changes to add ss_id and pmid to all new items and avoid duplicate bi…

…bkeys
DIAGNijmegen · Nov 30, 2023 · 69b1565 · 69b1565
1 parent d2db236
commit 69b1565
Show file tree

Hide file tree

Showing 8 changed files with 5,310 additions and 2,725 deletions.
diff --git a/diag.bib b/diag.bib
diff --git a/diag_orig_and_ss_merged.bib b/diag_orig_and_ss_merged.bib
diff --git a/scripts/MergeChanges.ipynb b/scripts/MergeChanges.ipynb
@@ -2,19 +2,22 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 15,
+   "id": "f92463da",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "sys.path.append('C:/Users/keeli/nov23/repos/Literature')\n",
+    "sys.path.append('C:/Users/keeli/nov23/repos/Literature/scripts')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
    "id": "d377a755",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "C:\\Users\\keeli\\anaconda3\\envs\\lit-env\\lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import pandas as pd\n",
     "import os\n",
@@ -24,7 +27,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 17,
    "id": "f6cf2984",
    "metadata": {},
    "outputs": [],
@@ -66,7 +69,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 18,
    "id": "5b5596e1",
    "metadata": {},
    "outputs": [],
@@ -83,7 +86,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 19,
    "id": "98489bba",
    "metadata": {},
    "outputs": [],
@@ -93,7 +96,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 20,
    "id": "2374dcc9",
    "metadata": {},
    "outputs": [],
@@ -103,7 +106,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 21,
    "id": "f38e2c4c",
    "metadata": {},
    "outputs": [],
@@ -117,7 +120,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 22,
    "id": "366debbe",
    "metadata": {},
    "outputs": [
@@ -127,7 +130,7 @@
        "\"KM: I propose that the updated bib file is the one we will keep and we only need to check if it misses anything that is in the original\\nfor entry in diag_bib_raw:\\n    if entry.type == 'string':\\n        continue\\n    bibkey = entry.key\\n    if bibkey in new_bibkeys:\\n        corresponding_entry = get_entry(updated_bib_raw, bibkey)\\n        if 'all_ss_ids' in corresponding_entry.fields:\\n            entry.fields['all_ss_ids'] = corresponding_entry.fields['all_ss_ids']\\n        if 'pmid' in corresponding_entry.fields:\\n            entry.fields['pmid'] = corresponding_entry.fields['pmid']\\n\""
       ]
      },
-     "execution_count": 8,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -150,15 +153,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 23,
    "id": "550580b1",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'Brou23', 'Twil23c', 'Hump23', 'Anto23a', 'Aswo23', 'Hend23b'}\n"
+      "{'Brou23', 'Hend23b', 'Hump23', 'Aswo23', 'Twil23c', 'Anto23a'}\n"
      ]
     }
    ],
@@ -169,7 +172,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 24,
    "id": "21522e57",
    "metadata": {},
    "outputs": [],
@@ -180,7 +183,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 25,
    "id": "3c023620",
    "metadata": {},
    "outputs": [],
@@ -190,7 +193,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 26,
    "id": "82d6aeeb",
    "metadata": {},
    "outputs": [
@@ -217,7 +220,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 27,
    "id": "6224df11",
    "metadata": {},
    "outputs": [],
@@ -227,7 +230,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 28,
    "id": "cf941ddf",
    "metadata": {},
    "outputs": [],
@@ -243,6 +246,14 @@
    "metadata": {},
    "outputs": [],
    "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ccdc05fc",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {