Resume Category Prediction.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 162,
   "id": "dd3c737e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 163,
   "id": "3befa95c",
   "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>Category</th>\n",
       "      <th>Resume</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Skills * Programming Languages: Python (pandas...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Education Details \\r\\nMay 2013 to May 2017 B.E...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Areas of Interest Deep Learning, Control Syste...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Skills â¢ R â¢ Python â¢ SAP HANA â¢ Table...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Education Details \\r\\n MCA   YMCAUST,  Faridab...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>957</th>\n",
       "      <td>Testing</td>\n",
       "      <td>Computer Skills: â¢ Proficient in MS office (...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>958</th>\n",
       "      <td>Testing</td>\n",
       "      <td>â Willingness to accept the challenges. â ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>959</th>\n",
       "      <td>Testing</td>\n",
       "      <td>PERSONAL SKILLS â¢ Quick learner, â¢ Eagerne...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>960</th>\n",
       "      <td>Testing</td>\n",
       "      <td>COMPUTER SKILLS &amp; SOFTWARE KNOWLEDGE MS-Power ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>961</th>\n",
       "      <td>Testing</td>\n",
       "      <td>Skill Set OS Windows XP/7/8/8.1/10 Database MY...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>962 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         Category                                             Resume\n",
       "0    Data Science  Skills * Programming Languages: Python (pandas...\n",
       "1    Data Science  Education Details \\r\\nMay 2013 to May 2017 B.E...\n",
       "2    Data Science  Areas of Interest Deep Learning, Control Syste...\n",
       "3    Data Science  Skills â¢ R â¢ Python â¢ SAP HANA â¢ Table...\n",
       "4    Data Science  Education Details \\r\\n MCA   YMCAUST,  Faridab...\n",
       "..            ...                                                ...\n",
       "957       Testing  Computer Skills: â¢ Proficient in MS office (...\n",
       "958       Testing  â Willingness to accept the challenges. â ...\n",
       "959       Testing  PERSONAL SKILLS â¢ Quick learner, â¢ Eagerne...\n",
       "960       Testing  COMPUTER SKILLS & SOFTWARE KNOWLEDGE MS-Power ...\n",
       "961       Testing  Skill Set OS Windows XP/7/8/8.1/10 Database MY...\n",
       "\n",
       "[962 rows x 2 columns]"
      ]
     },
     "execution_count": 163,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"UpdatedResumeDataset.csv\")\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 164,
   "id": "d6decaf5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 962 entries, 0 to 961\n",
      "Data columns (total 2 columns):\n",
      " #   Column    Non-Null Count  Dtype \n",
      "---  ------    --------------  ----- \n",
      " 0   Category  962 non-null    object\n",
      " 1   Resume    962 non-null    object\n",
      "dtypes: object(2)\n",
      "memory usage: 15.2+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 165,
   "id": "008ea984",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Java Developer               84\n",
       "Testing                      70\n",
       "DevOps Engineer              55\n",
       "Python Developer             48\n",
       "Web Designing                45\n",
       "HR                           44\n",
       "Hadoop                       42\n",
       "Blockchain                   40\n",
       "ETL Developer                40\n",
       "Operations Manager           40\n",
       "Data Science                 40\n",
       "Sales                        40\n",
       "Mechanical Engineer          40\n",
       "Arts                         36\n",
       "Database                     33\n",
       "Electrical Engineering       30\n",
       "Health and fitness           30\n",
       "PMO                          30\n",
       "Business Analyst             28\n",
       "DotNet Developer             28\n",
       "Automation Testing           26\n",
       "Network Security Engineer    25\n",
       "SAP Developer                24\n",
       "Civil Engineer               24\n",
       "Advocate                     20\n",
       "Name: Category, dtype: int64"
      ]
     },
     "execution_count": 165,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Category'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "id": "c216d416",
   "metadata": {},
   "outputs": [],
   "source": [
    "def cleanResume(resumeText):\n",
    "    resumeText = re.sub('http\\S+\\s*', ' ', resumeText)  # remove URLs\n",
    "    resumeText = re.sub('RT|cc', ' ', resumeText)  # remove RT and cc\n",
    "    resumeText = re.sub('#\\S+', '', resumeText)  # remove hashtags\n",
    "    resumeText = re.sub('@\\S+', '  ', resumeText)  # remove mentions\n",
    "    resumeText = re.sub('[%s]' % re.escape(\"\"\"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~\"\"\"), ' ', resumeText)  # remove punctuations\n",
    "    resumeText = re.sub(r'[^\\x00-\\x7f]',r' ', resumeText) \n",
