msreport 0.0.25__tar.gz → 0.0.26__tar.gz

{msreport-0.0.25 → msreport-0.0.26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: msreport
-Version: 0.0.25
+Version: 0.0.26
 Summary: Post processing and analysis of quantitative proteomics data
 Author-email: "David M. Hollenstein" <hollenstein.david@gmail.com>
 License: Apache-2.0

{msreport-0.0.25 → msreport-0.0.26}/msreport/__init__.py

@@ -10,4 +10,4 @@ import msreport.normalize
 import msreport.plot
 import msreport.reader
 
-__version__ = "0.0.25"
+__version__ = "0.0.26"

{msreport-0.0.25 → msreport-0.0.26}/msreport/helper/table.py

@@ -176,12 +176,22 @@ def find_sample_columns(
             columns.
 
     Returns:
-        A list of sample column names.
+        A list of column names containing the substring and any entry of 'samples'.
+        Columns are returned in the order of entries in 'samples'.
     """
+    WHITESPACE_CHARS = " ."
+
     matched_columns = []
-    for column in find_columns(table, substring):
-        if any([sample in column for sample in samples]):
-            matched_columns.append(column)
+    substring_columns = find_columns(table, substring)
+    for sample in samples:
+        sample_columns = [c for c in substring_columns if sample in c]
+        for col in sample_columns:
+            column_remainder = (
+                col.replace(substring, "").replace(sample, "").strip(WHITESPACE_CHARS)
+            )
+            if column_remainder == "":
+                matched_columns.append(col)
+                break
     return matched_columns
 
 

{msreport-0.0.25 → msreport-0.0.26}/msreport.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: msreport
-Version: 0.0.25
+Version: 0.0.26
 Summary: Post processing and analysis of quantitative proteomics data
 Author-email: "David M. Hollenstein" <hollenstein.david@gmail.com>
 License: Apache-2.0

{msreport-0.0.25 → msreport-0.0.26}/tests/test_helper.py

@@ -19,20 +19,35 @@ class TestFindColumns:
         assert columns == ["Test A", "Test B"]
 
 
-def test_find_sample_columns():
-    df = pd.DataFrame(
-        columns=[
-            "Test",
-            "Test Not_a_sample",
-            "Test Sample_A",
-            "Test Sample_B",
-            "Something else",
-        ]
-    )
-    samples = ["Sample_A", "Sample_B"]
-    tag = "Test"
-    columns = msreport.helper.find_sample_columns(df, tag, samples)
-    assert columns == ["Test Sample_A", "Test Sample_B"]
+class TestFindSampleColumns:
+    def test_find_sample_columns(self):
+        df = pd.DataFrame(
+            columns=[
+                "Tag",
+                "Tag Not_a_sample",
+                "Tag Sample_A",
+                "Tag Sample_B",
+                "Something else",
+            ]
+        )
+        samples = ["Sample_A", "Sample_B"]
+        tag = "Tag"
+        columns = msreport.helper.find_sample_columns(df, tag, samples)
+        assert columns == ["Tag Sample_A", "Tag Sample_B"]
+
+    def test_columns_are_returned_in_order_of_samples(self):
+        df = pd.DataFrame(columns=["Tag Sample_B", "Tag Sample_A"])
+        samples = ["Sample_A", "Sample_B"]
+        tag = "Tag"
+        columns = msreport.helper.find_sample_columns(df, tag, samples)
+        assert columns == ["Tag Sample_A", "Tag Sample_B"]
+
+    def test_correct_mapping_with_samples_that_are_substrings(self):
+        df = pd.DataFrame(columns=["Tag SampleB_1", "Tag B_1"])
+        samples = ["B_1"]
+        tag = "Tag"
+        columns = msreport.helper.find_sample_columns(df, tag, samples)
+        assert columns == ["Tag B_1"]
 
 
 class TestKeepRowsByPartialMatch: