Skip to content

Instantly share code, notes, and snippets.

@decisionstats
Created October 30, 2016 11:50
Show Gist options
  • Save decisionstats/43e332cdff2d5a7599f4e61205e8788f to your computer and use it in GitHub Desktop.
Save decisionstats/43e332cdff2d5a7599f4e61205e8788f to your computer and use it in GitHub Desktop.
{
"cells": [
{
"cell_type": "code",
"execution_count": 48,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"names=['Ajay','Vijay','Ra Jay','Jayesh']"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"list"
]
},
"execution_count": 49,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type(names)"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'Vijay'"
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"names[1]"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"str"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"type(names[1])"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'ja'"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"names[0][1:3]"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"' Jay'"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"names[2][2:]"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"' Jayyesh'"
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"names[2][2:] + names[3][2:]"
]
},
{
"cell_type": "code",
"execution_count": 55,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'vijay'"
]
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"names[1].lower()"
]
},
{
"cell_type": "code",
"execution_count": 56,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'RaJay'"
]
},
"execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"names[2].replace(\" \",\"\")"
]
},
{
"cell_type": "code",
"execution_count": 57,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from datetime import datetime"
]
},
{
"cell_type": "code",
"execution_count": 58,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"date_object=datetime.strptime(\"7nov-2007\",\"%d%b-%Y\")"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"datetime.datetime(2007, 11, 7, 0, 0)"
]
},
"execution_count": 59,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"date_object"
]
},
{
"cell_type": "code",
"execution_count": 60,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2007\n",
"11\n",
"7\n",
"0\n"
]
}
],
"source": [
"print(format(date_object.year))\n",
"print(format(date_object.month))\n",
"print(format(date_object.day))\n",
"print(format(date_object.hour))"
]
},
{
"cell_type": "code",
"execution_count": 61,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"datetime.datetime(2016, 10, 30, 16, 57, 42, 142041)"
]
},
"execution_count": 61,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"datetime.now()"
]
},
{
"cell_type": "code",
"execution_count": 62,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"datetime.timedelta(3280, 61062, 216745)"
]
},
"execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"datetime.now()-date_object"
]
},
{
"cell_type": "code",
"execution_count": 63,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"a=datetime.now()-date_object"
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"3280"
]
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"a.days"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"61062"
]
},
"execution_count": 65,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"a.seconds"
]
},
{
"cell_type": "code",
"execution_count": 66,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 67,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"diamonds =pd.read_csv(\"https://vincentarelbundock.github.io/Rdatasets/csv/ggplot2/diamonds.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 68,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"RangeIndex(start=0, stop=53940, step=1)"
]
},
"execution_count": 68,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.index"
]
},
{
"cell_type": "code",
"execution_count": 69,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"Index(['Unnamed: 0', 'carat', 'cut', 'color', 'clarity', 'depth', 'table',\n",
" 'price', 'x', 'y', 'z'],\n",
" dtype='object')"
]
},
"execution_count": 69,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.columns"
]
},
{
"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>Unnamed: 0</th>\n",
