Added table of submissions by month

arxiv_productivity_covid.ipynb

@@ -2,31 +2,32 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Script to scrape arXiv to compute number of astro papers published each day\n",
     "# URL form is\n",
     "# https://arxiv.org/search/advanced?advanced=1&date-from_date=2019-03-16&date-to_date=2019-03-17&terms-0-operator=AND&terms-0-field=title&classification-physics=y&classification-physics_archives=astro-ph&classification-include_cross_list=include&date-year=&date-filter_by=date_range\n",
     "#\n",
-    "# Written by BMG 19 Mar 2020"
+    "# Written by BMG 19 Mar 2020\n",
+    "# Updated by MDJH Apr, Dec 2020"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Install required packages\n",
     "\n",
-    "#%pip install -r requirements.txt\n"
+    "#%pip install -r requirements.txt"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -37,7 +38,6 @@
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
     "from matplotlib.pyplot import figure\n",
-    "import matplotlib.dates as mdates\n",
     "\n",
     "\n",
     "def daterange(start_date, end_date):\n",
@@ -47,11 +47,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Using info from https://web.archive.org/web/20200319144443/https://hackersandslackers.com/scraping-urls-with-beautifulsoup/\n",
+    "# Using info from https://web.archive.org/web/20200319144443/ and https://hackersandslackers.com/scraping-urls-with-beautifulsoup/\n",
     "\n",
     "# Set headers to not trigger robot alert\n",
     "headers = requests.utils.default_headers()\n",
@@ -60,14 +60,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
    "metadata": {
     "scrolled": false
    },
    "outputs": [],
    "source": [
-    "# Loop through years\n",
+    "# Define empty dictionary for storage\n",
+    "submissions = {}\n",
     "\n",
+    "# Loop through years\n",
     "num2020 = np.array([])\n",
     "date2020 = np.array([])\n",
     "num2019 = np.array([])\n",
@@ -100,12 +102,16 @@
     "    date2020 = np.append(date2020,date2)\n",
     "    num2020 = np.append(num2020,num1)\n",
     "    date2019 = np.append(date2019,date4)\n",
-    "    num2019 = np.append(num2019,num2)\n"
+    "    num2019 = np.append(num2019,num2)\n",
+    "\n",
+    "# Store weekly submissions in dictionary (duplicate entries will just be overwritten)\n",
+    "    submissions.update({date2:num1})\n",
+    "    submissions.update({date4:num2})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -116,7 +122,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "metadata": {
     "scrolled": true
    },
@@ -129,17 +135,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "day2020 = [datetime.strptime(x, '%Y-%m-%d') for x in date2020]\n",
-    "day2019 = [datetime.strptime(x, '%Y-%m-%d') for x in date2019]\n"
+    "day2019 = [datetime.strptime(x, '%Y-%m-%d') for x in date2019]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -185,7 +191,40 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "# Calculate monthly submissions\n",
+    "yrs = ['2018-','2019-','2020-']\n",
+    "mths = ['{:02d}'.format(x) for x in list(range(1,13))]\n",
+    "months = [y+m for m in mths for y in yrs]\n",
+    "\n",
+    "subs = []\n",
+    "\n",
+    "for month in months:\n",
+    "    num = [int(value) for key, value in submissions.items() if month in key]\n",
+    "    total = np.sum(num, dtype=int)\n",
+    "\n",
+    "    subs.append(total)\n",
+    "\n",
+    "monthly_submissions = np.reshape(np.array(subs), (-1, len(yrs)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Display monthly submissions\n",
+    "yrs = [y.strip('-') for y in yrs]\n",
+    "row_format ='{:>10}' * (len(yrs) + 1)\n",
+    "\n",
+    "print('Submissions by month:')\n",
+    "print('')\n",
+    "print(row_format.format('', *yrs))\n",
+    "print(row_format.format('','====','====','===='))\n",
+    "for month, row in zip(mths, monthly_submissions):\n",
+    "    print(row_format.format(month, *row))"
+   ]
   },
   {
    "cell_type": "code",