{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from csv import DictReader" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# read in the input file and count by day\n", "input_file = open(\"hp_wiki.tsv\", 'r', encoding=\"utf-8\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "edits_by_day = {}\n", "for row in DictReader(input_file, delimiter=\"\\t\"):\n", " day_string = row['timestamp'][0:10]\n", "\n", " if day_string in edits_by_day:\n", " edits_by_day[day_string] = edits_by_day[day_string] + 1\n", " else:\n", " edits_by_day[day_string] = 1" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "input_file.close()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# output the counts by day\n", "output_file = open(\"hp_edits_by_day.tsv\", \"w\", encoding='utf-8')\n", "\n", "# write a header\n", "print(\"date\\tedits\", file=output_file)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# iterate through every day and print out data into the file\n", "for day_string in edits_by_day.keys():\n", " print(\"\\t\".join([day_string, str(edits_by_day[day_string])]), file=output_file)\n", "\n", "output_file.close()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 2 }