Reduce

lib/daccess.py

@@ -20,11 +20,8 @@ from .tools import firstOfDay, firstOfYear, firstOfMonth
 
 
 class ConfigFields(object):
-    LOGGER = "logger"  # deprecated
     DEVICE = "logger"
-    # DBID = "database ID"
     DBNAME = "headerout (DB)"
-    RECORD = "record"
     VARNAME = "headerout"
     DATE = "Date Time"
     START_DATE = "date start"
@@ -33,17 +30,12 @@ class ConfigFields(object):
     STARTDATE = "date start"
     ENDDATE = "date end"
     UNIT = "units"
-    HEADNAME = "headerout (final)"
     DEPTH = "depth/height (m)"
-    HEIGHT = DEPTH
     MIN = "Min"
     MAX = "Max"
-    DERIVED = "derived/influenced variables"
-    COMPARE = "compare with/emergency replacement"
     FLAG1 = "max percentage missing data for aggregation resulting in flag 1"
     FLAG2 = "max percentage missing data for aggregation resulting in flag 2"
     AGGREGATION_TYPE = "AGGREGATION_TYPE"
-    # LEVEL1_FNAME = "level 1 data file name"
     DEPENDENCIES = "derived from/influenced by var"
 
 CONFIG_FIELDMAP = {
@@ -82,7 +74,6 @@ def readExcel(sheets):
         grouper = out.groupby(by=ConfigFields.VARNAME)
         # remove the duplicates without a registered DBNAME (necessary e.g. HH-T3/Tpot01)
         out = grouper.apply(lambda df: df.sort_values([ConfigFields.DBNAME]).iloc[0])
-        # out = out.drop_duplicates(ConfigFields.VARNAME)
         return out
     return pd.DataFrame()
 
@@ -201,7 +192,6 @@ def prepareTable(df,                   # type: pd.DataFrame
                  nbits=None,           # type: Optional[int]
                  drop_record=True,     # type: bool
                  drop_empty=False,
-                 # drop_duplicated_rows=True,
                  drop_duplicated_timestamps=True,
                  freq=None,             # type: Optional[str]
                  ):
@@ -213,9 +203,6 @@ def prepareTable(df,                   # type: pd.DataFrame
     df.index.rename(IndexFields.DATE, inplace=True)
 
     if not df.empty:
-        # if drop_duplicated_rows:
-        #     df = df.drop_duplicates()
-
         if drop_duplicated_timestamps:
             df = squeezeTimestamps(df)
 
@@ -270,9 +257,6 @@ def columnKeys(col):
     elif col.lower().startswith("record"):
         return col, "record"
     return col.split(" ")[0], IndexFields.DATA
-    # elif col.endswith("]"):
-    #     return col.split(" ")[0], IndexFields.DATA
-    # return col, col
 
 
 def setColumns(df, level):
@@ -390,21 +374,6 @@ def _toDatetime(dates, formats):
     raise ValueError(f"time data does not match any of the given formats: '{formats}'")
 
 
-# def readManflagFile(fname):
-#     formats = {"%d.%m.%Y %H:%M:%S", "%d.%m.%Y %H:%M"}
-
-#     df = pd.read_csv(fname, comment="#", encoding="latin")
-#     df["start"] = _toDatetime(df["start"], formats)
-#     df["end"] = _toDatetime(df["end"], formats)
-
-#     now = pd.Timestamp.now()
-#     df = (df
-#           .set_index("var_id")
-#           .fillna(value={'start': now, 'end': now})
-#           .fillna(np.nan))
-#     return df
-
-
 def _readSoilnetL0File(fname):
 
     badchars = re.escape(re.sub(r"[_.:]", "", string.punctuation))