From 7df06cae4e7d76265d0f6d26dec6a6c2c00d766f Mon Sep 17 00:00:00 2001
From: Gabe <33893811+Gabefire@users.noreply.github.com>
Date: Thu, 7 Mar 2024 13:53:27 -0600
Subject: [PATCH] [SN-73/98] Added workflow status filter to export_data
 notebook for projects (#1461)

---
 examples/exports/export_data.ipynb | 29 ++++++++++++++++++++++++-----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/examples/exports/export_data.ipynb b/examples/exports/export_data.ipynb
index d26cedacf..602a160e9 100644
--- a/examples/exports/export_data.ipynb
+++ b/examples/exports/export_data.ipynb
@@ -98,6 +98,7 @@
         "- `label_created_at`\n",
         "- `data_row_ids`\n",
         "- `batch_ids`\n",
+        "- `workflow_status`\n",
         "\n",
         "#### Filter details\n",
         "You can set the range for `last_activity_at` and `label_created_at` in the following formats: \n",
@@ -109,9 +110,16 @@
         "\n",
         "The `last_activity_at` filter captures the creation and modification of labels, metadata, workflow status, comments, and reviews.\n",
         "\n",
-        "If you wish to specify data rows to export, uncomment the `data_row_ids` filter and provide a list of applicable IDs. The data rows must be part of a batch attached to the project in question. You can provide up to 2,000 data row IDs.\n",
+        "If you wish to specify data rows to export, uncomment the `data_row_ids` or `global_keys` filter and provide a list of applicable IDs. The data rows must be part of a batch attached to the project in question. You can provide up to 2,000 data row IDs.\n",
         "\n",
-        "The `batch_ids` filter allows you to specify data rows for export based on their associated batch ID. This is particularly useful when `data_row_ids` is not sufficient due to 2,000 data row IDs limit. "
+        "The `batch_ids` filter allows you to specify data rows for export based on their associated batch ID. This is particularly useful when `data_row_ids` is not sufficient due to 2,000 data row IDs limit. \n",
+        "\n",
+        "\n",
+        "The `workflow_status` filter allows you to specify data rows in a given work flow step. This filter only accepts one value. For example, `filters = {\"workflow_status\": \"InReview\"}`. The filer accepts the following:\n",
+        "- `ToLabel`\n",
+        "- `InReview`\n",
+        "- `InRework`\n",
+        "- `Done`\n"
       ],
       "cell_type": "markdown"
     },
@@ -151,8 +159,10 @@
         "filters= {\n",
         "  \"last_activity_at\": [\"2000-01-01 00:00:00\", \"2050-01-01 00:00:00\"],\n",
         "  \"label_created_at\": [\"2000-01-01 00:00:00\", \"2050-01-01 00:00:00\"],\n",
+        "  # \"global_keys\": [\"<global_key>\", \"<global_key>\"],\n",
         "  # \"data_row_ids\": [\"<data_row_id>\", \"<data_row_id>\"],\n",
         "  # \"batch_ids\": [\"<batch_id>\", \"<batch_id>\"],\n",
+        "  # \"workflow_status\": \"<workflow_status>\"\n",
         "}\n",
         "\n",
         "export_task = project.export_v2(params=export_params, filters=filters)\n",
@@ -195,8 +205,10 @@
         "filters= {\n",
         "  \"last_activity_at\": [\"2000-01-01 00:00:00\", \"2050-01-01 00:00:00\"],\n",
         "  \"label_created_at\": [\"2000-01-01 00:00:00\", \"2050-01-01 00:00:00\"],\n",
+        "  # \"global_keys\": [\"<global_key>\", \"<global_key>\"],\n",
         "  # \"data_row_ids\": [\"<data_row_id>\", \"<data_row_id>\"],\n",
         "  # \"batch_ids\": [\"<batch_id>\", \"<batch_id>\"],\n",
+        "  # \"workflow_status\": \"<workflow_status>\"\n",
         "}\n",
         "\n",
         "client.enable_experimental = True\n",
@@ -284,10 +296,11 @@
         "    - Accepts a list of model run IDs. If provided, the labels and predicitions created _in these model runs_ will be included. \n",
         "\n",
         "### Filters\n",
-        "When you export data rows from a project, you can specify the included data rows with the following filters:\n",
+        "When you export data rows from a dataset, you can specify the included data rows with the following filters:\n",
         "- `last_activity_at`\n",
         "- `label_created_at`\n",
         "- `data_row_ids`\n",
+        "- `global_keys`\n",
         "\n",
         "See the _Export data rows from a project_ section above for additional details on each filter. "
       ],
@@ -329,7 +342,10 @@
         "\n",
         "# Note: Filters follow AND logic, so typically using one filter is sufficient.\n",
         "filters= {\n",
-        "  \"last_activity_at\": [\"2000-01-01 00:00:00\", \"2050-01-01 00:00:00\"]\n",
+        "  \"last_activity_at\": [\"2000-01-01 00:00:00\", \"2050-01-01 00:00:00\"],\n",
+        "  \"label_created_at\": [\"2000-01-01 00:00:00\", \"2050-01-01 00:00:00\"],\n",
+        "  # \"global_keys\": [\"<global_key>\", \"<global_key>\"],\n",
+        "  # \"data_row_ids\": [\"<data_row_id>\", \"<data_row_id>\"],\n",
         "}\n",
         "\n",
         "export_task = dataset.export_v2(params=export_params, filters=filters)\n",
@@ -372,7 +388,10 @@
         "\n",
         "# Note: Filters follow AND logic, so typically using one filter is sufficient.\n",
         "filters= {\n",
-        "  \"last_activity_at\": [\"2000-01-01 00:00:00\", \"2050-01-01 00:00:00\"]\n",
+        "  \"last_activity_at\": [\"2000-01-01 00:00:00\", \"2050-01-01 00:00:00\"],\n",
+        "  \"label_created_at\": [\"2000-01-01 00:00:00\", \"2050-01-01 00:00:00\"],\n",
+        "  # \"global_keys\": [\"<global_key>\", \"<global_key>\"],\n",
+        "  # \"data_row_ids\": [\"<data_row_id>\", \"<data_row_id>\"],\n",
         "}\n",
         "\n",
         "client.enable_experimental = True\n",