Skip to content

Instantly share code, notes, and snippets.

@GeorgyGol

GeorgyGol/Soccer.ipynb

Created June 19, 2017 17:33
Show Gist options
  • Save GeorgyGol/35fc36b4e073db7b846ccc4d756ea786 to your computer and use it in GitHub Desktop.
Save GeorgyGol/35fc36b4e073db7b846ccc4d756ea786 to your computer and use it in GitHub Desktop.
Download ZIP
Soccer predict
Display the source blob
Display the rendered blob
Raw
Soccer.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"source": [
"## Soccer predict notepad\n",
"Models for predict results soccer games\n",
"### Source date:\n",
"Ranking - https://www.fifa.com/fifa-world-ranking/ranking-table/men/ <br/>\n",
"Results of international championship and selecting games"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import re"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/egor/anaconda3/lib/python3.6/site-packages/ipykernel/__main__.py:3: FutureWarning: currently extract(expand=None) means expand=False (return Index/Series/DataFrame) but in a future version of pandas this will be changed to expand=True (return DataFrame)\n",
" app.launch_new_instance()\n",
"/home/egor/anaconda3/lib/python3.6/site-packages/ipykernel/__main__.py:5: FutureWarning: currently extract(expand=None) means expand=False (return Index/Series/DataFrame) but in a future version of pandas this will be changed to expand=True (return DataFrame)\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Rank</th>\n",
" <th>Team</th>\n",
" <th>Total Points</th>\n",
" <th>Previous Points</th>\n",
" <th>+/-</th>\n",
" <th>Avg.</th>\n",
" <th>AVG WGT</th>\n",
" <th>Avg..1</th>\n",
" <th>AVG WGT.1</th>\n",
" <th>Avg..2</th>\n",
" <th>AVG WGT.2</th>\n",
" <th>Avg..3</th>\n",
" <th>AVG WGT.3</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Country Code</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>BRA</th>\n",
" <td>1</td>\n",
" <td>Brazil</td>\n",
" <td>1715.02</td>\n",
" <td>1672</td>\n",
" <td>0</td>\n",
" <td>1038.91</td>\n",
" <td>1038.91</td>\n",
" <td>555.56</td>\n",
" <td>277.78</td>\n",
" <td>793.26</td>\n",
" <td>237.98</td>\n",
" <td>801.78</td>\n",
" <td>160.36</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ARG</th>\n",
" <td>2</td>\n",
" <td>Argentina</td>\n",
" <td>1626.23</td>\n",
" <td>1603</td>\n",
" <td>0</td>\n",
" <td>877.12</td>\n",
" <td>877.12</td>\n",
" <td>741.10</td>\n",
" <td>370.55</td>\n",
" <td>919.87</td>\n",
" <td>275.96</td>\n",
" <td>512.98</td>\n",
" <td>102.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th>GER</th>\n",
" <td>3</td>\n",
" <td>Germany</td>\n",
" <td>1511.44</td>\n",
" <td>1464</td>\n",
" <td>0</td>\n",
" <td>857.80</td>\n",
" <td>857.80</td>\n",
" <td>412.01</td>\n",
" <td>206.00</td>\n",
" <td>1153.12</td>\n",
" <td>345.94</td>\n",
" <td>508.50</td>\n",
" <td>101.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CHI</th>\n",
" <td>4</td>\n",
" <td>Chile</td>\n",
" <td>1422.14</td>\n",
" <td>1411</td>\n",
" <td>0</td>\n",
" <td>756.47</td>\n",
" <td>756.47</td>\n",
" <td>793.85</td>\n",
" <td>396.92</td>\n",
" <td>489.13</td>\n",
" <td>146.74</td>\n",
" <td>610.01</td>\n",
" <td>122.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>COL</th>\n",
" <td>5</td>\n",
" <td>Colombia</td>\n",
" <td>1365.63</td>\n",
" <td>1348</td>\n",
" <td>0</td>\n",
" <td>705.66</td>\n",
" <td>705.66</td>\n",
" <td>597.24</td>\n",
" <td>298.62</td>\n",
" <td>821.59</td>\n",
" <td>246.48</td>\n",
" <td>574.37</td>\n",
" <td>114.87</td>\n",
" </tr>\n",
" <tr>\n",
" <th>FRA</th>\n",
" <td>6</td>\n",
" <td>France</td>\n",
" <td>1332.16</td>\n",
" <td>1294</td>\n",
" <td>0</td>\n",
" <td>855.30</td>\n",
" <td>855.30</td>\n",
" <td>351.26</td>\n",
" <td>175.63</td>\n",
" <td>704.66</td>\n",
" <td>211.40</td>\n",
" <td>449.18</td>\n",
" <td>89.84</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BEL</th>\n",
" <td>7</td>\n",
" <td>Belgium</td>\n",
" <td>1291.57</td>\n",
" <td>1281</td>\n",
" <td>0</td>\n",
" <td>597.83</td>\n",
" <td>597.83</td>\n",
" <td>587.90</td>\n",
" <td>293.95</td>\n",
" <td>961.05</td>\n",
" <td>288.32</td>\n",
" <td>557.40</td>\n",
" <td>111.48</td>\n",
" </tr>\n",
" <tr>\n",
" <th>POR</th>\n",
" <td>8</td>\n",
" <td>Portugal</td>\n",
" <td>1266.76</td>\n",
" <td>1259</td>\n",
" <td>0</td>\n",
" <td>671.59</td>\n",
" <td>671.59</td>\n",
" <td>564.84</td>\n",
" <td>282.42</td>\n",
" <td>617.62</td>\n",
" <td>185.29</td>\n",
" <td>637.29</td>\n",
" <td>127.46</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SUI</th>\n",
" <td>9</td>\n",
" <td>Switzerland</td>\n",
" <td>1263.29</td>\n",
" <td>1212</td>\n",
" <td>0</td>\n",
" <td>788.68</td>\n",
" <td>788.68</td>\n",
" <td>355.32</td>\n",
" <td>177.66</td>\n",
" <td>563.16</td>\n",
" <td>168.95</td>\n",
" <td>640.01</td>\n",
" <td>128.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ESP</th>\n",
" <td>10</td>\n",
" <td>Spain</td>\n",
" <td>1198.19</td>\n",
" <td>1204</td>\n",
" <td>0</td>\n",
" <td>597.37</td>\n",
" <td>597.37</td>\n",
" <td>669.64</td>\n",
" <td>334.82</td>\n",
" <td>443.99</td>\n",
" <td>133.20</td>\n",
" <td>664.00</td>\n",
" <td>132.80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>POL</th>\n",
" <td>10</td>\n",
" <td>Poland</td>\n",
" <td>1197.70</td>\n",
" <td>1183</td>\n",
" <td>1</td>\n",
" <td>764.51</td>\n",
" <td>764.51</td>\n",
" <td>450.51</td>\n",
" <td>225.25</td>\n",
" <td>554.05</td>\n",
" <td>166.21</td>\n",
" <td>208.62</td>\n",
" <td>41.72</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ITA</th>\n",
" <td>12</td>\n",
" <td>Italy</td>\n",
" <td>1193.23</td>\n",
" <td>1165</td>\n",
" <td>0</td>\n",
" <td>708.03</td>\n",
" <td>708.03</td>\n",
" <td>417.65</td>\n",
" <td>208.82</td>\n",
" <td>550.06</td>\n",
" <td>165.02</td>\n",
" <td>556.81</td>\n",
" <td>111.36</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WAL</th>\n",
" <td>13</td>\n",
" <td>Wales</td>\n",
" <td>1119.36</td>\n",
" <td>1119</td>\n",
" <td>0</td>\n",
" <td>683.10</td>\n",
" <td>683.10</td>\n",
" <td>404.91</td>\n",
" <td>202.46</td>\n",
" <td>572.55</td>\n",
" <td>171.77</td>\n",
" <td>310.21</td>\n",
" <td>62.04</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ENG</th>\n",
" <td>13</td>\n",
" <td>England</td>\n",
" <td>1119.17</td>\n",
" <td>1103</td>\n",
" <td>1</td>\n",
" <td>591.57</td>\n",
" <td>591.57</td>\n",
" <td>544.52</td>\n",
" <td>272.26</td>\n",
" <td>520.33</td>\n",
" <td>156.10</td>\n",
" <td>496.25</td>\n",
" <td>99.25</td>\n",
" </tr>\n",
" <tr>\n",
" <th>PER</th>\n",
" <td>15</td>\n",
" <td>Peru</td>\n",
" <td>1108.36</td>\n",
" <td>1044</td>\n",
" <td>2</td>\n",
" <td>809.83</td>\n",
" <td>809.83</td>\n",
" <td>369.85</td>\n",
" <td>184.93</td>\n",
" <td>203.83</td>\n",
" <td>61.15</td>\n",
" <td>262.31</td>\n",
" <td>52.46</td>\n",
" </tr>\n",
" <tr>\n",
" <th>URU</th>\n",
" <td>16</td>\n",
" <td>Uruguay</td>\n",
" <td>1098.77</td>\n",
" <td>1097</td>\n",
" <td>-1</td>\n",
" <td>487.69</td>\n",
" <td>487.69</td>\n",
" <td>582.68</td>\n",
" <td>291.34</td>\n",
" <td>618.27</td>\n",
" <td>185.48</td>\n",
" <td>671.34</td>\n",
" <td>134.27</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MEX</th>\n",
" <td>17</td>\n",
" <td>Mexico</td>\n",
" <td>1049.98</td>\n",
" <td>1076</td>\n",
" <td>-1</td>\n",
" <td>583.06</td>\n",
" <td>583.06</td>\n",
" <td>492.90</td>\n",
" <td>246.45</td>\n",
" <td>449.51</td>\n",
" <td>134.85</td>\n",
" <td>428.06</td>\n",
" <td>85.61</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CRO</th>\n",
" <td>18</td>\n",
" <td>Croatia</td>\n",
" <td>1033.11</td>\n",
" <td>1016</td>\n",
" <td>0</td>\n",
" <td>637.83</td>\n",
" <td>637.83</td>\n",
" <td>356.79</td>\n",
" <td>178.39</td>\n",
" <td>536.15</td>\n",
" <td>160.84</td>\n",
" <td>280.24</td>\n",
" <td>56.05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CRC</th>\n",
" <td>19</td>\n",
" <td>Costa Rica</td>\n",
" <td>912.74</td>\n",
" <td>902</td>\n",
" <td>1</td>\n",
" <td>477.40</td>\n",
" <td>477.40</td>\n",
" <td>306.98</td>\n",
" <td>153.49</td>\n",
" <td>629.32</td>\n",
" <td>188.80</td>\n",
" <td>465.28</td>\n",
" <td>93.06</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EGY</th>\n",
" <td>20</td>\n",
" <td>Egypt</td>\n",
" <td>902.98</td>\n",
" <td>910</td>\n",
" <td>-1</td>\n",
" <td>568.68</td>\n",
" <td>568.68</td>\n",
" <td>323.98</td>\n",
" <td>161.99</td>\n",
" <td>234.47</td>\n",
" <td>70.34</td>\n",
" <td>509.84</td>\n",
" <td>101.97</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SVK</th>\n",
" <td>21</td>\n",
" <td>Slovakia</td>\n",
" <td>882.98</td>\n",
" <td>846</td>\n",
" <td>3</td>\n",
" <td>428.49</td>\n",
" <td>428.49</td>\n",
" <td>339.80</td>\n",
" <td>169.90</td>\n",
" <td>737.30</td>\n",
" <td>221.19</td>\n",
" <td>317.00</td>\n",
" <td>63.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ISL</th>\n",
" <td>22</td>\n",
" <td>Iceland</td>\n",
" <td>876.96</td>\n",
" <td>872</td>\n",
" <td>-1</td>\n",
" <td>506.60</td>\n",
" <td>506.60</td>\n",
" <td>339.98</td>\n",
" <td>169.99</td>\n",
" <td>465.47</td>\n",
" <td>139.64</td>\n",
" <td>303.64</td>\n",
" <td>60.73</td>\n",
" </tr>\n",
" <tr>\n",
" <th>USA</th>\n",
" <td>23</td>\n",
" <td>USA</td>\n",
" <td>861.29</td>\n",
" <td>847</td>\n",
" <td>0</td>\n",
" <td>453.11</td>\n",
" <td>453.11</td>\n",
" <td>373.96</td>\n",
" <td>186.98</td>\n",
" <td>306.40</td>\n",
" <td>91.92</td>\n",
" <td>646.42</td>\n",
" <td>129.28</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ECU</th>\n",
" <td>24</td>\n",
" <td>Ecuador</td>\n",
" <td>858.06</td>\n",
" <td>839</td>\n",
" <td>1</td>\n",
" <td>403.45</td>\n",
" <td>403.45</td>\n",
" <td>578.57</td>\n",
" <td>289.29</td>\n",
" <td>371.72</td>\n",
" <td>111.52</td>\n",
" <td>269.01</td>\n",
" <td>53.80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>TUR</th>\n",
" <td>25</td>\n",
" <td>Turkey</td>\n",
" <td>NaN</td>\n",
" <td>863</td>\n",
" <td>-3</td>\n",
" <td>386.42</td>\n",
" <td>386.42</td>\n",
" <td>619.75</td>\n",
" <td>309.87</td>\n",
" <td>243.05</td>\n",
" <td>72.91</td>\n",
" <td>428.96</td>\n",
" <td>85.79</td>\n",
" </tr>\n",
" <tr>\n",
" <th>IRL</th>\n",
" <td>26</td>\n",
" <td>Republic of Ireland</td>\n",
" <td>853.67</td>\n",
" <td>823</td>\n",
" <td>0</td>\n",
" <td>487.91</td>\n",
" <td>487.91</td>\n",
" <td>469.67</td>\n",
" <td>234.83</td>\n",
" <td>337.84</td>\n",
" <td>101.35</td>\n",
" <td>147.85</td>\n",
" <td>29.57</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SEN</th>\n",
" <td>27</td>\n",
" <td>Senegal</td>\n",
" <td>838.99</td>\n",
" <td>805</td>\n",
" <td>3</td>\n",
" <td>479.05</td>\n",
" <td>479.05</td>\n",
" <td>269.36</td>\n",
" <td>134.68</td>\n",
" <td>584.93</td>\n",
" <td>175.48</td>\n",
" <td>248.88</td>\n",
" <td>49.78</td>\n",
" </tr>\n",
" <tr>\n",
" <th>NIR</th>\n",
" <td>28</td>\n",
" <td>Northern Ireland</td>\n",
" <td>837.49</td>\n",
" <td>823</td>\n",
" <td>-2</td>\n",
" <td>389.48</td>\n",
" <td>389.48</td>\n",
" <td>507.98</td>\n",
" <td>253.99</td>\n",
" <td>497.95</td>\n",
" <td>149.39</td>\n",
" <td>223.19</td>\n",
" <td>44.64</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BIH</th>\n",
" <td>29</td>\n",
" <td>Bosnia and Herzegovina</td>\n",
" <td>835.35</td>\n",
" <td>815</td>\n",
" <td>0</td>\n",
" <td>422.21</td>\n",
" <td>422.21</td>\n",
" <td>474.51</td>\n",
" <td>237.25</td>\n",
" <td>350.96</td>\n",
" <td>105.29</td>\n",
" <td>352.99</td>\n",
" <td>70.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th>IRN</th>\n",
" <td>30</td>\n",
" <td>Iran</td>\n",
" <td>828.66</td>\n",
" <td>820</td>\n",
" <td>-2</td>\n",
" <td>470.21</td>\n",
" <td>470.21</td>\n",
" <td>321.98</td>\n",
" <td>160.99</td>\n",
" <td>398.22</td>\n",
" <td>119.47</td>\n",
" <td>389.96</td>\n",
" <td>77.99</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MLT</th>\n",
" <td>182</td>\n",
" <td>Malta</td>\n",
" <td>83.54</td>\n",
" <td>86</td>\n",
" <td>0</td>\n",
" <td>11.74</td>\n",
" <td>11.74</td>\n",
" <td>64.57</td>\n",
" <td>32.29</td>\n",
" <td>49.85</td>\n",
" <td>14.96</td>\n",
" <td>122.81</td>\n",
" <td>24.56</td>\n",
" </tr>\n",
" <tr>\n",
" <th>GUM</th>\n",
" <td>183</td>\n",
" <td>Guam</td>\n",
" <td>81.72</td>\n",
" <td>82</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>113.42</td>\n",
" <td>56.71</td>\n",
" <td>54.64</td>\n",
" <td>16.39</td>\n",
" <td>43.10</td>\n",
" <td>8.62</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MAC</th>\n",
" <td>184</td>\n",
" <td>Macau</td>\n",
" <td>76.55</td>\n",
" <td>77</td>\n",
" <td>0</td>\n",
" <td>53.13</td>\n",
" <td>53.13</td>\n",
" <td>8.50</td>\n",
" <td>4.25</td>\n",
" <td>63.92</td>\n",
" <td>19.18</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BER</th>\n",
" <td>185</td>\n",
" <td>Bermuda</td>\n",
" <td>75.44</td>\n",
" <td>75</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>53.98</td>\n",
" <td>26.99</td>\n",
" <td>161.50</td>\n",
" <td>48.45</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>LIE</th>\n",
" <td>186</td>\n",
" <td>Liechtenstein</td>\n",
" <td>69.43</td>\n",
" <td>64</td>\n",
" <td>3</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>26.87</td>\n",
" <td>13.44</td>\n",
" <td>162.64</td>\n",
" <td>48.79</td>\n",
" <td>36.00</td>\n",
" <td>7.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>AND</th>\n",
" <td>186</td>\n",
" <td>Andorra</td>\n",
" <td>68.82</td>\n",
" <td>66</td>\n",
" <td>1</td>\n",
" <td>62.94</td>\n",
" <td>62.94</td>\n",
" <td>7.37</td>\n",
" <td>3.69</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>11.00</td>\n",
" <td>2.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BRU</th>\n",
" <td>188</td>\n",
" <td>Brunei Darussalam</td>\n",
" <td>64.81</td>\n",
" <td>65</td>\n",
" <td>0</td>\n",
" <td>42.50</td>\n",
" <td>42.50</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>74.38</td>\n",
" <td>22.31</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ASA</th>\n",
" <td>189</td>\n",
" <td>American Samoa</td>\n",
" <td>63.75</td>\n",
" <td>64</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>127.50</td>\n",
" <td>63.75</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>COK</th>\n",
" <td>189</td>\n",
" <td>Cook Islands</td>\n",
" <td>63.75</td>\n",
" <td>64</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>127.50</td>\n",
" <td>63.75</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SAM</th>\n",
" <td>189</td>\n",
" <td>Samoa</td>\n",
" <td>63.75</td>\n",
" <td>64</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>127.50</td>\n",
" <td>63.75</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BAN</th>\n",
" <td>192</td>\n",
" <td>Bangladesh</td>\n",
" <td>61.52</td>\n",
" <td>60</td>\n",
" <td>1</td>\n",
" <td>21.25</td>\n",
" <td>21.25</td>\n",
" <td>37.63</td>\n",
" <td>18.81</td>\n",
" <td>59.50</td>\n",
" <td>17.85</td>\n",
" <td>18.06</td>\n",
" <td>3.61</td>\n",
" </tr>\n",
" <tr>\n",
" <th>DMA</th>\n",
" <td>193</td>\n",
" <td>Dominica</td>\n",
" <td>60.82</td>\n",
" <td>74</td>\n",
" <td>-7</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>63.75</td>\n",
" <td>31.88</td>\n",
" <td>79.71</td>\n",
" <td>23.91</td>\n",
" <td>25.14</td>\n",
" <td>5.03</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SEY</th>\n",
" <td>194</td>\n",
" <td>Seychelles</td>\n",
" <td>56.92</td>\n",
" <td>51</td>\n",
" <td>2</td>\n",
" <td>6.07</td>\n",
" <td>6.07</td>\n",
" <td>65.61</td>\n",
" <td>32.80</td>\n",
" <td>25.08</td>\n",
" <td>7.52</td>\n",
" <td>52.63</td>\n",
" <td>10.53</td>\n",
" </tr>\n",
" <tr>\n",
" <th>DJI</th>\n",
" <td>195</td>\n",
" <td>Djibouti</td>\n",
" <td>53.12</td>\n",
" <td>53</td>\n",
" <td>-1</td>\n",
" <td>53.13</td>\n",
" <td>53.13</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>TLS</th>\n",
" <td>196</td>\n",
" <td>Timor-Leste</td>\n",
" <td>50.76</td>\n",
" <td>52</td>\n",
" <td>-1</td>\n",
" <td>4.72</td>\n",
" <td>4.72</td>\n",
" <td>28.33</td>\n",
" <td>14.17</td>\n",
" <td>106.25</td>\n",
" <td>31.88</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MNG</th>\n",
" <td>197</td>\n",
" <td>Mongolia</td>\n",
" <td>NaN</td>\n",
" <td>34</td>\n",
" <td>0</td>\n",
" <td>34.00</td>\n",
" <td>34.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SRI</th>\n",
" <td>197</td>\n",
" <td>Sri Lanka</td>\n",
" <td>33.70</td>\n",
" <td>34</td>\n",
" <td>0</td>\n",
" <td>8.50</td>\n",
" <td>8.50</td>\n",
" <td>25.50</td>\n",
" <td>12.75</td>\n",
" <td>24.29</td>\n",
" <td>7.29</td>\n",
" <td>25.80</td>\n",
" <td>5.16</td>\n",
" </tr>\n",
" <tr>\n",
" <th>VIR</th>\n",
" <td>199</td>\n",
" <td>US Virgin Islands</td>\n",
" <td>26.39</td>\n",
" <td>26</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>87.98</td>\n",
" <td>26.39</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>PAK</th>\n",
" <td>200</td>\n",
" <td>Pakistan</td>\n",
" <td>23.85</td>\n",
" <td>24</td>\n",
" <td>1</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>50.83</td>\n",
" <td>15.25</td>\n",
" <td>43.00</td>\n",
" <td>8.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th>TCA</th>\n",
" <td>201</td>\n",
" <td>Turks and Caicos Islands</td>\n",
" <td>19.80</td>\n",
" <td>20</td>\n",
" <td>1</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>66.00</td>\n",
" <td>19.80</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MSR</th>\n",
" <td>201</td>\n",
" <td>Montserrat</td>\n",
" <td>19.58</td>\n",
" <td>26</td>\n",
" <td>-2</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>21.25</td>\n",
" <td>6.38</td>\n",
" <td>66.00</td>\n",
" <td>13.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CAY</th>\n",
" <td>203</td>\n",
" <td>Cayman Islands</td>\n",
" <td>12.75</td>\n",
" <td>13</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>42.50</td>\n",
" <td>12.75</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SMR</th>\n",
" <td>204</td>\n",
" <td>San Marino</td>\n",
" <td>11.88</td>\n",
" <td>12</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>39.60</td>\n",
" <td>11.88</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>VGB</th>\n",
" <td>205</td>\n",
" <td>British Virgin Islands</td>\n",
" <td>6.38</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>21.25</td>\n",
" <td>6.38</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>AIA</th>\n",
" <td>206</td>\n",
" <td>Anguilla</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BAH</th>\n",
" <td>206</td>\n",
" <td>Bahamas</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ERI</th>\n",
" <td>206</td>\n",
" <td>Eritrea</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>GIB</th>\n",
" <td>206</td>\n",
" <td>Gibraltar</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>SOM</th>\n",
" <td>206</td>\n",
" <td>Somalia</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>TGA</th>\n",
" <td>206</td>\n",
" <td>Tonga</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>211 rows × 13 columns</p>\n",
