fix column names

Author: fedorov

notebooks/getting_started/part2_searching_basics.ipynb

@@ -29,12 +29,10 @@
         "\n",
         "In this notebook you will be introduced into how IDC organizes the metadata accompanying images available in IDC, and how that metadata can be used to define subsets of data.\n",
         "\n",
-        "This documentation page can be used as a complement if you would like to learn more about how IDC metadata is organized: https://learn.canceridc.dev/data/organization-of-data/files-and-metadata.\n",
-        "\n",
         "---\n",
         "Initial version: Nov 2022\n",
         "\n",
-        "Updated: Oct 2023\n"
+        "Updated:\n"
       ]
     },
     {
@@ -233,7 +231,7 @@
         "\n",
         "![portal_filters](https://www.dropbox.com/s/qt3dhzara1ap7s3/portal_filters.png?raw=1)\n",
         "\n",
-        "* \"Primary site location\" maps to the `tcia_tumorLocation` column\n",
+        "* \"Primary site location\" maps to the `collection_tumorLocation` column\n",
         "* \"Body Part Examined\" -> `BodyPartExamined`\n",
         "* \"Modality\" -> `Modality`\n",
         "\n"
@@ -245,7 +243,7 @@
         "id": "3kkHUgqaP2tl"
       },
       "source": [
-        "### Exercise 1: Write the query to list all values for `tcia_tumorLocation`\n",
+        "### Exercise 1: Write the query to list all values for `collection_tumorLocation`\n",
         "\n",
         "In the cell below, we pre-filled the code by copying the previous cell. All you need to do is write the query!\n",
         "\n",
@@ -308,8 +306,8 @@
         "SELECT\n",
         "  collection_id,\n",
         "  STRING_AGG(DISTINCT(Modality)) as modalities,\n",
-        "  STRING_AGG(DISTINCT(tcia_tumorLocation)) as tumor_locations,\n",
-        "  STRING_AGG(DISTINCT(tcia_species)) as species\n",
+        "  STRING_AGG(DISTINCT(collection_tumorLocation)) as tumor_locations,\n",
+        "  STRING_AGG(DISTINCT(collection_species)) as species\n",
         "FROM\n",
         "  bigquery-public-data.idc_current.dicom_all\n",
         "GROUP BY\n",
@@ -371,7 +369,7 @@
         "WHERE\n",
         "  # write the selection criteria under this line!\n",
         "  # Use AND operator to combine the filter values for the\n",
-        "  # Modality and tcia_tumorLocation to select collections that\n",
+        "  # Modality and collection_tumorLocation to select collections that\n",
         "  # include MR images for Lung cancer locations\n",
         "  # Note that SQL uses single = for comparison, and strings should\n",
         "  # be enclosed in \"\"\n",
@@ -467,8 +465,8 @@
         "SELECT\n",
         "  collection_id,\n",
         "  STRING_AGG(DISTINCT(Modality)) as modalities,\n",
-        "  STRING_AGG(DISTINCT(tcia_tumorLocation)) as tumor_locations,\n",
-        "  STRING_AGG(DISTINCT(tcia_species)) as species\n",
+        "  STRING_AGG(DISTINCT(collection_tumorLocation)) as tumor_locations,\n",
+        "  STRING_AGG(DISTINCT(collection_species)) as species\n",
         "  # count number of distinct patients\n",
         "  # count number of distinct studies\n",
         "  # count number of distinct series\n",
@@ -521,7 +519,7 @@
         "FROM\n",
         "  bigquery-public-data.idc_current.dicom_all\n",
         "WHERE\n",
-        "  Modality = \"MR\" AND tcia_tumorLocation = \"Liver\"\n",
+        "  Modality = \"MR\" AND collection_tumorLocation = \"Liver\"\n",
         "\n",
         "# note the use of this new operator that makes the query\n",
         "# return just the first one of the matching rows\n",
@@ -577,7 +575,7 @@
         "  SELECT\n",
         "    StudyInstanceUID,\n",
         "    STRING_AGG(DISTINCT(collection_id)) AS collection_id,\n",
-        "    STRING_AGG(DISTINCT(tcia_tumorLocation)) AS tcia_tumorLocation,\n",
+        "    STRING_AGG(DISTINCT(collection_tumorLocation)) AS collection_tumorLocation,\n",
         "    ARRAY_AGG(DISTINCT(Modality)) AS modalities\n",
         "  FROM\n",
         "    bigquery-public-data.idc_current.dicom_all\n",
@@ -592,7 +590,7 @@
         "WHERE\n",
         "  \"CT\" IN UNNEST(modalities)\n",
         "  AND \"SEG\" IN UNNEST(modalities)\n",
-        "  AND tcia_tumorLocation = \"Lung\"\n",
+        "  AND collection_tumorLocation = \"Lung\"\n",
         "LIMIT\n",
         "  1\n",
         "\"\"\"\n",