" <th>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0.23</td>\n",
" <td>Ideal</td>\n",
" <td>E</td>\n",
" <td>SI2</td>\n",
" <td>61.5</td>\n",
" <td>55.0</td>\n",
" <td>326</td>\n",
" <td>3.95</td>\n",
" <td>3.98</td>\n",
" <td>2.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>0.21</td>\n",
" <td>Premium</td>\n",
" <td>E</td>\n",
" <td>SI1</td>\n",
" <td>59.8</td>\n",
" <td>61.0</td>\n",
" <td>326</td>\n",
" <td>3.89</td>\n",
" <td>3.84</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>0.23</td>\n",
" <td>Good</td>\n",
" <td>E</td>\n",
" <td>VS1</td>\n",
" <td>56.9</td>\n",
" <td>65.0</td>\n",
" <td>327</td>\n",
" <td>4.05</td>\n",
" <td>4.07</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>0.29</td>\n",
" <td>Premium</td>\n",
" <td>I</td>\n",
" <td>VS2</td>\n",
" <td>62.4</td>\n",
" <td>58.0</td>\n",
" <td>334</td>\n",
" <td>4.20</td>\n",
" <td>4.23</td>\n",
" <td>2.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>0.31</td>\n",
" <td>Good</td>\n",
" <td>J</td>\n",
" <td>SI2</td>\n",
" <td>63.3</td>\n",
" <td>58.0</td>\n",
" <td>335</td>\n",
" <td>4.34</td>\n",
" <td>4.35</td>\n",
" <td>2.75</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 carat cut color clarity depth table price x y \\\n",
"0 1 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 \n",
"1 2 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 \n",
"2 3 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 \n",
"3 4 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 \n",
"4 5 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 \n",
"\n",
" z \n",
"0 2.43 \n",
"1 2.31 \n",
"2 2.31 \n",
"3 2.63 \n",
"4 2.75 "
]
},
"execution_count": 70,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.head()"
]
},
{
"cell_type": "code",
"execution_count": 71,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Unnamed: 0</th>\n",
" <th>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>53935</th>\n",
" <td>53936</td>\n",
" <td>0.72</td>\n",
" <td>Ideal</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>60.8</td>\n",
" <td>57.0</td>\n",
" <td>2757</td>\n",
" <td>5.75</td>\n",
" <td>5.76</td>\n",
" <td>3.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53936</th>\n",
" <td>53937</td>\n",
" <td>0.72</td>\n",
" <td>Good</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>63.1</td>\n",
" <td>55.0</td>\n",
" <td>2757</td>\n",
" <td>5.69</td>\n",
" <td>5.75</td>\n",
" <td>3.61</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53937</th>\n",
" <td>53938</td>\n",
" <td>0.70</td>\n",
" <td>Very Good</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>62.8</td>\n",
" <td>60.0</td>\n",
" <td>2757</td>\n",
" <td>5.66</td>\n",
" <td>5.68</td>\n",
" <td>3.56</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53938</th>\n",
" <td>53939</td>\n",
" <td>0.86</td>\n",
" <td>Premium</td>\n",
" <td>H</td>\n",
" <td>SI2</td>\n",
" <td>61.0</td>\n",
" <td>58.0</td>\n",
" <td>2757</td>\n",
" <td>6.15</td>\n",
" <td>6.12</td>\n",
" <td>3.74</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53939</th>\n",
" <td>53940</td>\n",
" <td>0.75</td>\n",
" <td>Ideal</td>\n",
" <td>D</td>\n",
" <td>SI2</td>\n",
" <td>62.2</td>\n",
" <td>55.0</td>\n",
" <td>2757</td>\n",
" <td>5.83</td>\n",
" <td>5.87</td>\n",
" <td>3.64</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 carat cut color clarity depth table price x \\\n",
"53935 53936 0.72 Ideal D SI1 60.8 57.0 2757 5.75 \n",
"53936 53937 0.72 Good D SI1 63.1 55.0 2757 5.69 \n",
"53937 53938 0.70 Very Good D SI1 62.8 60.0 2757 5.66 \n",
"53938 53939 0.86 Premium H SI2 61.0 58.0 2757 6.15 \n",
"53939 53940 0.75 Ideal D SI2 62.2 55.0 2757 5.83 \n",
"\n",
" y z \n",
"53935 5.76 3.50 \n",
"53936 5.75 3.61 \n",
"53937 5.68 3.56 \n",
"53938 6.12 3.74 \n",
"53939 5.87 3.64 "
]
},
"execution_count": 71,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.tail()"
]
},
{
"cell_type": "code",
"execution_count": 72,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"(53940, 11)"
]
},
"execution_count": 72,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.shape"
]
},
{
"cell_type": "code",
"execution_count": 73,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"53940"
]
},
