From 63accc5adf97f530ee8f08eb98b2ef12170e8435 Mon Sep 17 00:00:00 2001
From: anmol thapar <mr.anmolthapar@gmail.com>
Date: Wed, 26 Jun 2024 11:29:00 +0100
Subject: [PATCH 1/2] bug: update cluster assign to write qcreport on qc
 failiures

---
 PopPUNK/assign.py |  9 +++++----
 PopPUNK/qc.py     | 43 ++++++++++++++++++++++++++++++++++++-------
 2 files changed, 41 insertions(+), 11 deletions(-)

diff --git a/PopPUNK/assign.py b/PopPUNK/assign.py
index da8adc87..7cc66b2c 100644
--- a/PopPUNK/assign.py
+++ b/PopPUNK/assign.py
@@ -372,7 +372,7 @@ def assign_query_hdf5(dbFuncs,
     from .plot import writeClusterCsv
 
     from .qc import qcDistMat, qcQueryAssignments, prune_distance_matrix, \
-        prune_query_distance_matrix
+        prune_query_distance_matrix, write_qc_failure_report
 
     from .sketchlib import addRandom
 
@@ -489,12 +489,13 @@ def assign_query_hdf5(dbFuncs,
         # QC distance matrix
         if qc_dict['run_qc']:
             sys.stderr.write("Running QC on distance matrix\n")
-            seq_names_passing = \
-                frozenset(qcDistMat(qrDistMat, rNames, qNames, ref_db, qc_dict)[0])
-            failed_samples = frozenset(qNames) - seq_names_passing
+            seq_names_passing, failed_samples_dict = qcDistMat(qrDistMat, rNames, qNames, ref_db, qc_dict)            
+            failed_samples = frozenset(qNames) - frozenset(seq_names_passing)
             if len(failed_samples) > 0:
                 sys.stderr.write(f"{len(failed_samples)} samples failed:\n"
                                  f"{','.join(failed_samples)}\n")
+                write_qc_failure_report(failed_samples, [failed_samples_dict], output)
+                
                 if len(failed_samples) == len(qNames):
                     sys.exit(1)
                 else:
diff --git a/PopPUNK/qc.py b/PopPUNK/qc.py
index 9ae8359f..e45d5d45 100755
--- a/PopPUNK/qc.py
+++ b/PopPUNK/qc.py
@@ -472,14 +472,43 @@ def remove_qc_fail(qc_dict, names, passed, fail_dicts, ref_db, distMat, prefix,
                     overwrite=True, threads=threads)
 
     # write failing & reasons
-    with open(f"{prefix}/{os.path.basename(prefix)}_qcreport.txt", 'w') as qc_file:
-        for sample in failed:
-            reasons = []
-            for fail_test in fail_dicts:
-                if sample in fail_test:
-                    reasons += (fail_test[sample])
-            qc_file.write(f"{sample}\t{','.join(reasons)}\n")
+    write_qc_failure_report(failed, fail_dicts, prefix)
+
+def write_qc_failure_report(failed_samples, fail_dicts, output_prefix):
+    """
+    Writes a report of failed samples and their reasons to a file.
 
+    Parameters:
+    - failed_samples: A list of samples that have failed.
+    - fail_dicts: A list of dictionaries, each mapping samples to their failure reasons.
+    - output_prefix: The prefix for the output file path.
+    """
+    # Accumulate output lines for each failed sample
+    failed_output_lines = [
+        f"{sample}\t{','.join(get_failure_reasons(sample, fail_dicts))}\n"
+        for sample in failed_samples
+    ]
+    with open(f"{output_prefix}/{os.path.basename(output_prefix)}_qcreport.txt", 'w') as qc_file:
+        qc_file.writelines(failed_output_lines)
+
+def get_failure_reasons(sample, fail_dicts):
+    """
+    Retrieves all failure reasons for a given sample across multiple dictionaries.
+
+    Parameters:
+    - sample: The sample to retrieve failure reasons for.
+    - fail_dicts: A list of dictionaries, each mapping samples to their failure reasons.
+
+    Returns:
+    A list of failure reasons for the given sample.
+    """
+    return [
+        reason
+        for fail_dict in fail_dicts
+        if sample in fail_dict
+        for reason in fail_dict[sample]
+    ]
+    
 def pickTypeIsolate(prefix, refList):
     """Selects a type isolate as that with a minimal proportion
     of missing data.

From db1bce4af630acd38cce413d0bd865d1335a5df0 Mon Sep 17 00:00:00 2001
From: anmol thapar <mr.anmolthapar@gmail.com>
Date: Wed, 3 Jul 2024 08:22:00 +0100
Subject: [PATCH 2/2] chore: update version

---
 PopPUNK/__init__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/PopPUNK/__init__.py b/PopPUNK/__init__.py
index a3f1eb11..9a9c3eeb 100644
--- a/PopPUNK/__init__.py
+++ b/PopPUNK/__init__.py
@@ -3,7 +3,7 @@
 
 '''PopPUNK (POPulation Partitioning Using Nucleotide Kmers)'''
 
-__version__ = '2.6.5'
+__version__ = '2.6.6'
 
 # Minimum sketchlib version
 SKETCHLIB_MAJOR = 2