{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import ast\n",
    "from urllib.parse import urlparse\n",
    "import tldextract\n",
    "\n",
    "import pandas as pd\n",
    "from sklearn.preprocessing import MultiLabelBinarizer\n",
    "from sklearn.svm import OneClassSVM \n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import f1_score\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_pickle('../data/processed/features.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>verified_email</th>\n",
       "      <th>verified_primary_email</th>\n",
       "      <th>n_works</th>\n",
       "      <th>n_doi</th>\n",
       "      <th>n_arxiv</th>\n",
       "      <th>n_pmc</th>\n",
       "      <th>n_other_pids</th>\n",
       "      <th>n_emails</th>\n",
       "      <th>n_urls</th>\n",
       "      <th>n_ids</th>\n",
       "      <th>n_keywords</th>\n",
       "      <th>n_employment</th>\n",
       "      <th>n_education</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</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>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\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>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\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>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\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>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <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>10989644</th>\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>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10989645</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10989646</th>\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>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10989647</th>\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>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10989648</th>\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>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10989649 rows × 14 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          verified_email  verified_primary_email  n_works  n_doi  n_arxiv  \\\n",
       "0                      0                       0        0      0        0   \n",
       "1                      1                       1        0      0        0   \n",
       "2                      1                       1        0      0        0   \n",
       "3                      1                       1        0      0        0   \n",
       "4                      1                       1        0      0        0   \n",
       "...                  ...                     ...      ...    ...      ...   \n",
       "10989644               1                       1        0      0        0   \n",
       "10989645               1                       1        7      7        0   \n",
       "10989646               1                       1        0      0        0   \n",
       "10989647               1                       1        0      0        0   \n",
       "10989648               1                       1        0      0        0   \n",
       "\n",
       "          n_pmc  n_other_pids  n_emails  n_urls  n_ids  n_keywords  \\\n",
       "0             0             0       NaN     NaN    NaN         NaN   \n",
       "1             0             0       NaN     NaN    NaN         NaN   \n",
       "2             0             0       NaN     NaN    NaN         NaN   \n",
       "3             0             0       NaN     NaN    NaN         NaN   \n",
       "4             0             0       NaN     NaN    NaN         NaN   \n",
       "...         ...           ...       ...     ...    ...         ...   \n",
       "10989644      0             0       NaN     NaN    NaN         NaN   \n",
       "10989645      1             0       NaN     NaN    NaN         NaN   \n",
       "10989646      0             0       NaN     NaN    NaN         NaN   \n",
       "10989647      0             0       NaN     NaN    NaN         NaN   \n",
       "10989648      0             0       NaN     NaN    NaN         NaN   \n",
       "\n",
       "          n_employment  n_education  label  \n",
       "0                  NaN          NaN      0  \n",
       "1                  1.0          NaN      0  \n",
       "2                  NaN          NaN      0  \n",
       "3                  1.0          NaN      0  \n",
       "4                  2.0          NaN      0  \n",
       "...                ...          ...    ...  \n",
       "10989644           1.0          2.0      0  \n",
       "10989645           2.0          2.0      1  \n",
       "10989646           NaN          NaN      0  \n",
       "10989647           1.0          2.0      0  \n",
       "10989648           NaN          NaN      0  \n",
       "\n",
       "[10989649 rows x 14 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.fillna(0, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>verified_email</th>\n",
       "      <th>verified_primary_email</th>\n",
       "      <th>n_works</th>\n",
       "      <th>n_doi</th>\n",
       "      <th>n_arxiv</th>\n",
       "      <th>n_pmc</th>\n",
       "      <th>n_other_pids</th>\n",
       "      <th>n_emails</th>\n",
       "      <th>n_urls</th>\n",
       "      <th>n_ids</th>\n",
       "      <th>n_keywords</th>\n",
       "      <th>n_employment</th>\n",
       "      <th>n_education</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <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>10989644</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10989645</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10989646</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10989647</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10989648</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10989649 rows × 14 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          verified_email  verified_primary_email  n_works  n_doi  n_arxiv  \\\n",
       "0                      0                       0        0      0        0   \n",
       "1                      1                       1        0      0        0   \n",
       "2                      1                       1        0      0        0   \n",
       "3                      1                       1        0      0        0   \n",
       "4                      1                       1        0      0        0   \n",
       "...                  ...                     ...      ...    ...      ...   \n",
       "10989644               1                       1        0      0        0   \n",
       "10989645               1                       1        7      7        0   \n",
       "10989646               1                       1        0      0        0   \n",
       "10989647               1                       1        0      0        0   \n",
       "10989648               1                       1        0      0        0   \n",
       "\n",
       "          n_pmc  n_other_pids  n_emails  n_urls  n_ids  n_keywords  \\\n",
       "0             0             0       0.0     0.0    0.0         0.0   \n",
       "1             0             0       0.0     0.0    0.0         0.0   \n",
       "2             0             0       0.0     0.0    0.0         0.0   \n",
       "3             0             0       0.0     0.0    0.0         0.0   \n",
       "4             0             0       0.0     0.0    0.0         0.0   \n",
       "...         ...           ...       ...     ...    ...         ...   \n",
       "10989644      0             0       0.0     0.0    0.0         0.0   \n",
       "10989645      1             0       0.0     0.0    0.0         0.0   \n",
       "10989646      0             0       0.0     0.0    0.0         0.0   \n",
       "10989647      0             0       0.0     0.0    0.0         0.0   \n",
       "10989648      0             0       0.0     0.0    0.0         0.0   \n",
       "\n",
       "          n_employment  n_education  label  \n",
       "0                  0.0          0.0      0  \n",
       "1                  1.0          0.0      0  \n",
       "2                  0.0          0.0      0  \n",
       "3                  1.0          0.0      0  \n",
       "4                  2.0          0.0      0  \n",
       "...                ...          ...    ...  \n",
       "10989644           1.0          2.0      0  \n",
       "10989645           2.0          2.0      1  \n",
       "10989646           0.0          0.0      0  \n",
       "10989647           1.0          2.0      0  \n",
       "10989648           0.0          0.0      0  \n",
       "\n",
       "[10989649 rows x 14 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "verified_email            2664886\n",
       "verified_primary_email    2664886\n",
       "n_works                   2664886\n",
       "n_doi                     2664886\n",
       "n_arxiv                   2664886\n",
       "n_pmc                     2664886\n",
       "n_other_pids              2664886\n",
       "n_emails                  2664886\n",
       "n_urls                    2664886\n",
       "n_ids                     2664886\n",
       "n_keywords                2664886\n",
       "n_employment              2664886\n",
       "n_education               2664886\n",
       "label                     2664886\n",
       "dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.label == 1].count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "verified_email            8324763\n",
       "verified_primary_email    8324763\n",
       "n_works                   8324763\n",
       "n_doi                     8324763\n",
       "n_arxiv                   8324763\n",
       "n_pmc                     8324763\n",
       "n_other_pids              8324763\n",
       "n_emails                  8324763\n",
       "n_urls                    8324763\n",
       "n_ids                     8324763\n",
       "n_keywords                8324763\n",
       "n_employment              8324763\n",
       "n_education               8324763\n",
       "label                     8324763\n",
       "dtype: int64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.label == 0].count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# split into train/test sets\n",
    "X = df.loc[:,'verified_email':'n_education']\n",
    "y = df['label']\n",
    "trainX, testX, trainy, testy = train_test_split(X, y, train_size=0.5, random_state=2, stratify=y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>verified_email</th>\n",
       "      <th>verified_primary_email</th>\n",
       "      <th>n_works</th>\n",
       "      <th>n_doi</th>\n",
       "      <th>n_arxiv</th>\n",
       "      <th>n_pmc</th>\n",
       "      <th>n_other_pids</th>\n",
       "      <th>n_emails</th>\n",
       "      <th>n_urls</th>\n",
       "      <th>n_ids</th>\n",
       "      <th>n_keywords</th>\n",
       "      <th>n_employment</th>\n",
       "      <th>n_education</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>6325067</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6140551</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3258315</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10948983</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10089158</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <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>2398808</th>\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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3622839</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1389679</th>\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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6594722</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>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4589084</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>11</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5494824 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          verified_email  verified_primary_email  n_works  n_doi  n_arxiv  \\\n",
       "6325067                1                       1        0      0        0   \n",
       "6140551                1                       1        0      0        0   \n",
       "3258315                1                       1        0      0        0   \n",
       "10948983               1                       1        0      0        0   \n",
       "10089158               1                       1        0      0        0   \n",
       "...                  ...                     ...      ...    ...      ...   \n",
       "2398808                0                       0        1      1        0   \n",
       "3622839                1                       1        0      0        0   \n",
       "1389679                1                       1        0      0        0   \n",
       "6594722                0                       0        0      0        0   \n",
       "4589084                1                       1       11      0        0   \n",
       "\n",
       "          n_pmc  n_other_pids  n_emails  n_urls  n_ids  n_keywords  \\\n",
       "6325067       0             0       0.0     0.0    1.0         0.0   \n",
       "6140551       0             0       0.0     0.0    0.0         0.0   \n",
       "3258315       0             0       0.0     1.0    0.0         2.0   \n",
       "10948983      0             0       0.0     0.0    0.0         0.0   \n",
       "10089158      0             0       0.0     0.0    0.0         0.0   \n",
       "...         ...           ...       ...     ...    ...         ...   \n",
       "2398808       0             0       0.0     0.0    0.0         0.0   \n",
       "3622839       0             0       0.0     0.0    0.0         0.0   \n",
       "1389679       0             0       0.0     0.0    0.0         0.0   \n",
       "6594722       0             0       0.0     0.0    0.0         0.0   \n",
       "4589084       0             0       0.0     0.0    0.0         0.0   \n",
       "\n",
       "          n_employment  n_education  \n",
       "6325067            1.0          1.0  \n",
       "6140551            0.0          0.0  \n",
       "3258315            0.0          0.0  \n",
       "10948983           1.0          0.0  \n",
       "10089158           0.0          0.0  \n",
       "...                ...          ...  \n",
       "2398808            0.0          0.0  \n",
       "3622839            1.0          1.0  \n",
       "1389679            0.0          0.0  \n",
       "6594722            0.0          0.0  \n",
       "4589084            1.0          0.0  \n",
       "\n",
       "[5494824 rows x 13 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "trainX"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# define outlier detection model\n",
    "model = OneClassSVM(gamma='scale', nu=0.5)\n",
    "\n",
    "# fit on majority class\n",
    "trainX = trainX[trainy==1]\n",
    "model.fit(trainX)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# detect outliers in the test set\n",
    "yhat = model.predict(testX)\n",
    "\n",
    "# mark inliers 1, outliers -1\n",
    "testy[testy == 0] = -1\n",
    "testy[testy == 1] = 1\n",
    "\n",
    "# calculate score\n",
    "score = f1_score(testy, yhat, pos_label=-1)\n",
    "print('F1 Score: %.3f' % score)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}