"execution_count": 73,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(diamonds)"
]
},
{
"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>Unnamed: 0</th>\n",
" <th>carat</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>53940.000000</td>\n",
" <td>53940.000000</td>\n",
" <td>53940.000000</td>\n",
" <td>53940.000000</td>\n",
" <td>53940.000000</td>\n",
" <td>53940.000000</td>\n",
" <td>53940.000000</td>\n",
" <td>53940.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>26970.500000</td>\n",
" <td>0.797940</td>\n",
" <td>61.749405</td>\n",
" <td>57.457184</td>\n",
" <td>3932.799722</td>\n",
" <td>5.731157</td>\n",
" <td>5.734526</td>\n",
" <td>3.538734</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>15571.281097</td>\n",
" <td>0.474011</td>\n",
" <td>1.432621</td>\n",
" <td>2.234491</td>\n",
" <td>3989.439738</td>\n",
" <td>1.121761</td>\n",
" <td>1.142135</td>\n",
" <td>0.705699</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>1.000000</td>\n",
" <td>0.200000</td>\n",
" <td>43.000000</td>\n",
" <td>43.000000</td>\n",
" <td>326.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>13485.750000</td>\n",
" <td>0.400000</td>\n",
" <td>61.000000</td>\n",
" <td>56.000000</td>\n",
" <td>950.000000</td>\n",
" <td>4.710000</td>\n",
" <td>4.720000</td>\n",
" <td>2.910000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>26970.500000</td>\n",
" <td>0.700000</td>\n",
" <td>61.800000</td>\n",
" <td>57.000000</td>\n",
" <td>2401.000000</td>\n",
" <td>5.700000</td>\n",
" <td>5.710000</td>\n",
" <td>3.530000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>40455.250000</td>\n",
" <td>1.040000</td>\n",
" <td>62.500000</td>\n",
" <td>59.000000</td>\n",
" <td>5324.250000</td>\n",
" <td>6.540000</td>\n",
" <td>6.540000</td>\n",
" <td>4.040000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>53940.000000</td>\n",
" <td>5.010000</td>\n",
" <td>79.000000</td>\n",
" <td>95.000000</td>\n",
" <td>18823.000000</td>\n",
" <td>10.740000</td>\n",
" <td>58.900000</td>\n",
" <td>31.800000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 carat depth table price \\\n",
"count 53940.000000 53940.000000 53940.000000 53940.000000 53940.000000 \n",
"mean 26970.500000 0.797940 61.749405 57.457184 3932.799722 \n",
"std 15571.281097 0.474011 1.432621 2.234491 3989.439738 \n",
"min 1.000000 0.200000 43.000000 43.000000 326.000000 \n",
"25% 13485.750000 0.400000 61.000000 56.000000 950.000000 \n",
"50% 26970.500000 0.700000 61.800000 57.000000 2401.000000 \n",
"75% 40455.250000 1.040000 62.500000 59.000000 5324.250000 \n",
"max 53940.000000 5.010000 79.000000 95.000000 18823.000000 \n",
"\n",
" x y z \n",
"count 53940.000000 53940.000000 53940.000000 \n",
"mean 5.731157 5.734526 3.538734 \n",
"std 1.121761 1.142135 0.705699 \n",
"min 0.000000 0.000000 0.000000 \n",
"25% 4.710000 4.720000 2.910000 \n",
"50% 5.700000 5.710000 3.530000 \n",
"75% 6.540000 6.540000 4.040000 \n",
"max 10.740000 58.900000 31.800000 "
]
},
"execution_count": 74,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.describe()"
]
},
{
"cell_type": "code",
"execution_count": 75,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"diamonds=diamonds.drop(\"Unnamed: 0\",1)"
]
},
{
"cell_type": "code",
"execution_count": 76,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"Index(['carat', 'cut', 'color', 'clarity', 'depth', 'table', 'price', 'x', 'y',\n",
" 'z'],\n",
" dtype='object')"
]
},
"execution_count": 76,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.columns"
]
},
{
"cell_type": "code",
"execution_count": 77,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"RangeIndex(start=0, stop=53940, step=1)"
]
},
"execution_count": 77,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.index"
]
},
{
"cell_type": "code",
"execution_count": 85,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"diamonds2=diamonds.sort_index(axis=1,ascending=\"false\")"
]
},
{
"cell_type": "code",
"execution_count": 87,
"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>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.23</td>\n",
" <td>Ideal</td>\n",
" <td>E</td>\n",
" <td>SI2</td>\n",
" <td>61.5</td>\n",
" <td>55.0</td>\n",
" <td>326</td>\n",
" <td>3.95</td>\n",
" <td>3.98</td>\n",
