diff --git a/download_data.ipynb b/download_data.ipynb index c4b700c..10d9433 100644 --- a/download_data.ipynb +++ b/download_data.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 1, + "execution_count": 6, "id": "5e2107a5", "metadata": {}, "outputs": [], @@ -12,7 +12,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 7, "id": "bcc889e5", "metadata": {}, "outputs": [ @@ -20,25 +20,38 @@ "name": "stdout", "output_type": "stream", "text": [ - "Requirement already satisfied: kaggle in /home/mikolaj/.local/lib/python3.8/site-packages (1.5.12)\n", - "Requirement already satisfied: urllib3 in /usr/lib/python3/dist-packages (from kaggle) (1.22)\n", - "Requirement already satisfied: six>=1.10 in /usr/lib/python3/dist-packages (from kaggle) (1.11.0)\n", - "Requirement already satisfied: requests in /home/mikolaj/.local/lib/python3.8/site-packages (from kaggle) (2.25.1)\n", - "Requirement already satisfied: certifi in /usr/lib/python3/dist-packages (from kaggle) (2018.1.18)\n", - "Requirement already satisfied: python-slugify in /home/mikolaj/.local/lib/python3.8/site-packages (from kaggle) (6.1.1)\n", - "Requirement already satisfied: python-dateutil in /home/mikolaj/.local/lib/python3.8/site-packages (from kaggle) (2.8.1)\n", - "Requirement already satisfied: tqdm in /home/mikolaj/.local/lib/python3.8/site-packages (from kaggle) (4.59.0)\n", - "Requirement already satisfied: text-unidecode>=1.3 in /home/mikolaj/.local/lib/python3.8/site-packages (from python-slugify->kaggle) (1.3)\n", - "Requirement already satisfied: chardet<5,>=3.0.2 in /usr/lib/python3/dist-packages (from requests->kaggle) (3.0.4)\n", - "Requirement already satisfied: idna<3,>=2.5 in /home/mikolaj/.local/lib/python3.8/site-packages (from requests->kaggle) (2.10)\n", - "\u001b[33mWARNING: You are using pip version 21.3.1; however, version 22.0.4 is available.\n", + "Collecting kaggle\n", + " Using cached kaggle-1.5.12.tar.gz (58 kB)\n", + "Requirement already satisfied: certifi in /usr/lib/python3/dist-packages (from kaggle) (2019.11.28)\n", + "Requirement already satisfied: python-dateutil in /usr/lib/python3/dist-packages (from kaggle) (2.7.3)\n", + "Collecting python-slugify\n", + " Using cached python_slugify-6.1.1-py2.py3-none-any.whl (9.1 kB)\n", + "Requirement already satisfied: requests in /usr/lib/python3/dist-packages (from kaggle) (2.22.0)\n", + "Requirement already satisfied: six>=1.10 in /usr/lib/python3/dist-packages (from kaggle) (1.14.0)\n", + "Collecting tqdm\n", + " Downloading tqdm-4.63.0-py2.py3-none-any.whl (76 kB)\n", + "\u001b[K |████████████████████████████████| 76 kB 1.7 MB/s eta 0:00:011\n", + "\u001b[?25hRequirement already satisfied: urllib3 in /usr/lib/python3/dist-packages (from kaggle) (1.25.8)\n", + "Collecting text-unidecode>=1.3\n", + " Using cached text_unidecode-1.3-py2.py3-none-any.whl (78 kB)\n", + "Building wheels for collected packages: kaggle\n", + " Building wheel for kaggle (setup.py) ... \u001b[?25ldone\n", + "\u001b[?25h Created wheel for kaggle: filename=kaggle-1.5.12-py3-none-any.whl size=73052 sha256=02172fba1c0ec42884ad8bcbb3c3b99749f529299444b00aaa946e78b9dfcb1f\n", + " Stored in directory: /home/students/s444463/.cache/pip/wheels/29/da/11/144cc25aebdaeb4931b231e25fd34b394e6a5725cbb2f50106\n", + "Successfully built kaggle\n", + "Installing collected packages: text-unidecode, tqdm, python-slugify, kaggle\n", + "\u001b[33m WARNING: The script tqdm is installed in '/home/students/s444463/.local/bin' which is not on PATH.\n", + " Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\u001b[0m\n", + "\u001b[33m WARNING: The script kaggle is installed in '/home/students/s444463/.local/bin' which is not on PATH.\n", + " Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\u001b[0m\n", + "Successfully installed kaggle-1.5.12 python-slugify-6.1.1 text-unidecode-1.3 tqdm-4.63.0\n", + "\u001b[33mWARNING: You are using pip version 21.2.4; however, version 22.0.4 is available.\n", "You should consider upgrading via the '/usr/bin/python3 -m pip install --upgrade pip' command.\u001b[0m\n", - "Requirement already satisfied: pandas in /home/mikolaj/.local/lib/python3.8/site-packages (1.1.5)\n", - "Requirement already satisfied: numpy>=1.15.4 in /home/mikolaj/.local/lib/python3.8/site-packages (from pandas) (1.19.5)\n", - "Requirement already satisfied: pytz>=2017.2 in /usr/lib/python3/dist-packages (from pandas) (2018.3)\n", - "Requirement already satisfied: python-dateutil>=2.7.3 in /home/mikolaj/.local/lib/python3.8/site-packages (from pandas) (2.8.1)\n", - "Requirement already satisfied: six>=1.5 in /usr/lib/python3/dist-packages (from python-dateutil>=2.7.3->pandas) (1.11.0)\n", - "\u001b[33mWARNING: You are using pip version 21.3.1; however, version 22.0.4 is available.\n", + "Requirement already satisfied: pandas in /usr/lib/python3/dist-packages (0.25.3)\n", + "\u001b[33mWARNING: You are using pip version 21.2.4; however, version 22.0.4 is available.\n", + "You should consider upgrading via the '/usr/bin/python3 -m pip install --upgrade pip' command.\u001b[0m\n", + "Requirement already satisfied: numpy in /usr/lib/python3/dist-packages (1.17.4)\n", + "\u001b[33mWARNING: You are using pip version 21.2.4; however, version 22.0.4 is available.\n", "You should consider upgrading via the '/usr/bin/python3 -m pip install --upgrade pip' command.\u001b[0m\n" ] } @@ -51,7 +64,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 8, "id": "02a4034f", "metadata": {}, "outputs": [ @@ -59,8 +72,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Warning: Your Kaggle API key is readable by other users on this system! To fix this, you can run 'chmod 600 /home/mikolaj/.kaggle/kaggle.json'\n", - "real-or-fake-fake-jobposting-prediction.zip: Skipping, found more recently modified local copy (use --force to force download)\n" + "/bin/bash: kaggle: command not found\r\n" ] } ], @@ -72,7 +84,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 9, "id": "5035aef0", "metadata": {}, "outputs": [ @@ -80,8 +92,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Archive: real-or-fake-fake-jobposting-prediction.zip\n", - " inflating: fake_job_postings.csv \n" + "unzip: cannot find or open real-or-fake-fake-jobposting-prediction.zip, real-or-fake-fake-jobposting-prediction.zip.zip or real-or-fake-fake-jobposting-prediction.zip.ZIP.\r\n" ] } ], @@ -91,7 +102,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 10, "id": "14344d2f", "metadata": {}, "outputs": [ @@ -99,19 +110,22 @@ "name": "stdout", "output_type": "stream", "text": [ - "Requirement already satisfied: seaborn in /home/mikolaj/.local/lib/python3.8/site-packages (0.11.2)\n", - "Requirement already satisfied: scipy>=1.0 in /home/mikolaj/.local/lib/python3.8/site-packages (from seaborn) (1.7.2)\n", - "Requirement already satisfied: matplotlib>=2.2 in /home/mikolaj/.local/lib/python3.8/site-packages (from seaborn) (3.4.2)\n", - "Requirement already satisfied: numpy>=1.15 in /home/mikolaj/.local/lib/python3.8/site-packages (from seaborn) (1.19.5)\n", - "Requirement already satisfied: pandas>=0.23 in /home/mikolaj/.local/lib/python3.8/site-packages (from seaborn) (1.1.5)\n", - "Requirement already satisfied: python-dateutil>=2.7 in /home/mikolaj/.local/lib/python3.8/site-packages (from matplotlib>=2.2->seaborn) (2.8.1)\n", - "Requirement already satisfied: pillow>=6.2.0 in /home/mikolaj/.local/lib/python3.8/site-packages (from matplotlib>=2.2->seaborn) (8.2.0)\n", - "Requirement already satisfied: cycler>=0.10 in /home/mikolaj/.local/lib/python3.8/site-packages (from matplotlib>=2.2->seaborn) (0.10.0)\n", - "Requirement already satisfied: kiwisolver>=1.0.1 in /home/mikolaj/.local/lib/python3.8/site-packages (from matplotlib>=2.2->seaborn) (1.3.1)\n", - "Requirement already satisfied: pyparsing>=2.2.1 in /home/mikolaj/.local/lib/python3.8/site-packages (from matplotlib>=2.2->seaborn) (2.4.7)\n", - "Requirement already satisfied: pytz>=2017.2 in /usr/lib/python3/dist-packages (from pandas>=0.23->seaborn) (2018.3)\n", - "Requirement already satisfied: six in /usr/lib/python3/dist-packages (from cycler>=0.10->matplotlib>=2.2->seaborn) (1.11.0)\n", - "\u001b[33mWARNING: You are using pip version 21.3.1; however, version 22.0.4 is available.\n", + "Collecting seaborn\n", + " Downloading seaborn-0.11.2-py3-none-any.whl (292 kB)\n", + "\u001b[K |████████████████████████████████| 292 kB 2.8 MB/s eta 0:00:01\n", + "\u001b[?25hRequirement already satisfied: scipy>=1.0 in /usr/lib/python3/dist-packages (from seaborn) (1.3.3)\n", + "Requirement already satisfied: pandas>=0.23 in /usr/lib/python3/dist-packages (from seaborn) (0.25.3)\n", + "Requirement already satisfied: numpy>=1.15 in /usr/lib/python3/dist-packages (from seaborn) (1.17.4)\n", + "Requirement already satisfied: matplotlib>=2.2 in /home/students/s444463/.local/lib/python3.8/site-packages (from seaborn) (3.4.3)\n", + "Requirement already satisfied: kiwisolver>=1.0.1 in /home/students/s444463/.local/lib/python3.8/site-packages (from matplotlib>=2.2->seaborn) (1.3.2)\n", + "Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.8/dist-packages (from matplotlib>=2.2->seaborn) (8.3.2)\n", + "Requirement already satisfied: cycler>=0.10 in /home/students/s444463/.local/lib/python3.8/site-packages (from matplotlib>=2.2->seaborn) (0.10.0)\n", + "Requirement already satisfied: pyparsing>=2.2.1 in /usr/local/lib/python3.8/dist-packages (from matplotlib>=2.2->seaborn) (2.4.7)\n", + "Requirement already satisfied: python-dateutil>=2.7 in /usr/lib/python3/dist-packages (from matplotlib>=2.2->seaborn) (2.7.3)\n", + "Requirement already satisfied: six in /usr/lib/python3/dist-packages (from cycler>=0.10->matplotlib>=2.2->seaborn) (1.14.0)\n", + "Installing collected packages: seaborn\n", + "Successfully installed seaborn-0.11.2\n", + "\u001b[33mWARNING: You are using pip version 21.2.4; however, version 22.0.4 is available.\n", "You should consider upgrading via the '/usr/bin/python3 -m pip install --upgrade pip' command.\u001b[0m\n" ] } @@ -122,7 +136,7 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 11, "id": "0f5ebfab", "metadata": {}, "outputs": [ @@ -525,7 +539,7 @@ "[17880 rows x 18 columns]" ] }, - "execution_count": 22, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -538,7 +552,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 19, "id": "edbf49da", "metadata": {}, "outputs": [ @@ -557,412 +571,20 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": 13, "id": "bc594582", "metadata": {}, "outputs": [ { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
job_idtitlelocationdepartmentsalary_rangecompany_profiledescriptionrequirementsbenefitstelecommutinghas_company_logohas_questionsemployment_typerequired_experiencerequired_educationindustryfunctionfraudulent
01Marketing InternUS, NY, New YorkMarketingWe're Food52, and we've created a groundbreaki...Food52, a fast-growing, James Beard Award-winn...Experience with content management systems a m...010OtherInternshipMarketing0
12Customer Service - Cloud Video ProductionNZ, , AucklandSuccess90 Seconds, the worlds Cloud Video Production ...Organised - Focused - Vibrant - Awesome!Do you...What we expect from you:Your key responsibilit...What you will get from usThrough being part of...010Full-timeNot ApplicableMarketing and AdvertisingCustomer Service0
23Commissioning Machinery Assistant (CMA)US, IA, WeverValor Services provides Workforce Solutions th...Our client, located in Houston, is actively se...Implement pre-commissioning and commissioning ...0100
34Account Executive - Washington DCUS, DC, WashingtonSalesOur passion for improving quality of life thro...THE COMPANY: ESRI – Environmental Systems Rese...EDUCATION: Bachelor’s or Master’s in GIS, busi...Our culture is anything but corporate—we have ...010Full-timeMid-Senior levelBachelor's DegreeComputer SoftwareSales0
45Bill Review ManagerUS, FL, Fort WorthSpotSource Solutions LLC is a Global Human Cap...JOB TITLE: Itemization Review ManagerLOCATION:...QUALIFICATIONS:RN license in the State of Texa...Full Benefits Offered011Full-timeMid-Senior levelBachelor's DegreeHospital & Health CareHealth Care Provider0
.........................................................