"</div>"
],
"text/plain": [
" Rank Team Total Points Previous Points \\\n",
"Country Code \n",
"BRA 1 Brazil 1715.02 1672 \n",
"ARG 2 Argentina 1626.23 1603 \n",
"GER 3 Germany 1511.44 1464 \n",
"CHI 4 Chile 1422.14 1411 \n",
"COL 5 Colombia 1365.63 1348 \n",
"FRA 6 France 1332.16 1294 \n",
"BEL 7 Belgium 1291.57 1281 \n",
"POR 8 Portugal 1266.76 1259 \n",
"SUI 9 Switzerland 1263.29 1212 \n",
"ESP 10 Spain 1198.19 1204 \n",
"POL 10 Poland 1197.70 1183 \n",
"ITA 12 Italy 1193.23 1165 \n",
"WAL 13 Wales 1119.36 1119 \n",
"ENG 13 England 1119.17 1103 \n",
"PER 15 Peru 1108.36 1044 \n",
"URU 16 Uruguay 1098.77 1097 \n",
"MEX 17 Mexico 1049.98 1076 \n",
"CRO 18 Croatia 1033.11 1016 \n",
"CRC 19 Costa Rica 912.74 902 \n",
"EGY 20 Egypt 902.98 910 \n",
"SVK 21 Slovakia 882.98 846 \n",
"ISL 22 Iceland 876.96 872 \n",
"USA 23 USA 861.29 847 \n",
"ECU 24 Ecuador 858.06 839 \n",
"TUR 25 Turkey NaN 863 \n",
"IRL 26 Republic of Ireland 853.67 823 \n",
"SEN 27 Senegal 838.99 805 \n",
"NIR 28 Northern Ireland 837.49 823 \n",
"BIH 29 Bosnia and Herzegovina 835.35 815 \n",
"IRN 30 Iran 828.66 820 \n",
"... ... ... ... ... \n",
"MLT 182 Malta 83.54 86 \n",
"GUM 183 Guam 81.72 82 \n",
"MAC 184 Macau 76.55 77 \n",
"BER 185 Bermuda 75.44 75 \n",
"LIE 186 Liechtenstein 69.43 64 \n",
"AND 186 Andorra 68.82 66 \n",
"BRU 188 Brunei Darussalam 64.81 65 \n",
"ASA 189 American Samoa 63.75 64 \n",
"COK 189 Cook Islands 63.75 64 \n",
"SAM 189 Samoa 63.75 64 \n",
"BAN 192 Bangladesh 61.52 60 \n",
"DMA 193 Dominica 60.82 74 \n",
"SEY 194 Seychelles 56.92 51 \n",
"DJI 195 Djibouti 53.12 53 \n",
"TLS 196 Timor-Leste 50.76 52 \n",
"MNG 197 Mongolia NaN 34 \n",
"SRI 197 Sri Lanka 33.70 34 \n",
"VIR 199 US Virgin Islands 26.39 26 \n",
"PAK 200 Pakistan 23.85 24 \n",
"TCA 201 Turks and Caicos Islands 19.80 20 \n",
"MSR 201 Montserrat 19.58 26 \n",
"CAY 203 Cayman Islands 12.75 13 \n",
"SMR 204 San Marino 11.88 12 \n",
"VGB 205 British Virgin Islands 6.38 5 \n",
"AIA 206 Anguilla NaN 0 \n",
"BAH 206 Bahamas NaN 0 \n",
"ERI 206 Eritrea NaN 0 \n",
"GIB 206 Gibraltar NaN 0 \n",
"SOM 206 Somalia NaN 0 \n",
"TGA 206 Tonga NaN 0 \n",
"\n",
" +/- Avg. AVG WGT Avg..1 AVG WGT.1 Avg..2 AVG WGT.2 \\\n",
"Country Code \n",
"BRA 0 1038.91 1038.91 555.56 277.78 793.26 237.98 \n",
"ARG 0 877.12 877.12 741.10 370.55 919.87 275.96 \n",
"GER 0 857.80 857.80 412.01 206.00 1153.12 345.94 \n",
"CHI 0 756.47 756.47 793.85 396.92 489.13 146.74 \n",
"COL 0 705.66 705.66 597.24 298.62 821.59 246.48 \n",
"FRA 0 855.30 855.30 351.26 175.63 704.66 211.40 \n",
"BEL 0 597.83 597.83 587.90 293.95 961.05 288.32 \n",
"POR 0 671.59 671.59 564.84 282.42 617.62 185.29 \n",
"SUI 0 788.68 788.68 355.32 177.66 563.16 168.95 \n",
"ESP 0 597.37 597.37 669.64 334.82 443.99 133.20 \n",
"POL 1 764.51 764.51 450.51 225.25 554.05 166.21 \n",
"ITA 0 708.03 708.03 417.65 208.82 550.06 165.02 \n",
"WAL 0 683.10 683.10 404.91 202.46 572.55 171.77 \n",
"ENG 1 591.57 591.57 544.52 272.26 520.33 156.10 \n",
"PER 2 809.83 809.83 369.85 184.93 203.83 61.15 \n",
"URU -1 487.69 487.69 582.68 291.34 618.27 185.48 \n",
"MEX -1 583.06 583.06 492.90 246.45 449.51 134.85 \n",
"CRO 0 637.83 637.83 356.79 178.39 536.15 160.84 \n",
"CRC 1 477.40 477.40 306.98 153.49 629.32 188.80 \n",
"EGY -1 568.68 568.68 323.98 161.99 234.47 70.34 \n",
"SVK 3 428.49 428.49 339.80 169.90 737.30 221.19 \n",
"ISL -1 506.60 506.60 339.98 169.99 465.47 139.64 \n",
"USA 0 453.11 453.11 373.96 186.98 306.40 91.92 \n",
"ECU 1 403.45 403.45 578.57 289.29 371.72 111.52 \n",
"TUR -3 386.42 386.42 619.75 309.87 243.05 72.91 \n",
"IRL 0 487.91 487.91 469.67 234.83 337.84 101.35 \n",
"SEN 3 479.05 479.05 269.36 134.68 584.93 175.48 \n",
"NIR -2 389.48 389.48 507.98 253.99 497.95 149.39 \n",
"BIH 0 422.21 422.21 474.51 237.25 350.96 105.29 \n",
"IRN -2 470.21 470.21 321.98 160.99 398.22 119.47 \n",
"... ... ... ... ... ... ... ... \n",
"MLT 0 11.74 11.74 64.57 32.29 49.85 14.96 \n",
"GUM 0 0.00 0.00 113.42 56.71 54.64 16.39 \n",
"MAC 0 53.13 53.13 8.50 4.25 63.92 19.18 \n",
"BER 0 0.00 0.00 53.98 26.99 161.50 48.45 \n",
"LIE 3 0.00 0.00 26.87 13.44 162.64 48.79 \n",
"AND 1 62.94 62.94 7.37 3.69 0.00 0.00 \n",
"BRU 0 42.50 42.50 0.00 0.00 74.38 22.31 \n",
"ASA 0 0.00 0.00 127.50 63.75 0.00 0.00 \n",
"COK 0 0.00 0.00 127.50 63.75 0.00 0.00 \n",
"SAM 0 0.00 0.00 127.50 63.75 0.00 0.00 \n",
"BAN 1 21.25 21.25 37.63 18.81 59.50 17.85 \n",
"DMA -7 0.00 0.00 63.75 31.88 79.71 23.91 \n",
"SEY 2 6.07 6.07 65.61 32.80 25.08 7.52 \n",
"DJI -1 53.13 53.13 0.00 0.00 0.00 0.00 \n",
"TLS -1 4.72 4.72 28.33 14.17 106.25 31.88 \n",
"MNG 0 34.00 34.00 0.00 0.00 0.00 0.00 \n",
"SRI 0 8.50 8.50 25.50 12.75 24.29 7.29 \n",
"VIR 0 0.00 0.00 0.00 0.00 87.98 26.39 \n",
"PAK 1 0.00 0.00 0.00 0.00 50.83 15.25 \n",
"TCA 1 0.00 0.00 0.00 0.00 66.00 19.80 \n",
"MSR -2 0.00 0.00 0.00 0.00 21.25 6.38 \n",
"CAY 0 0.00 0.00 0.00 0.00 42.50 12.75 \n",
"SMR 0 0.00 0.00 0.00 0.00 39.60 11.88 \n",
"VGB 0 0.00 0.00 0.00 0.00 21.25 6.38 \n",
"AIA 0 0.00 0.00 0.00 0.00 0.00 0.00 \n",
"BAH 0 0.00 0.00 0.00 0.00 0.00 0.00 \n",
"ERI 0 0.00 0.00 0.00 0.00 0.00 0.00 \n",
"GIB 0 0.00 0.00 0.00 0.00 0.00 0.00 \n",
"SOM 0 0.00 0.00 0.00 0.00 0.00 0.00 \n",
"TGA 0 0.00 0.00 0.00 0.00 0.00 0.00 \n",
"\n",
" Avg..3 AVG WGT.3 \n",
"Country Code \n",
"BRA 801.78 160.36 \n",
"ARG 512.98 102.60 \n",
"GER 508.50 101.70 \n",
"CHI 610.01 122.00 \n",
"COL 574.37 114.87 \n",
"FRA 449.18 89.84 \n",
"BEL 557.40 111.48 \n",
"POR 637.29 127.46 \n",
"SUI 640.01 128.00 \n",
"ESP 664.00 132.80 \n",
"POL 208.62 41.72 \n",
"ITA 556.81 111.36 \n",
"WAL 310.21 62.04 \n",
"ENG 496.25 99.25 \n",
"PER 262.31 52.46 \n",
"URU 671.34 134.27 \n",
"MEX 428.06 85.61 \n",
"CRO 280.24 56.05 \n",
"CRC 465.28 93.06 \n",
"EGY 509.84 101.97 \n",
"SVK 317.00 63.40 \n",
"ISL 303.64 60.73 \n",
"USA 646.42 129.28 \n",
"ECU 269.01 53.80 \n",
"TUR 428.96 85.79 \n",
"IRL 147.85 29.57 \n",
"SEN 248.88 49.78 \n",
"NIR 223.19 44.64 \n",
"BIH 352.99 70.60 \n",
"IRN 389.96 77.99 \n",
"... ... ... \n",
"MLT 122.81 24.56 \n",
"GUM 43.10 8.62 \n",
"MAC 0.00 0.00 \n",
"BER 0.00 0.00 \n",
"LIE 36.00 7.20 \n",
"AND 11.00 2.20 \n",
"BRU 0.00 0.00 \n",
"ASA 0.00 0.00 \n",
"COK 0.00 0.00 \n",
"SAM 0.00 0.00 \n",
"BAN 18.06 3.61 \n",
"DMA 25.14 5.03 \n",
"SEY 52.63 10.53 \n",
"DJI 0.00 0.00 \n",
"TLS 0.00 0.00 \n",
"MNG 0.00 0.00 \n",
"SRI 25.80 5.16 \n",
"VIR 0.00 0.00 \n",
"PAK 43.00 8.60 \n",
"TCA 0.00 0.00 \n",
"MSR 66.00 13.20 \n",
"CAY 0.00 0.00 \n",
"SMR 0.00 0.00 \n",
"VGB 0.00 0.00 \n",
"AIA 0.00 0.00 \n",
"BAH 0.00 0.00 \n",
"ERI 0.00 0.00 \n",
"GIB 0.00 0.00 \n",
"SOM 0.00 0.00 \n",
"TGA 0.00 0.00 \n",
"\n",
"[211 rows x 13 columns]"
]
},
"execution_count": 50,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_rank=pd.read_csv('ranking.csv', header=0, sep=';')\n",
"\n",
"df_rank['Country Code']=df_rank['Team'].str.extract('^([A-Z]{3})')\n",
"df_rank['Team']=df_rank['Team'].apply(lambda x: re.sub(r'^[A-Z]{3}', '', x))\n",
"df_rank['Total Points']=df_rank['Total Points'].str.extract('\\d+\\D(\\d+\\.\\d+)').astype(float)\n",
"df_rank.dropna(axis=1, how='all', inplace=True)\n",
"df_rank.set_index('Country Code', inplace=True)\n",
"\n",
"df_rank # rank of national team"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'Абхазия': 'Abkhazia', 'Австралия': 'Australia', 'Австрия': 'Austria', 'Азербайджан': 'Azerbaijan', 'Аландские острова': 'Aland Islands', 'Албания': 'Albania', 'Алжир': 'Algeria', 'Ангилья': 'Anguilla', 'Англия': 'England', 'Ангола': 'Angola', 'Андорра': 'Andorra', 'Аргентина': 'Argentina', 'Армения': 'Armenia', 'Аруба': 'Aruba', 'Афганистан': 'Afghanistan', 'Багамские острова': 'Bahamas', 'Бангладеш': 'Bangladesh', 'Барбадос': 'Barbados', 'Бахрейн': 'Bahrain', 'Беларусь': 'Belarus', 'Белиз': 'Belize', 'Бельгия': 'Belgium', 'Бенин': 'Benin', 'Болгария': 'Bulgaria', 'Боливия': 'Bolivia', 'Боливия, многонациональное государство': 'Bolivia', 'Босния и Герцеговина': 'Bosnia and Herzegovina', 'Ботсвана': 'Botswana', 'Бразилия': 'Brazil', 'Бруней': 'Brunei Darussalam', 'Бурунди': 'Burundi', 'Бутан': 'Bhutan', 'Ватикан': 'Vatican City', 'Великобритания': 'United Kingdom', 'Великобритания (Соединенное Королевство)': 'United Kingdom', 'Венгрия': 'Hungary', 'Венесуэла': 'Venezuela', 'Венесуэла, Боливарианская Республика': 'Venezuela', 'Восточный Тимор': 'Timor, East', 'Вьетнам': 'Viet Nam', 'Габон': 'Gabon', 'Гаити': 'Haiti', 'Гамбия': 'Gambia', 'Гана': 'Ghana', 'Гваделупа': 'Guadeloupe', 'Гватемала': 'Guatemala', 'Гвинея': 'Guinea', 'Гвинея-Бисау': 'Guinea-Bissau', 'Германия': 'Germany', 'Гибралтар': 'Gibraltar', 'Гондурас': 'Honduras', 'Гонконг': 'Hong Kong', 'Гренада': 'Grenada', 'Гренландия': 'Greenland', 'Греция': 'Greece', 'Грузия': 'Georgia', 'Гуам': 'Guam', 'Дания': 'Denmark', 'Доминика': 'Dominica', 'Доминиканская Республика': 'Dominican Republic', 'Египет': 'Egypt', 'Замбия': 'Zambia', 'Западная Сахара': 'Western Sahara', 'Зимбабве': 'Zimbabwe', 'Израиль': 'Israel', 'Индия': 'India', 'Индонезия': 'Indonesia', 'Иордания': 'Jordan', 'Ирак': 'Iraq', 'Иран': 'Iran', 'Иран, Исламская Республика': 'Iran', 'Ирландия': 'Ireland', 'Исландия': 'Iceland', 'Испания': 'Spain', 'Италия': 'Italy', 'Йемен': 'Yemen', 'КНДР (Северная Корея)': 'Korea, D.P.R.', 'Казахстан': 'Kazakhstan', 'Камбоджа': 'Cambodia', 'Камерун': 'Cameroon', 'Канада': 'Canada', 'Катар': 'Qatar', 'Кения': 'Kenya', 'Кипр': 'Cyprus', 'Киргизия': 'Kyrgyzstan', 'Кирибати': 'Kiribati', 'Китай': 'China', 'Колумбия': 'Colombia', 'Конго': 'Republic of the Congo', 'Конго, Демократическая Республика': 'Democratic Republic of the Congo', 'Корейская Народно-Демократическая Республика': 'Korea, D.P.R.', 'Корея Северная': 'Korea, D.P.R.', 'Корея Южная': 'Korea', 'Южная Корея': 'Korea', 'Корея, Республика': 'Korea', 'Коста-Рика': 'Costa Rica', \"Кот-д'Ивуар\": \"Cote d'Ivoire\", 'Кот-д’Ивуар': \"Cote d'Ivoire\", 'Куба': 'Cuba', 'Кувейт': 'Kuwait', 'ЛИЦА БЕЗ ГРАЖДАНСТВА': 'v.c.', 'Лаос': 'Lao P.D.R.', 'Лаосская Народно-Демократическая Республика': 'Lao P.D.R.', 'Латвия': 'Latvia', 'Лесото': 'Lesotho', 'Либерия': 'Liberia', 'Ливан': 'Lebanon', 'Ливия': 'Libyan Arab Jamahiriya', 'Литва': 'Lithuania', 'Лихтенштейн': 'Liechtenstein', 'Люксембург': 'Luxembourg', 'Маврикий': 'Mauritius', 'Мавритания': 'Mauritania', 'Мадагаскар': 'Madagascar', 'Македония': 'Macedonia', 'Малави': 'Malawi', 'Малайзия': 'Malaysia', 'Мали': 'Mali', 'Мальдивы': 'Maldives', 'Мальта': 'Malta', 'Марокко': 'Morocco', 'Мексика': 'Mexico', 'Мозамбик': 'Mozambique', 'Молдавия': 'Moldova', 'Молдова, Республика': 'Moldova Republic', 'Монако': 'Monaco', 'Монголия': 'Mongolia', 'Намибия': 'Namibia', 'Непал': 'Nepal', 'Нигер': 'Niger', 'Нигерия': 'Nigeria', 'Нидерланды': 'Netherlands', 'Никарагуа': 'Nicaragua', 'Новая Зеландия': 'New Zealand', 'Норвегия': 'Norway', 'ОАЭ': 'United Arab Emirates', 'Оман': 'Oman', 'Пакистан': 'Pakistan', 'Палестина': 'Palestine', 'Палестина, Государство': 'Palestine', 'Панама': 'Panama', 'Парагвай': 'Paraguay', 'Перу': 'Peru', 'Польша': 'Poland', 'Португалия': 'Portugal', 'Республика Корея': 'Korea', 'Республика Македония': 'Macedonia', 'Республика Молдова': 'Moldova Republic', 'Россия': 'Russia', 'Румыния': 'Romania', 'США': 'USA', 'Сан-Марино': 'San Marino', 'Саудовская Аравия': 'Saudi Arabia', 'Сенегал': 'Senegal', 'Сербия': 'Serbia', 'Сингапур': 'Singapore', 'Сирийская Арабская Республика': 'Syrian Arab Republic', 'Сирия': 'Syrian Arab Republic', 'Словакия': 'Slovakia', 'Словения': 'Slovenia', 'Соединенное Королевство (Великобритания)': 'United Kingdom', 'Соединенные Штаты': 'USA', 'Сомали': 'Somalia', 'Судан': 'Sudan', 'Таджикистан': 'Tajikistan', 'Таиланд': 'Thailand', 'Тайвань (Китай)': 'Taiwan', 'Танзания': 'Tanzania', 'Того': 'Togo', 'Тунис': 'Tunisia', 'Туркмения': 'Turkmenistan', 'Турция': 'Turkey', 'Уганда': 'Uganda', 'Узбекистан': 'Uzbekistan', 'Украина': 'Ukraine', 'Уругвай': 'Uruguay', 'Федеративные Штаты Микронезии': 'Micronesia', 'Фиджи': 'Fiji', 'Филиппины': 'Philippines', 'Финляндия': 'Finland', 'Франция': 'France', 'Хорватия': 'Croatia', 'Чад': 'Chad', 'Черногория': 'Montenegro', 'Чешская Республика': 'Czech Republic', 'Чили': 'Chile', 'Швейцария': 'Switzerland', 'Швеция': 'Sweden', 'Шри-Ланка': 'Sri Lanka', 'Эквадор': 'Ecuador', 'Эритрея': 'Eritrea', 'Эстония': 'Estonia', 'Эфиопия': 'Ethiopia', 'ЮАР': 'South Africa', 'Южная Африка': 'South Africa', 'Южная Осетия': 'South Ossetia', 'Ямайка': 'Jamaica', 'Япония': 'Japan', 'другие страны': 'other countries', 'North. Ireland': 'Northern Ireland', 'Голландия': 'Netherlands', 'Таити': 'Tahiti', 'Bosnia-Herzegov': 'Bosnia and Herzegovina', 'Korea': 'Korea Republic', 'Ireland': 'Republic of Ireland', 'Ireland Rep.': 'Republic of Ireland', 'Macedonia': 'FYR Macedonia'}\n"
]
}
],
"source": [
"df_rus_eng_translate=pd.read_csv('../Migration/countries_rus_eng.csv', header=None, names=['Rus', 'Eng'])\n",
"#df_rus_eng_translate.set_index('Rus', inplace=True)\n",
"\n",
"dict_translate=df_rus_eng_translate.set_index('Rus').to_dict()['Eng']\n",
"print(dict_translate)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Making dataframe for modeling\n",
"### Field 'Result' will be y - label for forecasting. \n",
"'1' - left team win, '-1' - right team win, '0' - draw\n",
"### Modeling will be on UEFA rank \n",
"Fields 'Total Points', 'Previous Points' and '+/-' from dataset"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Country 1</th>\n",
" <th>Country 2</th>\n",
" <th>Score 1</th>\n",
" <th>Score 2</th>\n",
" <th>result</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Brazil</td>\n",
" <td>Spain</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Uruguay</td>\n",
" <td>Italy</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Spain</td>\n",
" <td>Italy</td>\n",
" <td>7</td>\n",
" <td>6</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Brazil</td>\n",
" <td>Uruguay</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Italy</td>\n",
" <td>Brazil</td>\n",
" <td>2</td>\n",
" <td>4</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Japan</td>\n",
" <td>Mexico</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Italy</td>\n",
" <td>Japan</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>Brazil</td>\n",
" <td>Mexico</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Mexico</td>\n",
" <td>Italy</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>Brazil</td>\n",
" <td>Japan</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>Nigeria</td>\n",
" <td>Spain</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>Uruguay</td>\n",
" <td>Tahiti</td>\n",
" <td>8</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>Nigeria</td>\n",
" <td>Uruguay</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>Spain</td>\n",
" <td>Tahiti</td>\n",
" <td>10</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>Tahiti</td>\n",
" <td>Nigeria</td>\n",
" <td>1</td>\n",
" <td>6</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>Spain</td>\n",
" <td>Uruguay</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>USA</td>\n",
" <td>Brazil</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>Spain</td>\n",
" <td>South Africa</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>Brazil</td>\n",
" <td>South Africa</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>Spain</td>\n",
" <td>USA</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>Iraq</td>\n",
" <td>New Zealand</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>Spain</td>\n",
" <td>South Africa</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>South Africa</td>\n",
" <td>New Zealand</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>Spain</td>\n",
" <td>Iraq</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>New Zealand</td>\n",
" <td>Spain</td>\n",
" <td>0</td>\n",
" <td>5</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>South Africa</td>\n",
" <td>Iraq</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>Egypt</td>\n",
" <td>USA</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>Italy</td>\n",
" <td>Brazil</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>Egypt</td>\n",
" <td>Italy</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>USA</td>\n",
" <td>Brazil</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>256</th>\n",
" <td>Haiti</td>\n",
" <td>Peru</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>257</th>\n",
" <td>Brazil</td>\n",
" <td>Ecuador</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>258</th>\n",
" <td>Jamaica</td>\n",
" <td>Venezuela</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>259</th>\n",
" <td>Mexico</td>\n",
" <td>Uruguay</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>260</th>\n",
" <td>Panama</td>\n",
" <td>Bolivia</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>261</th>\n",
" <td>Argentina</td>\n",
" <td>Chile</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>262</th>\n",
" <td>USA</td>\n",
" <td>Costa Rica</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>263</th>\n",
" <td>Colombia</td>\n",
" <td>Paraguay</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>264</th>\n",
" <td>Brazil</td>\n",
" <td>Haiti</td>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>265</th>\n",
" <td>Ecuador</td>\n",
" <td>Peru</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>266</th>\n",
" <td>Uruguay</td>\n",
" <td>Venezuela</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>267</th>\n",
" <td>Mexico</td>\n",
" <td>Jamaica</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>268</th>\n",
" <td>Chile</td>\n",
" <td>Bolivia</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>269</th>\n",
" <td>Argentina</td>\n",
" <td>Panama</td>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>270</th>\n",
" <td>USA</td>\n",
" <td>Paraguay</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>271</th>\n",
" <td>Colombia</td>\n",
" <td>Costa Rica</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>272</th>\n",
" <td>Ecuador</td>\n",
" <td>Haiti</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>273</th>\n",
" <td>Brazil</td>\n",
" <td>Peru</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>274</th>\n",
" <td>Mexico</td>\n",
" <td>Venezuela</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>275</th>\n",
" <td>Uruguay</td>\n",
" <td>Jamaica</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>276</th>\n",
" <td>Chile</td>\n",
" <td>Panama</td>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>277</th>\n",
" <td>Argentina</td>\n",
" <td>Bolivia</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>278</th>\n",
" <td>USA</td>\n",
" <td>Ecuador</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>279</th>\n",
" <td>Peru</td>\n",
" <td>Colombia</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>280</th>\n",
" <td>Argentina</td>\n",
" <td>Venezuela</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>281</th>\n",
" <td>Mexico</td>\n",
" <td>Chile</td>\n",
" <td>0</td>\n",
" <td>7</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>282</th>\n",
" <td>USA</td>\n",
" <td>Argentina</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>283</th>\n",
" <td>Colombia</td>\n",
" <td>Chile</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>284</th>\n",
" <td>USA</td>\n",
" <td>Colombia</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>-1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>285</th>\n",
" <td>Argentina</td>\n",
" <td>Chile</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>286 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
" Country 1 Country 2 Score 1 Score 2 result\n",
"0 Brazil Spain 3 0 1\n",
"1 Uruguay Italy 2 3 -1\n",
"2 Spain Italy 7 6 1\n",
"3 Brazil Uruguay 2 1 1\n",
"4 Italy Brazil 2 4 -1\n",
"5 Japan Mexico 1 2 -1\n",
"6 Italy Japan 4 3 1\n",
"7 Brazil Mexico 2 0 1\n",
"8 Mexico Italy 1 2 -1\n",
"9 Brazil Japan 3 0 1\n",
"10 Nigeria Spain 0 3 -1\n",
"11 Uruguay Tahiti 8 0 1\n",
"12 Nigeria Uruguay 1 2 -1\n",
"13 Spain Tahiti 10 0 1\n",
"14 Tahiti Nigeria 1 6 -1\n",
"15 Spain Uruguay 2 1 1\n",
"16 USA Brazil 2 3 -1\n",
"17 Spain South Africa 3 2 1\n",
"18 Brazil South Africa 1 0 1\n",
"19 Spain USA 0 2 -1\n",
"20 Iraq New Zealand 0 0 0\n",
"21 Spain South Africa 2 0 1\n",
"22 South Africa New Zealand 2 0 1\n",
"23 Spain Iraq 1 0 1\n",
"24 New Zealand Spain 0 5 -1\n",
"25 South Africa Iraq 0 0 0\n",
"26 Egypt USA 0 3 -1\n",
"27 Italy Brazil 0 3 -1\n",
"28 Egypt Italy 1 0 1\n",
"29 USA Brazil 0 3 -1\n",
".. ... ... ... ... ...\n",
"256 Haiti Peru 0 1 -1\n",
"257 Brazil Ecuador 0 0 0\n",
"258 Jamaica Venezuela 0 1 -1\n",
"259 Mexico Uruguay 3 1 1\n",
"260 Panama Bolivia 2 1 1\n",
"261 Argentina Chile 2 1 1\n",
"262 USA Costa Rica 4 0 1\n",
"263 Colombia Paraguay 2 1 1\n",
"264 Brazil Haiti 7 1 1\n",
"265 Ecuador Peru 2 2 0\n",
"266 Uruguay Venezuela 0 1 -1\n",
"267 Mexico Jamaica 2 0 1\n",
"268 Chile Bolivia 2 1 1\n",
"269 Argentina Panama 5 0 1\n",
"270 USA Paraguay 1 0 1\n",
"271 Colombia Costa Rica 2 3 -1\n",
"272 Ecuador Haiti 4 0 1\n",
"273 Brazil Peru 0 1 -1\n",
"274 Mexico Venezuela 1 1 0\n",
"275 Uruguay Jamaica 3 0 1\n",
"276 Chile Panama 4 2 1\n",
"277 Argentina Bolivia 3 0 1\n",
"278 USA Ecuador 2 1 1\n",
"279 Peru Colombia 0 0 0\n",
"280 Argentina Venezuela 4 1 1\n",
"281 Mexico Chile 0 7 -1\n",
"282 USA Argentina 0 4 -1\n",
"283 Colombia Chile 0 2 -1\n",
"284 USA Colombia 0 1 -1\n",
"285 Argentina Chile 0 0 0\n",
"\n",
"[286 rows x 5 columns]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"lst_columns=['Country 1', 'Country 2', 'Score 1', 'Score 2']\n",
"df_results=pd.DataFrame(columns=lst_columns)\n",
"\n",
"def set_results(x):\n",
" if x['Score 1'] > x['Score 2']: return 1\n",
" if x['Score 1'] < x['Score 2']: return -1\n",
" return 0\n",
"\n",
"def translate_line(strLine):\n",
" words=list(filter(None, re.split('\\t| - |:|–', line))) \n",
" return [dict_translate.get(word.strip(), word.strip()) for word in words if word not in ['-', '–']]\n",
"\n",
" \n",
"f=open('results.txt', 'r')\n",
"for i, line in enumerate(f):\n",
" df_results.loc[i]=dict(zip(lst_columns, translate_line(line)))\n",
"\n",
"df_results[lst_columns[2:]].astype(int)\n",
"\n",
"#print(df_results['Score 2'].sort_values().unique().tolist())\n",
"df_results['result']=df_results.apply(set_results, axis=1)\n",
"df_results # dataframe with games results"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Country 1 Country 2 Score 1 Score 2 result Country 1 ID \\\n",
"0 Brazil Spain 3 0 1 27.0 \n",
"1 Italy Spain 2 0 1 95.0 \n",
"2 Nigeria Spain 0 3 -1 139.0 \n",
"3 New Zealand Spain 0 5 -1 136.0 \n",
"4 Croatia Spain 2 1 1 50.0 \n",
"5 FYR Macedonia Spain 1 2 -1 67.0 \n",
"6 Brazil Uruguay 2 1 1 27.0 \n",
"7 Spain Uruguay 2 1 1 173.0 \n",
"8 Italy Uruguay 0 1 -1 95.0 \n",
"9 Mexico Uruguay 3 1 1 124.0 \n",
"10 Nigeria Uruguay 1 2 -1 139.0 \n",
"11 Colombia Uruguay 2 0 1 43.0 \n",
"12 Brazil Mexico 2 0 1 27.0 \n",
"13 Brazil Mexico 0 0 0 27.0 \n",
"14 Japan Mexico 1 2 -1 97.0 \n",
"15 Japan Mexico 1 2 -1 97.0 \n",
"16 Germany Mexico 4 3 1 75.0 \n",
"17 Greece Mexico 0 0 0 78.0 \n",
"18 Netherlands Mexico 2 1 1 134.0 \n",
"19 Croatia Mexico 1 3 -1 50.0 \n",
"20 Portugal Mexico 2 2 0 151.0 \n",
"21 Brazil Japan 3 0 1 27.0 \n",
"22 Italy Japan 4 3 1 95.0 \n",
"23 Greece Japan 0 1 -1 78.0 \n",
"24 Cote d'Ivoire Japan 2 1 1 49.0 \n",
"25 Brazil South Africa 1 0 1 27.0 \n",
"26 Spain South Africa 3 2 1 173.0 \n",
"27 Spain South Africa 2 0 1 173.0 \n",
"28 Brazil Egypt 4 3 1 27.0 \n",
"29 Brazil Argentina 4 1 1 27.0 \n",
".. ... ... ... ... ... ... \n",
"241 Portugal Hungary 3 0 1 151.0 \n",
"242 Austria Hungary 0 2 -1 12.0 \n",
"243 Iceland Hungary 1 1 0 89.0 \n",
"244 Andorra Hungary 1 0 1 4.0 \n",
"245 Wales Serbia 1 1 0 207.0 \n",
"246 Georgia Serbia 1 3 -1 74.0 \n",
"247 Poland Armenia 2 1 1 150.0 \n",
"248 Montenegro Armenia 4 1 1 127.0 \n",
"249 Austria Moldova 2 0 1 12.0 \n",
"250 Georgia Moldova 1 1 0 74.0 \n",
"251 Romania Denmark 0 0 0 155.0 \n",
"252 Kazakhstan Denmark 1 3 -1 99.0 \n",
"253 Ukraine Finland 1 0 1 200.0 \n",
"254 Czech Republic Azerbaijan 0 0 0 54.0 \n",
"255 Northern Ireland Azerbaijan 4 0 1 140.0 \n",
"256 Czech Republic Norway 2 1 1 54.0 \n",
"257 Northern Ireland Norway 2 0 1 140.0 \n",
"258 Hungary Andorra 4 0 1 88.0 \n",
"259 Sweden Belarus 4 0 1 181.0 \n",
"260 Bulgaria Belarus 1 0 1 30.0 \n",
"261 Lithuania Malta 2 0 1 113.0 \n",
"262 Slovenia Malta 2 0 1 168.0 \n",
"263 Denmark Montenegro 0 1 -1 55.0 \n",
"264 Armenia Montenegro 3 2 1 9.0 \n",
"265 Denmark Kazakhstan 4 1 1 55.0 \n",
"266 Armenia Kazakhstan 2 0 1 9.0 \n",
"267 Malta Slovenia 0 1 -1 121.0 \n",
"268 Scotland Slovenia 1 0 1 161.0 \n",
"269 Belarus Bulgaria 2 1 1 18.0 \n",
"270 Moldova Georgia 2 2 0 125.0 \n",
"\n",
" Country 2 ID Rank_x Team_x Total Points_x ... \\\n",
"0 173.0 1 Brazil 1715.02 ... \n",
"1 173.0 12 Italy 1193.23 ... \n",
"2 173.0 38 Nigeria 729.70 ... \n",
"3 173.0 95 New Zealand 343.62 ... \n",
"4 173.0 18 Croatia 1033.11 ... \n",
"5 173.0 136 FYR Macedonia 217.80 ... \n",
"6 202.0 1 Brazil 1715.02 ... \n",
"7 202.0 10 Spain 1198.19 ... \n",
"8 202.0 12 Italy 1193.23 ... \n",
"9 202.0 17 Mexico 1049.98 ... \n",
"10 202.0 38 Nigeria 729.70 ... \n",
"11 202.0 5 Colombia 1365.63 ... \n",
"12 124.0 1 Brazil 1715.02 ... \n",
"13 124.0 1 Brazil 1715.02 ... \n",
"14 124.0 45 Japan 689.37 ... \n",
"15 124.0 45 Japan 689.37 ... \n",
"16 124.0 3 Germany 1511.44 ... \n",
"17 124.0 40 Greece 726.13 ... \n",
"18 124.0 31 Netherlands 819.56 ... \n",
"19 124.0 18 Croatia 1033.11 ... \n",
"20 124.0 8 Portugal 1266.76 ... \n",
"21 97.0 1 Brazil 1715.02 ... \n",
"22 97.0 12 Italy 1193.23 ... \n",
"23 97.0 40 Greece 726.13 ... \n",
"24 97.0 47 Cote d'Ivoire 684.76 ... \n",
"25 171.0 1 Brazil 1715.02 ... \n",
"26 171.0 10 Spain 1198.19 ... \n",
"27 171.0 10 Spain 1198.19 ... \n",
"28 60.0 1 Brazil 1715.02 ... \n",
"29 8.0 1 Brazil 1715.02 ... \n",
".. ... ... ... ... ... \n",
"241 88.0 8 Portugal 1266.76 ... \n",
"242 88.0 35 Austria 750.24 ... \n",
"243 88.0 22 Iceland 876.96 ... \n",
"244 88.0 186 Andorra 68.82 ... \n",
"245 163.0 13 Wales 1119.36 ... \n",
"246 163.0 122 Georgia 270.80 ... \n",
"247 9.0 10 Poland 1197.70 ... \n",
"248 9.0 52 Montenegro 647.17 ... \n",
"249 125.0 35 Austria 750.24 ... \n",
"250 125.0 122 Georgia 270.80 ... \n",
"251 55.0 46 Romania 686.06 ... \n",
"252 55.0 100 Kazakhstan 331.20 ... \n",
"253 70.0 37 Ukraine 737.33 ... \n",
"254 13.0 44 Czech Republic 689.72 ... \n",
"255 13.0 28 Northern Ireland 837.49 ... \n",
"256 141.0 44 Czech Republic 689.72 ... \n",
"257 141.0 28 Northern Ireland 837.49 ... \n",
"258 4.0 33 Hungary 801.61 ... \n",
"259 18.0 34 Sweden 792.81 ... \n",
"260 18.0 60 Bulgaria 615.23 ... \n",
"261 121.0 104 Lithuania 327.41 ... \n",
"262 121.0 56 Slovenia 630.69 ... \n",
"263 127.0 51 Denmark 660.02 ... \n",
"264 127.0 68 Armenia 527.13 ... \n",
"265 99.0 51 Denmark 660.02 ... \n",
"266 99.0 68 Armenia 527.13 ... \n",
"267 168.0 182 Malta 83.54 ... \n",
"268 168.0 61 Scotland 603.05 ... \n",
"269 30.0 83 Belarus 418.60 ... \n",
"270 74.0 161 Moldova 135.11 ... \n",
"\n",
" +/-_y Avg._y AVG WGT_y Avg..1_y AVG WGT.1_y Avg..2_y AVG WGT.2_y \\\n",
"0 0 597.37 597.37 669.64 334.82 443.99 133.20 \n",
"1 0 597.37 597.37 669.64 334.82 443.99 133.20 \n",
"2 0 597.37 597.37 669.64 334.82 443.99 133.20 \n",
"3 0 597.37 597.37 669.64 334.82 443.99 133.20 \n",
"4 0 597.37 597.37 669.64 334.82 443.99 133.20 \n",
"5 0 597.37 597.37 669.64 334.82 443.99 133.20 \n",
"6 -1 487.69 487.69 582.68 291.34 618.27 185.48 \n",
"7 -1 487.69 487.69 582.68 291.34 618.27 185.48 \n",
"8 -1 487.69 487.69 582.68 291.34 618.27 185.48 \n",
"9 -1 487.69 487.69 582.68 291.34 618.27 185.48 \n",
"10 -1 487.69 487.69 582.68 291.34 618.27 185.48 \n",
"11 -1 487.69 487.69 582.68 291.34 618.27 185.48 \n",
"12 -1 583.06 583.06 492.90 246.45 449.51 134.85 \n",
"13 -1 583.06 583.06 492.90 246.45 449.51 134.85 \n",
"14 -1 583.06 583.06 492.90 246.45 449.51 134.85 \n",
"15 -1 583.06 583.06 492.90 246.45 449.51 134.85 \n",
"16 -1 583.06 583.06 492.90 246.45 449.51 134.85 \n",
"17 -1 583.06 583.06 492.90 246.45 449.51 134.85 \n",
"18 -1 583.06 583.06 492.90 246.45 449.51 134.85 \n",
"19 -1 583.06 583.06 492.90 246.45 449.51 134.85 \n",
