Updated Firestore with new mapping (#807)

probml · May 5, 2022 · 324c860 · 324c860
1 parent 6ca3df4
commit 324c860
Show file tree

Hide file tree

Showing 7 changed files with 4,892 additions and 22 deletions.
diff --git a/misc/data_upload_firestore.ipynb b/misc/data_upload_firestore.ipynb
diff --git a/misc/database_backup_book1_old_urls.csv b/misc/database_backup_book1_old_urls.csv
diff --git a/misc/database_backup_book1_old_urls.json b/misc/database_backup_book1_old_urls.json
diff --git a/misc/figures_url_mapping_book1_backward_compatibility.csv b/misc/figures_url_mapping_book1_backward_compatibility.csv
diff --git a/misc/firestore_old_figures_data.ipynb b/misc/firestore_old_figures_data.ipynb
diff --git a/misc/mapping_figures_to_urls.ipynb b/misc/mapping_figures_to_urls.ipynb
@@ -2,28 +2,21 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "4b8112f4",
+   "id": "7275d268",
    "metadata": {},
    "source": [
-    "This script is takes, \n",
-    "\n",
-    "input: \"pml1.lof\" file which contains latex souce code of captions of figures\n",
-    "\n",
-    "output:mapping of fig_no to original_url "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "9727fce2",
-   "metadata": {},
-   "source": [
-    "## From Latex"
+    "This notebook is doing following steps:\n",
+    "1. Take input as \"pml1.lof\" and create mapping of fig_no to urls. \n",
+    "2. Create dummy notebook for figure which has multiple notebooks. Add caption (after preprocessing it) of such figure to this dummy notebooks which contains pointer to original notebooks of subfigures.\n",
+    "3. Again create mappig of fig_no to url but this time every fig_no has only one url\n",
+    "4. Check dead_urls \n",
+    "5. Firestore experiments: raw code to upload this urls in firestore"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
-   "id": "183398eb",
+   "execution_count": 1,
+   "id": "e6c8e9d9",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -40,6 +33,14 @@
     "    from probml_utils.url_utils import check_dead_urls, is_dead_url, github_url_to_colab_url"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "9727fce2",
+   "metadata": {},
+   "source": [
+    "## From Latex .lof"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 12,
@@ -2406,7 +2407,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 1,
    "id": "96922143",
    "metadata": {},
    "outputs": [],
@@ -2416,20 +2417,35 @@
     "except ModuleNotFoundError:\n",
     "    %pip install firebase_admin\n",
     "    from firebase_admin import credentials, firestore, initialize_app\n",
-    "from IPython.display import clear_output"
+    "from IPython.display import clear_output\n",
+    "\n",
+    "import json\n",
+    "import os"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 2,
    "id": "4f67d736",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<google.cloud.firestore_v1.client.Client at 0x7fcef41cac40>"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "key_path = \"../../key.json\"\n",
+    "key_path = \"../../key_probml_gcp.json\"\n",
     "cred = credentials.Certificate(key_path)\n",
     "default_app = initialize_app(cred)\n",
-    "db = firestore.client()"
+    "db = firestore.client()\n",
+    "db"
    ]
   },
   {

diff --git a/misc/non_figures_url_mapping_book1_backward_compatibility.csv b/misc/non_figures_url_mapping_book1_backward_compatibility.csv