diff --git a/your-code/main.ipynb b/your-code/main.ipynb index a5caf8b..aeb1eca 100755 --- a/your-code/main.ipynb +++ b/your-code/main.ipynb @@ -38,10 +38,227 @@ { "cell_type": "code", "execution_count": 2, - "metadata": {}, - "outputs": [], - "source": [ - "websites = pd.read_csv('../data/website.csv')" + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
| \n", + " | URL | \n", + "URL_LENGTH | \n", + "NUMBER_SPECIAL_CHARACTERS | \n", + "CHARSET | \n", + "SERVER | \n", + "CONTENT_LENGTH | \n", + "WHOIS_COUNTRY | \n", + "WHOIS_STATEPRO | \n", + "WHOIS_REGDATE | \n", + "WHOIS_UPDATED_DATE | \n", + "... | \n", + "DIST_REMOTE_TCP_PORT | \n", + "REMOTE_IPS | \n", + "APP_BYTES | \n", + "SOURCE_APP_PACKETS | \n", + "REMOTE_APP_PACKETS | \n", + "SOURCE_APP_BYTES | \n", + "REMOTE_APP_BYTES | \n", + "APP_PACKETS | \n", + "DNS_QUERY_TIMES | \n", + "Type | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "M0_109 | \n", + "16 | \n", + "7 | \n", + "iso-8859-1 | \n", + "nginx | \n", + "263.0 | \n", + "NaN | \n", + "NaN | \n", + "10/10/2015 18:21 | \n", + "NaN | \n", + "... | \n", + "0 | \n", + "2 | \n", + "700 | \n", + "9 | \n", + "10 | \n", + "1153 | \n", + "832 | \n", + "9 | \n", + "2.0 | \n", + "1 | \n", + "
| 1 | \n", + "B0_2314 | \n", + "16 | \n", + "6 | \n", + "UTF-8 | \n", + "Apache/2.4.10 | \n", + "15087.0 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "... | \n", + "7 | \n", + "4 | \n", + "1230 | \n", + "17 | \n", + "19 | \n", + "1265 | \n", + "1230 | \n", + "17 | \n", + "0.0 | \n", + "0 | \n", + "
| 2 | \n", + "B0_911 | \n", + "16 | \n", + "6 | \n", + "us-ascii | \n", + "Microsoft-HTTPAPI/2.0 | \n", + "324.0 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "... | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0.0 | \n", + "0 | \n", + "
| 3 | \n", + "B0_113 | \n", + "17 | \n", + "6 | \n", + "ISO-8859-1 | \n", + "nginx | \n", + "162.0 | \n", + "US | \n", + "AK | \n", + "7/10/1997 4:00 | \n", + "12/09/2013 0:45 | \n", + "... | \n", + "22 | \n", + "3 | \n", + "3812 | \n", + "39 | \n", + "37 | \n", + "18784 | \n", + "4380 | \n", + "39 | \n", + "8.0 | \n", + "0 | \n", + "
| 4 | \n", + "B0_403 | \n", + "17 | \n", + "6 | \n", + "UTF-8 | \n", + "NaN | \n", + "124140.0 | \n", + "US | \n", + "TX | \n", + "12/05/1996 0:00 | \n", + "11/04/2017 0:00 | \n", + "... | \n", + "2 | \n", + "5 | \n", + "4278 | \n", + "61 | \n", + "62 | \n", + "129889 | \n", + "4586 | \n", + "61 | \n", + "4.0 | \n", + "0 | \n", + "
5 rows × 21 columns
\n", + "| \n", + " | URL_LENGTH | \n", + "NUMBER_SPECIAL_CHARACTERS | \n", + "CONTENT_LENGTH | \n", + "TCP_CONVERSATION_EXCHANGE | \n", + "DIST_REMOTE_TCP_PORT | \n", + "REMOTE_IPS | \n", + "APP_BYTES | \n", + "SOURCE_APP_PACKETS | \n", + "REMOTE_APP_PACKETS | \n", + "SOURCE_APP_BYTES | \n", + "... | \n", + "country_GB | \n", + "country_IN | \n", + "country_JP | \n", + "country_PA | \n", + "country_UK | \n", + "country_US | \n", + "server_Apache | \n", + "server_Microsoft-HTTPAPI/2.0 | \n", + "server_Other | \n", + "server_nginx | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "16 | \n", + "7 | \n", + "263.0 | \n", + "7 | \n", + "0 | \n", + "2 | \n", + "700 | \n", + "9 | \n", + "10 | \n", + "1153 | \n", + "... | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "1 | \n", + "
| 1 | \n", + "16 | \n", + "6 | \n", + "15087.0 | \n", + "17 | \n", + "7 | \n", + "4 | \n", + "1230 | \n", + "17 | \n", + "19 | \n", + "1265 | \n", + "... | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "0 | \n", + "0 | \n", + "1 | \n", + "0 | \n", + "
| 2 | \n", + "16 | \n", + "6 | \n", + "324.0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "... | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "0 | \n", + "1 | \n", + "0 | \n", + "0 | \n", + "
| 3 | \n", + "17 | \n", + "6 | \n", + "162.0 | \n", + "31 | \n", + "22 | \n", + "3 | \n", + "3812 | \n", + "39 | \n", + "37 | \n", + "18784 | \n", + "... | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "1.0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "1 | \n", + "
| 4 | \n", + "17 | \n", + "6 | \n", + "124140.0 | \n", + "57 | \n", + "2 | \n", + "5 | \n", + "4278 | \n", + "61 | \n", + "62 | \n", + "129889 | \n", + "... | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "1.0 | \n", + "0 | \n", + "0 | \n", + "1 | \n", + "0 | \n", + "
| ... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "
| 1776 | \n", + "194 | \n", + "16 | \n", + "NaN | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "3 | \n", + "186 | \n", + "... | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "1 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "
| 1777 | \n", + "198 | \n", + "17 | \n", + "NaN | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "2 | \n", + "124 | \n", + "... | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "1 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "
| 1778 | \n", + "201 | \n", + "34 | \n", + "8904.0 | \n", + "83 | \n", + "2 | \n", + "6 | \n", + "6631 | \n", + "87 | \n", + "89 | \n", + "132181 | \n", + "... | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "1.0 | \n", + "0 | \n", + "0 | \n", + "1 | \n", + "0 | \n", + "
| 1779 | \n", + "234 | \n", + "34 | \n", + "NaN | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "... | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "1.0 | \n", + "0 | \n", + "0 | \n", + "1 | \n", + "0 | \n", + "
| 1780 | \n", + "249 | \n", + "40 | \n", + "24435.0 | \n", + "19 | \n", + "6 | \n", + "11 | \n", + "2314 | \n", + "25 | \n", + "28 | \n", + "3039 | \n", + "... | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "0.0 | \n", + "1.0 | \n", + "0 | \n", + "0 | \n", + "1 | \n", + "0 | \n", + "
1781 rows × 28 columns
\n", + "KNeighborsClassifier(n_neighbors=3)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
KNeighborsClassifier(n_neighbors=3)