"20 -1 583.06 583.06 492.90 246.45 449.51 134.85 \n",
"21 -1 407.86 407.86 266.44 133.22 344.24 103.27 \n",
"22 -1 407.86 407.86 266.44 133.22 344.24 103.27 \n",
"23 -1 407.86 407.86 266.44 133.22 344.24 103.27 \n",
"24 -1 407.86 407.86 266.44 133.22 344.24 103.27 \n",
"25 -1 286.27 286.27 265.08 132.54 290.93 87.28 \n",
"26 -1 286.27 286.27 265.08 132.54 290.93 87.28 \n",
"27 -1 286.27 286.27 265.08 132.54 290.93 87.28 \n",
"28 -1 568.68 568.68 323.98 161.99 234.47 70.34 \n",
"29 0 877.12 877.12 741.10 370.55 919.87 275.96 \n",
".. ... ... ... ... ... ... ... \n",
"241 -2 369.81 369.81 555.96 277.98 359.66 107.90 \n",
"242 -2 369.81 369.81 555.96 277.98 359.66 107.90 \n",
"243 -2 369.81 369.81 555.96 277.98 359.66 107.90 \n",
"244 -2 369.81 369.81 555.96 277.98 359.66 107.90 \n",
"245 -1 380.69 380.69 312.80 156.40 156.42 46.93 \n",
"246 -1 380.69 380.69 312.80 156.40 156.42 46.93 \n",
"247 -1 355.84 355.84 125.94 62.97 58.69 17.61 \n",
"248 -1 355.84 355.84 125.94 62.97 58.69 17.61 \n",
"249 -2 49.71 49.71 44.20 22.10 62.31 18.69 \n",
"250 -2 49.71 49.71 44.20 22.10 62.31 18.69 \n",
"251 0 313.01 313.01 312.44 156.22 401.06 120.32 \n",
"252 0 313.01 313.01 312.44 156.22 401.06 120.32 \n",
"253 -11 53.79 53.79 328.63 164.31 138.60 41.58 \n",
"254 11 309.78 309.78 111.87 55.94 77.92 23.38 \n",
"255 11 309.78 309.78 111.87 55.94 77.92 23.38 \n",
"256 -1 108.03 108.03 333.68 166.84 273.54 82.06 \n",
"257 -1 108.03 108.03 333.68 166.84 273.54 82.06 \n",
"258 1 62.94 62.94 7.37 3.69 0.00 0.00 \n",
"259 -5 191.07 191.07 265.17 132.59 221.07 66.32 \n",
"260 -5 191.07 191.07 265.17 132.59 221.07 66.32 \n",
"261 0 11.74 11.74 64.57 32.29 49.85 14.96 \n",
"262 0 11.74 11.74 64.57 32.29 49.85 14.96 \n",
"263 10 489.06 489.06 107.02 53.51 254.43 76.33 \n",
"264 10 489.06 489.06 107.02 53.51 254.43 76.33 \n",
"265 4 171.38 171.38 213.84 106.92 89.97 26.99 \n",
"266 4 171.38 171.38 213.84 106.92 89.97 26.99 \n",
"267 -1 327.78 327.78 224.33 112.17 278.03 83.41 \n",
"268 -1 327.78 327.78 224.33 112.17 278.03 83.41 \n",
"269 -5 378.68 378.68 233.89 116.94 307.40 92.22 \n",
"270 0 156.24 156.24 165.72 82.86 27.23 8.17 \n",
"\n",
" Avg..3_y AVG WGT.3_y Country ID_y \n",
"0 664.00 132.80 173 \n",
"1 664.00 132.80 173 \n",
"2 664.00 132.80 173 \n",
"3 664.00 132.80 173 \n",
"4 664.00 132.80 173 \n",
"5 664.00 132.80 173 \n",
"6 671.34 134.27 202 \n",
"7 671.34 134.27 202 \n",
"8 671.34 134.27 202 \n",
"9 671.34 134.27 202 \n",
"10 671.34 134.27 202 \n",
"11 671.34 134.27 202 \n",
"12 428.06 85.61 124 \n",
"13 428.06 85.61 124 \n",
"14 428.06 85.61 124 \n",
"15 428.06 85.61 124 \n",
"16 428.06 85.61 124 \n",
"17 428.06 85.61 124 \n",
"18 428.06 85.61 124 \n",
"19 428.06 85.61 124 \n",
"20 428.06 85.61 124 \n",
"21 225.10 45.02 97 \n",
"22 225.10 45.02 97 \n",
"23 225.10 45.02 97 \n",
"24 225.10 45.02 97 \n",
"25 206.65 41.33 171 \n",
"26 206.65 41.33 171 \n",
"27 206.65 41.33 171 \n",
"28 509.84 101.97 60 \n",
"29 512.98 102.60 8 \n",
".. ... ... ... \n",
"241 229.60 45.92 88 \n",
"242 229.60 45.92 88 \n",
"243 229.60 45.92 88 \n",
"244 229.60 45.92 88 \n",
"245 408.40 81.68 163 \n",
"246 408.40 81.68 163 \n",
"247 453.61 90.72 9 \n",
"248 453.61 90.72 9 \n",
"249 223.03 44.61 125 \n",
"250 223.03 44.61 125 \n",
"251 352.36 70.47 55 \n",
"252 352.36 70.47 55 \n",
"253 315.75 63.15 70 \n",
"254 249.52 49.90 13 \n",
"255 249.52 49.90 13 \n",
"256 169.75 33.95 141 \n",
"257 169.75 33.95 141 \n",
"258 11.00 2.20 4 \n",
"259 143.14 28.63 18 \n",
"260 143.14 28.63 18 \n",
"261 122.81 24.56 121 \n",
"262 122.81 24.56 121 \n",
"263 141.37 28.27 127 \n",
"264 141.37 28.27 127 \n",
"265 129.57 25.91 99 \n",
"266 129.57 25.91 99 \n",
"267 536.69 107.34 168 \n",
"268 536.69 107.34 168 \n",
"269 136.95 27.39 30 \n",
"270 117.66 23.53 74 \n",
"\n",
"[271 rows x 35 columns]\n"
]
}
],
"source": [
"lstR=pd.DataFrame(df_rank['Team'].sort_values().unique(), columns=['Country'])\n",
"ser_code=lstR.reset_index().set_index('Country')['index']\n",
"\n",
"df_rank['Country ID']=df_rank['Team'].map(ser_code)\n",
"df_results['Country 1 ID']=df_results['Country 1'].map(ser_code)\n",
"df_results['Country 2 ID']=df_results['Country 2'].map(ser_code)\n",
"\n",
"pd_model=pd.merge(df_results, df_rank.dropna(), how='inner', left_on='Country 1 ID', right_on='Country ID')\n",
"pd_model=pd.merge(pd_model, df_rank.dropna(), how='inner', left_on='Country 2 ID', right_on='Country ID')\n",
"print(pd_model)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" result Total Points_x Previous Points_x +/-_x Total Points_y \\\n",
"0 1 1715.02 1672 0 1198.19 \n",
"1 1 1193.23 1165 0 1198.19 \n",
"2 -1 729.70 726 2 1198.19 \n",
"3 -1 343.62 301 17 1198.19 \n",
"4 1 1033.11 1016 0 1198.19 \n",
"5 -1 217.80 225 -3 1198.19 \n",
"6 1 1715.02 1672 0 1098.77 \n",
"7 1 1198.19 1204 0 1098.77 \n",
"8 -1 1193.23 1165 0 1098.77 \n",
"9 1 1049.98 1076 -1 1098.77 \n",
"10 -1 729.70 726 2 1098.77 \n",
"11 1 1365.63 1348 0 1098.77 \n",
"12 1 1715.02 1672 0 1049.98 \n",
"13 0 1715.02 1672 0 1049.98 \n",
"14 -1 689.37 685 -1 1049.98 \n",
"15 -1 689.37 685 -1 1049.98 \n",
"16 1 1511.44 1464 0 1049.98 \n",
"17 0 726.13 730 -1 1049.98 \n",
"18 1 819.56 792 1 1049.98 \n",
"19 -1 1033.11 1016 0 1049.98 \n",
"20 0 1266.76 1259 0 1049.98 \n",
"21 1 1715.02 1672 0 689.37 \n",
"22 1 1193.23 1165 0 689.37 \n",
"23 -1 726.13 730 -1 689.37 \n",
"24 1 684.76 672 1 689.37 \n",
"25 1 1715.02 1672 0 547.42 \n",
"26 1 1198.19 1204 0 547.42 \n",
"27 1 1198.19 1204 0 547.42 \n",
"28 1 1715.02 1672 0 902.98 \n",
"29 1 1715.02 1672 0 1626.23 \n",
".. ... ... ... ... ... \n",
"241 1 1266.76 1259 0 801.61 \n",
"242 -1 750.24 762 1 801.61 \n",
"243 0 876.96 872 -1 801.61 \n",
"244 1 68.82 66 1 801.61 \n",
"245 0 1119.36 1119 0 665.70 \n",
"246 -1 270.80 274 0 665.70 \n",
"247 1 1197.70 1183 1 527.13 \n",
"248 1 647.17 560 10 527.13 \n",
"249 1 750.24 762 1 135.11 \n",
"250 0 270.80 274 0 135.11 \n",
"251 0 686.06 676 1 660.02 \n",
"252 -1 331.20 325 4 660.02 \n",
"253 1 737.33 761 0 322.83 \n",
"254 0 689.72 679 2 438.99 \n",
"255 1 837.49 823 -2 438.99 \n",
"256 1 689.72 679 2 390.88 \n",
"257 1 837.49 823 -2 390.88 \n",
"258 1 801.61 801 -2 68.82 \n",
"259 1 792.81 768 0 418.60 \n",
"260 1 615.23 614 -5 418.60 \n",
"261 1 327.41 331 -4 83.54 \n",
"262 1 630.69 614 -1 83.54 \n",
"263 -1 660.02 657 0 647.17 \n",
"264 1 527.13 527 -1 647.17 \n",
"265 1 660.02 657 0 331.20 \n",
"266 1 527.13 527 -1 331.20 \n",
"267 -1 83.54 86 0 630.69 \n",
"268 1 603.05 589 -2 630.69 \n",
"269 1 418.60 428 -5 615.23 \n",
"270 0 135.11 142 -2 270.80 \n",
"\n",
" Previous Points_y +/-_y \n",
"0 1204 0 \n",
"1 1204 0 \n",
"2 1204 0 \n",
"3 1204 0 \n",
"4 1204 0 \n",
"5 1204 0 \n",
"6 1097 -1 \n",
"7 1097 -1 \n",
"8 1097 -1 \n",
"9 1097 -1 \n",
"10 1097 -1 \n",
"11 1097 -1 \n",
"12 1076 -1 \n",
"13 1076 -1 \n",
"14 1076 -1 \n",
"15 1076 -1 \n",
"16 1076 -1 \n",
"17 1076 -1 \n",
"18 1076 -1 \n",
"19 1076 -1 \n",
"20 1076 -1 \n",
"21 685 -1 \n",
"22 685 -1 \n",
"23 685 -1 \n",
"24 685 -1 \n",
"25 539 -1 \n",
"26 539 -1 \n",
"27 539 -1 \n",
"28 910 -1 \n",
"29 1603 0 \n",
".. ... ... \n",
"241 801 -2 \n",
"242 801 -2 \n",
"243 801 -2 \n",
"244 801 -2 \n",
"245 671 -1 \n",
"246 671 -1 \n",
"247 527 -1 \n",
"248 527 -1 \n",
"249 142 -2 \n",
"250 142 -2 \n",
"251 657 0 \n",
"252 657 0 \n",
"253 335 -11 \n",
"254 386 11 \n",
"255 386 11 \n",
"256 387 -1 \n",
"257 387 -1 \n",
"258 66 1 \n",
"259 428 -5 \n",
"260 428 -5 \n",
"261 86 0 \n",
"262 86 0 \n",
"263 560 10 \n",
"264 560 10 \n",
"265 325 4 \n",
"266 325 4 \n",
"267 614 -1 \n",
"268 614 -1 \n",
"269 614 -5 \n",
"270 274 0 \n",
"\n",
"[271 rows x 7 columns]\n"
]
}
],
"source": [
"lst_model_fld=['result', 'Total Points_x', \n",
" 'Previous Points_x', '+/-_x', \n",
" 'Total Points_y', \n",
" 'Previous Points_y', '+/-_y']\n",
"print(pd_model[lst_model_fld]) # dataframe for model\n",
"\n",
"# label = result, 1 - win Country 1, -1 - win Country 2, 0 - draw"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'Total Points_x': 1715.02, 'Previous Points_x': 1672, '+/-_x': 0, 'Total Points_y': 1511.4400000000001, 'Previous Points_y': 1464, '+/-_y': 0}\n"
]
}
],
"source": [
"#'Brazil', 'Germania'\n",
"#print(ser_code.index.tolist())\n",
"\n",
"def make_test_data(strCountry1Name, strCountry2Name):\n",
" sc1=ser_code[strCountry1Name]\n",
" sc2=ser_code[strCountry2Name]\n",
" pd1=df_rank[df_rank['Team']==strCountry1Name][['Total Points', \n",
" 'Previous Points', '+/-', ]]\n",
" pd2=df_rank[df_rank['Team']==strCountry2Name][['Total Points', \n",
" 'Previous Points', '+/-', ]]\n",
" return { 'Total Points_x':pd1['Total Points'].values[0], \n",
" 'Previous Points_x':pd1['Previous Points'].values[0], '+/-_x':pd1['+/-'].values[0], \n",
" 'Total Points_y':pd2['Total Points'].values[0], \n",
" 'Previous Points_y':pd2['Previous Points'].values[0], '+/-_y':pd1['+/-'].values[0]}\n",
"\n",
"print(make_test_data('Brazil', 'Germany'))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Let's do modeling\n",
"Testing models on 2017 FIFA Confederations Cup"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.model_selection import train_test_split\n",
"\n",
"X=pd_model[lst_model_fld[1:]]\n",
"y=pd_model[lst_model_fld[0]]\n",
"\n",
"X_train, X_test, y_train, y_test=train_test_split(X, y, random_state=0)\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[['Russia-Portugal'], ['Mexico-New Zealand'], ['Mexico-Russia'], ['New Zealand-Portugal'], ['Australia-Germany'], ['Cameroon-Australia'], ['Germany-Chile'], ['Germany-Cameroon'], ['Chile-Australia']]\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>+/-_x</th>\n",
" <th>+/-_y</th>\n",
" <th>Previous Points_x</th>\n",
" <th>Previous Points_y</th>\n",
" <th>Total Points_x</th>\n",
" <th>Total Points_y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>-2</td>\n",
" <td>-2</td>\n",
" <td>561</td>\n",
" <td>1259</td>\n",
" <td>560.85</td>\n",
" <td>1266.76</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" <td>1076</td>\n",
" <td>301</td>\n",
" <td>1049.98</td>\n",
" <td>343.62</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>-1</td>\n",
" <td>-1</td>\n",
" <td>1076</td>\n",
" <td>561</td>\n",
" <td>1049.98</td>\n",
" <td>560.85</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>17</td>\n",
" <td>17</td>\n",
" <td>301</td>\n",
" <td>1259</td>\n",
" <td>343.62</td>\n",
" <td>1266.76</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>661</td>\n",
" <td>1464</td>\n",
" <td>681.26</td>\n",
" <td>1511.44</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>779</td>\n",
" <td>661</td>\n",
" <td>811.05</td>\n",
" <td>681.26</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1464</td>\n",
" <td>1411</td>\n",
" <td>1511.44</td>\n",
" <td>1422.14</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1464</td>\n",
" <td>779</td>\n",
" <td>1511.44</td>\n",
" <td>811.05</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1411</td>\n",
" <td>661</td>\n",
" <td>1422.14</td>\n",
" <td>681.26</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" +/-_x +/-_y Previous Points_x Previous Points_y Total Points_x \\\n",
"0 -2 -2 561 1259 560.85 \n",
"1 -1 -1 1076 301 1049.98 \n",
"2 -1 -1 1076 561 1049.98 \n",
"3 17 17 301 1259 343.62 \n",
"4 2 2 661 1464 681.26 \n",
"5 1 1 779 661 811.05 \n",
"6 0 0 1464 1411 1511.44 \n",
"7 0 0 1464 779 1511.44 \n",
"8 0 0 1411 661 1422.14 \n",
"\n",
" Total Points_y \n",
"0 1266.76 \n",
"1 343.62 \n",
"2 560.85 \n",
"3 1266.76 \n",
"4 1511.44 \n",
"5 681.26 \n",
"6 1422.14 \n",
"7 811.05 \n",
"8 681.26 "
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interst= [['Россия', 'Португалия'],\n",
"['Мексика', 'Новая Зеландия'],\n",
"['Мексика', 'Россия'],\n",
"['Новая Зеландия', 'Португалия'],\n",
"['Австралия', 'Германия'],\n",
"['Камерун', 'Австралия'],\n",
"['Германия', 'Чили'],\n",
"['Германия', 'Камерун'],\n",
"['Чили', 'Австралия']]\n",
"\n",
"query_list=[]\n",
"for_result_lst=[]\n",
"\n",
"for item in interst:\n",
" itm=[dict_translate.get(word.strip(), word.strip()) for word in item]\n",
" for_result_lst.append(['-'.join(itm)])\n",
" #print(itm)\n",
" dct=make_test_data(itm[0], itm[1])\n",
" query_list.append(dct)\n",
"pd_query=pd.DataFrame(query_list)\n",
"print(for_result_lst)\n",
"pd_query"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Suport Vector Machine"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Best params SVC: {'C': 1, 'gamma': 0.1}\n",
"Best score SVC: 0.507389162562\n",
" mean_fit_time mean_score_time mean_test_score mean_train_score param_C \\\n",
"0 0.010737 0.003676 0.502463 0.502469 0.01 \n",
"1 0.008093 0.002622 0.502463 0.502469 0.01 \n",
"2 0.007453 0.002485 0.502463 0.502469 0.01 \n",
"3 0.007781 0.002583 0.502463 0.502469 0.01 \n",
"4 0.007531 0.002505 0.502463 0.502469 0.01 \n",
"5 0.007813 0.003336 0.502463 0.502469 0.1 \n",
"6 0.007763 0.002581 0.502463 0.502469 0.1 \n",
"7 0.007808 0.002538 0.502463 0.502469 0.1 \n",
"8 0.007591 0.002564 0.502463 0.502469 0.1 \n",
"9 0.007634 0.002537 0.502463 0.502469 0.1 \n",
"10 0.007913 0.002575 0.502463 0.995062 1 \n",
"11 0.007861 0.002576 0.507389 0.997531 1 \n",
"12 0.007912 0.002648 0.507389 0.997531 1 \n",
"13 0.008001 0.002680 0.507389 0.997531 1 \n",
"14 0.008392 0.002653 0.507389 0.997531 1 \n",
"15 0.009105 0.002857 0.502463 0.997531 10 \n",
"16 0.008336 0.002661 0.507389 0.997531 10 \n",
"17 0.008212 0.002527 0.507389 0.997531 10 \n",
"18 0.008173 0.002461 0.507389 0.997531 10 \n",
"19 0.008239 0.002479 0.507389 0.997531 10 \n",
"20 0.008584 0.002591 0.502463 0.997531 100 \n",
"21 0.008395 0.002538 0.507389 0.997531 100 \n",
"22 0.008277 0.002503 0.507389 0.997531 100 \n",
"23 0.008246 0.002512 0.507389 0.997531 100 \n",
"24 0.008197 0.002603 0.507389 0.997531 100 \n",
"\n",
" param_gamma params rank_test_score \\\n",
"0 0.01 {'C': 0.01, 'gamma': 0.01} 13 \n",
"1 0.1 {'C': 0.01, 'gamma': 0.1} 13 \n",
"2 1 {'C': 0.01, 'gamma': 1} 13 \n",
"3 10 {'C': 0.01, 'gamma': 10} 13 \n",
"4 100 {'C': 0.01, 'gamma': 100} 13 \n",
"5 0.01 {'C': 0.1, 'gamma': 0.01} 13 \n",
"6 0.1 {'C': 0.1, 'gamma': 0.1} 13 \n",
"7 1 {'C': 0.1, 'gamma': 1} 13 \n",
"8 10 {'C': 0.1, 'gamma': 10} 13 \n",
"9 100 {'C': 0.1, 'gamma': 100} 13 \n",
"10 0.01 {'C': 1, 'gamma': 0.01} 13 \n",
"11 0.1 {'C': 1, 'gamma': 0.1} 1 \n",
"12 1 {'C': 1, 'gamma': 1} 1 \n",
"13 10 {'C': 1, 'gamma': 10} 1 \n",
"14 100 {'C': 1, 'gamma': 100} 1 \n",
"15 0.01 {'C': 10, 'gamma': 0.01} 13 \n",
"16 0.1 {'C': 10, 'gamma': 0.1} 1 \n",
"17 1 {'C': 10, 'gamma': 1} 1 \n",
"18 10 {'C': 10, 'gamma': 10} 1 \n",
"19 100 {'C': 10, 'gamma': 100} 1 \n",
"20 0.01 {'C': 100, 'gamma': 0.01} 13 \n",
"21 0.1 {'C': 100, 'gamma': 0.1} 1 \n",
"22 1 {'C': 100, 'gamma': 1} 1 \n",
"23 10 {'C': 100, 'gamma': 10} 1 \n",
"24 100 {'C': 100, 'gamma': 100} 1 \n",
"\n",
" split0_test_score split0_train_score split1_test_score \\\n",
"0 0.500000 0.503704 0.500000 \n",
"1 0.500000 0.503704 0.500000 \n",
"2 0.500000 0.503704 0.500000 \n",
"3 0.500000 0.503704 0.500000 \n",
"4 0.500000 0.503704 0.500000 \n",
"5 0.500000 0.503704 0.500000 \n",
"6 0.500000 0.503704 0.500000 \n",
"7 0.500000 0.503704 0.500000 \n",
"8 0.500000 0.503704 0.500000 \n",
"9 0.500000 0.503704 0.500000 \n",
"10 0.514706 0.992593 0.500000 \n",
"11 0.514706 1.000000 0.514706 \n",
"12 0.514706 1.000000 0.514706 \n",
"13 0.514706 1.000000 0.514706 \n",
"14 0.514706 1.000000 0.514706 \n",
"15 0.514706 1.000000 0.500000 \n",
"16 0.514706 1.000000 0.514706 \n",
"17 0.514706 1.000000 0.514706 \n",
"18 0.514706 1.000000 0.514706 \n",
"19 0.514706 1.000000 0.514706 \n",
"20 0.514706 1.000000 0.500000 \n",
"21 0.514706 1.000000 0.514706 \n",
"22 0.514706 1.000000 0.514706 \n",
"23 0.514706 1.000000 0.514706 \n",
"24 0.514706 1.000000 0.514706 \n",
"\n",
" split1_train_score split2_test_score split2_train_score std_fit_time \\\n",
"0 0.503704 0.507463 0.5 0.001431 \n",
"1 0.503704 0.507463 0.5 0.000501 \n",
"2 0.503704 0.507463 0.5 0.000066 \n",
"3 0.503704 0.507463 0.5 0.000605 \n",
"4 0.503704 0.507463 0.5 0.000082 \n",
"5 0.503704 0.507463 0.5 0.000193 \n",
"6 0.503704 0.507463 0.5 0.000030 \n",
"7 0.503704 0.507463 0.5 0.000139 \n",
"8 0.503704 0.507463 0.5 0.000027 \n",
"9 0.503704 0.507463 0.5 0.000092 \n",
"10 0.992593 0.492537 1.0 0.000031 \n",
"11 0.992593 0.492537 1.0 0.000024 \n",
"12 0.992593 0.492537 1.0 0.000245 \n",
"13 0.992593 0.492537 1.0 0.000078 \n",
"14 0.992593 0.492537 1.0 0.000671 \n",
"15 0.992593 0.492537 1.0 0.000401 \n",
"16 0.992593 0.492537 1.0 0.000103 \n",
"17 0.992593 0.492537 1.0 0.000106 \n",
"18 0.992593 0.492537 1.0 0.000087 \n",
"19 0.992593 0.492537 1.0 0.000141 \n",
"20 0.992593 0.492537 1.0 0.000121 \n",
"21 0.992593 0.492537 1.0 0.000108 \n",
"22 0.992593 0.492537 1.0 0.000096 \n",
"23 0.992593 0.492537 1.0 0.000090 \n",
"24 0.992593 0.492537 1.0 0.000094 \n",
"\n",
" std_score_time std_test_score std_train_score \n",
"0 0.000596 0.003509 0.001746 \n",
"1 0.000028 0.003509 0.001746 \n",
"2 0.000035 0.003509 0.001746 \n",
"3 0.000086 0.003509 0.001746 \n",
"4 0.000039 0.003509 0.001746 \n",
"5 0.000952 0.003509 0.001746 \n",
"6 0.000006 0.003509 0.001746 \n",
"7 0.000024 0.003509 0.001746 \n",
"8 0.000022 0.003509 0.001746 \n",
"9 0.000014 0.003509 0.001746 \n",
"10 0.000015 0.009206 0.003492 \n",
"11 0.000016 0.010424 0.003492 \n",
"12 0.000130 0.010424 0.003492 \n",
"13 0.000062 0.010424 0.003492 \n",
"14 0.000054 0.010424 0.003492 \n",
"15 0.000168 0.009206 0.003492 \n",
"16 0.000028 0.010424 0.003492 \n",
"17 0.000009 0.010424 0.003492 \n",
"18 0.000020 0.010424 0.003492 \n",
"19 0.000022 0.010424 0.003492 \n",
"20 0.000028 0.009206 0.003492 \n",
"21 0.000011 0.010424 0.003492 \n",
"22 0.000004 0.010424 0.003492 \n",
"23 0.000044 0.010424 0.003492 \n",
"24 0.000070 0.010424 0.003492 \n"
]
}
],
"source": [
"from sklearn.model_selection import GridSearchCV\n",
"from sklearn.svm import SVC\n",
"\n",
"grid_Params={'C':[0.01, 0.1, 1, 10, 100], 'gamma':[0.01, 0.1, 1, 10, 100]}\n",
"\n",
"grid1=GridSearchCV(SVC(kernel='rbf'), param_grid=grid_Params, scoring='precision_micro')\n",
"grid1.fit(X_train, y_train)\n",
"\n",
"print('Best params SVC: ', grid1.best_params_)\n",
"print('Best score SVC: ', grid1.best_score_)\n",
"\n",
"dtf_res=pd.DataFrame(grid1.cv_results_)\n",
"print(dtf_res)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(['Russia-Portugal'], 1)\n",
"(['Mexico-New Zealand'], 1)\n",
"(['Mexico-Russia'], 1)\n",
"(['New Zealand-Portugal'], 1)\n",
"(['Australia-Germany'], 1)\n",
"(['Cameroon-Australia'], 1)\n",
"(['Germany-Chile'], 1)\n",
"(['Germany-Cameroon'], 1)\n",
"(['Chile-Australia'], 1)\n"
]
}
],
"source": [
"lr=list(zip(for_result_lst, grid1.predict(pd_query)))\n",
"for i in lr:\n",
" print(i)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Logistic Regression"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Best params (max. accurancy): {'C': 1}\n",
"Best score (accurancy): 0.679802955665\n",
" mean_fit_time mean_score_time mean_test_score mean_train_score param_C \\\n",
"0 0.006273 0.003627 0.669951 0.692121 0.01 \n",
"1 0.009819 0.004126 0.669951 0.694590 0.1 \n",
"2 0.006643 0.001253 0.679803 0.699492 1 \n",
"3 0.006298 0.001140 0.674877 0.706881 10 \n",
"4 0.006943 0.001191 0.669951 0.704430 100 \n",
"\n",
" params rank_test_score split0_test_score split0_train_score \\\n",
"0 {'C': 0.01} 3 0.735294 0.666667 \n",
"1 {'C': 0.1} 3 0.735294 0.674074 \n",
"2 {'C': 1} 1 0.720588 0.674074 \n",
"3 {'C': 10} 2 0.720588 0.688889 \n",
"4 {'C': 100} 3 0.720588 0.688889 \n",
"\n",
" split1_test_score split1_train_score split2_test_score \\\n",
"0 0.617647 0.718519 0.656716 \n",
"1 0.617647 0.718519 0.656716 \n",
"2 0.647059 0.718519 0.671642 \n",
"3 0.647059 0.718519 0.656716 \n",
"4 0.647059 0.718519 0.641791 \n",
"\n",
" split2_train_score std_fit_time std_score_time std_test_score \\\n",
"0 0.691176 0.001221 0.002711 0.049035 \n",
"1 0.691176 0.002999 0.003954 0.049035 \n",
"2 0.705882 0.000429 0.000087 0.030632 \n",
"3 0.713235 0.000529 0.000005 0.032680 \n",
"4 0.705882 0.000598 0.000045 0.036003 \n",
"\n",
" std_train_score \n",
"0 0.021179 \n",
"1 0.018304 \n",
"2 0.018699 \n",
"3 0.012904 \n",
"4 0.012140 \n"
]
}
],
"source": [
"from sklearn.linear_model import LogisticRegression\n",
"grid_ParamsLG={'C':[0.01, 0.1, 1, 10, 100]}\n",
"\n",
"grid4=GridSearchCV(LogisticRegression(), param_grid=grid_ParamsLG, scoring='precision_micro')\n",
"grid4.fit(X_train, y_train)\n",
"\n",
"print('Best params (max. accurancy): ', grid4.best_params_)\n",
"print('Best score (accurancy): ', grid4.best_score_)\n",
"\n",
"dtf_res=pd.DataFrame(grid4.cv_results_)\n",
"print(dtf_res)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(['Russia-Portugal'], 1)\n",
"(['Mexico-New Zealand'], -1)\n",
"(['Mexico-Russia'], -1)\n",
"(['New Zealand-Portugal'], 1)\n",
"(['Australia-Germany'], 1)\n",
"(['Cameroon-Australia'], -1)\n",
"(['Germany-Chile'], -1)\n",
"(['Germany-Cameroon'], -1)\n",
"(['Chile-Australia'], -1)\n"
]
}
],
"source": [
"lr=list(zip(for_result_lst, grid4.predict(pd_query)))\n",
"for i in lr:\n",
" print(i)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Decision Tree"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Best params Tree (max. accurancy): {'max_depth': 3}\n",
"Best score Tree (accurancy): 0.620689655172\n",
" mean_fit_time mean_score_time mean_test_score mean_train_score \\\n",
"0 0.003494 0.000635 0.561576 0.598475 \n",
"1 0.005093 0.000628 0.620690 0.721641 \n",
"2 0.006272 0.000863 0.527094 0.812745 \n",
"3 0.004217 0.000809 0.527094 0.982716 \n",
"4 0.004187 0.000829 0.546798 0.997531 \n",
"5 0.004157 0.000797 0.551724 0.997531 \n",
"6 0.003973 0.000772 0.536946 0.997531 \n",
"7 0.003935 0.000803 0.571429 0.997531 \n",
"\n",
" param_max_depth params rank_test_score split0_test_score \\\n",
"0 1 {'max_depth': 1} 3 0.529412 \n",
"1 3 {'max_depth': 3} 1 0.617647 \n",
"2 5 {'max_depth': 5} 7 0.500000 \n",
"3 10 {'max_depth': 10} 7 0.500000 \n",
"4 15 {'max_depth': 15} 5 0.514706 \n",
"5 30 {'max_depth': 30} 4 0.558824 \n",
"6 50 {'max_depth': 50} 6 0.500000 \n",
"7 100 {'max_depth': 100} 2 0.588235 \n",
"\n",
" split0_train_score split1_test_score split1_train_score \\\n",
"0 0.548148 0.544118 0.629630 \n",
"1 0.674074 0.588235 0.755556 \n",
"2 0.770370 0.558824 0.829630 \n",
"3 0.985185 0.529412 0.962963 \n",
"4 1.000000 0.573529 0.992593 \n",
"5 1.000000 0.544118 0.992593 \n",
"6 1.000000 0.544118 0.992593 \n",
"7 1.000000 0.573529 0.992593 \n",
"\n",
" split2_test_score split2_train_score std_fit_time std_score_time \\\n",
"0 0.611940 0.617647 0.000704 0.000070 \n",
"1 0.656716 0.735294 0.002309 0.000015 \n",
"2 0.522388 0.838235 0.002340 0.000030 \n",
"3 0.552239 1.000000 0.000095 0.000018 \n",
"4 0.552239 1.000000 0.000198 0.000033 \n",
"5 0.552239 1.000000 0.000256 0.000027 \n",
"6 0.567164 1.000000 0.000064 0.000012 \n",
"7 0.552239 1.000000 0.000020 0.000043 \n",
"\n",
" std_test_score std_train_score \n",
"0 0.035859 0.035921 \n",
"1 0.028005 0.034637 \n",
"2 0.024299 0.030169 \n",
"3 0.021363 0.015221 \n",
"4 0.024375 0.003492 \n",
"5 0.006029 0.003492 \n",
"6 0.027854 0.003492 \n",
"7 0.014753 0.003492 \n"
]
}
],
"source": [
"from sklearn import tree\n",
"\n",
"grid_ParamsDT={'max_depth':[1, 3, 5, 10, 15, 30, 50, 100]}\n",
"\n",
"grid2=GridSearchCV(tree.DecisionTreeClassifier(), param_grid=grid_ParamsDT, scoring='accuracy')\n",
"grid2.fit(X_train, y_train)\n",
"\n",
"print('Best params Tree (max. accurancy): ', grid2.best_params_)\n",
"print('Best score Tree (accurancy): ', grid2.best_score_)\n",
"\n",
"dtf_res=pd.DataFrame(grid2.cv_results_)\n",
"print(dtf_res)"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(['Russia-Portugal'], -1)\n",
"(['Mexico-New Zealand'], -1)\n",
"(['Mexico-Russia'], -1)\n",
"(['New Zealand-Portugal'], -1)\n",
"(['Australia-Germany'], -1)\n",
"(['Cameroon-Australia'], -1)\n",
"(['Germany-Chile'], -1)\n",
"(['Germany-Cameroon'], -1)\n",
"(['Chile-Australia'], -1)\n"
]
}
],
"source": [
"lr=list(zip(for_result_lst, grid2.predict(pd_query)))\n",
"for i in lr:\n",
" print(i)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## KNeighbors Classifier"
]
},
{
"cell_type": "code",
"execution_count": 46,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Best params Neighbors: {'n_neighbors': 30}\n",
"Best score Neighbors: 0.699507389163\n",
" mean_fit_time mean_score_time mean_test_score mean_train_score \\\n",
"0 0.004447 0.001541 0.571429 0.997531 \n",
"1 0.003654 0.001534 0.591133 0.758678 \n",
"2 0.005916 0.002833 0.620690 0.721714 \n",
"3 0.003978 0.002118 0.640394 0.704484 \n",
"4 0.003707 0.002097 0.674877 0.694553 \n",
"5 0.003673 0.002191 0.699507 0.692121 \n",
"6 0.003630 0.002286 0.674877 0.689706 \n",
"7 0.003666 0.002450 0.674877 0.674927 \n",
"8 0.003508 0.002543 0.665025 0.677397 \n",
"9 0.003504 0.002553 0.610837 0.605955 \n",
"\n",
" param_n_neighbors params rank_test_score split0_test_score \\\n",
"0 1 {'n_neighbors': 1} 10 0.588235 \n",
"1 3 {'n_neighbors': 3} 9 0.661765 \n",
"2 5 {'n_neighbors': 5} 7 0.691176 \n",
"3 15 {'n_neighbors': 15} 6 0.691176 \n",
"4 20 {'n_neighbors': 20} 2 0.691176 \n",
"5 30 {'n_neighbors': 30} 1 0.691176 \n",
"6 35 {'n_neighbors': 35} 2 0.691176 \n",
"7 50 {'n_neighbors': 50} 2 0.691176 \n",
"8 70 {'n_neighbors': 70} 5 0.632353 \n",
"9 100 {'n_neighbors': 100} 8 0.602941 \n",
"\n",
" split0_train_score split1_test_score split1_train_score \\\n",
"0 1.000000 0.588235 0.992593 \n",
"1 0.770370 0.544118 0.770370 \n",
"2 0.733333 0.544118 0.725926 \n",
"3 0.711111 0.602941 0.718519 \n",
"4 0.666667 0.632353 0.711111 \n",
"5 0.696296 0.676471 0.688889 \n",
"6 0.696296 0.647059 0.703704 \n",
"7 0.674074 0.661765 0.696296 \n",
"8 0.681481 0.676471 0.696296 \n",
"9 0.600000 0.588235 0.629630 \n",
"\n",
" split2_test_score split2_train_score std_fit_time std_score_time \\\n",
"0 0.537313 1.000000 0.001846 0.000065 \n",
"1 0.567164 0.735294 0.000726 0.000067 \n",
"2 0.626866 0.705882 0.003488 0.001134 \n",
"3 0.626866 0.683824 0.000266 0.000073 \n",
"4 0.701493 0.705882 0.000071 0.000067 \n",
"5 0.731343 0.691176 0.000039 0.000021 \n",
"6 0.686567 0.669118 0.000003 0.000037 \n",
"7 0.671642 0.654412 0.000044 0.000009 \n",
"8 0.686567 0.654412 0.000094 0.000286 \n",
"9 0.641791 0.588235 0.000049 0.000096 \n",
"\n",
" std_test_score std_train_score \n",
"0 0.023945 0.003492 \n",
"1 0.051002 0.016535 \n",
"2 0.060340 0.011596 \n",
"3 0.037338 0.014919 \n",
"4 0.030472 0.019834 \n",
"5 0.023142 0.003097 \n",
"6 0.019832 0.014869 \n",
"7 0.012249 0.017110 \n",
"8 0.023550 0.017342 \n",
"9 0.022544 0.017416 \n"
]
}
],
"source": [
"from sklearn.neighbors import KNeighborsClassifier \n",
"\n",
"grid_ParamsKNN={'n_neighbors':[1, 3, 5, 15, 20, 30, 35, 50, 70, 100]}\n",
"\n",
"grid3=GridSearchCV(KNeighborsClassifier(), param_grid=grid_ParamsKNN, scoring='accuracy')\n",
"grid3.fit(X_train, y_train)\n",
"\n",
"print('Best params Neighbors: ', grid3.best_params_)\n",
"print('Best score Neighbors: ', grid3.best_score_)\n",
"\n",
"dtf_res=pd.DataFrame(grid3.cv_results_)\n",
"print(dtf_res)\n",
"\n",
"#'precsion_micro' is not a valid scoring value. Valid options are \n",
"#['accuracy', 'adjusted_rand_score', 'average_precision', 'f1', 'f1_macro', \n",
"# 'f1_micro', 'f1_samples', 'f1_weighted', 'neg_log_loss', 'neg_mean_absolute_error', \n",
"# 'neg_mean_squared_error', 'neg_median_absolute_error', 'precision', 'precision_macro', \n",
"# 'precision_micro', 'precision_samples', 'precision_weighted', 'r2', 'recall', 'recall_macro', \n",
"# 'recall_micro', 'recall_samples', 'recall_weighted', 'roc_auc']"
]
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(['Russia-Portugal'], -1)\n",
"(['Mexico-New Zealand'], -1)\n",
"(['Mexico-Russia'], -1)\n",
"(['New Zealand-Portugal'], -1)\n",
"(['Australia-Germany'], -1)\n",
"(['Cameroon-Australia'], -1)\n",
"(['Germany-Chile'], -1)\n",
"(['Germany-Cameroon'], -1)\n",
"(['Chile-Australia'], -1)\n",
"0.558823529412\n"
]
}
],
"source": [
"lr=list(zip(for_result_lst, grid3.predict(pd_query)))\n",
"for i in lr:\n",
" print(i)\n",
"\n",
"print(grid3.score(X_test, y_test))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"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": "3.6.0"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment