alihan/Data-Visualization
1
0
Fork 0
mirror of https://github.com/datasciencescoop/Data-Visualization.git synced 2021-05-12 19:42:19 +03:00
Code Issues Projects Releases Wiki Activity
Files
bac3fe37e0a2b5d6fdff07e7a78d05476cd15536
Data-Visualization/Seaborn/1. Loading Datasets.ipynb
abhat222 3471b55ae1 Create 1. Loading Datasets.ipynb
2020-05-09 17:42:11 +05:30

4257 lines
138 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<!DOCTYPE html>\n",
"<html>\n",
"<body>\n",
"<div align=\"center\">\n",
"<h3>Prepared by Asif Bhat</h3>\n",
" \n",
"<h1>Data Visualization With Seaborn</h1>\n",
"\n",
"<h3>Follow Me on - <a href=\"https://www.linkedin.com/in/asif-bhat/\">LinkedIn</a>&nbsp; <a href=\"https://mobile.twitter.com/_asifbhat_\">Twitter</a>&nbsp; <a href=\"https://www.instagram.com/datasciencescoop/?hl=en\">Instagram</a>&nbsp; <a href=\"https://www.facebook.com/datasciencescoop/\">Facebook</a></h3>\n",
"\n",
"</div>\n",
"</body>\n",
"</html>"
]
},
{
"cell_type": "code",
"execution_count": 674,
"metadata": {},
"outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"import pandas as pd\n",
"import seaborn as sns\n",
"import matplotlib as mpl"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Loading Datasets"
]
},
{
"cell_type": "code",
"execution_count": 675,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>#</th>\n",
" <th>Name</th>\n",
" <th>Type 1</th>\n",
" <th>Type 2</th>\n",
" <th>HP</th>\n",
" <th>Attack</th>\n",
" <th>Defense</th>\n",
" <th>Sp. Atk</th>\n",
" <th>Sp. Def</th>\n",
" <th>Speed</th>\n",
" <th>Generation</th>\n",
" <th>Legendary</th>\n",
" <th>Total</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Bulbasaur</td>\n",
" <td>Grass</td>\n",
" <td>Poison</td>\n",
" <td>45</td>\n",
" <td>49</td>\n",
" <td>49</td>\n",
" <td>65</td>\n",
" <td>65</td>\n",
" <td>45</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>318</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>Ivysaur</td>\n",
" <td>Grass</td>\n",
" <td>Poison</td>\n",
" <td>60</td>\n",
" <td>62</td>\n",
" <td>63</td>\n",
" <td>80</td>\n",
" <td>80</td>\n",
" <td>60</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>405</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>Venusaur</td>\n",
" <td>Grass</td>\n",
" <td>Poison</td>\n",
" <td>80</td>\n",
" <td>82</td>\n",
" <td>83</td>\n",
" <td>100</td>\n",
" <td>100</td>\n",
" <td>80</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>525</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>VenusaurMega Venusaur</td>\n",
" <td>Grass</td>\n",
" <td>Poison</td>\n",
" <td>80</td>\n",
" <td>100</td>\n",
" <td>123</td>\n",
" <td>122</td>\n",
" <td>120</td>\n",
" <td>80</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>625</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>Charmander</td>\n",
" <td>Fire</td>\n",
" <td>NaN</td>\n",
" <td>39</td>\n",
" <td>52</td>\n",
" <td>43</td>\n",
" <td>60</td>\n",
" <td>50</td>\n",
" <td>65</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>309</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>5</td>\n",
" <td>Charmeleon</td>\n",
" <td>Fire</td>\n",
" <td>NaN</td>\n",
" <td>58</td>\n",
" <td>64</td>\n",
" <td>58</td>\n",
" <td>80</td>\n",
" <td>65</td>\n",
" <td>80</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>405</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>6</td>\n",
" <td>Charizard</td>\n",
" <td>Fire</td>\n",
" <td>Flying</td>\n",
" <td>78</td>\n",
" <td>84</td>\n",
" <td>78</td>\n",
" <td>109</td>\n",
" <td>85</td>\n",
" <td>100</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>534</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>6</td>\n",
" <td>CharizardMega Charizard X</td>\n",
" <td>Fire</td>\n",
" <td>Dragon</td>\n",
" <td>78</td>\n",
" <td>130</td>\n",
" <td>111</td>\n",
" <td>130</td>\n",
" <td>85</td>\n",
" <td>100</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>634</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>6</td>\n",
" <td>CharizardMega Charizard Y</td>\n",
" <td>Fire</td>\n",
" <td>Flying</td>\n",
" <td>78</td>\n",
" <td>104</td>\n",
" <td>78</td>\n",
" <td>159</td>\n",
" <td>115</td>\n",
" <td>100</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>634</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>7</td>\n",
" <td>Squirtle</td>\n",
" <td>Water</td>\n",
" <td>NaN</td>\n",
" <td>44</td>\n",
" <td>48</td>\n",
" <td>65</td>\n",
" <td>50</td>\n",
" <td>64</td>\n",
" <td>43</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>314</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" # Name Type 1 Type 2 HP Attack Defense Sp. Atk \\\n",
"0 1 Bulbasaur Grass Poison 45 49 49 65 \n",
"1 2 Ivysaur Grass Poison 60 62 63 80 \n",
"2 3 Venusaur Grass Poison 80 82 83 100 \n",
"3 3 VenusaurMega Venusaur Grass Poison 80 100 123 122 \n",
"4 4 Charmander Fire NaN 39 52 43 60 \n",
"5 5 Charmeleon Fire NaN 58 64 58 80 \n",
"6 6 Charizard Fire Flying 78 84 78 109 \n",
"7 6 CharizardMega Charizard X Fire Dragon 78 130 111 130 \n",
"8 6 CharizardMega Charizard Y Fire Flying 78 104 78 159 \n",
"9 7 Squirtle Water NaN 44 48 65 50 \n",
"\n",
" Sp. Def Speed Generation Legendary Total \n",
"0 65 45 1 False 318 \n",
"1 80 60 1 False 405 \n",
"2 100 80 1 False 525 \n",
"3 120 80 1 False 625 \n",
"4 50 65 1 False 309 \n",
"5 65 80 1 False 405 \n",
"6 85 100 1 False 534 \n",
"7 85 100 1 False 634 \n",
"8 115 100 1 False 634 \n",
"9 64 43 1 False 314 "
]
},
"execution_count": 675,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pokemon = pd.read_csv(\"pokemon_updated.csv\")\n",
"pokemon.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 676,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>gender</th>\n",
" <th>race/ethnicity</th>\n",
" <th>parental level of education</th>\n",
" <th>lunch</th>\n",
" <th>test preparation course</th>\n",
" <th>math score</th>\n",
" <th>reading score</th>\n",
" <th>writing score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>female</td>\n",
" <td>group B</td>\n",
" <td>bachelor's degree</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>72</td>\n",
" <td>72</td>\n",
" <td>74</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>female</td>\n",
" <td>group C</td>\n",
" <td>some college</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>69</td>\n",
" <td>90</td>\n",
" <td>88</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>female</td>\n",
" <td>group B</td>\n",
" <td>master's degree</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>90</td>\n",
" <td>95</td>\n",
" <td>93</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>male</td>\n",
" <td>group A</td>\n",
" <td>associate's degree</td>\n",
" <td>free/reduced</td>\n",
" <td>none</td>\n",
" <td>47</td>\n",
" <td>57</td>\n",
" <td>44</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>male</td>\n",
" <td>group C</td>\n",
" <td>some college</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>76</td>\n",
" <td>78</td>\n",
" <td>75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>female</td>\n",
" <td>group B</td>\n",
" <td>associate's degree</td>\n",
" <td>standard</td>\n",
" <td>none</td>\n",
" <td>71</td>\n",
" <td>83</td>\n",
" <td>78</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>female</td>\n",
" <td>group B</td>\n",
" <td>some college</td>\n",
" <td>standard</td>\n",
" <td>completed</td>\n",
" <td>88</td>\n",
" <td>95</td>\n",
" <td>92</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>male</td>\n",
" <td>group B</td>\n",
" <td>some college</td>\n",
" <td>free/reduced</td>\n",
" <td>none</td>\n",
" <td>40</td>\n",
" <td>43</td>\n",
" <td>39</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>male</td>\n",
" <td>group D</td>\n",
" <td>high school</td>\n",
" <td>free/reduced</td>\n",
" <td>completed</td>\n",
" <td>64</td>\n",
" <td>64</td>\n",
" <td>67</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>female</td>\n",
" <td>group B</td>\n",
" <td>high school</td>\n",
" <td>free/reduced</td>\n",
" <td>none</td>\n",
" <td>38</td>\n",
" <td>60</td>\n",
" <td>50</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" gender race/ethnicity parental level of education lunch \\\n",
"0 female group B bachelor's degree standard \n",
"1 female group C some college standard \n",
"2 female group B master's degree standard \n",
"3 male group A associate's degree free/reduced \n",
"4 male group C some college standard \n",
"5 female group B associate's degree standard \n",
"6 female group B some college standard \n",
"7 male group B some college free/reduced \n",
"8 male group D high school free/reduced \n",
"9 female group B high school free/reduced \n",
"\n",
" test preparation course math score reading score writing score \n",
"0 none 72 72 74 \n",
"1 completed 69 90 88 \n",
"2 none 90 95 93 \n",
"3 none 47 57 44 \n",
"4 none 76 78 75 \n",
"5 none 71 83 78 \n",
"6 completed 88 95 92 \n",
"7 none 40 43 39 \n",
"8 completed 64 64 67 \n",
"9 none 38 60 50 "
]
},
"execution_count": 676,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"stdperf = pd.read_csv(\"studentp.csv\")\n",
"stdperf.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 677,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Country</th>\n",
" <th>Confirmed</th>\n",
" <th>Recovered</th>\n",
" <th>Deaths</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Date</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2020-01-22</th>\n",
" <td>Afghanistan</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2020-01-22</th>\n",
" <td>Albania</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2020-01-22</th>\n",
" <td>Algeria</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2020-01-22</th>\n",
" <td>Andorra</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2020-01-22</th>\n",
" <td>Angola</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2020-01-22</th>\n",
" <td>Antigua and Barbuda</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2020-01-22</th>\n",
" <td>Argentina</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2020-01-22</th>\n",
" <td>Armenia</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2020-01-22</th>\n",
" <td>Australia</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2020-01-22</th>\n",
" <td>Austria</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Country Confirmed Recovered Deaths\n",
"Date \n",
"2020-01-22 Afghanistan 0 0 0\n",
"2020-01-22 Albania 0 0 0\n",
"2020-01-22 Algeria 0 0 0\n",
"2020-01-22 Andorra 0 0 0\n",
"2020-01-22 Angola 0 0 0\n",
"2020-01-22 Antigua and Barbuda 0 0 0\n",
"2020-01-22 Argentina 0 0 0\n",
"2020-01-22 Armenia 0 0 0\n",
"2020-01-22 Australia 0 0 0\n",
"2020-01-22 Austria 0 0 0"
]
},
"execution_count": 677,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"corona = pd.read_csv('C:/Users/DELL/Documents/GitHub/Public/COVID-19/covid/data/countries-aggregated.csv' ,\n",
" index_col='Date' , parse_dates=True)\n",
"corona.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 678,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Shape of You</th>\n",
" <th>Despacito</th>\n",
" <th>Something Just Like This</th>\n",
" <th>HUMBLE.</th>\n",
" <th>Unforgettable</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Date</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>2017-01-06</th>\n",
" <td>12287078</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-01-07</th>\n",
" <td>13190270</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-01-08</th>\n",
" <td>13099919</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-01-09</th>\n",
" <td>14506351</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-01-10</th>\n",
" <td>14275628</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-01-11</th>\n",
" <td>14372699</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-01-12</th>\n",
" <td>14148108</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-01-13</th>\n",
" <td>14536236</td>\n",
" <td>275178.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-01-14</th>\n",
" <td>14173311</td>\n",
" <td>1144886.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-01-15</th>\n",
" <td>12889849</td>\n",
" <td>1288198.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Shape of You Despacito Something Just Like This HUMBLE. \\\n",
"Date \n",
"2017-01-06 12287078 NaN NaN NaN \n",
"2017-01-07 13190270 NaN NaN NaN \n",
"2017-01-08 13099919 NaN NaN NaN \n",
"2017-01-09 14506351 NaN NaN NaN \n",
"2017-01-10 14275628 NaN NaN NaN \n",
"2017-01-11 14372699 NaN NaN NaN \n",
"2017-01-12 14148108 NaN NaN NaN \n",
"2017-01-13 14536236 275178.0 NaN NaN \n",
"2017-01-14 14173311 1144886.0 NaN NaN \n",
"2017-01-15 12889849 1288198.0 NaN NaN \n",
"\n",
" Unforgettable \n",
"Date \n",
"2017-01-06 NaN \n",
"2017-01-07 NaN \n",
"2017-01-08 NaN \n",
"2017-01-09 NaN \n",
"2017-01-10 NaN \n",
"2017-01-11 NaN \n",
"2017-01-12 NaN \n",
"2017-01-13 NaN \n",
"2017-01-14 NaN \n",
"2017-01-15 NaN "
]
},
"execution_count": 678,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"spotify = pd.read_csv(\"spotify.csv\" , index_col=\"Date\")\n",
"spotify.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 679,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>longitude</th>\n",
" <th>latitude</th>\n",
" <th>housing_median_age</th>\n",
" <th>total_rooms</th>\n",
" <th>total_bedrooms</th>\n",
" <th>population</th>\n",
" <th>households</th>\n",
" <th>median_income</th>\n",
" <th>median_house_value</th>\n",
" <th>ocean_proximity</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>20635</th>\n",
" <td>-121.09</td>\n",
" <td>39.48</td>\n",
" <td>25.0</td>\n",
" <td>1665.0</td>\n",
" <td>374.0</td>\n",
" <td>845.0</td>\n",
" <td>330.0</td>\n",
" <td>1.5603</td>\n",
" <td>78100.0</td>\n",
" <td>INLAND</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20636</th>\n",
" <td>-121.21</td>\n",
" <td>39.49</td>\n",
" <td>18.0</td>\n",
" <td>697.0</td>\n",
" <td>150.0</td>\n",
" <td>356.0</td>\n",
" <td>114.0</td>\n",
" <td>2.5568</td>\n",
" <td>77100.0</td>\n",
" <td>INLAND</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20637</th>\n",
" <td>-121.22</td>\n",
" <td>39.43</td>\n",
" <td>17.0</td>\n",
" <td>2254.0</td>\n",
" <td>485.0</td>\n",
" <td>1007.0</td>\n",
" <td>433.0</td>\n",
" <td>1.7000</td>\n",
" <td>92300.0</td>\n",
" <td>INLAND</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20638</th>\n",
" <td>-121.32</td>\n",
" <td>39.43</td>\n",
" <td>18.0</td>\n",
" <td>1860.0</td>\n",
" <td>409.0</td>\n",
" <td>741.0</td>\n",
" <td>349.0</td>\n",
" <td>1.8672</td>\n",
" <td>84700.0</td>\n",
" <td>INLAND</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20639</th>\n",
" <td>-121.24</td>\n",
" <td>39.37</td>\n",
" <td>16.0</td>\n",
" <td>2785.0</td>\n",
" <td>616.0</td>\n",
" <td>1387.0</td>\n",
" <td>530.0</td>\n",
" <td>2.3886</td>\n",
" <td>89400.0</td>\n",
" <td>INLAND</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" longitude latitude housing_median_age total_rooms total_bedrooms \\\n",
"20635 -121.09 39.48 25.0 1665.0 374.0 \n",
"20636 -121.21 39.49 18.0 697.0 150.0 \n",
"20637 -121.22 39.43 17.0 2254.0 485.0 \n",
"20638 -121.32 39.43 18.0 1860.0 409.0 \n",
"20639 -121.24 39.37 16.0 2785.0 616.0 \n",
"\n",
" population households median_income median_house_value \\\n",
"20635 845.0 330.0 1.5603 78100.0 \n",
"20636 356.0 114.0 2.5568 77100.0 \n",
"20637 1007.0 433.0 1.7000 92300.0 \n",
"20638 741.0 349.0 1.8672 84700.0 \n",
"20639 1387.0 530.0 2.3886 89400.0 \n",
"\n",
" ocean_proximity \n",
"20635 INLAND \n",
"20636 INLAND \n",
"20637 INLAND \n",
"20638 INLAND \n",
"20639 INLAND "
]
},
"execution_count": 679,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"housing = pd.read_csv('C:/Users/DELL/Documents/GitHub/Data-Visualization/housing.csv')\n",
"housing.tail()"
]
},
{
"cell_type": "code",
"execution_count": 680,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>age</th>\n",
" <th>sex</th>\n",
" <th>bmi</th>\n",
" <th>children</th>\n",
" <th>smoker</th>\n",
" <th>region</th>\n",
" <th>charges</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>19</td>\n",
" <td>female</td>\n",
" <td>27.900</td>\n",
" <td>0</td>\n",
" <td>yes</td>\n",
" <td>southwest</td>\n",
" <td>16884.92400</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>18</td>\n",
" <td>male</td>\n",
" <td>33.770</td>\n",
" <td>1</td>\n",
" <td>no</td>\n",
" <td>southeast</td>\n",
" <td>1725.55230</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>28</td>\n",
" <td>male</td>\n",
" <td>33.000</td>\n",
" <td>3</td>\n",
" <td>no</td>\n",
" <td>southeast</td>\n",
" <td>4449.46200</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>33</td>\n",
" <td>male</td>\n",
" <td>22.705</td>\n",
" <td>0</td>\n",
" <td>no</td>\n",
" <td>northwest</td>\n",
" <td>21984.47061</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>32</td>\n",
" <td>male</td>\n",
" <td>28.880</td>\n",
" <td>0</td>\n",
" <td>no</td>\n",
" <td>northwest</td>\n",
" <td>3866.85520</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>31</td>\n",
" <td>female</td>\n",
" <td>25.740</td>\n",
" <td>0</td>\n",
" <td>no</td>\n",
" <td>southeast</td>\n",
" <td>3756.62160</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>46</td>\n",
" <td>female</td>\n",
" <td>33.440</td>\n",
" <td>1</td>\n",
" <td>no</td>\n",
" <td>southeast</td>\n",
" <td>8240.58960</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>37</td>\n",
" <td>female</td>\n",
" <td>27.740</td>\n",
" <td>3</td>\n",
" <td>no</td>\n",
" <td>northwest</td>\n",
" <td>7281.50560</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>37</td>\n",
" <td>male</td>\n",
" <td>29.830</td>\n",
" <td>2</td>\n",
" <td>no</td>\n",
" <td>northeast</td>\n",
" <td>6406.41070</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>60</td>\n",
" <td>female</td>\n",
" <td>25.840</td>\n",
" <td>0</td>\n",
" <td>no</td>\n",
" <td>northwest</td>\n",
" <td>28923.13692</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" age sex bmi children smoker region charges\n",
"0 19 female 27.900 0 yes southwest 16884.92400\n",
