projects.mako.cc - harrypotter-wikipedia-cdsw/blob - harrypotter_edit_trend.ipynb

   1 {
   2  "cells": [
   3   {
   4    "cell_type": "code",
   5    "execution_count": null,
   6    "metadata": {},
   7    "outputs": [],
   8    "source": [
   9     "from csv import DictReader"
  10    ]
  11   },
  12   {
  13    "cell_type": "code",
  14    "execution_count": null,
  15    "metadata": {},
  16    "outputs": [],
  17    "source": [
  18     "# read in the input file and count by day\n",
  19     "input_file = open(\"hp_wiki.tsv\", 'r', encoding=\"utf-8\")"
  20    ]
  21   },
  22   {
  23    "cell_type": "code",
  24    "execution_count": null,
  25    "metadata": {},
  26    "outputs": [],
  27    "source": [
  28     "edits_by_day = {}\n",
  29     "for row in DictReader(input_file, delimiter=\"\\t\"):\n",
  30     "    day_string = row['timestamp'][0:10]\n",
  31     "\n",
  32     "    if day_string in edits_by_day:\n",
  33     "        edits_by_day[day_string] = edits_by_day[day_string] + 1\n",
  34     "    else:\n",
  35     "        edits_by_day[day_string] = 1"
  36    ]
  37   },
  38   {
  39    "cell_type": "code",
  40    "execution_count": null,
  41    "metadata": {},
  42    "outputs": [],
  43    "source": [
  44     "input_file.close()"
  45    ]
  46   },
  47   {
  48    "cell_type": "code",
  49    "execution_count": null,
  50    "metadata": {},
  51    "outputs": [],
  52    "source": [
  53     "# output the counts by day\n",
  54     "output_file = open(\"hp_edits_by_day.tsv\", \"w\", encoding='utf-8')\n",
  55     "\n",
  56     "# write a header\n",
  57     "print(\"date\\tedits\", file=output_file)"
  58    ]
  59   },
  60   {
  61    "cell_type": "code",
  62    "execution_count": null,
  63    "metadata": {},
  64    "outputs": [],
  65    "source": [
  66     "# iterate through every day and print out data into the file\n",
  67     "for day_string in edits_by_day:\n",
  68     "    print(\"\\t\".join([day_string, str(edits_by_day[day_string])]), file=output_file)\n",
  69     "\n",
  70     "output_file.close()"
  71    ]
  72   },
  73   {
  74    "cell_type": "code",
  75    "execution_count": null,
  76    "metadata": {},
  77    "outputs": [],
  78    "source": []
  79   }
  80  ],
  81  "metadata": {
  82   "kernelspec": {
  83    "display_name": "Python 3",
  84    "language": "python",
  85    "name": "python3"
  86   },
  87   "language_info": {
  88    "codemirror_mode": {
  89     "name": "ipython",
  90     "version": 3
  91    },
  92    "file_extension": ".py",
  93    "mimetype": "text/x-python",
  94    "name": "python",
  95    "nbconvert_exporter": "python",
  96    "pygments_lexer": "ipython3",
  97    "version": "3.7.3"
  98   }
  99  },
 100  "nbformat": 4,
 101  "nbformat_minor": 2
 102 }