{ "cells": [ { "cell_type": "markdown", "metadata": { "colab_type": "text", "id": "view-in-github" }, "source": [ "\"Open" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "NEY9t4qA3nuM", "outputId": "eed1a9cb-063d-4ecc-b230-fa843af408f5" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Mounted at /content/drive\n" ] } ], "source": [ "from google.colab import drive\n", "drive.mount('/content/drive')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "CeYjJxz11e87", "outputId": "be6cba46-2887-4880-e32a-94243418c4f5" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Collecting sentence-transformers\n", " Downloading sentence_transformers-3.0.1-py3-none-any.whl.metadata (10 kB)\n", "Collecting datasets\n", " Downloading datasets-2.20.0-py3-none-any.whl.metadata (19 kB)\n", "Requirement already satisfied: transformers<5.0.0,>=4.34.0 in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (4.42.4)\n", "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (4.66.4)\n", "Requirement already satisfied: torch>=1.11.0 in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (2.3.1+cu121)\n", "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (1.26.4)\n", "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (1.3.2)\n", "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (1.13.1)\n", "Requirement already satisfied: huggingface-hub>=0.15.1 in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (0.23.5)\n", "Requirement already satisfied: Pillow in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (9.4.0)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets) (3.15.4)\n", "Collecting pyarrow>=15.0.0 (from datasets)\n", " Downloading pyarrow-17.0.0-cp310-cp310-manylinux_2_28_x86_64.whl.metadata (3.3 kB)\n", "Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets) (0.6)\n", "Collecting dill<0.3.9,>=0.3.0 (from datasets)\n", " Downloading dill-0.3.8-py3-none-any.whl.metadata (10 kB)\n", "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (2.1.4)\n", "Collecting requests>=2.32.2 (from datasets)\n", " Downloading requests-2.32.3-py3-none-any.whl.metadata (4.6 kB)\n", "Collecting xxhash (from datasets)\n", " Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n", "Collecting multiprocess (from datasets)\n", " Downloading multiprocess-0.70.16-py310-none-any.whl.metadata (7.2 kB)\n", "Collecting fsspec<=2024.5.0,>=2023.1.0 (from fsspec[http]<=2024.5.0,>=2023.1.0->datasets)\n", " Downloading fsspec-2024.5.0-py3-none-any.whl.metadata (11 kB)\n", "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.10.0)\n", "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (24.1)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)\n", "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (2.3.4)\n", "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n", "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.2.0)\n", "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.1)\n", "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.5)\n", "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.4)\n", "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.15.1->sentence-transformers) (4.12.2)\n", "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (3.3.2)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (3.7)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (2.0.7)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (2024.7.4)\n", "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (1.13.1)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (3.3)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (3.1.4)\n", "Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch>=1.11.0->sentence-transformers)\n", " Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch>=1.11.0->sentence-transformers)\n", " Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch>=1.11.0->sentence-transformers)\n", " Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n", "Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch>=1.11.0->sentence-transformers)\n", " Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n", "Collecting nvidia-cublas-cu12==12.1.3.1 (from torch>=1.11.0->sentence-transformers)\n", " Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-cufft-cu12==11.0.2.54 (from torch>=1.11.0->sentence-transformers)\n", " Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-curand-cu12==10.3.2.106 (from torch>=1.11.0->sentence-transformers)\n", " Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n", "Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch>=1.11.0->sentence-transformers)\n", " Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n", "Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch>=1.11.0->sentence-transformers)\n", " Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n", "Collecting nvidia-nccl-cu12==2.20.5 (from torch>=1.11.0->sentence-transformers)\n", " Using cached nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl.metadata (1.8 kB)\n", "Collecting nvidia-nvtx-cu12==12.1.105 (from torch>=1.11.0->sentence-transformers)\n", " Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.7 kB)\n", "Requirement already satisfied: triton==2.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (2.3.1)\n", "Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.11.0->sentence-transformers)\n", " Using cached nvidia_nvjitlink_cu12-12.6.20-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.34.0->sentence-transformers) (2024.5.15)\n", "Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.34.0->sentence-transformers) (0.4.3)\n", "Requirement already satisfied: tokenizers<0.20,>=0.19 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.34.0->sentence-transformers) (0.19.1)\n", "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n", "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2024.1)\n", "Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2024.1)\n", "Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->sentence-transformers) (1.4.2)\n", "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->sentence-transformers) (3.5.0)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.11.0->sentence-transformers) (2.1.5)\n", "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.11.0->sentence-transformers) (1.3.0)\n", "Downloading sentence_transformers-3.0.1-py3-none-any.whl (227 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m227.1/227.1 kB\u001b[0m \u001b[31m7.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading datasets-2.20.0-py3-none-any.whl (547 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m547.8/547.8 kB\u001b[0m \u001b[31m26.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading dill-0.3.8-py3-none-any.whl (116 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m11.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading fsspec-2024.5.0-py3-none-any.whl (316 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m316.1/316.1 kB\u001b[0m \u001b[31m28.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading pyarrow-17.0.0-cp310-cp310-manylinux_2_28_x86_64.whl (39.9 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m39.9/39.9 MB\u001b[0m \u001b[31m29.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading requests-2.32.3-py3-none-any.whl (64 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m64.9/64.9 kB\u001b[0m \u001b[31m6.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hUsing cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n", "Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n", "Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n", "Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n", "Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n", "Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n", "Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n", "Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n", "Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n", "Using cached nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl (176.2 MB)\n", "Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n", "Downloading multiprocess-0.70.16-py310-none-any.whl (134 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m12.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m19.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hUsing cached nvidia_nvjitlink_cu12-12.6.20-py3-none-manylinux2014_x86_64.whl (19.7 MB)\n", "Installing collected packages: xxhash, requests, pyarrow, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, fsspec, dill, nvidia-cusparse-cu12, nvidia-cudnn-cu12, multiprocess, nvidia-cusolver-cu12, datasets, sentence-transformers\n", " Attempting uninstall: requests\n", " Found existing installation: requests 2.31.0\n", " Uninstalling requests-2.31.0:\n", " Successfully uninstalled requests-2.31.0\n", " Attempting uninstall: pyarrow\n", " Found existing installation: pyarrow 14.0.2\n", " Uninstalling pyarrow-14.0.2:\n", " Successfully uninstalled pyarrow-14.0.2\n", " Attempting uninstall: fsspec\n", " Found existing installation: fsspec 2024.6.1\n", " Uninstalling fsspec-2024.6.1:\n", " Successfully uninstalled fsspec-2024.6.1\n", "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", "cudf-cu12 24.4.1 requires pyarrow<15.0.0a0,>=14.0.1, but you have pyarrow 17.0.0 which is incompatible.\n", "gcsfs 2024.6.1 requires fsspec==2024.6.1, but you have fsspec 2024.5.0 which is incompatible.\n", "google-colab 1.0.0 requires requests==2.31.0, but you have requests 2.32.3 which is incompatible.\n", "ibis-framework 8.0.0 requires pyarrow<16,>=2, but you have pyarrow 17.0.0 which is incompatible.\u001b[0m\u001b[31m\n", "\u001b[0mSuccessfully installed datasets-2.20.0 dill-0.3.8 fsspec-2024.5.0 multiprocess-0.70.16 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.20.5 nvidia-nvjitlink-cu12-12.6.20 nvidia-nvtx-cu12-12.1.105 pyarrow-17.0.0 requests-2.32.3 sentence-transformers-3.0.1 xxhash-3.4.1\n" ] } ], "source": [ "!pip install sentence-transformers datasets" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "T9M3cn300hRx" }, "outputs": [], "source": [ "import pandas as pd\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "APiDpjb907ew", "outputId": "a6eca4df-cc17-42bd-c7e9-45d56b59f111" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"df\",\n \"rows\": 31203,\n \"fields\": [\n {\n \"column\": \"Unnamed: 0\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 9007,\n \"min\": 0,\n \"max\": 31202,\n \"num_unique_values\": 31203,\n \"samples\": [\n 22038,\n 8868,\n 1092\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"clean_cv\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 637,\n \"samples\": [\n \"participated intra college cricket competition various sport event group dance college cultural programme education detail msc computer science pune pune university bsc computer science pune pune university hsc semi english pune maharashatra board ssc semi english pune maharashatra board dot net developer dot net developer skill detail html cs sql experience six month javascript experience le one year month sql two thousand twelve experience le one year detail company description\",\n \"network administrator span lnetworkspan span ladministratorspan greer sc work experience network administrator department education spartanburg sc present implemented local area network lan wide area network wan intranet extranets data network maintained network availability multiple networking environment administering cisco campusbased switching environment fiberbased copperbased ethernet connectivity 1gig 10gig installs manages maintains cisco switching component support campus wan distributed core architecture work cisco chassisbased system internet circuit termination equipment advanced cisco management tool managed cisco prime infrastructure analyze network health workflow access information security requirement performing router switch administration interface configuration switching protocol experience network router switch strong cisco switch router configuration experience workd knowledge tcpip dns acls arp radius ipv6 dhcp intrusion prevention authentication isp circuit connection developed execute test plan check infrastructure system performance performed network modeling analysis defined diagram design business technology initiative enforced policy standardizing system network technician u department state dc enterprise work changed password unlocked account need added device new softwareapplications need troubleshoot application freezing printer working hardware actively troubleshoot level issue transferred call appropriate technician assigned ticket filed issue sorted ticket answered field need supportedcomputer network operating system o include program record version linux microsoft windowsserver io alcatel xosaos designed installed maintained repaireddata communication link fiberoptic tactical fiberoptic cabling analyzedand evaluated system output designand manipulateddatabase information produce nonroutine reportsweekly aviation logistics specialist united state marine corp jacksonville nc deployed 26th meu deployed al assad worked buying team product ordered proactively minimize stock situation plan truckload stock transfer well order inventory maintain healthy product level evaluating buying report sale trend tracked managed adjustment 3pl hmi database reconcile change well investigate resolve discrepancy kept 3pl web portal updated change respond alert timely manner processed invoice 3pl ensure accurate timely resolution maintained regular proactive communication 3pl team participated buying meeting prepared question information skus need reviewed discussed based inventory analysis prepared analysis reporting overall statistic offered continuous improvement idea overall process needed used forklift microsoft office managed designated group packup kit aviation asset well group designated packup kit support aircraft squadron recommend approved asset stocking packup kit recommend consumable item inclusion commutated various customersrepresentatives via telephone email naval message rectify discrepancy ordered stocked required repairable consumables approved increase decrease loaded stock item record sir navy enterprise resource planning nerp database master record file mrf nalcomis database ensured picking ticket pulled delivered timely manner ensured complete order entered automated system determined problem may affectdelay material availability initiate corrective action conducted onload onboard offload inventory cycle count maintained local carcasstracking program accurately track account part material education bachelor bachelor science cybersecurity purdue university global west lafayette present associate associate degree diesel technology applied service management wyo techblairsville blairsville pa military service branch united state marine corp rank corporal certificationslicenses epa refrigerant recovery recycling certification core type present epa refrigerant recovery recycling certification present certified vsat installer basic vsat theory course introduction vsat frequency band satellite orbit vsat link terminology vsat latency rain fade sun outage solar transit event adaptive coding modulation acm linear polarization circular polarization decibel db dc voltage rf safety vsat glossary term tool equipment documentation hand tool cable software test equipment adaptor comms spare consumables ppe documentation checklist indoor equipment equipment rack ups scpc modem comtech paradise datacom tdma outdoor equipment low noise block lnb upconverter buc rf feed assembly antenna sat dish antenna offset antenna mount nonpenetrating mount rf coax ntype connector termination ftype connector termination power grounding stabilized autoaquire antenna stabilized antenna theory acu configuration sea tel antenna intellian spacetrack antenna remote site site survey arrival install location jha take work area dish alignment dish pointing elevation azimuth polarization remote commissioning compression point 1db point test cross polarization xpol voip data site documentation fault dish pointing dish movement low rx signal tx power problem slow data poor voice crosspol issue certified fiber optic technician certified premise cabling technician cpct\",\n \"cpa candidate strong financial accounting audit experience knowledge internal control enterprise risk management gl pl b reconciliation work paper cost cash control ap ar different accounting software participated coordination financial planning budget management function monitored analyzed operating result budget managed preparation official report actual revenue transfer expense financial outlook forecast collaborated department manager corporate staff develop business plan created guide financial control planning procedure exceptional communication interpersonal skill adept forming strong working relationship diverse internal external business partner account receivable payable payroll corporate expense analysis tax proficiency bookkeeping reporting journal entry account reconciliation entrusted process high responsibility task work independently demonstrated professionalism communicating department manager client supplier interacted wide variety personality developing business plan preparing report supervised role mapping workflow delegated task oversaw work coworkers enhanced leadership teamwork team coordination ability strong quantitative technical accounting skill independently driven accomplish immediate assigned goal long term company objective highlight analytical reasoning financial statement analysis strength regulatory reporting compliance testing knowledge understands foreign tax reporting budget forecasting expertise account reconciliation expert peoplesoft knowledge great plain familiarity complex problem solving excellent managerial technique strong organizational skill sec call reporting proficiency general ledger accounting expert customer relation superior research skill flexible team player advanced computer proficiency pc mac effective time management accomplishment formally recognized excellence achieved financial analysis budgeting forecasting experience volunteer accountant company name city state federal compliance review preparation corporation insurance partnership private foundation tax return coordinate fixed asset accountant necessary information correct tax depreciation calculation review tax depreciation calculation schedule accuracy analyze accrual account deductibility pertaining provision tax return assist completion tax footnote statement identify reportable transaction disclosure consolidated tax return prepare tax filing new entity dissolution liquidation assist audit request research implementation tax consequence participate implementation new provision fixed asset erp system accountant company name city state responsible various general accounting duty including account payable banking check request special project needed processed account payable including purchase order entry invoice approval entry follow vendor aging reporting processed check various credit assisted end close financial reporting performed reconciliation bank account including reconciliation deposit account receivable maintaining accounting record preparing account management information small business accountancy advising client business transaction merger acquisition corporate finance advising client area business improvement dealing insolvency detecting preventing fraud forensic accounting managing junior colleague accountant manager company name city state performed periodic budgeting modeling project cash requirement prepared financial regulatory report required law regulation addition opening office ajman sharjah prepared annual expense forecast including necessary recommended action required manage cost achieve budget executed account receivable reporting enhancement reconciliation procedure order integrate quickbooks accounting software vision software managed accounting operation accounting close account reporting reconciliation received recorded banked cash check voucher well reconciled record bank transaction developed online invoicing procedure several customer order streamline account receivable process reduced invoice turn performed complex general accounting function including preparation journal entry account analysis balance sheet reconciliation education master business administration accounting keller graduate school management city state master science accounting financial management keller graduate school management city state u certificate essential bookkeeping computerized accounting technology holding ny driving license type skill proficient microsoft office suite access quickbooks turbo tax vision accounting software peach tree dac easy sage peoplesoft advance microsoft excel\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"clean_jd\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 452,\n \"samples\": [\n \"design deliver solu bi sale partner mp expert sale academy program foundation continuous development program analyze day today need training sale team manage new solu bi sale partner mp orientation product training create training module solu bi sale partner mp stay date current market trend changing demand sale environment maintaining existing solu bi sale partner mp expert achieve target beyond target requirement bachelor degree human resource business administration marketing relevant field proven two year experience sale trainer similar role preferable ecommerce banking multi