code",
"execution_count": 37,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import re\n",
"import numpy as np\n",
"import pandas as pd\n"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"numlist=[\"$10000\",\"$20,000\",\"30,000\",40000,\"50000 \"]"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"for i,value in enumerate(numlist):\n",
" numlist[i]=re.sub(r\"([$,])\",\"\",str(value))\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"['10000', '20000', '30000', '40000', '50000 ']"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"numlist"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"20000"
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"int(numlist[1])"
]
},
{
"cell_type": "code",
"execution_count": 56,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"for i,value in enumerate(numlist):\n",
" numlist[i]=int(value)"
]
},
{
"cell_type": "code",
"execution_count": 57,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"[10000, 20000, 30000, 40000, 50000]"
]
},
"execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"numlist"
]
},
{
"cell_type": "code",
"execution_count": 58,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"30000.0"
]
},
"execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.mean(numlist)"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"numlist2=str(numlist)"
]
},
{
"cell_type": "code",
"execution_count": 60,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"['[10000, 20000, 30000, 40000, 50000]']"
]
},
"execution_count": 60,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"numlist2.split(None,0)"
]
},
{
"cell_type": "code",
"execution_count": 61,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'[10000, 20000, 30000, 40000, 50000]'"
]
},
"execution_count": 61,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"numlist2.split(None,0)[0]"
]
},
{
"cell_type": "code",
"execution_count": 62,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"titanic =pd.read_csv(\"https://vincentarelbundock.github.io/Rdatasets/csv/datasets/Titanic.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"titanic=titanic.drop('Unnamed: 0', 1)"
]
},
{
"cell_type": "code",
"execution_count": 66,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 1313 entries, 0 to 1312\n",
"Data columns (total 6 columns):\n",
"Name 1313 non-null object\n",
"PClass 1313 non-null object\n",
"Age 756 non-null float64\n",
"Sex 1313 non-null object\n",
"Survived 1313 non-null int64\n",
"SexCode 1313 non-null int64\n",
"dtypes: float64(1), int64(2), object(3)\n",
"memory usage: 61.6+ KB\n"
]
}
],
"source": [
"titanic.info()"
]
},
{
"cell_type": "code",
"execution_count": 67,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Name</th>\n",
" <th>PClass</th>\n",
" <th>Age</th>\n",
" <th>Sex</th>\n",
" <th>Survived</th>\n",
" <th>SexCode</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Allen, Miss Elisabeth Walton</td>\n",
" <td>1st</td>\n",
" <td>29.00</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Allison, Miss Helen Loraine</td>\n",
" <td>1st</td>\n",
" <td>2.00</td>\n",
" <td>female</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Allison, Mr Hudson Joshua Creighton</td>\n",
" <td>1st</td>\n",
" <td>30.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Allison, Mrs Hudson JC (Bessie Waldo Daniels)</td>\n",
" <td>1st</td>\n",
" <td>25.00</td>\n",
" <td>female</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Allison, Master Hudson Trevor</td>\n",
" <td>1st</td>\n",
" <td>0.92</td>\n",
" <td>male</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Name PClass Age Sex \\\n",
"0 Allen, Miss Elisabeth Walton 1st 29.00 female \n",
"1 Allison, Miss Helen Loraine 1st 2.00 female \n",
"2 Allison, Mr Hudson Joshua Creighton 1st 30.00 male \n",
"3 Allison, Mrs Hudson JC (Bessie Waldo Daniels) 1st 25.00 female \n",
"4 Allison, Master Hudson Trevor 1st 0.92 male \n",
"\n",
" Survived SexCode \n",
"0 1 1 \n",
"1 0 1 \n",
"2 0 0 \n",
"3 0 1 \n",
"4 1 0 "
]
},
"execution_count": 67,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"titanic.head()"
]
},
{
"cell_type": "code",
"execution_count": 69,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"<class 'pandas.core.frame.DataFrame'>\n",
"<class 'numpy.ndarray'>\n"
]
}
],
"source": [
"a=titanic.iloc[:,1:]\n",
"b=titanic.iloc[:,1:].values\n",
"\n",
"print(type(titanic))\n",
"print(type(a))\n",
"print(type(b))"
]
},
{
"cell_type": "code",
"execution_count": 70,
"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>PClass</th>\n",
" <th>Age</th>\n",
" <th>Sex</th>\n",
" <th>Survived</th>\n",
" <th>SexCode</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1st</td>\n",
" <td>29.00</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1st</td>\n",
" <td>2.00</td>\n",
" <td>female</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1st</td>\n",
" <td>30.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1st</td>\n",
" <td>25.00</td>\n",
" <td>female</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1st</td>\n",
" <td>0.92</td>\n",
" <td>male</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>1st</td>\n",
" <td>47.00</td>\n",
" <td>male</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>1st</td>\n",
" <td>63.00</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>1st</td>\n",
" <td>39.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>1st</td>\n",
" <td>58.00</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>1st</td>\n",
" <td>71.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>1st</td>\n",
" <td>47.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>1st</td>\n",
" <td>19.00</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>1st</td>\n",
" <td>NaN</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>1st</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>1st</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>1st</td>\n",
" <td>50.00</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>1st</td>\n",
" <td>24.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>1st</td>\n",
" <td>36.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>1st</td>\n",
" <td>37.00</td>\n",
" <td>male</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>1st</td>\n",
" <td>47.00</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>1st</td>\n",
" <td>26.00</td>\n",
" <td>male</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>1st</td>\n",
" <td>25.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>1st</td>\n",
" <td>25.00</td>\n",
" <td>male</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>1st</td>\n",
" <td>19.00</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>1st</td>\n",
" <td>28.00</td>\n",
" <td>male</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>1st</td>\n",
" <td>45.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>1st</td>\n",
" <td>39.00</td>\n",
" <td>male</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>1st</td>\n",
" <td>30.00</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>1st</td>\n",
" <td>58.00</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>1st</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>0</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>1283</th>\n",
" <td>3rd</td>\n",
" <td>14.00</td>\n",
" <td>female</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1284</th>\n",
" <td>3rd</td>\n",
" <td>22.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1285</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1286</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1287</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1288</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1289</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1290</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1291</th>\n",
" <td>3rd</td>\n",
" <td>51.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1292</th>\n",
" <td>3rd</td>\n",
" <td>18.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1293</th>\n",
" <td>3rd</td>\n",
" <td>45.00</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1294</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1295</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1296</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1297</th>\n",
" <td>3rd</td>\n",
" <td>28.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1298</th>\n",
" <td>3rd</td>\n",
" <td>21.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1299</th>\n",
" <td>3rd</td>\n",
" <td>27.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1300</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1301</th>\n",
" <td>3rd</td>\n",
" <td>36.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1302</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1303</th>\n",
" <td>3rd</td>\n",
" <td>27.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1304</th>\n",
" <td>3rd</td>\n",
" <td>15.00</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1305</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1306</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>female</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1307</th>\n",
" <td>3rd</td>\n",
" <td>NaN</td>\n",
" <td>female</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1308</th>\n",
" <td>3rd</td>\n",
" <td>27.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1309</th>\n",
" <td>3rd</td>\n",
" <td>26.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1310</th>\n",
" <td>3rd</td>\n",
" <td>22.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1311</th>\n",
" <td>3rd</td>\n",
" <td>24.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1312</th>\n",
" <td>3rd</td>\n",
" <td>29.00</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1313 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
" PClass Age Sex Survived SexCode\n",
"0 1st 29.00 female 1 1\n",
"1 1st 2.00 female 0 1\n",
"2 1st 30.00 male 0 0\n",
"3 1st 25.00 female 0 1\n",
