fixed sanity check

sensospot_data/columns.py

@@ -30,7 +30,8 @@ RAW_DATA_COLUMNS_RENAME_MAP = {
     "Spot.Sat. (%)": RAW_DATA_SPOT_SAT,
 }
 
-# meta data extracted from filename
+# meta data extracted from filename and path
+META_DATA_ANALYSIS_NAME = "Analysis.Name"
 META_DATA_WELL_NAME = "Well.Name"
 META_DATA_WELL_ROW = "Well.Row"
 META_DATA_WELL_COLUMN = "Well.Column"
@@ -59,6 +60,7 @@ PARSED_DATA_COLUMN_SET = {
     RAW_DATA_POS_ID,
     RAW_DATA_SPOT_FOUND,
     RAW_DATA_SPOT_DIAMETER,
+    META_DATA_ANALYSIS_NAME,
     META_DATA_WELL_NAME,
     META_DATA_WELL_ROW,
     META_DATA_WELL_COLUMN,
@@ -66,3 +68,15 @@ PARSED_DATA_COLUMN_SET = {
     META_DATA_PARAMETERS_CHANNEL,
     META_DATA_PARAMETERS_TIME,
 }
+
+# list of columns to ensure a pandas numeric type
+RAW_DATA_NUMERIC_COLUMNS = {
+    RAW_DATA_BKG_MEAN,
+    RAW_DATA_SPOT_MEAN,
+    RAW_DATA_BKG_MEDIAN,
+    RAW_DATA_SPOT_MEDIAN,
+    RAW_DATA_BKG_STDDEV,
+    RAW_DATA_SPOT_STDDEV,
+    RAW_DATA_BKG_SUM,
+    RAW_DATA_SPOT_SUM,
+}

sensospot_data/parser.py

@@ -16,7 +16,8 @@ from .columns import (
     META_DATA_EXPOSURE_ID,
     META_DATA_WELL_COLUMN,
     PARSED_DATA_COLUMN_SET,
-    RAW_DATA_NORMALIZATION_MAP,
+    META_DATA_ANALYSIS_NAME,
+    RAW_DATA_NUMERIC_COLUMNS,
     RAW_DATA_COLUMNS_RENAME_MAP,
 )
 from .parameters import add_optional_measurement_parameters
@@ -75,8 +76,9 @@ def parse_file(data_file):
 
     will race a ValueError, if metadata could not be extracted
     """
-    measurement_info = _extract_measurement_info(Path(data_file))
-    data_frame = _parse_csv(data_file)
+    data_path = Path(data_file).resolve()
+    measurement_info = _extract_measurement_info(data_path)
+    data_frame = _parse_csv(data_path)
     # normalized well name
     data_frame[
         META_DATA_WELL_NAME
@@ -84,6 +86,7 @@ def parse_file(data_file):
     data_frame[META_DATA_WELL_ROW] = measurement_info.row
     data_frame[META_DATA_WELL_COLUMN] = measurement_info.column
     data_frame[META_DATA_EXPOSURE_ID] = measurement_info.exposure
+    data_frame[META_DATA_ANALYSIS_NAME] = data_path.parent.name
     return _cleanup_data_columns(data_frame)
 
 
@@ -133,16 +136,17 @@ def _sanity_check(data_frame):
             f"Measurements are missing: {expected_rows} != {len(data_frame)}"
         )
     # set the right data type for measurement columns
-    for raw_column in RAW_DATA_NORMALIZATION_MAP:
+    for raw_column in RAW_DATA_NUMERIC_COLUMNS:
         data_frame[raw_column] = pandas.to_numeric(data_frame[raw_column])
     return data_frame
 
 
 def parse_folder(folder, quiet=False):
     """parses all csv files in a folder to one large dataframe"""
-    file_list = list_csv_files(Path(folder))
+    folder_path = Path(folder)
+    file_list = list_csv_files(folder_path)
     data_frame = parse_multiple_files(file_list)
-    data_frame = add_optional_measurement_parameters(data_frame, folder)
+    data_frame = add_optional_measurement_parameters(data_frame, folder_path)
     if quiet:
         return data_frame
     return _sanity_check(data_frame)

tests/test_parser.py

@@ -172,6 +172,7 @@ def test_parse_file(example_file):
         "Well.Row",
         "Well.Column",
         "Exposure.Id",
+        "Analysis.Name",
     }
 
     assert set(result.columns) == columns
@@ -179,6 +180,7 @@ def test_parse_file(example_file):
     assert result["Well.Row"][0] == "A"
     assert result["Well.Column"][0] == 1
     assert result["Exposure.Id"][0] == 1
+    assert result["Analysis.Name"][0] == "mtp_wo_parameters"
 
 
 def test_parse_file_raises_error(example_dir):