update meta

murthylab · Aug 14, 2023 · ca27697 · ca27697
1 parent eac7cc8
commit ca27697
Show file tree

Hide file tree

Showing 5 changed files with 37,835 additions and 16,137 deletions.
diff --git a/src/configuration.py b/src/configuration.py
@@ -15,7 +15,10 @@
 COMPRESSED_TAR_FILE_FORMAT_AND_COMMAND = "compressed TAR archive (.tar.gz)", "tar -xvf"
 # take care of various working directories (tests, local app, cloud app, update scripts)
 APP_ROOT = os.getenv("APP_HOME", "codex").replace("/", "")
-DOWNLOADABLE_FILES_METADATA_FILE = f"{os.getcwd().split(APP_ROOT)[0]}/{APP_ROOT}/src/data/downloadable_files_metadata.json"
+APP_ROOT_PATH = f"{os.getcwd().split(APP_ROOT)[0]}/{APP_ROOT}"
+DOWNLOADABLE_FILES_METADATA_FILE = (
+    f"{APP_ROOT_PATH}/src/data/downloadable_files_metadata.json"
+)
 DOWNLOADABLE_CSV_TITLES_AND_DESCRIPTIONS = {
     "neurons": "Cell name, group and NT type predictions. "
     "For every cell in the dataset, specifies auto-generated name and group (based on primary input and output "
@@ -94,7 +97,7 @@
 
 
 def load_json_file(name):
-    fname = f"{os.getcwd().split(APP_ROOT)[0]}/{APP_ROOT}/src/data/{name}.json"
+    fname = f"{APP_ROOT_PATH}/src/data/{name}.json"
     with open(fname) as f:
         return json.load(f)
 

diff --git a/src/data/downloadable_files_metadata.json b/src/data/downloadable_files_metadata.json
@@ -7,7 +7,7 @@
       "morphology_clusters.csv.gz": 736744,
       "connectivity_clusters.csv.gz": 522912,
       "connections.csv.gz": 26124953,
-      "labels.csv.gz": 3707310,
+      "labels.csv.gz": 3710381,
       "coordinates.csv.gz": 4584155,
       "connectivity_tags.csv.gz": 653687,
       "neuropil_synapse_table.csv.gz": 4490002
@@ -84,17 +84,17 @@
         "col 5 - nt_type": "6 unique values"
       },
       "labels.csv.gz": {
-        "# rows": "129,398 (+ header)",
+        "# rows": "129,492 (+ header)",
         "# columns": "9",
-        "col 1 - root_id": "93,772 unique values",
-        "col 2 - label": "6,731 unique values",
+        "col 1 - root_id": "93,822 unique values",
+        "col 2 - label": "6,734 unique values",
         "col 3 - user_id": "143 unique values",
-        "col 4 - position": "108,325 unique values",
-        "col 5 - supervoxel_id": "107,555 unique values",
+        "col 4 - position": "108,418 unique values",
+        "col 5 - supervoxel_id": "107,646 unique values",
         "col 6 - label_id": "all rows contain unique values",
-        "col 7 - date_created": "39,776 unique values",
-        "col 8 - user_name": "140 unique values in 128,748 rows, empty in 650 rows",
-        "col 9 - user_affiliation": "53 unique values in 128,685 rows, empty in 713 rows"
+        "col 7 - date_created": "39,797 unique values",
+        "col 8 - user_name": "140 unique values in 128,842 rows, empty in 650 rows",
+        "col 9 - user_affiliation": "53 unique values in 128,779 rows, empty in 713 rows"
       },
       "coordinates.csv.gz": {
         "# rows": "207,700 (+ header)",