"4 1st 0.92 male 1 0\n",
"5 1st 47.00 male 1 0\n",
"6 1st 63.00 female 1 1\n",
"7 1st 39.00 male 0 0\n",
"8 1st 58.00 female 1 1\n",
"9 1st 71.00 male 0 0\n",
"10 1st 47.00 male 0 0\n",
"11 1st 19.00 female 1 1\n",
"12 1st NaN female 1 1\n",
"13 1st NaN male 1 0\n",
"14 1st NaN male 0 0\n",
"15 1st 50.00 female 1 1\n",
"16 1st 24.00 male 0 0\n",
"17 1st 36.00 male 0 0\n",
"18 1st 37.00 male 1 0\n",
"19 1st 47.00 female 1 1\n",
"20 1st 26.00 male 1 0\n",
"21 1st 25.00 male 0 0\n",
"22 1st 25.00 male 1 0\n",
"23 1st 19.00 female 1 1\n",
"24 1st 28.00 male 1 0\n",
"25 1st 45.00 male 0 0\n",
"26 1st 39.00 male 1 0\n",
"27 1st 30.00 female 1 1\n",
"28 1st 58.00 female 1 1\n",
"29 1st NaN male 0 0\n",
"... ... ... ... ... ...\n",
"1283 3rd 14.00 female 0 1\n",
"1284 3rd 22.00 male 0 0\n",
"1285 3rd NaN male 0 0\n",
"1286 3rd NaN male 0 0\n",
"1287 3rd NaN male 0 0\n",
"1288 3rd NaN male 0 0\n",
"1289 3rd NaN male 1 0\n",
"1290 3rd NaN male 0 0\n",
"1291 3rd 51.00 male 0 0\n",
"1292 3rd 18.00 male 0 0\n",
"1293 3rd 45.00 female 1 1\n",
"1294 3rd NaN male 0 0\n",
"1295 3rd NaN male 0 0\n",
"1296 3rd NaN male 0 0\n",
"1297 3rd 28.00 male 0 0\n",
"1298 3rd 21.00 male 0 0\n",
"1299 3rd 27.00 male 0 0\n",
"1300 3rd NaN male 0 0\n",
"1301 3rd 36.00 male 0 0\n",
"1302 3rd NaN male 1 0\n",
"1303 3rd 27.00 male 0 0\n",
"1304 3rd 15.00 female 1 1\n",
"1305 3rd NaN male 0 0\n",
"1306 3rd NaN female 0 1\n",
"1307 3rd NaN female 0 1\n",
"1308 3rd 27.00 male 0 0\n",
"1309 3rd 26.00 male 0 0\n",
"1310 3rd 22.00 male 0 0\n",
"1311 3rd 24.00 male 0 0\n",
"1312 3rd 29.00 male 0 0\n",
"\n",
"[1313 rows x 5 columns]"
]
},
"execution_count": 70,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"a"
]
},
{
"cell_type": "code",
"execution_count": 71,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([['1st', 29.0, 'female', 1, 1],\n",
" ['1st', 2.0, 'female', 0, 1],\n",
" ['1st', 30.0, 'male', 0, 0],\n",
" ..., \n",
" ['3rd', 22.0, 'male', 0, 0],\n",
" ['3rd', 24.0, 'male', 0, 0],\n",
" ['3rd', 29.0, 'male', 0, 0]], dtype=object)"
]
},
"execution_count": 71,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"b"
]
},
{
"cell_type": "code",
"execution_count": 75,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"Index(['PClass', 'Age', 'Sex', 'Survived', 'SexCode'], dtype='object')"
]
},
"execution_count": 75,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"titanic.columns[1:]"
]
},
{
"cell_type": "code",
"execution_count": 76,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([['1st', 29.0, 'female', 1, 1],\n",
" ['1st', 2.0, 'female', 0, 1],\n",
" ['1st', 30.0, 'male', 0, 0],\n",
" ..., \n",
" ['3rd', 22.0, 'male', 0, 0],\n",
" ['3rd', 24.0, 'male', 0, 0],\n",
" ['3rd', 29.0, 'male', 0, 0]], dtype=object)"
]
},
"execution_count": 76,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"titanic.as_matrix(columns=titanic.columns[1:])"
]
},
{
"cell_type": "code",
"execution_count": 81,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data=titanic.as_matrix(columns=titanic.columns[1:])"
]
},
{
"cell_type": "code",
"execution_count": 86,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"1313"
]
},
"execution_count": 86,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(data)"
]
},
{
"cell_type": "code",
"execution_count": 91,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"range(0, 1313)"
]
},
"execution_count": 91,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"range(0,len(data))\n"
]
},
{
"cell_type": "code",
"execution_count": 92,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
" g=pd.DataFrame(data=data[0:,0:], # values\n",
" index=range(0,len(data)), # 1st column as index\n",
" columns=titanic.columns[1:]) # 1st row as the column names"
]
},
{
"cell_type": "code",
"execution_count": 93,
"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>PClass</th>\n",
" <th>Age</th>\n",
" <th>Sex</th>\n",
" <th>Survived</th>\n",
" <th>SexCode</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1st</td>\n",
" <td>29</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1st</td>\n",
" <td>2</td>\n",
" <td>female</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1st</td>\n",
" <td>30</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1st</td>\n",
" <td>25</td>\n",
" <td>female</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1st</td>\n",
" <td>0.92</td>\n",
" <td>male</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" PClass Age Sex Survived SexCode\n",
"0 1st 29 female 1 1\n",
"1 1st 2 female 0 1\n",
"2 1st 30 male 0 0\n",
"3 1st 25 female 0 1\n",
"4 1st 0.92 male 1 0"
]
},
"execution_count": 93,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"g.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"anaconda-cloud": {},
"kernelspec": {
"display_name": "Python [Root]",
"language": "python",
"name": "Python [Root]"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.2"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment