From c4ce7aba35b6eae8c9f63e46f04b316b9d44abf2 Mon Sep 17 00:00:00 2001
From: Scott Lowe <scott.code.lowe@gmail.com>
Date: Wed, 8 May 2024 23:29:17 +0100
Subject: [PATCH] JNB: More EDA and new output files

---
 notebooks/explore-depth-columns.ipynb | 80 ++++++++++++++++++++++++++-
 1 file changed, 79 insertions(+), 1 deletion(-)

diff --git a/notebooks/explore-depth-columns.ipynb b/notebooks/explore-depth-columns.ipynb
index 2f3c590..53305b9 100644
--- a/notebooks/explore-depth-columns.ipynb
+++ b/notebooks/explore-depth-columns.ipynb
@@ -30,13 +30,19 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "b6f9ebdb",
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "# Load datasets from this directory\n",
     "dirname = \"../query-outputs_2022-01-01\"\n",
+    "dirname = \"../query-outputs_2023-03-07_extras/\"\n",
+    "dirname = \"../query-outputs_2023-03-30c/\"\n",
+    "# dirname = \"../query-outputs_2023-03-30c\"\n",
     "# Pangaea benthic image dataset file with filtered dataset IDs\n",
     "pangaea_file = \"../full-dataset/pangaea_2022-01-24_filtered.csv\"\n",
+    "pangaea_file = \"../datasetcsvs/pangaea_2023-03-30c_with-tiles4.csv\"\n",
     "pangaea_df = pd.read_csv(pangaea_file)\n",
     "ds_ids = pangaea_df.dataset.unique()\n",
     "print(f\"Total {len(ds_ids)} datasets to process.\")"
@@ -186,6 +192,78 @@
     "    print(f\"{c:.<35s} {count:4d}\")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a251b7dd-673b-43c0-b948-bb83019aedb1",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "column_examples[\"sal\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "42a79516-2ab2-45ee-b876-daf12758ed00",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "column_examples[\"area\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "235276c3-d887-46b6-a453-2873a636533a",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "column_examples[\"length\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "897336e0-d260-46d4-a71b-7e882e785ce5",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "column_examples[\"classification\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0f159be9-f6dc-4d0f-ae6a-a781a9983cdf",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "column_examples[\"content\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8d804d2f-6adb-42f3-b164-68fe42a08b92",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "column_examples[\"ground vis\"]"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "a07b478a-bd3d-417f-8e88-f49ea585c812",