    "    resumeText = re.sub('\\s+', ' ', resumeText)  # remove extra whitespace\n",
    "    return resumeText"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 167,
   "id": "8bdcbf63",
   "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>Category</th>\n",
       "      <th>Resume</th>\n",
       "      <th>cleanedResume</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Skills * Programming Languages: Python (pandas...</td>\n",
       "      <td>Skills Programming Languages Python pandas num...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Education Details \\r\\nMay 2013 to May 2017 B.E...</td>\n",
       "      <td>Education Details May 2013 to May 2017 B E UIT...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Areas of Interest Deep Learning, Control Syste...</td>\n",
       "      <td>Areas of Interest Deep Learning Control System...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Skills â¢ R â¢ Python â¢ SAP HANA â¢ Table...</td>\n",
       "      <td>Skills R Python SAP HANA Tableau SAP HANA SQL ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Education Details \\r\\n MCA   YMCAUST,  Faridab...</td>\n",
       "      <td>Education Details MCA YMCAUST Faridabad Haryan...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>957</th>\n",
       "      <td>Testing</td>\n",
       "      <td>Computer Skills: â¢ Proficient in MS office (...</td>\n",
       "      <td>Computer Skills Proficient in MS office Word B...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>958</th>\n",
       "      <td>Testing</td>\n",
       "      <td>â Willingness to accept the challenges. â ...</td>\n",
       "      <td>Willingness to a ept the challenges Positive ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>959</th>\n",
       "      <td>Testing</td>\n",
       "      <td>PERSONAL SKILLS â¢ Quick learner, â¢ Eagerne...</td>\n",
       "      <td>PERSONAL SKILLS Quick learner Eagerness to lea...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>960</th>\n",
       "      <td>Testing</td>\n",
       "      <td>COMPUTER SKILLS &amp; SOFTWARE KNOWLEDGE MS-Power ...</td>\n",
       "      <td>COMPUTER SKILLS SOFTWARE KNOWLEDGE MS Power Po...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>961</th>\n",
       "      <td>Testing</td>\n",
       "      <td>Skill Set OS Windows XP/7/8/8.1/10 Database MY...</td>\n",
       "      <td>Skill Set OS Windows XP 7 8 8 1 10 Database MY...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>962 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         Category                                             Resume  \\\n",
       "0    Data Science  Skills * Programming Languages: Python (pandas...   \n",
       "1    Data Science  Education Details \\r\\nMay 2013 to May 2017 B.E...   \n",
       "2    Data Science  Areas of Interest Deep Learning, Control Syste...   \n",
       "3    Data Science  Skills â¢ R â¢ Python â¢ SAP HANA â¢ Table...   \n",
       "4    Data Science  Education Details \\r\\n MCA   YMCAUST,  Faridab...   \n",
       "..            ...                                                ...   \n",
       "957       Testing  Computer Skills: â¢ Proficient in MS office (...   \n",
       "958       Testing  â Willingness to accept the challenges. â ...   \n",
       "959       Testing  PERSONAL SKILLS â¢ Quick learner, â¢ Eagerne...   \n",
       "960       Testing  COMPUTER SKILLS & SOFTWARE KNOWLEDGE MS-Power ...   \n",
       "961       Testing  Skill Set OS Windows XP/7/8/8.1/10 Database MY...   \n",
       "\n",
       "                                         cleanedResume  \n",
       "0    Skills Programming Languages Python pandas num...  \n",
       "1    Education Details May 2013 to May 2017 B E UIT...  \n",
       "2    Areas of Interest Deep Learning Control System...  \n",
       "3    Skills R Python SAP HANA Tableau SAP HANA SQL ...  \n",
       "4    Education Details MCA YMCAUST Faridabad Haryan...  \n",
       "..                                                 ...  \n",
       "957  Computer Skills Proficient in MS office Word B...  \n",
       "958   Willingness to a ept the challenges Positive ...  \n",
       "959  PERSONAL SKILLS Quick learner Eagerness to lea...  \n",
       "960  COMPUTER SKILLS SOFTWARE KNOWLEDGE MS Power Po...  \n",
       "961  Skill Set OS Windows XP 7 8 8 1 10 Database MY...  \n",
       "\n",
       "[962 rows x 3 columns]"
      ]
     },
     "execution_count": 167,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['cleanedResume'] = df['Resume'].apply(lambda x: cleanResume(x))\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "id": "54a3fb34",
   "metadata": {},
   "outputs": [],
   "source": [
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 169,
   "id": "43241924",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import LabelEncoder\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.pipeline import Pipeline\n",
    "\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "\n",
    "from sklearn.model_selection import train_test_split, GridSearchCV\n",
    "\n",
    "from sklearn.preprocessing import FunctionTransformer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 170,
   "id": "3c4cbf00",
   "metadata": {},
   "outputs": [],
   "source": [
    "models = {\n",
    "    'logistic_regression' : {\n",
    "        'model' : LogisticRegression(max_iter=10000),\n",
    "        'params' : {\n",
    "            'C' : [1,5,10,15,20],\n",
    "            'solver' : ['lbfgs', 'liblinear']\n",
    "        }\n",
    "    },\n",
    "    'decision_tree' : {\n",
    "        'model' : DecisionTreeClassifier(),\n",
    "        'params' : {\n",
    "            'criterion' : ['gini', 'entropy']\n",
    "        }\n",
    "    },\n",
    "    'random_forest' : {\n",
    "        'model' : RandomForestClassifier(),\n",
    "        'params' : {\n",
    "            'criterion' : ['gini', 'entropy'],\n",
    "            'n_estimators' : [10,20,30,40,50,100]\n",
    "        }\n",
    "    },\n",
    "#     'gaussian_nb' : {\n",
    "#         'model' : GaussianNB(),\n",
    "#         'params' : {}\n",
    "#     },\n",
    "    'svm' : {\n",
    "        'model' : SVC(gamma='auto'),\n",
    "        'params' : {\n",
    "            'C' : [1,5,10,15,20],\n",
    "            'kernel' : ['linear', 'rbf']\n",
    "        }\n",
    "    },\n",
    "    'knn' : {\n",
    "        'model' : KNeighborsClassifier(),\n",
    "        'params' : {\n",
    "            'n_neighbors' : [3,5,7,11,13,15,17,19,21],\n",
    "            'p' : [1,2]\n",
    "        }\n",
    "    }\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 171,
   "id": "b696b5d6",
   "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>Category</th>\n",
       "      <th>Resume</th>\n",
       "      <th>cleanedResume</th>\n",
       "      <th>new_categ</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Skills * Programming Languages: Python (pandas...</td>\n",
       "      <td>Skills Programming Languages Python pandas num...</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Education Details \\r\\nMay 2013 to May 2017 B.E...</td>\n",
       "      <td>Education Details May 2013 to May 2017 B E UIT...</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Areas of Interest Deep Learning, Control Syste...</td>\n",
       "      <td>Areas of Interest Deep Learning Control System...</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Skills â¢ R â¢ Python â¢ SAP HANA â¢ Table...</td>\n",
       "      <td>Skills R Python SAP HANA Tableau SAP HANA SQL ...</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Data Science</td>\n",
       "      <td>Education Details \\r\\n MCA   YMCAUST,  Faridab...</td>\n",
       "      <td>Education Details MCA YMCAUST Faridabad Haryan...</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>957</th>\n",
       "      <td>Testing</td>\n",
       "      <td>Computer Skills: â¢ Proficient in MS office (...</td>\n",
       "      <td>Computer Skills Proficient in MS office Word B...</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>958</th>\n",
       "      <td>Testing</td>\n",
       "      <td>â Willingness to accept the challenges. â ...</td>\n",
       "      <td>Willingness to a ept the challenges Positive ...</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>959</th>\n",
       "      <td>Testing</td>\n",
       "      <td>PERSONAL SKILLS â¢ Quick learner, â¢ Eagerne...</td>\n",
       "      <td>PERSONAL SKILLS Quick learner Eagerness to lea...</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>960</th>\n",
       "      <td>Testing</td>\n",
       "      <td>COMPUTER SKILLS &amp; SOFTWARE KNOWLEDGE MS-Power ...</td>\n",
       "      <td>COMPUTER SKILLS SOFTWARE KNOWLEDGE MS Power Po...</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>961</th>\n",
       "      <td>Testing</td>\n",
       "      <td>Skill Set OS Windows XP/7/8/8.1/10 Database MY...</td>\n",
       "      <td>Skill Set OS Windows XP 7 8 8 1 10 Database MY...</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>962 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         Category                                             Resume  \\\n",
       "0    Data Science  Skills * Programming Languages: Python (pandas...   \n",
       "1    Data Science  Education Details \\r\\nMay 2013 to May 2017 B.E...   \n",
       "2    Data Science  Areas of Interest Deep Learning, Control Syste...   \n",
       "3    Data Science  Skills â¢ R â¢ Python â¢ SAP HANA â¢ Table...   \n",
       "4    Data Science  Education Details \\r\\n MCA   YMCAUST,  Faridab...   \n",
       "..            ...                                                ...   \n",
       "957       Testing  Computer Skills: â¢ Proficient in MS office (...   \n",
       "958       Testing  â Willingness to accept the challenges. â ...   \n",
       "959       Testing  PERSONAL SKILLS â¢ Quick learner, â¢ Eagerne...   \n",
       "960       Testing  COMPUTER SKILLS & SOFTWARE KNOWLEDGE MS-Power ...   \n",
       "961       Testing  Skill Set OS Windows XP/7/8/8.1/10 Database MY...   \n",
       "\n",
       "                                         cleanedResume  new_categ  \n",
       "0    Skills Programming Languages Python pandas num...          6  \n",
       "1    Education Details May 2013 to May 2017 B E UIT...          6  \n",
       "2    Areas of Interest Deep Learning Control System...          6  \n",
       "3    Skills R Python SAP HANA Tableau SAP HANA SQL ...          6  \n",
       "4    Education Details MCA YMCAUST Faridabad Haryan...          6  \n",
       "..                                                 ...        ...  \n",
       "957  Computer Skills Proficient in MS office Word B...         23  \n",
       "958   Willingness to a ept the challenges Positive ...         23  \n",
       "959  PERSONAL SKILLS Quick learner Eagerness to lea...         23  \n",
       "960  COMPUTER SKILLS SOFTWARE KNOWLEDGE MS Power Po...         23  \n",
       "961  Skill Set OS Windows XP 7 8 8 1 10 Database MY...         23  \n",
       "\n",
       "[962 rows x 4 columns]"
      ]
     },
     "execution_count": 171,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['new_categ'] = le.fit_transform(df['Category'])\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 172,
   "id": "8d31035a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'Advocate': 0,\n",
       " 'Arts': 1,\n",
       " 'Automation Testing': 2,\n",
       " 'Blockchain': 3,\n",
       " 'Business Analyst': 4,\n",
       " 'Civil Engineer': 5,\n",
       " 'Data Science': 6,\n",
       " 'Database': 7,\n",
       " 'DevOps Engineer': 8,\n",
       " 'DotNet Developer': 9,\n",
       " 'ETL Developer': 10,\n",
       " 'Electrical Engineering': 11,\n",
       " 'HR': 12,\n",
       " 'Hadoop': 13,\n",
       " 'Health and fitness': 14,\n",
       " 'Java Developer': 15,\n",
       " 'Mechanical Engineer': 16,\n",
       " 'Network Security Engineer': 17,\n",
       " 'Operations Manager': 18,\n",
       " 'PMO': 19,\n",
       " 'Python Developer': 20,\n",
       " 'SAP Developer': 21,\n",
       " 'Sales': 22,\n",
       " 'Testing': 23,\n",
       " 'Web Designing': 24}"
      ]
     },
     "execution_count": 172,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "le.fit(df['Category'])\n",
    "le_name_mapping = dict(zip(le.classes_, le.transform(le.classes_)))\n",
    "le_name_mapping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 173,
   "id": "039a2195",
   "metadata": {},
   "outputs": [],
   "source": [
    "def trans_func(inp):\n",
    "    inp = inp.apply(lambda x: cleanResume(x))\n",
    "    return inp.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 174,
   "id": "15a6f3db",
   "metadata": {},
   "outputs": [],
   "source": [
    "transformer = FunctionTransformer(trans_func)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 175,
   "id": "b927bd2c",
   "metadata": {},
   "outputs": [],
   "source": [
    "pipeline = Pipeline([\n",
    "    ('cleaner',transformer),\n",
    "    ('vectorizer',TfidfVectorizer()),\n",
    "    ('model', LogisticRegression())\n",
    "]) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 176,
   "id": "8debaf42",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train, x_test, y_train, y_test = train_test_split(df['Resume'],df['new_categ'],test_size = 0.25,random_state=10,stratify=df['new_categ'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 177,
   "id": "7cfb6774",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-8 {color: black;background-color: white;}#sk-container-id-8 pre{padding: 0;}#sk-container-id-8 div.sk-toggleable {background-color: white;}#sk-container-id-8 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-8 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-8 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-8 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-8 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-8 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-8 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-8 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-8 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-8 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-8 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-8 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-8 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-8 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-8 div.sk-item {position: relative;z-index: 1;}#sk-container-id-8 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-8 div.sk-item::before, #sk-container-id-8 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-8 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-8 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-8 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-8 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-8 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-8 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-8 div.sk-label-container {text-align: center;}#sk-container-id-8 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-8 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-8\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;cleaner&#x27;,\n",
       "                 FunctionTransformer(func=&lt;function trans_func at 0x00000173B1734160&gt;)),\n",
       "                (&#x27;vectorizer&#x27;, TfidfVectorizer()),\n",
       "                (&#x27;model&#x27;, LogisticRegression())])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-28\" type=\"checkbox\" ><label for=\"sk-estimator-id-28\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;cleaner&#x27;,\n",
       "                 FunctionTransformer(func=&lt;function trans_func at 0x00000173B1734160&gt;)),\n",
       "                (&#x27;vectorizer&#x27;, TfidfVectorizer()),\n",
       "                (&#x27;model&#x27;, LogisticRegression())])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-29\" type=\"checkbox\" ><label for=\"sk-estimator-id-29\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function trans_func at 0x00000173B1734160&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-30\" type=\"checkbox\" ><label for=\"sk-estimator-id-30\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">TfidfVectorizer</label><div class=\"sk-toggleable__content\"><pre>TfidfVectorizer()</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-31\" type=\"checkbox\" ><label for=\"sk-estimator-id-31\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression()</pre></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('cleaner',\n",
       "                 FunctionTransformer(func=<function trans_func at 0x00000173B1734160>)),\n",
       "                ('vectorizer', TfidfVectorizer()),\n",
       "                ('model', LogisticRegression())])"
      ]
     },
     "execution_count": 177,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipeline.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "id": "21078be0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.966804979253112"
      ]
     },
     "execution_count": 178,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipeline.score(x_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 179,
   "id": "f4358bf0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"â\\x80¢ Good communication skill â\\x80¢ Quick learner â\\x80¢ Keen to find solutionsEducation Details \\r\\n MBA Marketing and International Business Management Pune, Maharashtra Pune University\\r\\n B-Tech Tech Nagpur, Maharashtra RTM Nagpur University\\r\\nG.M. Arts, Commerce & Science \\r\\n\\r\\nG.M. Arts, Commerce & Science\\r\\nSkill Details \\r\\nCompany Details \\r\\ncompany - Samarth College\\r\\ndescription - of Engineering        30          7        210 \\r\\n5      College to campus             VJ College of Pharmacy         10 days' workshop       10\\r\\n\\r\\nG.M. Arts, Commerce & Science 6          Soft Skills                                               6 days' workshop           6\\r\\nCollege\\r\\n\\r\\nPersonality             G.M. Institute of Agricultural 7\\t\\t6 days' workshop           6\\r\\nDevelopment                        Diploma \\r\\n8          Soft Skills           Samarth College of Polytechnic     20 days' workshop       20\\r\\n\\r\\nTOTAL                                              350\\r\\nWORKING EXPERIENCE IN CORPORATE:\\r\\nSr. No               Topic                      Company                  No. of days    Total Hrs \\r\\n1       Presentation skill & Team    Elringklinger Automotives Pvt 1 Day           8 building Workshop             Ltd, Ranjangaon, Pune \\r\\n2           Negotiation skill & Kubler Automation Pvt Ltd., 2 days          16\\r\\nCommunication skill               Chakan, Pune \\r\\n3       Business Communication       Finanza Home Loans, Pimple 3 days          21 & Stress management               saudagar, Pune \\r\\n4        Team-building & Verbal       Sharvari Products Pvt Ltd, 2 days          16 communication                   Junner, Pune 7 days' 5             Entrepreneurship       Agriculture Research Centre,\\r\\nWorkshop        168\\r\\nDevelopment               Narayangaon, Pune (8 batches)\\r\\nTOTAL                                             229\\r\\n\\r\\nADJOINING SKILLS: â\\x80¢ Working knowledge of Windows operating system and MS Office â\\x80¢ Communicate well in English, Hindi & Marathi.\\r\\nâ\\x80¢ Organized and participated in events like gathering, teachers day, fashion show and various science exhibitions at college\""
      ]
     },
     "execution_count": 179,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "res = df['Resume'][134]\n",
    "res"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 180,
   "id": "fac9eda0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1])"
      ]
     },
     "execution_count": 180,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipeline.predict(pd.Series([res]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 158,
   "id": "aafaefe6",
   "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>model</th>\n",
       "      <th>best_score</th>\n",
       "      <th>best_params</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>logistic_regression</td>\n",
       "      <td>0.995855</td>\n",
       "      <td>{'C': 1, 'solver': 'lbfgs'}</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>decision_tree</td>\n",
       "      <td>0.995855</td>\n",
       "      <td>{'criterion': 'gini'}</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>random_forest</td>\n",
       "      <td>0.995855</td>\n",
       "      <td>{'criterion': 'gini', 'n_estimators': 10}</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>svm</td>\n",
       "      <td>0.995855</td>\n",
       "      <td>{'C': 1, 'kernel': 'linear'}</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>knn</td>\n",
       "      <td>0.987543</td>\n",
       "      <td>{'n_neighbors': 3, 'p': 2}</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 model  best_score                                best_params\n",
       "0  logistic_regression    0.995855                {'C': 1, 'solver': 'lbfgs'}\n",
       "1        decision_tree    0.995855                      {'criterion': 'gini'}\n",
       "2        random_forest    0.995855  {'criterion': 'gini', 'n_estimators': 10}\n",
       "3                  svm    0.995855               {'C': 1, 'kernel': 'linear'}\n",
       "4                  knn    0.987543                 {'n_neighbors': 3, 'p': 2}"
      ]
     },
     "execution_count": 158,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scores = []\n",
    "for model_name, mp in models.items():\n",
    "    clf =  GridSearchCV(mp['model'], mp['params'], cv=5, return_train_score=False)\n",
    "    pipeline = Pipeline([\n",
    "    ('cleaner',transformer),\n",
    "    ('vectorizer',TfidfVectorizer()),\n",
    "    ('model', clf)\n",
    "    ]) \n",
    "    pipeline.fit(df['Resume'],df['new_categ'])\n",
    "    scores.append({\n",
    "        'model': model_name,\n",
    "        'best_score': clf.best_score_,\n",
    "        'best_params': clf.best_params_\n",
    "    })\n",
    "    \n",
    "df1 = pd.DataFrame(scores,columns=['model','best_score','best_params'])\n",
    "df1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 199,
   "id": "1a020d95",
   "metadata": {},
   "outputs": [],
   "source": [
    "pipeline = Pipeline([\n",
    "    ('cleaner',transformer),\n",
    "    ('vectorizer',TfidfVectorizer()),\n",
    "    ('model', RandomForestClassifier(criterion='gini',n_estimators=10))\n",
    "]) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 200,
   "id": "7e935edd",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train, x_test, y_train, y_test = train_test_split(df['Resume'],df['new_categ'],test_size = 0.25,random_state=10,stratify=df['new_categ'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 201,
   "id": "618b4383",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-13 {color: black;background-color: white;}#sk-container-id-13 pre{padding: 0;}#sk-container-id-13 div.sk-toggleable {background-color: white;}#sk-container-id-13 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-13 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-13 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-13 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-13 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-13 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-13 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-13 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-13 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-13 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-13 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-13 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-13 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-13 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-13 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-13 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-13 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-13 div.sk-item {position: relative;z-index: 1;}#sk-container-id-13 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-13 div.sk-item::before, #sk-container-id-13 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-13 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-13 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-13 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-13 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-13 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-13 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-13 div.sk-label-container {text-align: center;}#sk-container-id-13 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-13 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-13\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;cleaner&#x27;,\n",
       "                 FunctionTransformer(func=&lt;function trans_func at 0x00000173B1734160&gt;)),\n",
       "                (&#x27;vectorizer&#x27;, TfidfVectorizer()),\n",
       "                (&#x27;model&#x27;, RandomForestClassifier(n_estimators=10))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-48\" type=\"checkbox\" ><label for=\"sk-estimator-id-48\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;cleaner&#x27;,\n",
       "                 FunctionTransformer(func=&lt;function trans_func at 0x00000173B1734160&gt;)),\n",
       "                (&#x27;vectorizer&#x27;, TfidfVectorizer()),\n",
       "                (&#x27;model&#x27;, RandomForestClassifier(n_estimators=10))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-49\" type=\"checkbox\" ><label for=\"sk-estimator-id-49\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function trans_func at 0x00000173B1734160&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-50\" type=\"checkbox\" ><label for=\"sk-estimator-id-50\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">TfidfVectorizer</label><div class=\"sk-toggleable__content\"><pre>TfidfVectorizer()</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-51\" type=\"checkbox\" ><label for=\"sk-estimator-id-51\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(n_estimators=10)</pre></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('cleaner',\n",
       "                 FunctionTransformer(func=<function trans_func at 0x00000173B1734160>)),\n",
       "                ('vectorizer', TfidfVectorizer()),\n",
       "                ('model', RandomForestClassifier(n_estimators=10))])"
      ]
     },
     "execution_count": 201,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipeline.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 202,
   "id": "935d4b99",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.975103734439834"
      ]
     },