"1 18 male 33.770 1 no southeast 1725.55230\n",
"2 28 male 33.000 3 no southeast 4449.46200\n",
"3 33 male 22.705 0 no northwest 21984.47061\n",
"4 32 male 28.880 0 no northwest 3866.85520\n",
"5 31 female 25.740 0 no southeast 3756.62160\n",
"6 46 female 33.440 1 no southeast 8240.58960\n",
"7 37 female 27.740 3 no northwest 7281.50560\n",
"8 37 male 29.830 2 no northeast 6406.41070\n",
"9 60 female 25.840 0 no northwest 28923.13692"
]
},
"execution_count": 680,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"insurance = pd.read_csv('C:/Users/DELL/Documents/GitHub/Data-Visualization/insurance.csv')\n",
"insurance.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 681,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Age</th>\n",
" <th>Gender</th>\n",
" <th>Period</th>\n",
" <th>Unemployed</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>16 to 19 years</td>\n",
" <td>Men</td>\n",
" <td>2005-01-01</td>\n",
" <td>91000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>20 to 24 years</td>\n",
" <td>Men</td>\n",
" <td>2005-01-01</td>\n",
" <td>175000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>25 to 34 years</td>\n",
" <td>Men</td>\n",
" <td>2005-01-01</td>\n",
" <td>194000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>35 to 44 years</td>\n",
" <td>Men</td>\n",
" <td>2005-01-01</td>\n",
" <td>201000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>45 to 54 years</td>\n",
" <td>Men</td>\n",
" <td>2005-01-01</td>\n",
" <td>207000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>55 to 64 years</td>\n",
" <td>Men</td>\n",
" <td>2005-01-01</td>\n",
" <td>101000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>65 years and over</td>\n",
" <td>Men</td>\n",
" <td>2005-01-01</td>\n",
" <td>33000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>16 to 19 years</td>\n",
" <td>Women</td>\n",
" <td>2005-01-01</td>\n",
" <td>38000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>20 to 24 years</td>\n",
" <td>Women</td>\n",
" <td>2005-01-01</td>\n",
" <td>90000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>25 to 34 years</td>\n",
" <td>Women</td>\n",
" <td>2005-01-01</td>\n",
" <td>142000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Age Gender Period Unemployed\n",
"0 16 to 19 years Men 2005-01-01 91000\n",
"1 20 to 24 years Men 2005-01-01 175000\n",
"2 25 to 34 years Men 2005-01-01 194000\n",
"3 35 to 44 years Men 2005-01-01 201000\n",
"4 45 to 54 years Men 2005-01-01 207000\n",
"5 55 to 64 years Men 2005-01-01 101000\n",
"6 65 years and over Men 2005-01-01 33000\n",
"7 16 to 19 years Women 2005-01-01 38000\n",
"8 20 to 24 years Women 2005-01-01 90000\n",
"9 25 to 34 years Women 2005-01-01 142000"
]
},
"execution_count": 681,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"employment = pd.read_excel(\"unemployment.xlsx\")\n",
"employment.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 683,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ticket</th>\n",
" <th>requestor</th>\n",
" <th>RequestorSeniority</th>\n",
" <th>ITOwner</th>\n",
" <th>FiledAgainst</th>\n",
" <th>TicketType</th>\n",
" <th>Severity</th>\n",
" <th>Priority</th>\n",
" <th>daysOpen</th>\n",
" <th>Satisfaction</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>1929</td>\n",
" <td>1 - Junior</td>\n",
" <td>50</td>\n",
" <td>Systems</td>\n",
" <td>Issue</td>\n",
" <td>2 - Normal</td>\n",
" <td>0 - Unassigned</td>\n",
" <td>3</td>\n",
" <td>1 - Unsatisfied</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>1587</td>\n",
" <td>2 - Regular</td>\n",
" <td>15</td>\n",
" <td>Software</td>\n",
" <td>Request</td>\n",
" <td>1 - Minor</td>\n",
" <td>1 - Low</td>\n",
" <td>5</td>\n",
" <td>1 - Unsatisfied</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>925</td>\n",
" <td>2 - Regular</td>\n",
" <td>15</td>\n",
" <td>Access/Login</td>\n",
" <td>Request</td>\n",
" <td>2 - Normal</td>\n",
" <td>0 - Unassigned</td>\n",
" <td>0</td>\n",
" <td>0 - Unknown</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>413</td>\n",
" <td>4 - Management</td>\n",
" <td>22</td>\n",
" <td>Systems</td>\n",
" <td>Request</td>\n",
" <td>2 - Normal</td>\n",
" <td>0 - Unassigned</td>\n",
" <td>20</td>\n",
" <td>0 - Unknown</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>318</td>\n",
" <td>1 - Junior</td>\n",
" <td>22</td>\n",
" <td>Access/Login</td>\n",
" <td>Request</td>\n",
" <td>2 - Normal</td>\n",
" <td>1 - Low</td>\n",
" <td>1</td>\n",
" <td>1 - Unsatisfied</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>6</td>\n",
" <td>858</td>\n",
" <td>4 - Management</td>\n",
" <td>38</td>\n",
" <td>Access/Login</td>\n",
" <td>Request</td>\n",
" <td>2 - Normal</td>\n",
" <td>3 - High</td>\n",
" <td>0</td>\n",
" <td>0 - Unknown</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>7</td>\n",
" <td>1978</td>\n",
" <td>3 - Senior</td>\n",
" <td>10</td>\n",
" <td>Systems</td>\n",
" <td>Request</td>\n",
" <td>2 - Normal</td>\n",
" <td>3 - High</td>\n",
" <td>9</td>\n",
" <td>0 - Unknown</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>8</td>\n",
" <td>1209</td>\n",
" <td>4 - Management</td>\n",
" <td>1</td>\n",
" <td>Software</td>\n",
" <td>Request</td>\n",
" <td>2 - Normal</td>\n",
" <td>0 - Unassigned</td>\n",
" <td>15</td>\n",
" <td>0 - Unknown</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>9</td>\n",
" <td>887</td>\n",
" <td>2 - Regular</td>\n",
" <td>14</td>\n",
" <td>Software</td>\n",
" <td>Request</td>\n",
" <td>2 - Normal</td>\n",
" <td>2 - Medium</td>\n",
" <td>6</td>\n",
" <td>1 - Unsatisfied</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>10</td>\n",
" <td>1780</td>\n",
" <td>3 - Senior</td>\n",
" <td>46</td>\n",
" <td>Access/Login</td>\n",
" <td>Request</td>\n",
" <td>2 - Normal</td>\n",
" <td>1 - Low</td>\n",
" <td>1</td>\n",
" <td>1 - Unsatisfied</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" ticket requestor RequestorSeniority ITOwner FiledAgainst TicketType \\\n",
"0 1 1929 1 - Junior 50 Systems Issue \n",
"1 2 1587 2 - Regular 15 Software Request \n",
"2 3 925 2 - Regular 15 Access/Login Request \n",
"3 4 413 4 - Management 22 Systems Request \n",
"4 5 318 1 - Junior 22 Access/Login Request \n",
"5 6 858 4 - Management 38 Access/Login Request \n",
"6 7 1978 3 - Senior 10 Systems Request \n",
"7 8 1209 4 - Management 1 Software Request \n",
"8 9 887 2 - Regular 14 Software Request \n",
"9 10 1780 3 - Senior 46 Access/Login Request \n",
"\n",
" Severity Priority daysOpen Satisfaction \n",
"0 2 - Normal 0 - Unassigned 3 1 - Unsatisfied \n",
"1 1 - Minor 1 - Low 5 1 - Unsatisfied \n",
"2 2 - Normal 0 - Unassigned 0 0 - Unknown \n",
"3 2 - Normal 0 - Unassigned 20 0 - Unknown \n",
"4 2 - Normal 1 - Low 1 1 - Unsatisfied \n",
"5 2 - Normal 3 - High 0 0 - Unknown \n",
"6 2 - Normal 3 - High 9 0 - Unknown \n",
"7 2 - Normal 0 - Unassigned 15 0 - Unknown \n",
"8 2 - Normal 2 - Medium 6 1 - Unsatisfied \n",
"9 2 - Normal 1 - Low 1 1 - Unsatisfied "
]
},
"execution_count": 683,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"helpdesk = pd.read_csv(\"helpdesk.csv\")\n",
"helpdesk.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 684,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Species</th>\n",
" <th>Weight</th>\n",
" <th>Length1</th>\n",
" <th>Length2</th>\n",
" <th>Length3</th>\n",
" <th>Height</th>\n",
" <th>Width</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Bream</td>\n",
" <td>242.0</td>\n",
" <td>23.2</td>\n",
" <td>25.4</td>\n",
" <td>30.0</td>\n",
" <td>11.5200</td>\n",
" <td>4.0200</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Bream</td>\n",
" <td>290.0</td>\n",
" <td>24.0</td>\n",
" <td>26.3</td>\n",
" <td>31.2</td>\n",
" <td>12.4800</td>\n",
" <td>4.3056</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Bream</td>\n",
" <td>340.0</td>\n",
" <td>23.9</td>\n",
" <td>26.5</td>\n",
" <td>31.1</td>\n",
" <td>12.3778</td>\n",
" <td>4.6961</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Bream</td>\n",
" <td>363.0</td>\n",
" <td>26.3</td>\n",
" <td>29.0</td>\n",
" <td>33.5</td>\n",
" <td>12.7300</td>\n",
" <td>4.4555</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Bream</td>\n",
" <td>430.0</td>\n",
" <td>26.5</td>\n",
" <td>29.0</td>\n",
" <td>34.0</td>\n",
" <td>12.4440</td>\n",
" <td>5.1340</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Bream</td>\n",
" <td>450.0</td>\n",
" <td>26.8</td>\n",
" <td>29.7</td>\n",
" <td>34.7</td>\n",
" <td>13.6024</td>\n",
" <td>4.9274</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Bream</td>\n",
" <td>500.0</td>\n",
" <td>26.8</td>\n",
" <td>29.7</td>\n",
" <td>34.5</td>\n",
" <td>14.1795</td>\n",
" <td>5.2785</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>Bream</td>\n",
" <td>390.0</td>\n",
" <td>27.6</td>\n",
" <td>30.0</td>\n",
" <td>35.0</td>\n",
" <td>12.6700</td>\n",
" <td>4.6900</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Bream</td>\n",
" <td>450.0</td>\n",
" <td>27.6</td>\n",
" <td>30.0</td>\n",
" <td>35.1</td>\n",
" <td>14.0049</td>\n",
" <td>4.8438</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>Bream</td>\n",
" <td>500.0</td>\n",
" <td>28.5</td>\n",
" <td>30.7</td>\n",
" <td>36.2</td>\n",
" <td>14.2266</td>\n",
" <td>4.9594</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Species Weight Length1 Length2 Length3 Height Width\n",
"0 Bream 242.0 23.2 25.4 30.0 11.5200 4.0200\n",
"1 Bream 290.0 24.0 26.3 31.2 12.4800 4.3056\n",
"2 Bream 340.0 23.9 26.5 31.1 12.3778 4.6961\n",
"3 Bream 363.0 26.3 29.0 33.5 12.7300 4.4555\n",
"4 Bream 430.0 26.5 29.0 34.0 12.4440 5.1340\n",
"5 Bream 450.0 26.8 29.7 34.7 13.6024 4.9274\n",
"6 Bream 500.0 26.8 29.7 34.5 14.1795 5.2785\n",
"7 Bream 390.0 27.6 30.0 35.0 12.6700 4.6900\n",
"8 Bream 450.0 27.6 30.0 35.1 14.0049 4.8438\n",
"9 Bream 500.0 28.5 30.7 36.2 14.2266 4.9594"
]
},
"execution_count": 684,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"fish= pd.read_csv(\"Fish.csv\")\n",
"fish.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 685,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>id</th>\n",
" <th>diet</th>\n",
" <th>pulse</th>\n",
" <th>time</th>\n",
" <th>kind</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>low fat</td>\n",
" <td>85</td>\n",
" <td>1 min</td>\n",
" <td>rest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>low fat</td>\n",
" <td>85</td>\n",
" <td>15 min</td>\n",
" <td>rest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>low fat</td>\n",
" <td>88</td>\n",
" <td>30 min</td>\n",
" <td>rest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2</td>\n",
" <td>low fat</td>\n",
" <td>90</td>\n",
" <td>1 min</td>\n",
" <td>rest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>low fat</td>\n",
" <td>92</td>\n",
" <td>15 min</td>\n",
" <td>rest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>2</td>\n",
" <td>low fat</td>\n",
" <td>93</td>\n",
" <td>30 min</td>\n",
" <td>rest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>3</td>\n",
" <td>low fat</td>\n",
" <td>97</td>\n",
" <td>1 min</td>\n",
" <td>rest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>3</td>\n",
" <td>low fat</td>\n",
" <td>97</td>\n",
" <td>15 min</td>\n",
" <td>rest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>3</td>\n",
" <td>low fat</td>\n",
" <td>94</td>\n",
" <td>30 min</td>\n",
" <td>rest</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>4</td>\n",
" <td>low fat</td>\n",
" <td>80</td>\n",
" <td>1 min</td>\n",
" <td>rest</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id diet pulse time kind\n",
"0 1 low fat 85 1 min rest\n",
"1 1 low fat 85 15 min rest\n",
"2 1 low fat 88 30 min rest\n",
"3 2 low fat 90 1 min rest\n",
"4 2 low fat 92 15 min rest\n",
"5 2 low fat 93 30 min rest\n",
"6 3 low fat 97 1 min rest\n",
"7 3 low fat 97 15 min rest\n",
"8 3 low fat 94 30 min rest\n",
"9 4 low fat 80 1 min rest"
]
},
"execution_count": 685,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"exercise = pd.read_csv(\"exercise.csv\")\n",
"exercise.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 686,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>country</th>\n",
" <th>year</th>\n",
" <th>sex</th>\n",
" <th>age</th>\n",
" <th>suicides_no</th>\n",
" <th>population</th>\n",
" <th>suicides/100k pop</th>\n",
" <th>country-year</th>\n",
" <th>HDI for year</th>\n",
" <th>gdp_for_year ($)</th>\n",
" <th>gdp_per_capita ($)</th>\n",
" <th>generation</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Albania</td>\n",
" <td>1987</td>\n",
" <td>male</td>\n",
" <td>15-24 years</td>\n",
" <td>21</td>\n",
" <td>312900</td>\n",
" <td>6.71</td>\n",
" <td>Albania1987</td>\n",
" <td>NaN</td>\n",
" <td>2,156,624,900</td>\n",
" <td>796</td>\n",
" <td>Generation X</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Albania</td>\n",
" <td>1987</td>\n",
" <td>male</td>\n",
" <td>35-54 years</td>\n",
" <td>16</td>\n",
" <td>308000</td>\n",
" <td>5.19</td>\n",
" <td>Albania1987</td>\n",
" <td>NaN</td>\n",
" <td>2,156,624,900</td>\n",
" <td>796</td>\n",
" <td>Silent</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Albania</td>\n",
" <td>1987</td>\n",
" <td>female</td>\n",
" <td>15-24 years</td>\n",
" <td>14</td>\n",
" <td>289700</td>\n",
" <td>4.83</td>\n",
" <td>Albania1987</td>\n",
" <td>NaN</td>\n",
" <td>2,156,624,900</td>\n",
" <td>796</td>\n",
" <td>Generation X</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Albania</td>\n",
" <td>1987</td>\n",
" <td>male</td>\n",
" <td>75+ years</td>\n",
" <td>1</td>\n",
" <td>21800</td>\n",
" <td>4.59</td>\n",
" <td>Albania1987</td>\n",
" <td>NaN</td>\n",
" <td>2,156,624,900</td>\n",
" <td>796</td>\n",
" <td>G.I. Generation</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Albania</td>\n",
" <td>1987</td>\n",
" <td>male</td>\n",
" <td>25-34 years</td>\n",
" <td>9</td>\n",
" <td>274300</td>\n",
" <td>3.28</td>\n",
" <td>Albania1987</td>\n",
" <td>NaN</td>\n",
" <td>2,156,624,900</td>\n",
" <td>796</td>\n",
" <td>Boomers</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Albania</td>\n",
" <td>1987</td>\n",
" <td>female</td>\n",
" <td>75+ years</td>\n",
" <td>1</td>\n",
" <td>35600</td>\n",
" <td>2.81</td>\n",
" <td>Albania1987</td>\n",
" <td>NaN</td>\n",
" <td>2,156,624,900</td>\n",
" <td>796</td>\n",
" <td>G.I. Generation</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Albania</td>\n",
" <td>1987</td>\n",
" <td>female</td>\n",
" <td>35-54 years</td>\n",
" <td>6</td>\n",
" <td>278800</td>\n",
" <td>2.15</td>\n",
" <td>Albania1987</td>\n",
" <td>NaN</td>\n",
" <td>2,156,624,900</td>\n",
" <td>796</td>\n",
" <td>Silent</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>Albania</td>\n",
" <td>1987</td>\n",
" <td>female</td>\n",
" <td>25-34 years</td>\n",
" <td>4</td>\n",
" <td>257200</td>\n",
" <td>1.56</td>\n",
" <td>Albania1987</td>\n",
" <td>NaN</td>\n",
" <td>2,156,624,900</td>\n",
" <td>796</td>\n",
" <td>Boomers</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Albania</td>\n",
" <td>1987</td>\n",
" <td>male</td>\n",
" <td>55-74 years</td>\n",
" <td>1</td>\n",
" <td>137500</td>\n",
" <td>0.73</td>\n",
" <td>Albania1987</td>\n",
" <td>NaN</td>\n",
" <td>2,156,624,900</td>\n",
" <td>796</td>\n",
" <td>G.I. Generation</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>Albania</td>\n",
" <td>1987</td>\n",
" <td>female</td>\n",
" <td>5-14 years</td>\n",
" <td>0</td>\n",
" <td>311000</td>\n",
" <td>0.00</td>\n",
" <td>Albania1987</td>\n",
" <td>NaN</td>\n",
" <td>2,156,624,900</td>\n",
" <td>796</td>\n",
" <td>Generation X</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" country year sex age suicides_no population \\\n",
"0 Albania 1987 male 15-24 years 21 312900 \n",
"1 Albania 1987 male 35-54 years 16 308000 \n",
"2 Albania 1987 female 15-24 years 14 289700 \n",
"3 Albania 1987 male 75+ years 1 21800 \n",
"4 Albania 1987 male 25-34 years 9 274300 \n",
"5 Albania 1987 female 75+ years 1 35600 \n",
"6 Albania 1987 female 35-54 years 6 278800 \n",
"7 Albania 1987 female 25-34 years 4 257200 \n",
"8 Albania 1987 male 55-74 years 1 137500 \n",
"9 Albania 1987 female 5-14 years 0 311000 \n",
"\n",
" suicides/100k pop country-year HDI for year gdp_for_year ($) \\\n",
"0 6.71 Albania1987 NaN 2,156,624,900 \n",
"1 5.19 Albania1987 NaN 2,156,624,900 \n",
"2 4.83 Albania1987 NaN 2,156,624,900 \n",
"3 4.59 Albania1987 NaN 2,156,624,900 \n",
"4 3.28 Albania1987 NaN 2,156,624,900 \n",
"5 2.81 Albania1987 NaN 2,156,624,900 \n",
"6 2.15 Albania1987 NaN 2,156,624,900 \n",
"7 1.56 Albania1987 NaN 2,156,624,900 \n",
"8 0.73 Albania1987 NaN 2,156,624,900 \n",
"9 0.00 Albania1987 NaN 2,156,624,900 \n",
"\n",
" gdp_per_capita ($) generation \n",
"0 796 Generation X \n",
"1 796 Silent \n",
"2 796 Generation X \n",
"3 796 G.I. Generation \n",
"4 796 Boomers \n",
"5 796 G.I. Generation \n",
"6 796 Silent \n",
"7 796 Boomers \n",
"8 796 G.I. Generation \n",
"9 796 Generation X "
]
},
"execution_count": 686,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"suicide = pd.read_csv(\"suicide.csv\") \n",
"suicide.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 687,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Type</th>\n",
" <th>Coverage</th>\n",
" <th>OdName</th>\n",
" <th>AREA</th>\n",
" <th>AreaName</th>\n",
" <th>REG</th>\n",
" <th>RegName</th>\n",
" <th>DEV</th>\n",
" <th>DevName</th>\n",
" <th>1980</th>\n",
" <th>...</th>\n",
" <th>2004</th>\n",
" <th>2005</th>\n",
" <th>2006</th>\n",
" <th>2007</th>\n",
" <th>2008</th>\n",
" <th>2009</th>\n",
" <th>2010</th>\n",
" <th>2011</th>\n",
" <th>2012</th>\n",
" <th>2013</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Immigrants</td>\n",
" <td>Foreigners</td>\n",
" <td>Afghanistan</td>\n",
" <td>935</td>\n",
" <td>Asia</td>\n",
" <td>5501</td>\n",
" <td>Southern Asia</td>\n",
" <td>902</td>\n",
" <td>Developing regions</td>\n",
" <td>16</td>\n",
" <td>...</td>\n",
" <td>2978</td>\n",
" <td>3436</td>\n",
" <td>3009</td>\n",
" <td>2652</td>\n",
" <td>2111</td>\n",
" <td>1746</td>\n",
" <td>1758</td>\n",
" <td>2203</td>\n",
" <td>2635</td>\n",
" <td>2004</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Immigrants</td>\n",
" <td>Foreigners</td>\n",
" <td>Albania</td>\n",
" <td>908</td>\n",
" <td>Europe</td>\n",
" <td>925</td>\n",
" <td>Southern Europe</td>\n",
" <td>901</td>\n",
" <td>Developed regions</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>1450</td>\n",
" <td>1223</td>\n",
" <td>856</td>\n",
" <td>702</td>\n",
" <td>560</td>\n",
" <td>716</td>\n",
" <td>561</td>\n",
" <td>539</td>\n",
" <td>620</td>\n",
" <td>603</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Immigrants</td>\n",
" <td>Foreigners</td>\n",
" <td>Algeria</td>\n",
" <td>903</td>\n",
" <td>Africa</td>\n",
" <td>912</td>\n",
" <td>Northern Africa</td>\n",
" <td>902</td>\n",
" <td>Developing regions</td>\n",
" <td>80</td>\n",
" <td>...</td>\n",
" <td>3616</td>\n",
" <td>3626</td>\n",
" <td>4807</td>\n",
" <td>3623</td>\n",
" <td>4005</td>\n",
" <td>5393</td>\n",
" <td>4752</td>\n",
" <td>4325</td>\n",
" <td>3774</td>\n",
" <td>4331</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Immigrants</td>\n",
" <td>Foreigners</td>\n",
" <td>American Samoa</td>\n",
" <td>909</td>\n",
" <td>Oceania</td>\n",
" <td>957</td>\n",
" <td>Polynesia</td>\n",
" <td>902</td>\n",
" <td>Developing regions</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Immigrants</td>\n",
" <td>Foreigners</td>\n",
" <td>Andorra</td>\n",
" <td>908</td>\n",
" <td>Europe</td>\n",
" <td>925</td>\n",
" <td>Southern Europe</td>\n",
" <td>901</td>\n",
" <td>Developed regions</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 43 columns</p>\n",
"</div>"
],
"text/plain": [
" Type Coverage OdName AREA AreaName REG \\\n",
"0 Immigrants Foreigners Afghanistan 935 Asia 5501 \n",
"1 Immigrants Foreigners Albania 908 Europe 925 \n",
"2 Immigrants Foreigners Algeria 903 Africa 912 \n",
"3 Immigrants Foreigners American Samoa 909 Oceania 957 \n",
"4 Immigrants Foreigners Andorra 908 Europe 925 \n",
"\n",
" RegName DEV DevName 1980 ... 2004 2005 2006 \\\n",
"0 Southern Asia 902 Developing regions 16 ... 2978 3436 3009 \n",
"1 Southern Europe 901 Developed regions 1 ... 1450 1223 856 \n",
"2 Northern Africa 902 Developing regions 80 ... 3616 3626 4807 \n",
"3 Polynesia 902 Developing regions 0 ... 0 0 1 \n",
"4 Southern Europe 901 Developed regions 0 ... 0 0 1 \n",
"\n",
" 2007 2008 2009 2010 2011 2012 2013 \n",
"0 2652 2111 1746 1758 2203 2635 2004 \n",
"1 702 560 716 561 539 620 603 \n",
"2 3623 4005 5393 4752 4325 3774 4331 \n",
"3 0 0 0 0 0 0 0 \n",
"4 1 0 0 0 0 1 1 \n",
"\n",
"[5 rows x 43 columns]"
]
},
"execution_count": 687,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"canada = pd.read_csv(\"canada.csv\")\n",
"canada.head()"
]
},
{
"cell_type": "code",
"execution_count": 688,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['Type', 'Coverage', 'OdName', 'AREA', 'AreaName', 'REG', 'RegName',\n",
" 'DEV', 'DevName', '1980', '1981', '1982', '1983', '1984', '1985',\n",
" '1986', '1987', '1988', '1989', '1990', '1991', '1992', '1993', '1994',\n",
" '1995', '1996', '1997', '1998', '1999', '2000', '2001', '2002', '2003',\n",
" '2004', '2005', '2006', '2007', '2008', '2009', '2010', '2011', '2012',\n",
" '2013'],\n",
" dtype='object')"
]
},
"execution_count": 688,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"canada.columns"
]
},
{
"cell_type": "code",
"execution_count": 689,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>OdName</th>\n",
" <th>1980</th>\n",
" <th>1981</th>\n",
" <th>1982</th>\n",
" <th>1983</th>\n",
" <th>1984</th>\n",
" <th>1985</th>\n",
" <th>1986</th>\n",
" <th>1987</th>\n",
" <th>1988</th>\n",
" <th>...</th>\n",
" <th>2004</th>\n",
" <th>2005</th>\n",
" <th>2006</th>\n",
" <th>2007</th>\n",
" <th>2008</th>\n",
" <th>2009</th>\n",
" <th>2010</th>\n",
" <th>2011</th>\n",
" <th>2012</th>\n",
" <th>2013</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Afghanistan</td>\n",
" <td>16</td>\n",
" <td>39</td>\n",
" <td>39</td>\n",
" <td>47</td>\n",
" <td>71</td>\n",
" <td>340</td>\n",
" <td>496</td>\n",
" <td>741</td>\n",
" <td>828</td>\n",
" <td>...</td>\n",
" <td>2978</td>\n",
" <td>3436</td>\n",
" <td>3009</td>\n",
" <td>2652</td>\n",
" <td>2111</td>\n",
" <td>1746</td>\n",
" <td>1758</td>\n",
" <td>2203</td>\n",
" <td>2635</td>\n",
" <td>2004</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Albania</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>...</td>\n",
" <td>1450</td>\n",
" <td>1223</td>\n",
" <td>856</td>\n",
" <td>702</td>\n",
" <td>560</td>\n",
" <td>716</td>\n",
" <td>561</td>\n",
" <td>539</td>\n",
" <td>620</td>\n",
" <td>603</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Algeria</td>\n",
" <td>80</td>\n",
" <td>67</td>\n",
" <td>71</td>\n",
" <td>69</td>\n",
" <td>63</td>\n",
" <td>44</td>\n",
" <td>69</td>\n",
" <td>132</td>\n",
" <td>242</td>\n",
" <td>...</td>\n",
" <td>3616</td>\n",
" <td>3626</td>\n",
" <td>4807</td>\n",
" <td>3623</td>\n",
" <td>4005</td>\n",
" <td>5393</td>\n",
" <td>4752</td>\n",
" <td>4325</td>\n",
" <td>3774</td>\n",
" <td>4331</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>American Samoa</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Andorra</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 35 columns</p>\n",
"</div>"
],
"text/plain": [
" OdName 1980 1981 1982 1983 1984 1985 1986 1987 1988 ... \\\n",
"0 Afghanistan 16 39 39 47 71 340 496 741 828 ... \n",
"1 Albania 1 0 0 0 0 0 1 2 2 ... \n",
"2 Algeria 80 67 71 69 63 44 69 132 242 ... \n",
"3 American Samoa 0 1 0 0 0 0 0 1 0 ... \n",
"4 Andorra 0 0 0 0 0 0 2 0 0 ... \n",
"\n",
" 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 \n",
"0 2978 3436 3009 2652 2111 1746 1758 2203 2635 2004 \n",
"1 1450 1223 856 702 560 716 561 539 620 603 \n",
"2 3616 3626 4807 3623 4005 5393 4752 4325 3774 4331 \n",
"3 0 0 1 0 0 0 0 0 0 0 \n",
"4 0 0 1 1 0 0 0 0 1 1 \n",
"\n",
"[5 rows x 35 columns]"
]
},
"execution_count": 689,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"canada.drop(columns=['AREA' , 'DEV', 'DevName' , 'REG', 'Type', 'Coverage' , 'AreaName', 'RegName' ], inplace=True)\n",
"canada.head()"
]
},
{
"cell_type": "code",
"execution_count": 690,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Country</th>\n",
" <th>1980</th>\n",
" <th>1981</th>\n",
" <th>1982</th>\n",
" <th>1983</th>\n",
" <th>1984</th>\n",
" <th>1985</th>\n",
" <th>1986</th>\n",
" <th>1987</th>\n",
" <th>1988</th>\n",
" <th>...</th>\n",
" <th>2004</th>\n",
" <th>2005</th>\n",
" <th>2006</th>\n",
" <th>2007</th>\n",
" <th>2008</th>\n",
" <th>2009</th>\n",
" <th>2010</th>\n",
" <th>2011</th>\n",
" <th>2012</th>\n",
" <th>2013</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Country</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></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>Afghanistan</th>\n",
" <td>Afghanistan</td>\n",
" <td>16</td>\n",
" <td>39</td>\n",
" <td>39</td>\n",
" <td>47</td>\n",
" <td>71</td>\n",
" <td>340</td>\n",
" <td>496</td>\n",
" <td>741</td>\n",
" <td>828</td>\n",
" <td>...</td>\n",
" <td>2978</td>\n",
" <td>3436</td>\n",
" <td>3009</td>\n",
" <td>2652</td>\n",
" <td>2111</td>\n",
" <td>1746</td>\n",
" <td>1758</td>\n",
" <td>2203</td>\n",
" <td>2635</td>\n",
" <td>2004</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Albania</th>\n",
" <td>Albania</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>...</td>\n",
" <td>1450</td>\n",
" <td>1223</td>\n",
" <td>856</td>\n",
" <td>702</td>\n",
" <td>560</td>\n",
" <td>716</td>\n",
" <td>561</td>\n",
" <td>539</td>\n",
" <td>620</td>\n",
" <td>603</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Algeria</th>\n",
" <td>Algeria</td>\n",
" <td>80</td>\n",
" <td>67</td>\n",
" <td>71</td>\n",
" <td>69</td>\n",
" <td>63</td>\n",
" <td>44</td>\n",
" <td>69</td>\n",
" <td>132</td>\n",
" <td>242</td>\n",
" <td>...</td>\n",
" <td>3616</td>\n",
" <td>3626</td>\n",
" <td>4807</td>\n",
" <td>3623</td>\n",
" <td>4005</td>\n",
" <td>5393</td>\n",
" <td>4752</td>\n",
" <td>4325</td>\n",
" <td>3774</td>\n",
" <td>4331</td>\n",
" </tr>\n",
" <tr>\n",
" <th>American Samoa</th>\n",
" <td>American Samoa</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Andorra</th>\n",
" <td>Andorra</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 35 columns</p>\n",
"</div>"
],
"text/plain": [
" Country 1980 1981 1982 1983 1984 1985 1986 \\\n",
"Country \n",
"Afghanistan Afghanistan 16 39 39 47 71 340 496 \n",
"Albania Albania 1 0 0 0 0 0 1 \n",
"Algeria Algeria 80 67 71 69 63 44 69 \n",
"American Samoa American Samoa 0 1 0 0 0 0 0 \n",
"Andorra Andorra 0 0 0 0 0 0 2 \n",
"\n",
" 1987 1988 ... 2004 2005 2006 2007 2008 2009 2010 \\\n",
"Country ... \n",
"Afghanistan 741 828 ... 2978 3436 3009 2652 2111 1746 1758 \n",
"Albania 2 2 ... 1450 1223 856 702 560 716 561 \n",
"Algeria 132 242 ... 3616 3626 4807 3623 4005 5393 4752 \n",
"American Samoa 1 0 ... 0 0 1 0 0 0 0 \n",
"Andorra 0 0 ... 0 0 1 1 0 0 0 \n",
"\n",
" 2011 2012 2013 \n",
"Country \n",
"Afghanistan 2203 2635 2004 \n",
"Albania 539 620 603 \n",
"Algeria 4325 3774 4331 \n",
"American Samoa 0 0 0 \n",
"Andorra 0 1 1 \n",
"\n",
"[5 rows x 35 columns]"
]
},
"execution_count": 690,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"canada.rename(columns={'OdName':'Country'} , inplace=True)\n",
"canada.set_index(canada.Country,inplace=True)\n",
"canada.head()"
]
},
{
"cell_type": "code",
"execution_count": 691,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Country</th>\n",
" <th>1980</th>\n",
" <th>1981</th>\n",
" <th>1982</th>\n",
" <th>1983</th>\n",
" <th>1984</th>\n",
" <th>1985</th>\n",
" <th>1986</th>\n",
" <th>1987</th>\n",
" <th>1988</th>\n",
" <th>...</th>\n",
" <th>2004</th>\n",
" <th>2005</th>\n",
" <th>2006</th>\n",
" <th>2007</th>\n",
" <th>2008</th>\n",
" <th>2009</th>\n",
" <th>2010</th>\n",
" <th>2011</th>\n",
" <th>2012</th>\n",
" <th>2013</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Afghanistan</th>\n",
" <td>Afghanistan</td>\n",
" <td>16</td>\n",
" <td>39</td>\n",
" <td>39</td>\n",
" <td>47</td>\n",
" <td>71</td>\n",
" <td>340</td>\n",
" <td>496</td>\n",
" <td>741</td>\n",
" <td>828</td>\n",
" <td>...</td>\n",
" <td>2978</td>\n",
" <td>3436</td>\n",
" <td>3009</td>\n",
" <td>2652</td>\n",
" <td>2111</td>\n",
" <td>1746</td>\n",
" <td>1758</td>\n",
" <td>2203</td>\n",
" <td>2635</td>\n",
" <td>2004</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Albania</th>\n",
" <td>Albania</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>...</td>\n",
" <td>1450</td>\n",
" <td>1223</td>\n",
" <td>856</td>\n",
" <td>702</td>\n",
" <td>560</td>\n",
" <td>716</td>\n",
" <td>561</td>\n",
" <td>539</td>\n",
" <td>620</td>\n",
" <td>603</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Algeria</th>\n",
" <td>Algeria</td>\n",
" <td>80</td>\n",
" <td>67</td>\n",
" <td>71</td>\n",
" <td>69</td>\n",
" <td>63</td>\n",
" <td>44</td>\n",
" <td>69</td>\n",
" <td>132</td>\n",
" <td>242</td>\n",
" <td>...</td>\n",
" <td>3616</td>\n",
" <td>3626</td>\n",
" <td>4807</td>\n",
" <td>3623</td>\n",
" <td>4005</td>\n",
" <td>5393</td>\n",
" <td>4752</td>\n",
" <td>4325</td>\n",
" <td>3774</td>\n",
" <td>4331</td>\n",
" </tr>\n",
" <tr>\n",
" <th>American Samoa</th>\n",
" <td>American Samoa</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Andorra</th>\n",
" <td>Andorra</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 35 columns</p>\n",
"</div>"
],
"text/plain": [
" Country 1980 1981 1982 1983 1984 1985 1986 \\\n",
"Afghanistan Afghanistan 16 39 39 47 71 340 496 \n",
"Albania Albania 1 0 0 0 0 0 1 \n",
"Algeria Algeria 80 67 71 69 63 44 69 \n",
"American Samoa American Samoa 0 1 0 0 0 0 0 \n",
"Andorra Andorra 0 0 0 0 0 0 2 \n",
"\n",
" 1987 1988 ... 2004 2005 2006 2007 2008 2009 2010 \\\n",
"Afghanistan 741 828 ... 2978 3436 3009 2652 2111 1746 1758 \n",
"Albania 2 2 ... 1450 1223 856 702 560 716 561 \n",
"Algeria 132 242 ... 3616 3626 4807 3623 4005 5393 4752 \n",
"American Samoa 1 0 ... 0 0 1 0 0 0 0 \n",
"Andorra 0 0 ... 0 0 1 1 0 0 0 \n",
"\n",
" 2011 2012 2013 \n",
"Afghanistan 2203 2635 2004 \n",
"Albania 539 620 603 \n",
"Algeria 4325 3774 4331 \n",
"American Samoa 0 0 0 \n",
"Andorra 0 1 1 \n",
"\n",
"[5 rows x 35 columns]"
]
},
"execution_count": 691,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"canada.index.name=None\n",
"canada.head()"
]
},
{
"cell_type": "code",
"execution_count": 692,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>1980</th>\n",
" <th>1981</th>\n",
" <th>1982</th>\n",
" <th>1983</th>\n",
" <th>1984</th>\n",
" <th>1985</th>\n",
" <th>1986</th>\n",
" <th>1987</th>\n",
" <th>1988</th>\n",
" <th>1989</th>\n",
" <th>...</th>\n",
" <th>2004</th>\n",
" <th>2005</th>\n",
" <th>2006</th>\n",
" <th>2007</th>\n",
" <th>2008</th>\n",
" <th>2009</th>\n",
" <th>2010</th>\n",
" <th>2011</th>\n",
" <th>2012</th>\n",
" <th>2013</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Afghanistan</th>\n",
" <td>16</td>\n",
" <td>39</td>\n",
" <td>39</td>\n",
" <td>47</td>\n",
" <td>71</td>\n",
" <td>340</td>\n",
" <td>496</td>\n",
" <td>741</td>\n",
" <td>828</td>\n",
" <td>1076</td>\n",
" <td>...</td>\n",
" <td>2978</td>\n",
" <td>3436</td>\n",
" <td>3009</td>\n",
" <td>2652</td>\n",
" <td>2111</td>\n",
" <td>1746</td>\n",
" <td>1758</td>\n",
" <td>2203</td>\n",
" <td>2635</td>\n",
" <td>2004</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Albania</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>...</td>\n",
" <td>1450</td>\n",
" <td>1223</td>\n",
" <td>856</td>\n",
" <td>702</td>\n",
" <td>560</td>\n",
" <td>716</td>\n",
" <td>561</td>\n",
" <td>539</td>\n",
" <td>620</td>\n",
" <td>603</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Algeria</th>\n",
" <td>80</td>\n",
" <td>67</td>\n",
" <td>71</td>\n",
" <td>69</td>\n",
" <td>63</td>\n",
" <td>44</td>\n",
" <td>69</td>\n",
" <td>132</td>\n",
" <td>242</td>\n",
" <td>434</td>\n",
" <td>...</td>\n",
" <td>3616</td>\n",
" <td>3626</td>\n",
" <td>4807</td>\n",
" <td>3623</td>\n",
" <td>4005</td>\n",
" <td>5393</td>\n",
" <td>4752</td>\n",
" <td>4325</td>\n",
" <td>3774</td>\n",
" <td>4331</td>\n",
" </tr>\n",
" <tr>\n",
" <th>American Samoa</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Andorra</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 34 columns</p>\n",
"</div>"
],
"text/plain": [
" 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 \\\n",
"Afghanistan 16 39 39 47 71 340 496 741 828 1076 \n",
"Albania 1 0 0 0 0 0 1 2 2 3 \n",
"Algeria 80 67 71 69 63 44 69 132 242 434 \n",
"American Samoa 0 1 0 0 0 0 0 1 0 1 \n",
"Andorra 0 0 0 0 0 0 2 0 0 0 \n",
"\n",
" ... 2004 2005 2006 2007 2008 2009 2010 2011 2012 \\\n",
"Afghanistan ... 2978 3436 3009 2652 2111 1746 1758 2203 2635 \n",
"Albania ... 1450 1223 856 702 560 716 561 539 620 \n",
"Algeria ... 3616 3626 4807 3623 4005 5393 4752 4325 3774 \n",
"American Samoa ... 0 0 1 0 0 0 0 0 0 \n",
"Andorra ... 0 0 1 1 0 0 0 0 1 \n",
"\n",
" 2013 \n",
"Afghanistan 2004 \n",
"Albania 603 \n",
"Algeria 4331 \n",
"American Samoa 0 \n",
"Andorra 1 \n",
"\n",
"[5 rows x 34 columns]"
]
},
"execution_count": 692,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"del canada['Country']\n",
"canada.head()"
]
},
{
"cell_type": "code",
"execution_count": 693,
"metadata": {},
"outputs": [],
"source": [
"canada = canada.transpose()"
]
},
{
"cell_type": "code",
"execution_count": 694,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Afghanistan</th>\n",
" <th>Albania</th>\n",
" <th>Algeria</th>\n",
" <th>American Samoa</th>\n",
" <th>Andorra</th>\n",
" <th>Angola</th>\n",
" <th>Antigua and Barbuda</th>\n",
" <th>Argentina</th>\n",
" <th>Armenia</th>\n",
" <th>Australia</th>\n",
" <th>...</th>\n",
" <th>Uzbekistan</th>\n",
" <th>Vanuatu</th>\n",
" <th>Venezuela (Bolivarian Republic of)</th>\n",
" <th>Viet Nam</th>\n",
" <th>Western Sahara</th>\n",
" <th>Yemen</th>\n",
" <th>Zambia</th>\n",
" <th>Zimbabwe</th>\n",
" <th>Unknown</th>\n",
" <th>Total</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1980</th>\n",
" <td>16</td>\n",
" <td>1</td>\n",
" <td>80</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>368</td>\n",
" <td>0</td>\n",
" <td>702</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>103</td>\n",
" <td>1191</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>11</td>\n",
" <td>72</td>\n",
" <td>44000</td>\n",
" <td>143137</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1981</th>\n",
" <td>39</td>\n",
" <td>0</td>\n",
" <td>67</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>426</td>\n",
" <td>0</td>\n",
" <td>639</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>117</td>\n",
" <td>1829</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>17</td>\n",
" <td>114</td>\n",
" <td>18078</td>\n",
" <td>128641</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1982</th>\n",
" <td>39</td>\n",
" <td>0</td>\n",
" <td>71</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>626</td>\n",
" <td>0</td>\n",
" <td>484</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>174</td>\n",
" <td>2162</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>11</td>\n",
" <td>102</td>\n",
" <td>16904</td>\n",
" <td>121175</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1983</th>\n",
" <td>47</td>\n",
" <td>0</td>\n",
" <td>69</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>241</td>\n",
" <td>0</td>\n",
" <td>317</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>124</td>\n",
" <td>3404</td>\n",
" <td>0</td>\n",
" <td>6</td>\n",
" <td>7</td>\n",
" <td>44</td>\n",
" <td>13635</td>\n",
" <td>89185</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1984</th>\n",
" <td>71</td>\n",
" <td>0</td>\n",
" <td>63</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>42</td>\n",
" <td>237</td>\n",
" <td>0</td>\n",
" <td>317</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>142</td>\n",
" <td>7583</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>16</td>\n",
" <td>32</td>\n",
" <td>14855</td>\n",
" <td>88272</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 197 columns</p>\n",
"</div>"
],
"text/plain": [
" Afghanistan Albania Algeria American Samoa Andorra Angola \\\n",
"1980 16 1 80 0 0 1 \n",
"1981 39 0 67 1 0 3 \n",
"1982 39 0 71 0 0 6 \n",
"1983 47 0 69 0 0 6 \n",
"1984 71 0 63 0 0 4 \n",
"\n",
" Antigua and Barbuda Argentina Armenia Australia ... Uzbekistan \\\n",
"1980 0 368 0 702 ... 0 \n",
"1981 0 426 0 639 ... 0 \n",
"1982 0 626 0 484 ... 0 \n",
"1983 0 241 0 317 ... 0 \n",
"1984 42 237 0 317 ... 0 \n",
"\n",
" Vanuatu Venezuela (Bolivarian Republic of) Viet Nam Western Sahara \\\n",
"1980 0 103 1191 0 \n",
"1981 0 117 1829 0 \n",
"1982 0 174 2162 0 \n",
"1983 0 124 3404 0 \n",
"1984 0 142 7583 0 \n",
"\n",
" Yemen Zambia Zimbabwe Unknown Total \n",
"1980 1 11 72 44000 143137 \n",
"1981 2 17 114 18078 128641 \n",
"1982 1 11 102 16904 121175 \n",
"1983 6 7 44 13635 89185 \n",
"1984 0 16 32 14855 88272 \n",
"\n",
"[5 rows x 197 columns]"
]
},
"execution_count": 694,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"canada.head()"
]
},
{
"cell_type": "code",
"execution_count": 695,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Country</th>\n",
" <th>Year</th>\n",
" <th>Status</th>\n",
" <th>Life expectancy</th>\n",
" <th>Adult Mortality</th>\n",
" <th>infant deaths</th>\n",
" <th>Alcohol</th>\n",
" <th>percentage expenditure</th>\n",
" <th>Hepatitis B</th>\n",
" <th>Measles</th>\n",
" <th>...</th>\n",
" <th>Polio</th>\n",
" <th>Total expenditure</th>\n",
" <th>Diphtheria</th>\n",
" <th>HIV/AIDS</th>\n",
" <th>GDP</th>\n",
" <th>Population</th>\n",
" <th>thinness 1-19 years</th>\n",
" <th>thinness 5-9 years</th>\n",
" <th>Income composition of resources</th>\n",
" <th>Schooling</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Afghanistan</td>\n",
" <td>2015</td>\n",
" <td>Developing</td>\n",
" <td>65.0</td>\n",
" <td>263.0</td>\n",
" <td>62</td>\n",
" <td>0.01</td>\n",
" <td>71.279624</td>\n",
" <td>65.0</td>\n",
" <td>1154</td>\n",
" <td>...</td>\n",
" <td>6.0</td>\n",
" <td>8.16</td>\n",
" <td>65.0</td>\n",
" <td>0.1</td>\n",
" <td>584.259210</td>\n",
" <td>33736494.0</td>\n",
" <td>17.2</td>\n",
" <td>17.3</td>\n",
" <td>0.479</td>\n",
" <td>10.1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Afghanistan</td>\n",
" <td>2014</td>\n",
" <td>Developing</td>\n",
" <td>59.9</td>\n",
" <td>271.0</td>\n",
" <td>64</td>\n",
" <td>0.01</td>\n",
" <td>73.523582</td>\n",
" <td>62.0</td>\n",
" <td>492</td>\n",
" <td>...</td>\n",
" <td>58.0</td>\n",
" <td>8.18</td>\n",
" <td>62.0</td>\n",
" <td>0.1</td>\n",
" <td>612.696514</td>\n",
" <td>327582.0</td>\n",
" <td>17.5</td>\n",
" <td>17.5</td>\n",
" <td>0.476</td>\n",
" <td>10.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Afghanistan</td>\n",
" <td>2013</td>\n",
" <td>Developing</td>\n",
" <td>59.9</td>\n",
" <td>268.0</td>\n",
" <td>66</td>\n",
" <td>0.01</td>\n",
" <td>73.219243</td>\n",
" <td>64.0</td>\n",
" <td>430</td>\n",
" <td>...</td>\n",
" <td>62.0</td>\n",
" <td>8.13</td>\n",
" <td>64.0</td>\n",
" <td>0.1</td>\n",
" <td>631.744976</td>\n",
" <td>31731688.0</td>\n",
" <td>17.7</td>\n",
" <td>17.7</td>\n",
" <td>0.470</td>\n",
" <td>9.9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Afghanistan</td>\n",
" <td>2012</td>\n",
" <td>Developing</td>\n",
" <td>59.5</td>\n",
" <td>272.0</td>\n",
" <td>69</td>\n",
" <td>0.01</td>\n",
" <td>78.184215</td>\n",
" <td>67.0</td>\n",
" <td>2787</td>\n",
" <td>...</td>\n",
" <td>67.0</td>\n",
" <td>8.52</td>\n",
" <td>67.0</td>\n",
" <td>0.1</td>\n",
" <td>669.959000</td>\n",
" <td>3696958.0</td>\n",
" <td>17.9</td>\n",
" <td>18.0</td>\n",
" <td>0.463</td>\n",
" <td>9.8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Afghanistan</td>\n",
" <td>2011</td>\n",
" <td>Developing</td>\n",
" <td>59.2</td>\n",
" <td>275.0</td>\n",
" <td>71</td>\n",
" <td>0.01</td>\n",
" <td>7.097109</td>\n",
" <td>68.0</td>\n",
" <td>3013</td>\n",
" <td>...</td>\n",
" <td>68.0</td>\n",
" <td>7.87</td>\n",
" <td>68.0</td>\n",
" <td>0.1</td>\n",
" <td>63.537231</td>\n",
" <td>2978599.0</td>\n",
" <td>18.2</td>\n",
" <td>18.2</td>\n",
" <td>0.454</td>\n",
" <td>9.5</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 22 columns</p>\n",
"</div>"
],
"text/plain": [
" Country Year Status Life expectancy Adult Mortality \\\n",
"0 Afghanistan 2015 Developing 65.0 263.0 \n",
"1 Afghanistan 2014 Developing 59.9 271.0 \n",
"2 Afghanistan 2013 Developing 59.9 268.0 \n",
"3 Afghanistan 2012 Developing 59.5 272.0 \n",
"4 Afghanistan 2011 Developing 59.2 275.0 \n",
"\n",
" infant deaths Alcohol percentage expenditure Hepatitis B Measles \\\n",
"0 62 0.01 71.279624 65.0 1154 \n",
"1 64 0.01 73.523582 62.0 492 \n",
"2 66 0.01 73.219243 64.0 430 \n",
"3 69 0.01 78.184215 67.0 2787 \n",
"4 71 0.01 7.097109 68.0 3013 \n",
"\n",
" ... Polio Total expenditure Diphtheria HIV/AIDS GDP \\\n",
"0 ... 6.0 8.16 65.0 0.1 584.259210 \n",
"1 ... 58.0 8.18 62.0 0.1 612.696514 \n",
"2 ... 62.0 8.13 64.0 0.1 631.744976 \n",
"3 ... 67.0 8.52 67.0 0.1 669.959000 \n",
"4 ... 68.0 7.87 68.0 0.1 63.537231 \n",
"\n",
" Population thinness 1-19 years thinness 5-9 years \\\n",
"0 33736494.0 17.2 17.3 \n",
"1 327582.0 17.5 17.5 \n",
"2 31731688.0 17.7 17.7 \n",
"3 3696958.0 17.9 18.0 \n",
"4 2978599.0 18.2 18.2 \n",
"\n",
" Income composition of resources Schooling \n",
"0 0.479 10.1 \n",
"1 0.476 10.0 \n",
"2 0.470 9.9 \n",
"3 0.463 9.8 \n",
"4 0.454 9.5 \n",
"\n",
"[5 rows x 22 columns]"
]
},
"execution_count": 695,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"led = pd.read_csv(\"Life Expectancy Data.csv\")\n",
"led.head()"
]
},
{
"cell_type": "code",
"execution_count": 696,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>age</th>\n",
" <th>workclass</th>\n",
" <th>fnlwgt</th>\n",
" <th>education</th>\n",
" <th>education.num</th>\n",
" <th>marital.status</th>\n",
" <th>occupation</th>\n",
" <th>relationship</th>\n",
" <th>race</th>\n",
" <th>sex</th>\n",
" <th>capital.gain</th>\n",
" <th>capital.loss</th>\n",
" <th>hours.per.week</th>\n",
" <th>native.country</th>\n",
" <th>income</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>90</td>\n",
" <td>?</td>\n",
" <td>77053</td>\n",
" <td>HS-grad</td>\n",
" <td>9</td>\n",
" <td>Widowed</td>\n",
" <td>?</td>\n",
" <td>Not-in-family</td>\n",
" <td>White</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>4356</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>82</td>\n",
" <td>Private</td>\n",
" <td>132870</td>\n",
" <td>HS-grad</td>\n",
" <td>9</td>\n",
" <td>Widowed</td>\n",
" <td>Exec-managerial</td>\n",
" <td>Not-in-family</td>\n",
" <td>White</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>4356</td>\n",
" <td>18</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>66</td>\n",
" <td>?</td>\n",
" <td>186061</td>\n",
" <td>Some-college</td>\n",
" <td>10</td>\n",
" <td>Widowed</td>\n",
" <td>?</td>\n",
" <td>Unmarried</td>\n",
" <td>Black</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>4356</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>54</td>\n",
" <td>Private</td>\n",
" <td>140359</td>\n",
" <td>7th-8th</td>\n",
" <td>4</td>\n",
" <td>Divorced</td>\n",
" <td>Machine-op-inspct</td>\n",
" <td>Unmarried</td>\n",
" <td>White</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>3900</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>41</td>\n",
" <td>Private</td>\n",
" <td>264663</td>\n",
" <td>Some-college</td>\n",
" <td>10</td>\n",
" <td>Separated</td>\n",
" <td>Prof-specialty</td>\n",
" <td>Own-child</td>\n",
" <td>White</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>3900</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>34</td>\n",
" <td>Private</td>\n",
" <td>216864</td>\n",
" <td>HS-grad</td>\n",
" <td>9</td>\n",
" <td>Divorced</td>\n",
" <td>Other-service</td>\n",
" <td>Unmarried</td>\n",
" <td>White</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>3770</td>\n",
" <td>45</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>38</td>\n",
" <td>Private</td>\n",
" <td>150601</td>\n",
" <td>10th</td>\n",
" <td>6</td>\n",
" <td>Separated</td>\n",
" <td>Adm-clerical</td>\n",
" <td>Unmarried</td>\n",
" <td>White</td>\n",
" <td>Male</td>\n",
" <td>0</td>\n",
" <td>3770</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>74</td>\n",
" <td>State-gov</td>\n",
" <td>88638</td>\n",
" <td>Doctorate</td>\n",
" <td>16</td>\n",
" <td>Never-married</td>\n",
" <td>Prof-specialty</td>\n",
" <td>Other-relative</td>\n",
" <td>White</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>3683</td>\n",
" <td>20</td>\n",
" <td>United-States</td>\n",
" <td>&gt;50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>68</td>\n",
" <td>Federal-gov</td>\n",
" <td>422013</td>\n",
" <td>HS-grad</td>\n",
" <td>9</td>\n",
" <td>Divorced</td>\n",
" <td>Prof-specialty</td>\n",
" <td>Not-in-family</td>\n",
" <td>White</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>3683</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>41</td>\n",
" <td>Private</td>\n",
" <td>70037</td>\n",
" <td>Some-college</td>\n",
" <td>10</td>\n",
" <td>Never-married</td>\n",
" <td>Craft-repair</td>\n",
" <td>Unmarried</td>\n",
" <td>White</td>\n",
" <td>Male</td>\n",
" <td>0</td>\n",
" <td>3004</td>\n",
" <td>60</td>\n",
" <td>?</td>\n",
" <td>&gt;50K</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" age workclass fnlwgt education education.num marital.status \\\n",
"0 90 ? 77053 HS-grad 9 Widowed \n",
"1 82 Private 132870 HS-grad 9 Widowed \n",
"2 66 ? 186061 Some-college 10 Widowed \n",
"3 54 Private 140359 7th-8th 4 Divorced \n",
"4 41 Private 264663 Some-college 10 Separated \n",
"5 34 Private 216864 HS-grad 9 Divorced \n",
"6 38 Private 150601 10th 6 Separated \n",
"7 74 State-gov 88638 Doctorate 16 Never-married \n",
"8 68 Federal-gov 422013 HS-grad 9 Divorced \n",
"9 41 Private 70037 Some-college 10 Never-married \n",
"\n",
" occupation relationship race sex capital.gain \\\n",
"0 ? Not-in-family White Female 0 \n",
"1 Exec-managerial Not-in-family White Female 0 \n",
"2 ? Unmarried Black Female 0 \n",
"3 Machine-op-inspct Unmarried White Female 0 \n",
"4 Prof-specialty Own-child White Female 0 \n",
"5 Other-service Unmarried White Female 0 \n",
"6 Adm-clerical Unmarried White Male 0 \n",
"7 Prof-specialty Other-relative White Female 0 \n",
"8 Prof-specialty Not-in-family White Female 0 \n",
"9 Craft-repair Unmarried White Male 0 \n",
"\n",
" capital.loss hours.per.week native.country income \n",
"0 4356 40 United-States <=50K \n",
"1 4356 18 United-States <=50K \n",
"2 4356 40 United-States <=50K \n",
"3 3900 40 United-States <=50K \n",
"4 3900 40 United-States <=50K \n",
"5 3770 45 United-States <=50K \n",
"6 3770 40 United-States <=50K \n",
"7 3683 20 United-States >50K \n",
"8 3683 40 United-States <=50K \n",
"9 3004 60 ? >50K "
]
},
"execution_count": 696,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"adult = pd.read_csv(\"adult.csv\")\n",
"adult.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 697,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>age</th>\n",
" <th>workclass</th>\n",
" <th>fnlwgt</th>\n",
" <th>education</th>\n",
" <th>education.num</th>\n",
" <th>marital.status</th>\n",
" <th>occupation</th>\n",
" <th>relationship</th>\n",
" <th>race</th>\n",
" <th>sex</th>\n",
" <th>capital.gain</th>\n",
" <th>capital.loss</th>\n",
" <th>hours.per.week</th>\n",
" <th>native.country</th>\n",
" <th>income</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>82</td>\n",
" <td>Private</td>\n",
" <td>132870</td>\n",
" <td>HS-grad</td>\n",
" <td>9</td>\n",
" <td>Widowed</td>\n",
" <td>Exec-managerial</td>\n",
" <td>Not-in-family</td>\n",
" <td>White</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>4356</td>\n",
" <td>18</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>54</td>\n",
" <td>Private</td>\n",
" <td>140359</td>\n",
" <td>7th-8th</td>\n",
" <td>4</td>\n",
" <td>Divorced</td>\n",
" <td>Machine-op-inspct</td>\n",
" <td>Unmarried</td>\n",
" <td>White</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>3900</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>41</td>\n",
" <td>Private</td>\n",
" <td>264663</td>\n",
" <td>Some-college</td>\n",
" <td>10</td>\n",
" <td>Separated</td>\n",
" <td>Prof-specialty</td>\n",
" <td>Own-child</td>\n",
" <td>White</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>3900</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>34</td>\n",
" <td>Private</td>\n",
" <td>216864</td>\n",
" <td>HS-grad</td>\n",
" <td>9</td>\n",
" <td>Divorced</td>\n",
" <td>Other-service</td>\n",
" <td>Unmarried</td>\n",
" <td>White</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>3770</td>\n",
" <td>45</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>38</td>\n",
" <td>Private</td>\n",
" <td>150601</td>\n",
" <td>10th</td>\n",
" <td>6</td>\n",
" <td>Separated</td>\n",
" <td>Adm-clerical</td>\n",
" <td>Unmarried</td>\n",
" <td>White</td>\n",
" <td>Male</td>\n",
" <td>0</td>\n",
" <td>3770</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" age workclass fnlwgt education education.num marital.status \\\n",
"1 82 Private 132870 HS-grad 9 Widowed \n",
"3 54 Private 140359 7th-8th 4 Divorced \n",
"4 41 Private 264663 Some-college 10 Separated \n",
"5 34 Private 216864 HS-grad 9 Divorced \n",
"6 38 Private 150601 10th 6 Separated \n",
"\n",
" occupation relationship race sex capital.gain \\\n",
"1 Exec-managerial Not-in-family White Female 0 \n",
"3 Machine-op-inspct Unmarried White Female 0 \n",
"4 Prof-specialty Own-child White Female 0 \n",
"5 Other-service Unmarried White Female 0 \n",
"6 Adm-clerical Unmarried White Male 0 \n",
"\n",
" capital.loss hours.per.week native.country income \n",
"1 4356 18 United-States <=50K \n",
"3 3900 40 United-States <=50K \n",
"4 3900 40 United-States <=50K \n",
"5 3770 45 United-States <=50K \n",
"6 3770 40 United-States <=50K "
]
},
"execution_count": 697,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"adult = adult[adult[\"workclass\"].isin (['Private', 'State-gov', 'Federal-gov'])]\n",
"adult.head()"
]
},
{
"cell_type": "code",
"execution_count": 698,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>sepal_length</th>\n",
" <th>sepal_width</th>\n",
" <th>petal_length</th>\n",
" <th>petal_width</th>\n",
" <th>species</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>setosa</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>setosa</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>setosa</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>setosa</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>setosa</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" sepal_length sepal_width petal_length petal_width species\n",
"0 5.1 3.5 1.4 0.2 setosa\n",
"1 4.9 3.0 1.4 0.2 setosa\n",
"2 4.7 3.2 1.3 0.2 setosa\n",
"3 4.6 3.1 1.5 0.2 setosa\n",
"4 5.0 3.6 1.4 0.2 setosa"
]
},
"execution_count": 698,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"iris = sns.load_dataset(\"iris\")\n",
"iris.head()"
]
},
{
"cell_type": "code",
"execution_count": 700,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>mpg</th>\n",
" <th>cylinders</th>\n",
" <th>cubicinches</th>\n",
" <th>hp</th>\n",
" <th>weightlbs</th>\n",
" <th>time-to-60</th>\n",
" <th>year</th>\n",
" <th>brand</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>14.0</td>\n",
" <td>8</td>\n",
" <td>350</td>\n",
" <td>165</td>\n",
" <td>4209</td>\n",
" <td>12</td>\n",
" <td>1972</td>\n",
" <td>US.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>31.9</td>\n",
" <td>4</td>\n",
" <td>89</td>\n",
" <td>71</td>\n",
" <td>1925</td>\n",
" <td>14</td>\n",
" <td>1980</td>\n",
" <td>Europe.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>17.0</td>\n",
" <td>8</td>\n",
" <td>302</td>\n",
" <td>140</td>\n",
" <td>3449</td>\n",
" <td>11</td>\n",
" <td>1971</td>\n",
" <td>US.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>15.0</td>\n",
" <td>8</td>\n",
" <td>400</td>\n",
" <td>150</td>\n",
" <td>3761</td>\n",
" <td>10</td>\n",
" <td>1971</td>\n",
" <td>US.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>30.5</td>\n",
" <td>4</td>\n",
" <td>98</td>\n",
" <td>63</td>\n",
" <td>2051</td>\n",
" <td>17</td>\n",
" <td>1978</td>\n",
" <td>US.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>23.0</td>\n",
" <td>8</td>\n",
" <td>350</td>\n",
" <td>125</td>\n",
" <td>3900</td>\n",
" <td>17</td>\n",
" <td>1980</td>\n",
" <td>US.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>13.0</td>\n",
" <td>8</td>\n",
" <td>351</td>\n",
" <td>158</td>\n",
" <td>4363</td>\n",
" <td>13</td>\n",
" <td>1974</td>\n",
" <td>US.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>14.0</td>\n",
" <td>8</td>\n",
" <td>440</td>\n",
" <td>215</td>\n",
" <td>4312</td>\n",
" <td>9</td>\n",
" <td>1971</td>\n",
" <td>US.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>25.4</td>\n",
" <td>5</td>\n",
" <td>183</td>\n",
" <td>77</td>\n",
" <td>3530</td>\n",
" <td>20</td>\n",
" <td>1980</td>\n",
" <td>Europe.</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>37.7</td>\n",
" <td>4</td>\n",
" <td>89</td>\n",
" <td>62</td>\n",
" <td>2050</td>\n",
" <td>17</td>\n",
" <td>1982</td>\n",
" <td>Japan.</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" mpg cylinders cubicinches hp weightlbs time-to-60 year brand\n",
"0 14.0 8 350 165 4209 12 1972 US.\n",
"1 31.9 4 89 71 1925 14 1980 Europe.\n",
"2 17.0 8 302 140 3449 11 1971 US.\n",
"3 15.0 8 400 150 3761 10 1971 US.\n",
"4 30.5 4 98 63 2051 17 1978 US.\n",
"5 23.0 8 350 125 3900 17 1980 US.\n",
"6 13.0 8 351 158 4363 13 1974 US.\n",
"7 14.0 8 440 215 4312 9 1971 US.\n",
"8 25.4 5 183 77 3530 20 1980 Europe.\n",
"9 37.7 4 89 62 2050 17 1982 Japan."
]
},
"execution_count": 700,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"cars = pd.read_csv(\"cars.csv\")\n",
"cars.head(10)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.0"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in New Issue View Git Blame Copy Permalink