about summary refs log tree commit diff
path: root/scripts
diff options
context:
space:
mode:
authorFrederick Muriuki Muriithi <fredmanglis@gmail.com>2026-10-02 12:36:07 -0500
committerFrederick Muriuki Muriithi <fredmanglis@gmail.com>2026-10-02 12:39:59 -0500
commitae185c819f0bb7b31faacf8105cbfd885da752e2 (patch)
treeca5a7c7536cbd5b866fa590ef2f0c82ae3dfe311 /scripts
parent31437e9b7bed0fe2c2c499d91bc6308014b8421d (diff)
downloadgn-uploader-ae185c819f0bb7b31faacf8105cbfd885da752e2.tar.gz
Separate pre-processing of transposed and untransposed lines.
We pre-process the lines differently when working with transponed
lines than we do for untransposed lines -- the code reflects that
moving forward.
Diffstat (limited to 'scripts')
-rw-r--r--scripts/genotypes/preprocess_csv_collect_info.py53
-rw-r--r--scripts/genotypes/types.py17
2 files changed, 46 insertions, 24 deletions
diff --git a/scripts/genotypes/preprocess_csv_collect_info.py b/scripts/genotypes/preprocess_csv_collect_info.py
index 32ef1b2..9813f34 100644
--- a/scripts/genotypes/preprocess_csv_collect_info.py
+++ b/scripts/genotypes/preprocess_csv_collect_info.py
@@ -3,7 +3,7 @@ import sys
 import logging
 from pathlib import Path
 from dataclasses import asdict
-from typing import Union, Iterator
+from typing import Union, Iterator, Optional
 from argparse import Namespace, ArgumentParser
 
 from gn_libs.cli import SysExit
@@ -19,8 +19,9 @@ from scripts.cli.validators import file_exists
 
 from .types import (FileStats,
                     LineError,
-                    LineDetails,
-                    FieldsIdentity)
+                    FieldsIdentity,
+                    TransposedLineDetails,
+                    UntransposedLineDetails)
 
 
 logger = logging.getLogger(__name__)
@@ -65,7 +66,10 @@ def identify_columns(
     return FieldsIdentity(**_id, samples=_samples)
 
 
-def process_transposed(line: tuple[str, ...], na_strings: tuple[str, ...]) -> LineDetails:
+def process_transposed(
+        line: tuple[str, ...],
+        na_strings: tuple[str, ...]
+) -> TransposedLineDetails:
     """Process a line in a transposed file."""
     raise NotImplementedError("Please implement this!")
 
@@ -74,8 +78,9 @@ def process_untransposed(
         line: tuple[str, ...],
         settings: dict,
         headers: tuple[str, ...]
-) -> LineDetails:
+) -> UntransposedLineDetails:
     """Processed line in a non-transposed file."""
+    _marker: Optional[str] = None
     _errors: tuple[LineError, ...] = tuple()
     _symbols = tuple(_symb for _head, _symb in zip(headers, line)
                 if _head not in (
@@ -86,6 +91,7 @@ def process_untransposed(
 
     try:
         _idx = headers.index(settings["markers"])
+        _marker = line[_idx]
     except ValueError as _verr:
         _idx = 0
 
@@ -99,11 +105,12 @@ def process_untransposed(
             line=line
         ),)
 
-    return LineDetails(
+    return UntransposedLineDetails(
         line_content=line,
         line_header=line[0],
         geno_symbols=tuple(set(_symbols)),
-        errors=_errors)
+        errors=_errors,
+        marker=_marker)
 
 
 def validate_headers(
@@ -164,6 +171,7 @@ def file_statistics(filepath: Path, fileconfigs: dict) -> FileStats:
         "comment_lines": 0,
         "dot_geno_lines": 0
     }
+    _markers: tuple[str, ...]  = tuple()
     genosymbols: set[str] = set()
     # NOTES: Maybe do the .geno file custom fields check in a separate script?
 
@@ -174,28 +182,31 @@ def file_statistics(filepath: Path, fileconfigs: dict) -> FileStats:
         if line == headers:
             continue# skip headers line
 
-        line_dets = (
-        process_transposed(
-            line,
-            na_strings=fileconfigs["na_strings"])
-        if fileconfigs["transposed"]
-        else process_untransposed(
+        if fileconfigs["transposed"]:
+            t_line_dets = process_transposed(
+                line,
+                na_strings=fileconfigs["na_strings"])
+            headers = headers + (t_line_dets.line_header,)
+            genosymbols.update(t_line_dets.geno_symbols)
+            _errors = _errors + tuple(t_line_dets.errors)
+            if t_line_dets.is_markers_line:
+                _markers = tuple(t_line_dets.line_content[1:])
+        else:
+            line_dets = process_untransposed(
                 line,
                 fileconfigs,
-                headers=headers))
-        _errors = _errors + tuple(line_dets.errors)
-
-        if fileconfigs["transposed"]:
-            headers = headers + (line_dets.line_header,)
-
-        genosymbols.update(line_dets.geno_symbols)
-        # TODO: do more processing
+                headers=headers)
+            genosymbols.update(line_dets.geno_symbols)
+            _errors = _errors + tuple(line_dets.errors)
+            if bool(line_dets.marker):
+                _markers = _markers + (str(line_dets.marker),)
         continue # end of line processing
 
     return FileStats(
         **stats,
         geno_symbols=tuple(genosymbols),
         samples_list=col_ids.samples,
+        markers_list=_markers,
         errors=_errors)
 
 
diff --git a/scripts/genotypes/types.py b/scripts/genotypes/types.py
index 472bb1b..077e90e 100644
--- a/scripts/genotypes/types.py
+++ b/scripts/genotypes/types.py
@@ -1,6 +1,6 @@
 """The datatypes this package will use."""
+from typing import Sequence, Optional
 from dataclasses import field, dataclass
-from typing import Union, Sequence, Optional
 
 
 @dataclass
@@ -34,12 +34,23 @@ class LineError:
 
 
 @dataclass(frozen=True)
-class LineDetails:
+class TransposedLineDetails:
     """Data type for processed line details"""
-    line_content: Sequence[Union[str, None]]
+    line_content: Sequence[str]
     geno_symbols: Sequence[str]
     line_header: str
     errors: Sequence[LineError]
+    is_markers_line: bool = False
+
+
+@dataclass(frozen=True)
+class UntransposedLineDetails:
+    """Data type for processed line details"""
+    line_content: Sequence[str]
+    geno_symbols: Sequence[str]
+    line_header: str
+    errors: Sequence[LineError]
+    marker: Optional[str] = None
 
 
 @dataclass(frozen=True)