     "execution_count": 202,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipeline.score(x_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 214,
   "id": "49591339",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "with open('model_pipe','wb') as f:\n",
    "    pickle.dump(pipeline,f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 215,
   "id": "7ddc07ac",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('model_pipe','rb') as f:\n",
    "    mod2 = pickle.load(f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 216,
   "id": "fa7aaaf2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,\n",
       "        6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,\n",
       "        6,  6,  6,  6,  6,  6, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12,\n",
       "       12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12,\n",
       "       12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12,  0,\n",
       "        0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,\n",
       "        0,  0,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,\n",
       "        1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,\n",
       "        1,  1,  1,  1, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24,\n",
       "       24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24,\n",
       "       24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 16, 16,\n",
       "       16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,\n",
       "       16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,\n",
       "       16, 16, 16, 16, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22,\n",
       "       22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22,\n",
       "       22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 14, 14, 14, 14, 14, 14, 14,\n",
       "       14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14,\n",
       "       14, 14, 14, 14, 14, 14,  5,  5,  5,  5,  5,  5,  5,  5,  5,  5,  5,\n",
       "        5,  5,  5,  5,  5,  5,  5,  5,  5,  5,  5,  5,  5, 15, 15, 15, 15,\n",
       "       15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,\n",
       "       15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,\n",
       "       15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,\n",
       "       15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,\n",
       "       15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,  4,  4,  4,  4,  4,\n",
       "        4,  4,  4,  4,  4,  4,  4,  4,  4,  4,  4,  4,  4,  4,  4,  4,  4,\n",
       "        4,  4,  4,  4,  4,  4, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21,\n",
       "       21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21,  2,  2,  2,  2,\n",
       "        2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,\n",
       "        2,  2,  2,  2,  2, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11,\n",
       "       11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11,\n",
       "       11, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18,\n",
       "       18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18,\n",
       "       18, 18, 18, 18, 18, 18, 18, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,\n",
       "       20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,\n",
       "       20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,\n",
       "       20, 20, 20, 20,  8,  8,  8,  8, 19, 20,  2,  8,  8,  8,  8,  8,  8,\n",
       "        8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,\n",
       "        8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,\n",
       "        8,  8,  8,  8,  8,  8,  8,  8, 17, 17, 17, 17, 17, 17, 17, 17, 17,\n",
       "       17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 19,\n",
       "       19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,\n",
       "       19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,  7,  7,  7,  7,  7,\n",
       "        7,  7,  7,  7,  7,  6,  7,  7,  7,  7,  7,  7,  7,  7,  7,  7,  6,\n",
       "        7,  7,  7,  7,  7,  7,  7,  7,  7,  7,  6, 13, 13, 13, 13, 13, 13,\n",
       "       13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,\n",
       "       13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,\n",
       "       13, 13, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,\n",
       "       10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,\n",
       "       10, 10, 10, 10, 10, 10, 10, 10,  9,  9,  9,  9,  9,  9,  9,  9,  9,\n",
       "        9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,\n",
       "        9,  9,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,\n",
       "        3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,\n",
       "        3,  3,  3,  3,  3,  3,  3,  3, 23, 23, 23, 23, 23, 23, 23, 23, 23,\n",
       "       23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23,\n",
       "       23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23,\n",
       "       23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23,\n",
       "       23, 23, 23, 23, 23, 23, 23, 23, 23, 23])"
      ]
     },
     "execution_count": 216,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mod2.predict(df['Resume'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "98119ec7",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}