" <td>2.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.21</td>\n",
" <td>Premium</td>\n",
" <td>E</td>\n",
" <td>SI1</td>\n",
" <td>59.8</td>\n",
" <td>61.0</td>\n",
" <td>326</td>\n",
" <td>3.89</td>\n",
" <td>3.84</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.23</td>\n",
" <td>Good</td>\n",
" <td>E</td>\n",
" <td>VS1</td>\n",
" <td>56.9</td>\n",
" <td>65.0</td>\n",
" <td>327</td>\n",
" <td>4.05</td>\n",
" <td>4.07</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.29</td>\n",
" <td>Premium</td>\n",
" <td>I</td>\n",
" <td>VS2</td>\n",
" <td>62.4</td>\n",
" <td>58.0</td>\n",
" <td>334</td>\n",
" <td>4.20</td>\n",
" <td>4.23</td>\n",
" <td>2.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.31</td>\n",
" <td>Good</td>\n",
" <td>J</td>\n",
" <td>SI2</td>\n",
" <td>63.3</td>\n",
" <td>58.0</td>\n",
" <td>335</td>\n",
" <td>4.34</td>\n",
" <td>4.35</td>\n",
" <td>2.75</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" carat cut color clarity depth table price x y z\n",
"0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43\n",
"1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31\n",
"2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31\n",
"3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63\n",
"4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75"
]
},
"execution_count": 87,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.head()"
]
},
{
"cell_type": "code",
"execution_count": 86,
"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>carat</th>\n",
" <th>clarity</th>\n",
" <th>color</th>\n",
" <th>cut</th>\n",
" <th>depth</th>\n",
" <th>price</th>\n",
" <th>table</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.23</td>\n",
" <td>SI2</td>\n",
" <td>E</td>\n",
" <td>Ideal</td>\n",
" <td>61.5</td>\n",
" <td>326</td>\n",
" <td>55.0</td>\n",
" <td>3.95</td>\n",
" <td>3.98</td>\n",
" <td>2.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.21</td>\n",
" <td>SI1</td>\n",
" <td>E</td>\n",
" <td>Premium</td>\n",
" <td>59.8</td>\n",
" <td>326</td>\n",
" <td>61.0</td>\n",
" <td>3.89</td>\n",
" <td>3.84</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.23</td>\n",
" <td>VS1</td>\n",
" <td>E</td>\n",
" <td>Good</td>\n",
" <td>56.9</td>\n",
" <td>327</td>\n",
" <td>65.0</td>\n",
" <td>4.05</td>\n",
" <td>4.07</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.29</td>\n",
" <td>VS2</td>\n",
" <td>I</td>\n",
" <td>Premium</td>\n",
" <td>62.4</td>\n",
" <td>334</td>\n",
" <td>58.0</td>\n",
" <td>4.20</td>\n",
" <td>4.23</td>\n",
" <td>2.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.31</td>\n",
" <td>SI2</td>\n",
" <td>J</td>\n",
" <td>Good</td>\n",
" <td>63.3</td>\n",
" <td>335</td>\n",
" <td>58.0</td>\n",
" <td>4.34</td>\n",
" <td>4.35</td>\n",
" <td>2.75</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" carat clarity color cut depth price table x y z\n",
"0 0.23 SI2 E Ideal 61.5 326 55.0 3.95 3.98 2.43\n",
"1 0.21 SI1 E Premium 59.8 326 61.0 3.89 3.84 2.31\n",
"2 0.23 VS1 E Good 56.9 327 65.0 4.05 4.07 2.31\n",
"3 0.29 VS2 I Premium 62.4 334 58.0 4.20 4.23 2.63\n",
"4 0.31 SI2 J Good 63.3 335 58.0 4.34 4.35 2.75"
]
},
"execution_count": 86,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds2.head()"
]
},
{
"cell_type": "code",
"execution_count": 92,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/ajayohri/anaconda3/lib/python3.5/site-packages/ipykernel/__main__.py:1: FutureWarning: sort(columns=....) is deprecated, use sort_values(by=.....)\n",
" if __name__ == '__main__':\n"
]
}
],
"source": [
"diamonds3=diamonds.sort([\"price\"])"
]
},
{
"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>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.23</td>\n",
" <td>Ideal</td>\n",
" <td>E</td>\n",
" <td>SI2</td>\n",
" <td>61.5</td>\n",
" <td>55.0</td>\n",
" <td>326</td>\n",
" <td>3.95</td>\n",
" <td>3.98</td>\n",
" <td>2.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.21</td>\n",
" <td>Premium</td>\n",
" <td>E</td>\n",
" <td>SI1</td>\n",
" <td>59.8</td>\n",
" <td>61.0</td>\n",
" <td>326</td>\n",
" <td>3.89</td>\n",
" <td>3.84</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.23</td>\n",
" <td>Good</td>\n",
" <td>E</td>\n",
" <td>VS1</td>\n",
" <td>56.9</td>\n",
" <td>65.0</td>\n",
" <td>327</td>\n",
" <td>4.05</td>\n",
" <td>4.07</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.29</td>\n",
" <td>Premium</td>\n",
" <td>I</td>\n",
" <td>VS2</td>\n",
" <td>62.4</td>\n",
" <td>58.0</td>\n",
" <td>334</td>\n",
" <td>4.20</td>\n",
" <td>4.23</td>\n",
" <td>2.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.31</td>\n",
" <td>Good</td>\n",
" <td>J</td>\n",
" <td>SI2</td>\n",
" <td>63.3</td>\n",
" <td>58.0</td>\n",
" <td>335</td>\n",
" <td>4.34</td>\n",
" <td>4.35</td>\n",
" <td>2.75</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" carat cut color clarity depth table price x y z\n",
"0 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 2.43\n",
"1 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 2.31\n",
"2 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 2.31\n",
"3 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 2.63\n",
"4 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 2.75"
]
},
"execution_count": 93,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds3.head()"
]
},
{
"cell_type": "code",
"execution_count": 94,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"diamonds4=diamonds.dropna(how='any')"
]
},
{
"cell_type": "code",
"execution_count": 96,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"(53940, 10)"
]
},
"execution_count": 96,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds4.shape"
]
},
{
"cell_type": "code",
"execution_count": 97,
"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>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>0.30</td>\n",
" <td>Good</td>\n",
" <td>I</td>\n",
" <td>SI2</td>\n",
" <td>63.3</td>\n",
" <td>56.0</td>\n",
" <td>351</td>\n",
" <td>4.26</td>\n",
" <td>4.30</td>\n",
" <td>2.71</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>0.23</td>\n",
" <td>Very Good</td>\n",
" <td>E</td>\n",
" <td>VS2</td>\n",
" <td>63.8</td>\n",
" <td>55.0</td>\n",
" <td>352</td>\n",
" <td>3.85</td>\n",
" <td>3.92</td>\n",
" <td>2.48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>0.23</td>\n",
" <td>Very Good</td>\n",
" <td>H</td>\n",
" <td>VS1</td>\n",
" <td>61.0</td>\n",
" <td>57.0</td>\n",
" <td>353</td>\n",
" <td>3.94</td>\n",
" <td>3.96</td>\n",
" <td>2.41</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>0.31</td>\n",
" <td>Very Good</td>\n",
" <td>J</td>\n",
" <td>SI1</td>\n",
" <td>59.4</td>\n",
" <td>62.0</td>\n",
" <td>353</td>\n",
" <td>4.39</td>\n",
" <td>4.43</td>\n",
" <td>2.62</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>0.31</td>\n",
" <td>Very Good</td>\n",
" <td>J</td>\n",
" <td>SI1</td>\n",
" <td>58.1</td>\n",
" <td>62.0</td>\n",
" <td>353</td>\n",
" <td>4.44</td>\n",
" <td>4.47</td>\n",
" <td>2.59</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>0.23</td>\n",
" <td>Very Good</td>\n",
" <td>G</td>\n",
" <td>VVS2</td>\n",
" <td>60.4</td>\n",
" <td>58.0</td>\n",
" <td>354</td>\n",
" <td>3.97</td>\n",
" <td>4.01</td>\n",
" <td>2.41</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>0.24</td>\n",
" <td>Premium</td>\n",
" <td>I</td>\n",
" <td>VS1</td>\n",
" <td>62.5</td>\n",
" <td>57.0</td>\n",
" <td>355</td>\n",
" <td>3.97</td>\n",
" <td>3.94</td>\n",
" <td>2.47</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>0.30</td>\n",
" <td>Very Good</td>\n",
" <td>J</td>\n",
" <td>VS2</td>\n",
" <td>62.2</td>\n",
" <td>57.0</td>\n",
" <td>357</td>\n",
" <td>4.28</td>\n",
" <td>4.30</td>\n",
" <td>2.67</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>0.23</td>\n",
" <td>Very Good</td>\n",
" <td>D</td>\n",
" <td>VS2</td>\n",
" <td>60.5</td>\n",
" <td>61.0</td>\n",
" <td>357</td>\n",
" <td>3.96</td>\n",
" <td>3.97</td>\n",
" <td>2.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>0.23</td>\n",
" <td>Very Good</td>\n",
" <td>F</td>\n",
" <td>VS1</td>\n",
" <td>60.9</td>\n",
" <td>57.0</td>\n",
" <td>357</td>\n",
" <td>3.96</td>\n",
" <td>3.99</td>\n",
" <td>2.42</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>0.23</td>\n",
" <td>Very Good</td>\n",
" <td>F</td>\n",
" <td>VS1</td>\n",
" <td>60.0</td>\n",
" <td>57.0</td>\n",
" <td>402</td>\n",
" <td>4.00</td>\n",
" <td>4.03</td>\n",
" <td>2.41</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" carat cut color clarity depth table price x y z\n",