1787517876Account Director - DistributionCA, ON, TorontoSalesVend is looking for some awesome new talent to...Just in case this is the first time you’ve vis...To ace this role you:Will eat comprehensive St...What can you expect from us?We have an open cu...011Full-timeMid-Senior levelComputer SoftwareSales0
1787617877Payroll AccountantUS, PA, PhiladelphiaAccountingWebLinc is the e-commerce platform and service...The Payroll Accountant will focus primarily on...- B.A. or B.S. in Accounting- Desire to have f...Health &amp; WellnessMedical planPrescription ...011Full-timeMid-Senior levelBachelor's DegreeInternetAccounting/Auditing0
1787717878Project Cost Control Staff Engineer - Cost Con...US, TX, HoustonWe Provide Full Time Permanent Positions for m...Experienced Project Cost Control Staff Enginee...At least 12 years professional experience.Abil...000Full-time0
1787817879Graphic DesignerNG, LA, LagosNemsia Studios is looking for an experienced v...1. Must be fluent in the latest versions of Co...Competitive salary (compensation will be based...001ContractNot ApplicableProfessionalGraphic DesignDesign0
1787917880Web Application DevelopersNZ, N, WellingtonEngineeringVend is looking for some awesome new talent to...Who are we?Vend is an award winning web based ...We want to hear from you if:You have an in-dep...011Full-timeMid-Senior levelComputer SoftwareEngineering0
\n", - "

17880 rows × 18 columns

\n", - "
" - ], - "text/plain": [ - " job_id title \\\n", - "0 1 Marketing Intern \n", - "1 2 Customer Service - Cloud Video Production \n", - "2 3 Commissioning Machinery Assistant (CMA) \n", - "3 4 Account Executive - Washington DC \n", - "4 5 Bill Review Manager \n", - "... ... ... \n", - "17875 17876 Account Director - Distribution \n", - "17876 17877 Payroll Accountant \n", - "17877 17878 Project Cost Control Staff Engineer - Cost Con... \n", - "17878 17879 Graphic Designer \n", - "17879 17880 Web Application Developers \n", - "\n", - " location department salary_range \\\n", - "0 US, NY, New York Marketing \n", - "1 NZ, , Auckland Success \n", - "2 US, IA, Wever \n", - "3 US, DC, Washington Sales \n", - "4 US, FL, Fort Worth \n", - "... ... ... ... \n", - "17875 CA, ON, Toronto Sales \n", - "17876 US, PA, Philadelphia Accounting \n", - "17877 US, TX, Houston \n", - "17878 NG, LA, Lagos \n", - "17879 NZ, N, Wellington Engineering \n", - "\n", - " company_profile \\\n", - "0 We're Food52, and we've created a groundbreaki... \n", - "1 90 Seconds, the worlds Cloud Video Production ... \n", - "2 Valor Services provides Workforce Solutions th... \n", - "3 Our passion for improving quality of life thro... \n", - "4 SpotSource Solutions LLC is a Global Human Cap... \n", - "... ... \n", - "17875 Vend is looking for some awesome new talent to... \n", - "17876 WebLinc is the e-commerce platform and service... \n", - "17877 We Provide Full Time Permanent Positions for m... \n", - "17878 \n", - "17879 Vend is looking for some awesome new talent to... \n", - "\n", - " description \\\n", - "0 Food52, a fast-growing, James Beard Award-winn... \n", - "1 Organised - Focused - Vibrant - Awesome!Do you... \n", - "2 Our client, located in Houston, is actively se... \n", - "3 THE COMPANY: ESRI – Environmental Systems Rese... \n", - "4 JOB TITLE: Itemization Review ManagerLOCATION:... \n", - "... ... \n", - "17875 Just in case this is the first time you’ve vis... \n", - "17876 The Payroll Accountant will focus primarily on... \n", - "17877 Experienced Project Cost Control Staff Enginee... \n", - "17878 Nemsia Studios is looking for an experienced v... \n", - "17879 Who are we?Vend is an award winning web based ... \n", - "\n", - " requirements \\\n", - "0 Experience with content management systems a m... \n", - "1 What we expect from you:Your key responsibilit... \n", - "2 Implement pre-commissioning and commissioning ... \n", - "3 EDUCATION: Bachelor’s or Master’s in GIS, busi... \n", - "4 QUALIFICATIONS:RN license in the State of Texa... \n", - "... ... \n", - "17875 To ace this role you:Will eat comprehensive St... \n", - "17876 - B.A. or B.S. in Accounting- Desire to have f... \n", - "17877 At least 12 years professional experience.Abil... \n", - "17878 1. Must be fluent in the latest versions of Co... \n", - "17879 We want to hear from you if:You have an in-dep... \n", - "\n", - " benefits telecommuting \\\n", - "0 0 \n", - "1 What you will get from usThrough being part of... 0 \n", - "2 0 \n", - "3 Our culture is anything but corporate—we have ... 0 \n", - "4 Full Benefits Offered 0 \n", - "... ... ... \n", - "17875 What can you expect from us?We have an open cu... 0 \n", - "17876 Health & WellnessMedical planPrescription ... 0 \n", - "17877 0 \n", - "17878 Competitive salary (compensation will be based... 0 \n", - "17879 0 \n", - "\n", - " has_company_logo has_questions employment_type required_experience \\\n", - "0 1 0 Other Internship \n", - "1 1 0 Full-time Not Applicable \n", - "2 1 0 \n", - "3 1 0 Full-time Mid-Senior level \n", - "4 1 1 Full-time Mid-Senior level \n", - "... ... ... ... ... \n", - "17875 1 1 Full-time Mid-Senior level \n", - "17876 1 1 Full-time Mid-Senior level \n", - "17877 0 0 Full-time \n", - "17878 0 1 Contract Not Applicable \n", - "17879 1 1 Full-time Mid-Senior level \n", - "\n", - " required_education industry function \\\n", - "0 Marketing \n", - "1 Marketing and Advertising Customer Service \n", - "2 \n", - "3 Bachelor's Degree Computer Software Sales \n", - "4 Bachelor's Degree Hospital & Health Care Health Care Provider \n", - "... ... ... ... \n", - "17875 Computer Software Sales \n", - "17876 Bachelor's Degree Internet Accounting/Auditing \n", - "17877 \n", - "17878 Professional Graphic Design Design \n", - "17879 Computer Software Engineering \n", - "\n", - " fraudulent \n", - "0 0 \n", - "1 0 \n", - "2 0 \n", - "3 0 \n", - "4 0 \n", - "... ... \n", - "17875 0 \n", - "17876 0 \n", - "17877 0 \n", - "17878 0 \n", - "17879 0 \n", - "\n", - "[17880 rows x 18 columns]" - ] - }, - "execution_count": 29, - "metadata": {}, - "output_type": "execute_result" + "ename": "NameError", + "evalue": "name 'np' is not defined", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m/tmp/ipykernel_8616/866736318.py\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreplace\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnan\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m''\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mregex\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mNameError\u001b[0m: name 'np' is not defined" + ] } ], "source": [ @@ -972,39 +594,17 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": null, "id": "e60b3f32", "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - " 11547\n", - "Sales 551\n", - "Engineering 487\n", - "Marketing 401\n", - "Operations 270\n", - " ... \n", - "Pricing 1\n", - "Mobility 1\n", - "Housekeeping 1\n", - "An Impact Engine Company 1\n", - "Trainee 1\n", - "Name: department, Length: 1338, dtype: int64" - ] - }, - "execution_count": 30, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "data[\"department\"].value_counts()" ] }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 14, "id": "c5ac75f5", "metadata": {}, "outputs": [ @@ -1365,19 +965,20 @@ "max NaN 1.000000 " ] }, - "execution_count": 32, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ + "import numpy as np\n", "data = data.replace(np.nan, '', regex=True)\n", "data.describe(include='all')" ] }, { "cell_type": "code", - "execution_count": 39, + "execution_count": 15, "id": "4b0e77a4", "metadata": {}, "outputs": [ @@ -1392,7 +993,7 @@ "dtype: float64" ] }, - "execution_count": 39, + "execution_count": 15, "metadata": {}, "output_type": "execute_result" } @@ -1403,59 +1004,38 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": null, "id": "5a1d8ec7", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Defaulting to user installation because normal site-packages is not writeable\n", - "Collecting scikit-learn\n", - " Downloading scikit_learn-1.0.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (26.7 MB)\n", - " |████████████████████████████████| 26.7 MB 8.8 MB/s \n", - "\u001b[?25hRequirement already satisfied: numpy>=1.14.6 in /home/mikolaj/.local/lib/python3.8/site-packages (from scikit-learn) (1.19.5)\n", - "Requirement already satisfied: scipy>=1.1.0 in /home/mikolaj/.local/lib/python3.8/site-packages (from scikit-learn) (1.7.2)\n", - "Collecting threadpoolctl>=2.0.0\n", - " Downloading threadpoolctl-3.1.0-py3-none-any.whl (14 kB)\n", - "Requirement already satisfied: joblib>=0.11 in /home/mikolaj/.local/lib/python3.8/site-packages (from scikit-learn) (1.1.0)\n", - "Installing collected packages: threadpoolctl, scikit-learn\n", - "Successfully installed scikit-learn-1.0.2 threadpoolctl-3.1.0\n", - "\u001b[33mWARNING: You are using pip version 21.3.1; however, version 22.0.4 is available.\n", - "You should consider upgrading via the '/usr/bin/python3 -m pip install --upgrade pip' command.\u001b[0m\n", - "Note: you may need to restart the kernel to use updated packages.\n" - ] - } - ], + "outputs": [], "source": [ "pip install -U scikit-learn" ] }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 25, "id": "50813795", "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "English Teacher Abroad 235\n", - "Customer Service Associate 110\n", - "Graduates: English Teacher Abroad (Conversational) 104\n", - "English Teacher Abroad 72\n", - "Software Engineer 68\n", - " ... \n", - "Manager-Plastics Mfg Engineering - Full Time Permanent Job 1\n", - "Ruby on Rails Developer/Programmer 1\n", - "Appliance Technician 1\n", - "Need Oracle Fusion HCM Resource 1\n", - "Recruitment specialist 1\n", - "Name: title, Length: 8761, dtype: int64" + "English Teacher Abroad 230\n", + "Customer Service Associate 106\n", + "Graduates: English Teacher Abroad (Conversational) 96\n", + "English Teacher Abroad 71\n", + "Software Engineer 67\n", + " ... \n", + "Physician - MD, CMO 1\n", + "Financial News Editor 1\n", + "Senior Client Services Engineer 1\n", + "Online Marketing Manager Italy 1\n", + "Infrastructure Project Manager 1\n", + "Name: title, Length: 8461, dtype: int64" ] }, - "execution_count": 26, + "execution_count": 25, "metadata": {}, "output_type": "execute_result" } @@ -1463,29 +1043,31 @@ "source": [ "from sklearn.model_selection import train_test_split\n", "import sklearn\n", - "data_train, data_test = train_test_split(data, random_state=1)\n", + "data_train, data_test = train_test_split(data, test_size=5000, random_state=1)\n", + "data_dev, data_test = train_test_split(data_test, test_size=2500, random_state=1)\n", "data_train[\"title\"].value_counts()" ] }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 27, "id": "ea3c9f2e", "metadata": {}, "outputs": [ { - "data": { - "text/plain": [ - "0.3333333333333333" - ] - }, - "execution_count": 31, - "metadata": {}, - "output_type": "execute_result" + "name": "stdout", + "output_type": "stream", + "text": [ + "12880\n", + "2500\n", + "2500\n" + ] } ], "source": [ - "data_test.size/data_train.size" + "print(len(data_train))\n", + "print(len(data_dev))\n", + "print(len(data_test))" ] }, {