removed some cruft

sensospot_data/parser.py

@@ -17,6 +17,7 @@ from .columns import (
     COL_NAME_EXPOSURE_ID,
     COL_NAME_WELL_COLUMN,
     COL_NAME_SPOT_DIAMETER,
+    COLUMNS_RENAME_MAP
 )
 from .parameters import add_optional_measurement_parameters
 
@@ -28,25 +29,15 @@ REGEX_WELL = re.compile(
     re.VERBOSE | re.IGNORECASE,
 )
 
-COLUMNS_TO_DROP = ["Rect.", "Contour", "Id", "Name", "Foo"]
 COLUMNS_RENAME_MAP = {
     " ID ": COL_NAME_POS_ID,
     "Found": COL_NAME_SPOT_FOUND,
     "Dia.": COL_NAME_SPOT_DIAMETER,
 }
 
-CACHE_FILE_NAME = "raw_data.h5"
-
 FileInfo = namedtuple("FileInfo", ["row", "column", "exposure"])
 
 
-def _get_cache_table_name():
-    """ automatic hdf5 table name, avoids a circular import """
-    from . import VERSION_TABLE_NAME
-
-    return VERSION_TABLE_NAME
-
-
 def _guess_decimal_separator(file_handle):
     """ guesses the decimal spearator of a opened data file """
     file_handle.seek(0)
@@ -85,12 +76,15 @@ def _cleanup_data_columns(data_frame):
     return renamed.drop(columns=surplus_columns)
 
 
-def parse_file(data_file):
+def parse_file(data_file, silent=False):
     """ parses one data file and adds metadata to result """
     try:
         measurement_info = _extract_measurement_info(Path(data_file))
     except ValueError as e:
+        if silent:
             return None
+        else:
+            raise e
     data_frame = _parse_csv(data_file)
     data_frame[COL_NAME_WELL_ROW] = measurement_info.row
     data_frame[COL_NAME_WELL_COLUMN] = measurement_info.column
@@ -102,7 +96,7 @@ def parse_multiple_files(file_list):
     """ parses a list of file paths to one combined dataframe """
     if not file_list:
         raise ValueError("Empty file list provided")
-    collection = (parse_file(path) for path in file_list)
+    collection = (parse_file(path, silent=True) for path in file_list)
     filtered = (frame for frame in collection if frame is not None)
     data_frame = next(filtered)
     for next_frame in filtered:
@@ -113,7 +107,7 @@ def parse_multiple_files(file_list):
     return data_frame
 
 
-def _list_csv_files(folder):
+def list_csv_files(folder):
     """ returns all csv files in a folder """
     folder_path = Path(folder)
     files = (item for item in folder_path.iterdir() if item.is_file())
@@ -135,29 +129,7 @@ def _sanity_check(data_frame):
 
 def parse_folder(folder):
     """ parses all csv files in a folder to one large dataframe """
-    file_list = _list_csv_files(Path(folder))
+    file = list_csv_files(Path(folder))
     data_frame = parse_multiple_files(file_list)
     data_frame = add_optional_measurement_parameters(data_frame, folder)
     return _sanity_check(data_frame)
-
-
-def process_folder(folder, use_cache=True):
-    """ parses all csv files in a folder, adds some checks and more data """
-    hdf5_path = Path(folder) / CACHE_FILE_NAME
-    if use_cache:
-        try:
-            return pandas.read_hdf(hdf5_path, _get_cache_table_name())
-        except (FileNotFoundError, KeyError):
-            # either file or table doesn't exist
-            pass
-    data_frame = parse_folder(folder)
-    if use_cache:
-        try:
-            data_frame.to_hdf(
-                hdf5_path, _get_cache_table_name(), format="table"
-            )
-        except OSError:
-            # capturing high level OSError
-            # read only filesystems don't throw a more specific exception
-            pass
-    return data_frame