Add get charts function (#542)

* Add get charts function * code refactoring * solve linting * Add cookbook
run-llama · Dec 9, 2024 · 4740d06 · 4740d06
1 parent 3651a10
commit 4740d06
Show file tree

Hide file tree

Showing 5 changed files with 700 additions and 480 deletions.
diff --git a/examples/demo_get_charts.ipynb b/examples/demo_get_charts.ipynb
diff --git a/examples/demo_json_tour.ipynb b/examples/demo_json_tour.ipynb
@@ -37,7 +37,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "0879301c-ff91-4431-941a-6c0ef7cd8fe2",
    "metadata": {},
    "outputs": [],
@@ -65,7 +65,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "c39d408f-e885-4940-85c7-b09ca3bc7cb7",
    "metadata": {},
    "outputs": [
@@ -112,7 +112,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "9c9cd670-8229-4ad6-99a9-845bd82b7ec1",
    "metadata": {},
    "outputs": [
@@ -141,7 +141,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "c588c578",
    "metadata": {},
    "outputs": [
@@ -169,7 +169,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "f8845fac",
    "metadata": {},
    "outputs": [
@@ -206,7 +206,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "6eca0253",
    "metadata": {},
    "outputs": [
@@ -234,7 +234,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "id": "c0354ba7",
    "metadata": {},
    "outputs": [
@@ -287,7 +287,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "id": "d236a255",
    "metadata": {},
    "outputs": [
@@ -318,7 +318,7 @@
     }
    ],
    "source": [
-    "print(pages[0]['text'])"
+    "print(pages[0][\"text\"])"
    ]
   },
   {
@@ -339,7 +339,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "id": "63d2df6f",
    "metadata": {},
    "outputs": [
@@ -375,7 +375,7 @@
     }
    ],
    "source": [
-    "print(pages[0]['md'])"
+    "print(pages[0][\"md\"])"
    ]
   },
   {
@@ -429,7 +429,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": null,
    "id": "0975cbc4",
    "metadata": {},
    "outputs": [
@@ -450,8 +450,8 @@
     }
    ],
    "source": [
-    "image_data = pages[0]['images'][0].copy()\n",
-    "del image_data['ocr']\n",
+    "image_data = pages[0][\"images\"][0].copy()\n",
+    "del image_data[\"ocr\"]\n",
     "print(json.dumps(image_data, indent=2))"
    ]
   },
@@ -465,7 +465,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": null,
    "id": "908e1cfd",
    "metadata": {},
    "outputs": [
@@ -482,12 +482,12 @@
    "source": [
     "# Make a copy of json_objs with only the first page to avoid downloading all the images\n",
     "first_page_json = json_objs.copy()\n",
-    "first_page_json[0]['pages'] = [first_page_json[0]['pages'][0]]  # Keep only first page\n",
+    "first_page_json[0][\"pages\"] = [first_page_json[0][\"pages\"][0]]  # Keep only first page\n",
     "\n",
     "# get the SDK to download all the images to a local directory for us\n",
     "images = parser.get_images(first_page_json, download_path=\"./json_tour_screenshots\")\n",
     "\n",
-    "print(images[0]['path'])"
+    "print(images[0][\"path\"])"
    ]
   },
   {
@@ -508,7 +508,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": null,
    "id": "b8daf90d",
    "metadata": {},
    "outputs": [
@@ -618,7 +618,7 @@
     }
    ],
    "source": [
-    "print(json.dumps(pages[0]['images'][0]['ocr'],indent=2))"
+    "print(json.dumps(pages[0][\"images\"][0][\"ocr\"], indent=2))"
    ]
   },
   {
@@ -641,7 +641,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": null,
    "id": "c10b9d7d",
    "metadata": {},
    "outputs": [
@@ -782,7 +782,7 @@
     }
    ],
    "source": [
-    "print(json.dumps(pages[0]['items'],indent=2))"
+    "print(json.dumps(pages[0][\"items\"], indent=2))"
    ]
   },
   {
@@ -807,7 +807,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": null,
    "id": "7d6404a5",
    "metadata": {},
    "outputs": [
@@ -857,7 +857,7 @@
     }
    ],
    "source": [
-    "print(json.dumps(pages[34]['items'][2],indent=2))"
+    "print(json.dumps(pages[34][\"items\"][2], indent=2))"
    ]
   },
   {
@@ -872,7 +872,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": null,
    "id": "fb0da11a",
    "metadata": {},
    "outputs": [
@@ -909,7 +909,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": null,
    "id": "e7e393e6",
    "metadata": {},
    "outputs": [
@@ -945,7 +945,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": null,
    "id": "29bf7e3c",
    "metadata": {},
    "outputs": [
@@ -967,8 +967,8 @@
     }
    ],
    "source": [
-    "link_page = link_parsed[0]['pages'][0]\n",
-    "print(json.dumps(link_page['links'],indent=2))"
+    "link_page = link_parsed[0][\"pages\"][0]\n",
+    "print(json.dumps(link_page[\"links\"], indent=2))"
    ]
   },
   {
@@ -995,8 +995,7 @@
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "pygments_lexer": "ipython3"
   }
  },
  "nbformat": 4,