From 6a1ba25445b00b7f7353cd8dd1006cbac8f81dfb Mon Sep 17 00:00:00 2001
From: Lalith Sagar Devagudi <lalithsagardevagudi@gmail.com>
Date: Tue, 30 Apr 2024 06:38:07 +0200
Subject: [PATCH] Add labeled data and fix broken links

---
 .../get_useful_sample_data.ipynb              | 43 +++++++++++++++++--
 .../get_useful_sample_data.md                 | 31 +++++++++++--
 2 files changed, 68 insertions(+), 6 deletions(-)

diff --git a/docs/hr/content/docs/reusable_snippets/get_useful_sample_data.ipynb b/docs/hr/content/docs/reusable_snippets/get_useful_sample_data.ipynb
index fc5777790f..f70c00c3b8 100644
--- a/docs/hr/content/docs/reusable_snippets/get_useful_sample_data.ipynb
+++ b/docs/hr/content/docs/reusable_snippets/get_useful_sample_data.ipynb
@@ -62,7 +62,7 @@
    "outputs": [],
    "source": [
     "# <tab: Image>\n",
-    "!curl -O s3://superduperdb-public-demo/images.zip && unzip images.zip\n",
+    "!curl -O https://superduperdb-public-demo.s3.amazonaws.com/images.zip && unzip images.zip\n",
     "import os\n",
     "from PIL import Image\n",
     "\n",
@@ -82,7 +82,7 @@
    "outputs": [],
    "source": [
     "# <tab: Video>\n",
-    "!curl -O s3://superduperdb-public-demo/videos.zip && unzip videos.zip\n",
+    "!curl -O https://superduperdb-public-demo.s3.amazonaws.com/videos.zip && unzip videos.zip\n",
     "import os\n",
     "\n",
     "data = [f'videos/{x}' for x in os.listdir('./videos')]\n",
@@ -100,13 +100,50 @@
    "outputs": [],
    "source": [
     "# <tab: Audio>\n",
-    "!curl -O s3://superduperdb-public-demo/audio.zip && unzip audio.zip\n",
+    "!curl -O https://superduperdb-public-demo.s3.amazonaws.com/audio.zip && unzip audio.zip\n",
     "import os\n",
     "\n",
     "data = [f'audios/{x}' for x in os.listdir('./audios')]\n",
     "sample_datapoint = data[-1]\n",
     "chunked_model_datatype = dtype('str')"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ce66da2f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# <tab: Text (Labeled)>\n",
+    "!curl -O https://superduperdb-public-demo.s3.amazonaws.com/text_labeled.json\n",
+    "import json\n",
+    "\n",
+    "with open(\"text_labeled.json\", \"r\") as f:\n",
+    "    data = json.load(f)\n",
+    "\n",
+    "sample_datapoint = data[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9740f757",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# <tab: Image (Labeled)>\n",
+    "!curl -O https://superduperdb-public-demo.s3.amazonaws.com/images_labeled.zip && unzip images_labeled.zip\n",
+    "import json\n",
+    "from PIL import Image\n",
+    "\n",
+    "with open('images_labeled/images_labeled.json', 'r') as f:\n",
+    "    data = json.load(f)\n",
+    "\n",
+    "data = [{'x': Image.open(d['image_path']), 'y': d['label']} for d in data]\n",
+    "\n",
+    "sample_datapoint = data[0]"
+   ]
   }
  ],
  "metadata": {
diff --git a/docs/hr/content/docs/reusable_snippets/get_useful_sample_data.md b/docs/hr/content/docs/reusable_snippets/get_useful_sample_data.md
index 2a9fd14efa..e42d5f265e 100644
--- a/docs/hr/content/docs/reusable_snippets/get_useful_sample_data.md
+++ b/docs/hr/content/docs/reusable_snippets/get_useful_sample_data.md
@@ -39,7 +39,7 @@ from superduperdb import dtype
     </TabItem>
     <TabItem value="Image" label="Image" default>
         ```python
-        !curl -O s3://superduperdb-public-demo/images.zip && unzip images.zip
+        !curl -O https://superduperdb-public-demo.s3.amazonaws.com/images.zip && unzip images.zip        
         import os
         from PIL import Image
         
@@ -53,7 +53,7 @@ from superduperdb import dtype
     </TabItem>
     <TabItem value="Video" label="Video" default>
         ```python
-        !curl -O s3://superduperdb-public-demo/videos.zip && unzip videos.zip
+        !curl -O https://superduperdb-public-demo.s3.amazonaws.com/videos.zip && unzip videos.zip
         import os
         
         data = [f'videos/{x}' for x in os.listdir('./videos')]
@@ -65,7 +65,7 @@ from superduperdb import dtype
     </TabItem>
     <TabItem value="Audio" label="Audio" default>
         ```python
-        !curl -O s3://superduperdb-public-demo/audio.zip && unzip audio.zip
+        !curl -O https://superduperdb-public-demo.s3.amazonaws.com/audio.zip && unzip audio.zip
         import os
         
         data = [f'audios/{x}' for x in os.listdir('./audios')]
@@ -73,4 +73,29 @@ from superduperdb import dtype
         chunked_model_datatype = dtype('str')        
         ```
     </TabItem>
+    <TabItem value="Text (Labeled)" label="Text (Labeled)" default>
+        ```python
+        !curl -O https://superduperdb-public-demo.s3.amazonaws.com/text_labeled.json
+        import json
+
+        with open("text_labeled.json", "r") as f:
+            data = json.load(f)
+
+        sample_datapoint = data[0]
+        ```
+    </TabItem>
+    <TabItem value="Image (Labeled)" label="Image (Labeled)" default>
+        ```python
+        !curl -O https://superduperdb-public-demo.s3.amazonaws.com/images_labeled.zip && unzip images_labeled.zip
+        import json
+        from PIL import Image
+
+        with open('images_labeled/images_labeled.json', 'r') as f:
+            data = json.load(f)
+
+        data = [{'x': Image.open(d['image_path']), 'y': d['label']} for d in data]
+
+        sample_datapoint = data[0]
+        ```
+    </TabItem>
 </Tabs>