io/read_metadata: Fix dtype for the index column

CHANGES.md

@@ -5,8 +5,10 @@
 ### Bug Fixes
 
 * schema: document node property values support `url`. This feature has been supported in Auspice since v2.25.0. [#1743][] (@joverlee521)
+* augur.io.read_metadata: Ensure that the index column's dtype is always "string" so that numeric ids don't get converted to numeric dtypes. [#1746][] (@joverlee521)
 
 [#1743]: https://github.com/nextstrain/augur/pull/1743
+[#1746]: https://github.com/nextstrain/augur/pull/1746
 
 ## 28.0.0 (30 January 2025)
 

augur/io/metadata.py

@@ -136,7 +136,7 @@ def read_metadata(metadata_file, delimiters=DEFAULT_DELIMITERS, columns=None, id
 
     if isinstance(dtype, dict):
         # Avoid reading numerical IDs as integers.
-        dtype["index_col"] = "string"
+        dtype[index_col] = "string"
 
         # Avoid reading year-only dates as integers.
         dtype[METADATA_DATE_COLUMN] = "string"

tests/functional/export_v2/cram/metadata-with-float-strains.t

@@ -0,0 +1,34 @@
+Setup
+
+  $ source "$TESTDIR"/_setup.sh
+
+Create files for testing.
+
+  $ cat >metadata.tsv <<~~
+  > strain	field_A	field_B
+  > 1.00	AA	AAA
+  > 2.00	BB	BBB
+  > 3.00	CC	CCC
+  > 4.00	DD	DDD
+  > 5.00	EE	EEE
+  > 6.00	FF	FFF
+  > ~~
+
+  $ cat >tree.nwk <<~~
+  > (1.00:1,(2.00:1,3.00:1)internalBC:2,(4.00:3,5.00:4,6.00:1)internalDEF:5)ROOT:0;
+  > ~~
+
+Run export with tree and metadata with additional columns.
+The metadata should match with the tree even though the names are floats
+because we force the index column to be strings.
+
+  $ ${AUGUR} export v2 \
+  >  --tree tree.nwk \
+  >  --metadata metadata.tsv \
+  >  --metadata-columns "field_A" "field_B" \
+  >  --maintainers "Nextstrain Team" \
+  >  --output dataset.json > /dev/null
+
+  $ python3 "$TESTDIR/../../../../scripts/diff_jsons.py" "$TESTDIR/../data/dataset-with-float-strains.json" dataset.json \
+  >   --exclude-paths "root['meta']['updated']" "root['meta']['maintainers']"
+  {}

tests/functional/export_v2/data/dataset-with-float-strains.json

@@ -0,0 +1,121 @@
+{
+  "version": "v2",
+  "meta": {
+    "updated": "2025-02-06",
+    "maintainers": [
+      {
+        "name": "Nextstrain Team"
+      }
+    ],
+    "colorings": [],
+    "filters": [],
+    "panels": [
+      "tree"
+    ]
+  },
+  "tree": {
+    "name": "ROOT",
+    "node_attrs": {
+      "div": 0
+    },
+    "branch_attrs": {},
+    "children": [
+      {
+        "name": "1.00",
+        "node_attrs": {
+          "div": 1.0,
+          "field_A": {
+            "value": "AA"
+          },
+          "field_B": {
+            "value": "AAA"
+          }
+        },
+        "branch_attrs": {}
+      },
+      {
+        "name": "internalBC",
+        "node_attrs": {
+          "div": 2.0
+        },
+        "branch_attrs": {},
+        "children": [
+          {
+            "name": "2.00",
+            "node_attrs": {
+              "div": 3.0,
+              "field_A": {
+                "value": "BB"
+              },
+              "field_B": {
+                "value": "BBB"
+              }
+            },
+            "branch_attrs": {}
+          },
+          {
+            "name": "3.00",
+            "node_attrs": {
+              "div": 3.0,
+              "field_A": {
+                "value": "CC"
+              },
+              "field_B": {
+                "value": "CCC"
+              }
+            },
+            "branch_attrs": {}
+          }
+        ]
+      },
+      {
+        "name": "internalDEF",
+        "node_attrs": {
+          "div": 5.0
+        },
+        "branch_attrs": {},
+        "children": [
+          {
+            "name": "4.00",
+            "node_attrs": {
+              "div": 8.0,
+              "field_A": {
+                "value": "DD"
+              },
+              "field_B": {
+                "value": "DDD"
+              }
+            },
+            "branch_attrs": {}
+          },
+          {
+            "name": "5.00",
+            "node_attrs": {
+              "div": 9.0,
+              "field_A": {
+                "value": "EE"
+              },
+              "field_B": {
+                "value": "EEE"
+              }
+            },
+            "branch_attrs": {}
+          },
+          {
+            "name": "6.00",
+            "node_attrs": {
+              "div": 6.0,
+              "field_A": {
+                "value": "FF"
+              },
+              "field_B": {
+                "value": "FFF"
+              }
+            },
+            "branch_attrs": {}
+          }
+        ]
+      }
+    ]
+  }
+}