finance insurance mlm industry strong data excel formula hand experience elearning platform solid communication presentation ability ability design effective sale training program great interpersonal\",\n \"applicant position preferred experience finance accounting field breve tab experience using microsoft dynamic nav sap program self motivated personnel manage knowledge fast learner able work independently following qualification job summary responsible account transaction ensuring business target within area reached preparing documentation relating account payable account receivable tax bank account payable handle daily bookkeeping invoice payable bank payment voucher make sure ap balance correct prepare payment schedule based cash availability due date invoice communicate local vendor balance payable payment detail account receivable prepare bank receipt payment received fixed asset maintain fixed asset register update data regularly case correction disposal transfer asset tax calculate prepare tax payment tax article twenty three twenty six four two twenty five liaise tax officer external auditor bank prepare monthly bank reconciliation general accounting handle bookkeeping posting accrual depreciation entry amortization expense monthly basis others checking employee monthly claim handle petty cash transaction monitor cash advance ad hoc k task finance accounting manager requirement university graduate bachelor degree accounting major fresh graduate welcome 2 year experience finance accounting field breve tab preferred preferable experience using microsoft dynamic nav sap program strong skill microsoft office excel advance powerpoint word proficient english language important age maximum twenty seven year old\",\n \"benefit competitive salary medical dental vision insurance four hundred one k retirement saving plan life insurance tuition assistance wellness reimbursement travel insurance paid holiday vacation cybersecurity analyst role within information technology cybersecurity group support company cybersecurity service cybersecurity analyst protect confidentiality integrity availability central hudson information technical environment also support enterprise security goal objective responsibility perform security risk assessment system implementation project ensure proper security control configuration implemented testing effectiveness understand analyze existing network security architecture security best practice provide recommendation ensure alignment internal policy monitor analyze security alert including trend root cause analysis detect respond mitigate information security related vulnerability incident evaluate system specific vulnerability scan work various department remediate high risk item assist responding cybersecurity incident including investigating documenting incident according incident response plan coordinate external consultant security assessment including developing implementing action plan address finding perform duty required assigned may include risk compliance assignment qualification required associate degree computer information system computer science cybersecurity related field study least three year experience information cybersecurity technical support lieu degree least five year experience information cybersecurity technical support demonstrated understanding network topology architecture protocol addressing scheme across multiple platform knowledge demonstrated ability operate window based linux based security tool well developed written verbal communication presentation skill planning organizational skill proven interpersonal facilitation negotiation problem resolution skill must able work minimal supervision work well pressure must able adapt variety assignment preferred bachelor degree computer information system computer science information security information assurance management information system one following certification scism security caspcisspcsslporgiac experience following highly desirable network management understanding packet dump data parsing system log basic scripting language siem please go click search career opportunity button follow direction submit application upload resume desired position application sent via email u mail accepted phone call agency please reply held strict confidence qualified applicant receive consideration employment discriminated basis race color religion sex sexual orientation gender identity national origin age disability protected veteran status central hudson gas electric corporation take affirmative action support policy employ advance employment individual minority woman protected veteran individual disability v evra federal contractor\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"label\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 1,\n \"num_unique_values\": 2,\n \"samples\": [\n 0,\n 1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe", "variable_name": "df" }, "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", "
Unnamed: 0clean_cvclean_jdlabel
00result oriented organized bilingual accounting...minimum education requirement bachelor degree ...1
11result oriented organized bilingual accounting...hiring talented candidate join accounting team...1
22result oriented organized bilingual accounting...duty proficient working excel skilled working ...1
33result oriented organized bilingual accounting...job description responsible supervising checki...1
44result oriented organized bilingual accounting...qualification one bachelor degree finance acco...1
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " Unnamed: 0 clean_cv \\\n", "0 0 result oriented organized bilingual accounting... \n", "1 1 result oriented organized bilingual accounting... \n", "2 2 result oriented organized bilingual accounting... \n", "3 3 result oriented organized bilingual accounting... \n", "4 4 result oriented organized bilingual accounting... \n", "\n", " clean_jd label \n", "0 minimum education requirement bachelor degree ... 1 \n", "1 hiring talented candidate join accounting team... 1 \n", "2 duty proficient working excel skilled working ... 1 \n", "3 job description responsible supervising checki... 1 \n", "4 qualification one bachelor degree finance acco... 1 " ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.read_csv('/content/drive/MyDrive/Dataset/data_supervised.csv')\n", "df.head(5)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "bGhdTl7S1Acc", "outputId": "5f110515-7cee-420a-a21c-e974b3f383c3" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 31203 entries, 0 to 31202\n", "Data columns (total 3 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 clean_cv 31203 non-null object\n", " 1 clean_jd 31203 non-null object\n", " 2 label 31203 non-null int64 \n", "dtypes: int64(1), object(2)\n", "memory usage: 731.4+ KB\n" ] } ], "source": [ "df = df[['clean_cv', 'clean_jd', 'label']]\n", "df.info()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "yBbEtHkG4fMu" }, "outputs": [], "source": [ "from sklearn.model_selection import train_test_split\n", "\n", "train_df, test_df = train_test_split(df, test_size=0.2, random_state=42)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "pVg2-oj_BFMz", "outputId": "bc7be86e-5cfe-4dc3-8273-04e962aa3117" }, "outputs": [ { "data": { "text/plain": [ "label\n", "1 12552\n", "0 12410\n", "Name: count, dtype: int64" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train_df['label'].value_counts()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "yoR2vQI4BHcn", "outputId": "103a260a-1f3d-45f8-ad3c-ed2eedab33a4" }, "outputs": [ { "data": { "text/plain": [ "label\n", "1 3166\n", "0 3075\n", "Name: count, dtype: int64" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_df['label'].value_counts()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 787, "referenced_widgets": [ "356db8ff26b34fdea0bdd8e8852dcbe9", "b3411029c4b1466083a7f3ba965a8c73", "3d0c3f7371b14cdab83e73384107e04f", "bc9641640e6a4931a2584f1d9875db00", "0f0e2c160c4e49758c3b42b1c1bc3a26", "50666f92e3634b9ba6e9e420fb5fe66d", "dc6cab2f0e224d53b29f9f5e2917900b", "b72208c16019432187132f306152f299", "49d10b8b4a0c48dba19193745de94eea", "f68da510c4d64d759c1d7a15fbdc5d75", "e30af98c65c549cb957e641bb3469cf7" ] }, "id": "QvPQ__Xf1Y4F", "outputId": "da47af35-f762-453f-b183-8eb033c9e18a" }, "outputs": [ { "data": { "text/html": [ "\n", "
\n", " \n", " \n", " [1801/4683 59:50 < 1:35:52, 0.50 it/s, Epoch 1.15/3]\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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
StepTraining LossValidation LossSts-dev Pearson CosineSts-dev Spearman CosineSts-dev Pearson ManhattanSts-dev Spearman ManhattanSts-dev Pearson EuclideanSts-dev Spearman EuclideanSts-dev Pearson DotSts-dev Spearman DotSts-dev Pearson MaxSts-dev Spearman Max
1000.2389000.5027860.9266730.8578400.9146880.8597180.9164410.8599570.8737140.8502440.9266730.859957
2000.2196000.4568770.9279120.8584150.9112090.8600140.9121140.8597910.8774330.8511570.9279120.860014
3000.1971000.7114040.9180550.8535680.9111550.8566800.9134240.8577750.8672990.8465290.9180550.857775
4000.1968000.5746670.9218280.8558710.9124260.8582380.9139690.8587040.8711270.8494000.9218280.858704
5000.1618000.5615770.9245190.8562900.9100560.8570710.9115360.8569760.8749250.8495740.9245190.857071
6000.1848000.5009880.9248240.8575850.9151250.8572040.9166430.8575310.8761180.8514000.9248240.857585
7000.0797000.7396820.9184630.8533020.9080450.8549340.9100430.8555940.8684110.8464860.9184630.855594
8000.1540000.7757930.9101250.8520670.9050310.8539320.9085260.8558840.8582770.8459970.9101250.855884
9000.1324000.4350650.9299780.8592240.9204230.8603210.9222300.8602710.8783610.8530420.9299780.860321
10000.1284000.6645110.9173000.8541270.9095500.8546190.9139070.8566220.8737850.8495350.9173000.856622
11000.1323000.4204660.9294520.8581840.9150880.8594050.9169290.8595120.8848970.8531430.9294520.859512
12000.1654000.4649250.9301990.8581470.9203890.8590280.9239890.8600210.8829350.8522550.9301990.860021
13000.1780000.4081050.9317780.8593080.9166020.8595530.9205040.8605460.8854730.8549850.9317780.860546
14000.1084000.5985920.9238160.8545830.9115670.8558610.9147880.8576630.8734110.8495830.9238160.857663
15000.1542000.3121460.9380190.8618190.9188250.8619380.9203510.8619770.8878630.8579180.9380190.861977
16000.1601000.2668990.9364080.8617640.9179240.8618960.9206970.8625350.8949040.8594130.9364080.862535
17000.0553000.2621630.9370520.8611780.9187260.8615760.9201620.8616190.8917140.8583920.9370520.861619

\n", "

\n", " \n", " \n", " [391/391 01:26]\n", "
\n", " " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "356db8ff26b34fdea0bdd8e8852dcbe9", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Computing widget examples: 0%| | 0/1 [00:00