"20 0.30 Good I SI2 63.3 56.0 351 4.26 4.30 2.71\n",
"21 0.23 Very Good E VS2 63.8 55.0 352 3.85 3.92 2.48\n",
"22 0.23 Very Good H VS1 61.0 57.0 353 3.94 3.96 2.41\n",
"23 0.31 Very Good J SI1 59.4 62.0 353 4.39 4.43 2.62\n",
"24 0.31 Very Good J SI1 58.1 62.0 353 4.44 4.47 2.59\n",
"25 0.23 Very Good G VVS2 60.4 58.0 354 3.97 4.01 2.41\n",
"26 0.24 Premium I VS1 62.5 57.0 355 3.97 3.94 2.47\n",
"27 0.30 Very Good J VS2 62.2 57.0 357 4.28 4.30 2.67\n",
"28 0.23 Very Good D VS2 60.5 61.0 357 3.96 3.97 2.40\n",
"29 0.23 Very Good F VS1 60.9 57.0 357 3.96 3.99 2.42\n",
"30 0.23 Very Good F VS1 60.0 57.0 402 4.00 4.03 2.41"
]
},
"execution_count": 97,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.ix[20:30]"
]
},
{
"cell_type": "code",
"execution_count": 98,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"20 Good\n",
"21 Very Good\n",
"22 Very Good\n",
"23 Very Good\n",
"24 Very Good\n",
"25 Very Good\n",
"26 Premium\n",
"27 Very Good\n",
"28 Very Good\n",
"29 Very Good\n",
"30 Very Good\n",
"Name: cut, dtype: object"
]
},
"execution_count": 98,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.ix[20:30].cut"
]
},
{
"cell_type": "code",
"execution_count": 99,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"20 I\n",
"21 E\n",
"22 H\n",
"23 J\n",
"24 J\n",
"25 G\n",
"26 I\n",
"27 J\n",
"28 D\n",
"29 F\n",
"30 F\n",
"Name: color, dtype: object"
]
},
"execution_count": 99,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.ix[20:30][\"color\"]"
]
},
{
"cell_type": "code",
"execution_count": 102,
"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>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>Good</td>\n",
" <td>I</td>\n",
" <td>SI2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>Very Good</td>\n",
" <td>E</td>\n",
" <td>VS2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>Very Good</td>\n",
" <td>H</td>\n",
" <td>VS1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>Very Good</td>\n",
" <td>J</td>\n",
" <td>SI1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>Very Good</td>\n",
" <td>J</td>\n",
" <td>SI1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>Very Good</td>\n",
" <td>G</td>\n",
" <td>VVS2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>Premium</td>\n",
" <td>I</td>\n",
" <td>VS1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>Very Good</td>\n",
" <td>J</td>\n",
" <td>VS2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>Very Good</td>\n",
" <td>D</td>\n",
" <td>VS2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>Very Good</td>\n",
" <td>F</td>\n",
" <td>VS1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" cut color clarity\n",
"20 Good I SI2\n",
"21 Very Good E VS2\n",
"22 Very Good H VS1\n",
"23 Very Good J SI1\n",
"24 Very Good J SI1\n",
"25 Very Good G VVS2\n",
"26 Premium I VS1\n",
"27 Very Good J VS2\n",
"28 Very Good D VS2\n",
"29 Very Good F VS1"
]
},
"execution_count": 102,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds[[\"cut\",\"color\",\"clarity\"]][20:30]"
]
},
{
"cell_type": "code",
"execution_count": 103,
"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>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ideal</td>\n",
" <td>E</td>\n",
" <td>SI2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Premium</td>\n",
" <td>E</td>\n",
" <td>SI1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Good</td>\n",
" <td>E</td>\n",
" <td>VS1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Premium</td>\n",
" <td>I</td>\n",
" <td>VS2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Good</td>\n",
" <td>J</td>\n",
" <td>SI2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" cut color clarity\n",
"0 Ideal E SI2\n",
"1 Premium E SI1\n",
"2 Good E VS1\n",
"3 Premium I VS2\n",
"4 Good J SI2"
]
},
"execution_count": 103,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds[[\"cut\",\"color\",\"clarity\"]].head()"
]
},
{
"cell_type": "code",
"execution_count": 105,
"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>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>Good</td>\n",
" <td>I</td>\n",
" <td>SI2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>Very Good</td>\n",
" <td>E</td>\n",
" <td>VS2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>Very Good</td>\n",
" <td>H</td>\n",
" <td>VS1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>Very Good</td>\n",
" <td>J</td>\n",
" <td>SI1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>Very Good</td>\n",
" <td>J</td>\n",
" <td>SI1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>Very Good</td>\n",
" <td>G</td>\n",
" <td>VVS2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>Premium</td>\n",
" <td>I</td>\n",
" <td>VS1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>Very Good</td>\n",
" <td>J</td>\n",
" <td>VS2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>Very Good</td>\n",
" <td>D</td>\n",
" <td>VS2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>Very Good</td>\n",
" <td>F</td>\n",
" <td>VS1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>Very Good</td>\n",
" <td>F</td>\n",
" <td>VS1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" cut color clarity\n",
"20 Good I SI2\n",
"21 Very Good E VS2\n",
"22 Very Good H VS1\n",
"23 Very Good J SI1\n",
"24 Very Good J SI1\n",
"25 Very Good G VVS2\n",
"26 Premium I VS1\n",
"27 Very Good J VS2\n",
"28 Very Good D VS2\n",
"29 Very Good F VS1\n",
"30 Very Good F VS1"
]
},
"execution_count": 105,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.ix[20:30,[\"cut\",\"color\",\"clarity\"]]"
]
},
{
"cell_type": "code",
"execution_count": 106,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import numpy as np"
]
},
{
"cell_type": "code",
"execution_count": 107,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"rows=np.random.choice(diamonds.index.values,round(0.0001*len(diamonds)))"
]
},
{
"cell_type": "code",
"execution_count": 110,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"53940"
]
},
"execution_count": 110,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(diamonds)"
]
},
{
"cell_type": "code",
"execution_count": 111,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"5.394"
]
},
"execution_count": 111,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"0.0001*len(diamonds)"
]
},
{
"cell_type": "code",
"execution_count": 112,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"5"
]
},
"execution_count": 112,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"round(0.0001*len(diamonds))"
]
},
{
"cell_type": "code",
"execution_count": 109,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([ 0, 1, 2, ..., 53937, 53938, 53939])"
]
},
"execution_count": 109,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.index.values"
]
},
{
"cell_type": "code",
"execution_count": 108,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[26766 43621 3614 35052 51042]\n"
]
}
],
"source": [
"print(rows)"
]
},
{
"cell_type": "code",
"execution_count": 114,
"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>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>26766</th>\n",
" <td>2.45</td>\n",
" <td>Ideal</td>\n",
" <td>F</td>\n",
" <td>SI2</td>\n",
" <td>62.0</td>\n",
" <td>55.0</td>\n",
" <td>16589</td>\n",
" <td>8.67</td>\n",
" <td>8.64</td>\n",
" <td>5.36</td>\n",
" </tr>\n",
" <tr>\n",
" <th>43621</th>\n",
" <td>0.46</td>\n",
" <td>Premium</td>\n",
" <td>F</td>\n",
" <td>VS1</td>\n",
" <td>60.5</td>\n",
" <td>58.0</td>\n",
" <td>1432</td>\n",
" <td>5.02</td>\n",
" <td>4.97</td>\n",
" <td>3.02</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3614</th>\n",
" <td>1.05</td>\n",
" <td>Ideal</td>\n",
" <td>I</td>\n",
" <td>VS2</td>\n",
" <td>62.2</td>\n",
" <td>56.0</td>\n",
" <td>3428</td>\n",
" <td>6.52</td>\n",
" <td>6.50</td>\n",
" <td>4.05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>35052</th>\n",
" <td>0.31</td>\n",
" <td>Ideal</td>\n",
" <td>F</td>\n",
" <td>VVS1</td>\n",
" <td>61.8</td>\n",
" <td>56.0</td>\n",
" <td>884</td>\n",
" <td>4.33</td>\n",
" <td>4.37</td>\n",
" <td>2.69</td>\n",
" </tr>\n",
" <tr>\n",
" <th>51042</th>\n",
" <td>0.70</td>\n",
" <td>Good</td>\n",
" <td>H</td>\n",
" <td>VS2</td>\n",
" <td>64.2</td>\n",
" <td>58.0</td>\n",
" <td>2330</td>\n",
" <td>5.58</td>\n",
" <td>5.61</td>\n",
" <td>3.59</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" carat cut color clarity depth table price x y z\n",
"26766 2.45 Ideal F SI2 62.0 55.0 16589 8.67 8.64 5.36\n",
"43621 0.46 Premium F VS1 60.5 58.0 1432 5.02 4.97 3.02\n",
"3614 1.05 Ideal I VS2 62.2 56.0 3428 6.52 6.50 4.05\n",
"35052 0.31 Ideal F VVS1 61.8 56.0 884 4.33 4.37 2.69\n",
"51042 0.70 Good H VS2 64.2 58.0 2330 5.58 5.61 3.59"
]
},
"execution_count": 114,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.ix[rows]"
]
},
{
"cell_type": "code",
"execution_count": 119,
"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>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>25998</th>\n",
" <td>4.01</td>\n",
" <td>Premium</td>\n",
" <td>I</td>\n",
" <td>I1</td>\n",
" <td>61.0</td>\n",
" <td>61.0</td>\n",
" <td>15223</td>\n",
" <td>10.14</td>\n",
" <td>10.10</td>\n",
" <td>6.17</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25999</th>\n",
" <td>4.01</td>\n",
" <td>Premium</td>\n",
" <td>J</td>\n",
" <td>I1</td>\n",
" <td>62.5</td>\n",
" <td>62.0</td>\n",
" <td>15223</td>\n",
" <td>10.02</td>\n",
" <td>9.94</td>\n",
" <td>6.24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26444</th>\n",
" <td>4.00</td>\n",
" <td>Very Good</td>\n",
" <td>I</td>\n",
" <td>I1</td>\n",
" <td>63.3</td>\n",
" <td>58.0</td>\n",
" <td>15984</td>\n",
" <td>10.01</td>\n",
" <td>9.94</td>\n",
" <td>6.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27130</th>\n",
" <td>4.13</td>\n",
" <td>Fair</td>\n",
" <td>H</td>\n",
" <td>I1</td>\n",
" <td>64.8</td>\n",
" <td>61.0</td>\n",
" <td>17329</td>\n",
" <td>10.00</td>\n",
" <td>9.85</td>\n",
" <td>6.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27415</th>\n",
" <td>5.01</td>\n",
" <td>Fair</td>\n",
" <td>J</td>\n",
" <td>I1</td>\n",
" <td>65.5</td>\n",
" <td>59.0</td>\n",
" <td>18018</td>\n",
" <td>10.74</td>\n",
" <td>10.54</td>\n",
" <td>6.98</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27630</th>\n",
" <td>4.50</td>\n",
" <td>Fair</td>\n",
" <td>J</td>\n",
" <td>I1</td>\n",
" <td>65.8</td>\n",
" <td>58.0</td>\n",
" <td>18531</td>\n",
" <td>10.23</td>\n",
" <td>10.16</td>\n",
" <td>6.72</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" carat cut color clarity depth table price x y z\n",
"25998 4.01 Premium I I1 61.0 61.0 15223 10.14 10.10 6.17\n",
"25999 4.01 Premium J I1 62.5 62.0 15223 10.02 9.94 6.24\n",
"26444 4.00 Very Good I I1 63.3 58.0 15984 10.01 9.94 6.31\n",
"27130 4.13 Fair H I1 64.8 61.0 17329 10.00 9.85 6.43\n",
"27415 5.01 Fair J I1 65.5 59.0 18018 10.74 10.54 6.98\n",
"27630 4.50 Fair J I1 65.8 58.0 18531 10.23 10.16 6.72"
]
},
"execution_count": 119,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds[diamonds['carat']>3.7]"
]
},
{
"cell_type": "code",
"execution_count": 123,
"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>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>25999</th>\n",
" <td>4.01</td>\n",
" <td>Premium</td>\n",
" <td>J</td>\n",
" <td>I1</td>\n",
" <td>62.5</td>\n",
" <td>62.0</td>\n",
" <td>15223</td>\n",
" <td>10.02</td>\n",
" <td>9.94</td>\n",
" <td>6.24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27415</th>\n",
" <td>5.01</td>\n",
" <td>Fair</td>\n",
" <td>J</td>\n",
" <td>I1</td>\n",
" <td>65.5</td>\n",
" <td>59.0</td>\n",
" <td>18018</td>\n",
" <td>10.74</td>\n",
" <td>10.54</td>\n",
" <td>6.98</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27630</th>\n",
" <td>4.50</td>\n",
" <td>Fair</td>\n",
" <td>J</td>\n",
" <td>I1</td>\n",
" <td>65.8</td>\n",
" <td>58.0</td>\n",
" <td>18531</td>\n",
" <td>10.23</td>\n",
" <td>10.16</td>\n",
" <td>6.72</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27679</th>\n",
" <td>3.51</td>\n",
" <td>Premium</td>\n",
" <td>J</td>\n",
" <td>VS2</td>\n",
" <td>62.5</td>\n",
" <td>59.0</td>\n",
" <td>18701</td>\n",
" <td>9.66</td>\n",
" <td>9.63</td>\n",
" <td>6.03</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" carat cut color clarity depth table price x y z\n",
"25999 4.01 Premium J I1 62.5 62.0 15223 10.02 9.94 6.24\n",
"27415 5.01 Fair J I1 65.5 59.0 18018 10.74 10.54 6.98\n",
"27630 4.50 Fair J I1 65.8 58.0 18531 10.23 10.16 6.72\n",
"27679 3.51 Premium J VS2 62.5 59.0 18701 9.66 9.63 6.03"
]
},
"execution_count": 123,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds.query('carat >3.5 and color == \"J\"')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"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