nets213-inclass-analysis.ipynb

nets213-inclass-analysis.ipynb

{
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "import csv\n",
        "\n",
        "with open('Batch_3517965_batch_results.csv', newline='') as csvfile:\n",
        "    reader = csv.reader(csvfile)\n",
        "    headers = next(reader)\n",
        "\n",
        "    data = []\n",
        "    for row in reader:\n",
        "        data.append(dict(zip(headers, row)))"
      ],
      "outputs": [],
      "execution_count": 9,
      "metadata": {
        "collapsed": false,
        "outputHidden": false,
        "inputHidden": false
      }
    },
    {
      "cell_type": "code",
      "source": [
        "def count_occurences(column_name):\n",
        "    labels = {}\n",
        "    for entry in data:\n",
        "        entry_label = entry[column_name]\n",
        "        if entry_label in labels:\n",
        "            labels[entry_label] += 1\n",
        "        else:\n",
        "            labels[entry_label] = 1\n",
        "    return labels\n",
        "\n\n",
        "def print_counts(counts):\n",
        "    print('\\n'.join(('{}: {}'.format(k, v) for k, v in sorted(counts.items(), key=lambda x: x[1], reverse=True))))"
      ],
      "outputs": [],
      "execution_count": 37,
      "metadata": {
        "collapsed": false,
        "outputHidden": false,
        "inputHidden": false
      }
    },
    {
      "cell_type": "code",
      "source": [
        "label_counts = count_occurences('Answer.sentiment.label')\n",
        "print_counts(label_counts)"
      ],
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Neutral: 393\n",
            "Negative: 267\n",
            "Positive: 241\n",
            "N/A: 106\n",
            "Extremely Negative: 78\n",
            "Extremely Positive: 16\n"
          ]
        }
      ],
      "execution_count": 38,
      "metadata": {
        "collapsed": false,
        "outputHidden": false,
        "inputHidden": false
      }
    },
    {
      "cell_type": "code",
      "source": [
        "worker_counts = count_occurences('WorkerId')\n",
        "print_counts(worker_counts)"
      ],
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "A20PV3RB3I0W8S: 207\n",
            "A2ZBYVQLDUZOV7: 202\n",
            "A252Z0ZJ7PF59Q: 199\n",
            "A34M93NJC830DP: 132\n",
            "A104V8NZIQFN2F: 127\n",
            "A3O1I9MATO3ZZN: 104\n",
            "A1DVKS3R9SLQ1H: 68\n",
            "A35ARURSRU6UAZ: 27\n",
            "A2HR7ZIX42FEPG: 26\n",
            "A1APYLD4DUK33J: 3\n",
            "AKSJ3C5O3V9RB: 2\n",
            "A3VXSCZ7NP7ZI2: 1\n",
            "A37WDOIQH6JM6V: 1\n",
            "A1506T1PAYRT16: 1\n",
            "A1FVXS8IM5QYO8: 1\n"
          ]
        }
      ],
      "execution_count": 39,
      "metadata": {
        "collapsed": false,
        "outputHidden": false,
        "inputHidden": false
      }
    },
    {
      "cell_type": "code",
      "source": [],
      "outputs": [],
      "execution_count": null,
      "metadata": {
        "collapsed": false,
        "outputHidden": false,
        "inputHidden": false
      }
    }
  ],
  "metadata": {
    "kernel_info": {
      "name": "python3"
    },
    "language_info": {
      "name": "python",
      "version": "3.7.1",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "kernelspec": {
      "name": "python3",
      "language": "python",
      "display_name": "Python 3"
    },
    "nteract": {
      "version": "0.12.3"
    },
    "gist_id": "3ca05a27a0c10421c906a5af69c46d0a"
  },
  "nbformat": 4,
  "nbformat_minor": 4
}