about summary refs log tree commit diff
path: root/scripts/genotypes
diff options
context:
space:
mode:
authorFrederick Muriuki Muriithi <fredmanglis@gmail.com>2026-10-01 12:37:08 -0500
committerFrederick Muriuki Muriithi <fredmanglis@gmail.com>2026-10-01 13:02:44 -0500
commitc04b75c5904bb30bd672e295ab66bbe670520c87 (patch)
tree743794ea970f671ed8d440a9f6d9133c45f0b2cd /scripts/genotypes
parent27ca6bc0677cc3ccfcfe4203e07f2dd9b5ac8889 (diff)
downloadgn-uploader-c04b75c5904bb30bd672e295ab66bbe670520c87.tar.gz
Fix type errors.
Diffstat (limited to 'scripts/genotypes')
-rw-r--r--scripts/genotypes/preprocess_csv_collect_info.py40
-rw-r--r--scripts/genotypes/types.py3
2 files changed, 23 insertions, 20 deletions
diff --git a/scripts/genotypes/preprocess_csv_collect_info.py b/scripts/genotypes/preprocess_csv_collect_info.py
index 2d76021..da5e904 100644
--- a/scripts/genotypes/preprocess_csv_collect_info.py
+++ b/scripts/genotypes/preprocess_csv_collect_info.py
@@ -2,8 +2,8 @@
 import sys
 import logging
 from pathlib import Path
-from typing import Iterator
 from dataclasses import asdict
+from typing import Union, Iterator
 from argparse import Namespace, ArgumentParser
 
 from gn_libs.cli import SysExit
@@ -29,7 +29,8 @@ def identify_columns(
         settings: dict[str, str]
 ) -> FieldsIdentity:
     """Identify columns using settings provided by user"""
-    _id = {}
+    _id: dict[str, Union[str, str]] = {}
+    _samples: tuple[str, ...] = tuple()
     for header in headers:
         if header.lower() == settings["markers"].lower():
             _id["marker"] = header
@@ -46,9 +47,9 @@ def identify_columns(
             _id["physical_distance"] = header
             continue
 
-        _id["samples"] = _id.get("samples", tuple()) + (header,)
+        _samples = _samples + (header,)
 
-    return FieldsIdentity(**_id)
+    return FieldsIdentity(**_id, samples=_samples)
 
 
 def process_transposed(line: tuple[str, ...], na_strings: tuple[str, ...]) -> LineDetails:
@@ -76,30 +77,35 @@ def process_untransposed(
 
 def file_statistics(lines: Iterator[str], fileconfigs: dict) -> FileStats:
     """Compute file statistics from the lines in the file."""
-    stats = {}
-    col_ids = tuple()
+    stats: dict = {
+        "data_lines": 0,
+        "total_lines": 0,
+        "blank_lines": 0,
+        "comment_lines": 0,
+        "dot_geno_lines": 0
+    }
     dotgeno = {}
     headers: tuple[str, ...] = tuple()
     genosymbols: set[str] = set()
     # errors: tuple()
     for line in lines:
-        stats["total_lines"] = stats.get("total_lines", 0) + 1
+        stats["total_lines"] = stats["total_lines"] + 1
         _line = line.strip()
         if _line == "":
-            stats["blank_lines"] = stats.get("blank_lines", 0) + 1
+            stats["blank_lines"] = stats["blank_lines"] + 1
             continue
 
         if _line.startswith(fileconfigs["comment.char"]):
-            stats["comment_lines"] = stats.get("comment_lines", 0) + 1
+            stats["comment_lines"] = stats["comment_lines"] + 1
             continue
 
         if _line.startswith("@"): # custom GeneNetwork Settings
-            stats["dot_geno_lines"] = stats.get("dot_geno_lines", 0) + 1
+            stats["dot_geno_lines"] = stats["dot_geno_lines"] + 1
             _fld = tuple(item.strip() for item in line.strip("@").split(":"))
             dotgeno[_fld[0]] = _fld[1]
             continue
 
-        stats["data_lines"] = stats.get("data_lines", 0) + 1
+        stats["data_lines"] = stats["data_lines"] + 1
         fields: tuple[str, ...] = tuple(
             fld.strip() for fld in line.split(fileconfigs["separator"]))
 
@@ -117,7 +123,7 @@ def file_statistics(lines: Iterator[str], fileconfigs: dict) -> FileStats:
                 headers = fields # First line ***IS** headers' line!
                 continue
             # ELSE: File **IS** transposed.
-            headers = headers + (fields[0])
+            headers = headers + (fields[0],)
             continue
 
         line_dets = (
@@ -131,7 +137,7 @@ def file_statistics(lines: Iterator[str], fileconfigs: dict) -> FileStats:
                 headers=headers))
 
         if fileconfigs["transposed"]:
-            headers = headers + (line_dets.header)
+            headers = headers + (line_dets.line_header,)
 
         genosymbols.update(line_dets.geno_symbols)
         # TODO: do more processing
@@ -140,11 +146,9 @@ def file_statistics(lines: Iterator[str], fileconfigs: dict) -> FileStats:
     col_ids = identify_columns(headers, fileconfigs)
     return FileStats(
         **stats,
-        **({"dot_geno_fields": DotGenoFields(**dotgeno)}
-           if bool(dotgeno)
-           else {}),
-        samples_list=col_ids.samples,
-        geno_symbols=tuple(genosymbols))
+        geno_symbols=tuple(genosymbols),
+        dot_geno_fields=(DotGenoFields(**dotgeno) if bool(dotgeno) else None),
+        samples_list=col_ids.samples)
 
 
 if __name__ == "__main__":
diff --git a/scripts/genotypes/types.py b/scripts/genotypes/types.py
index bf46606..482d8d4 100644
--- a/scripts/genotypes/types.py
+++ b/scripts/genotypes/types.py
@@ -29,7 +29,7 @@ class LineDetails:
     """Data type for processed line details"""
     line_content: Sequence[Union[str, None]]
     geno_symbols: Sequence[str]
-    line_header: Optional[str] = None
+    line_header: str
 
 
 @dataclass(frozen=True)
@@ -52,7 +52,6 @@ class FileStats:# pylint: disable=[too-many-instance-attributes]
     comment_lines: int = 0
     dot_geno_lines: int = 0
     dot_geno_fields: Optional[DotGenoFields] = None
-    samples: Sequence[str] = field(default_factory=tuple)
     samples_list: Sequence[str] = field(default_factory=tuple)
     markers_list: Sequence[str] = field(default_factory=tuple)
     errors: Sequence[LineError] = field(default_factory=tuple)