avoca 0.16.0__tar.gz → 0.17.0__tar.gz

{avoca-0.16.0 → avoca-0.17.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: avoca
-Version: 0.16.0
+Version: 0.17.0
 Summary: @voc@: Quality assessement of measurement data
 Project-URL: Homepage, https://gitlab.com/empa503/atmospheric-measurements/avoca
 Project-URL: Bug Tracker, https://gitlab.com/empa503/atmospheric-measurements/avoca/-/issues

{avoca-0.16.0 → avoca-0.17.0}/avoca/bindings/gcwerks.py

@@ -90,6 +90,8 @@ flag_values = {
     "F": QA_Flag.INVALIDATED_EXT,
     # X: An X flag is an 'un-do' the flag. If there is an automatic flag by GCWerks, but I decide I want that data point still included, I have the option to set an X flag.
     "X": ValidFlag,
+    # Nans read from pandas 
+    pd.NA: QA_Flag.MISSING,
 }
 
 # Show the flags and the columns they are applied to
@@ -229,9 +231,9 @@ def read_gcwerks(
         flags: pd.Series = serie_str.str[-1]
         if col[1] in cols_float:
             # Remove the flag value when given
-            serie_str = serie_str.apply(
-                lambda x: x[:-1] if x[-1] in flags_allowed else x
-            )
+            mask_flag_allowed = flags.isin(flags_allowed)
+            serie_str = serie_str.where(~mask_flag_allowed, serie_str.str[:-1])
+
             # Convert the serie to numeric
             df[col] = pd.to_numeric(serie_str, errors="coerce")
 

{avoca-0.16.0 → avoca-0.17.0}/avoca/io.py

@@ -8,6 +8,11 @@ date_format = "%Y-%m-%d %H:%M:%S"
 
 def to_csv(df: pd.DataFrame, path: Path, **kwargs) -> None:
     """Export a dataframe to a csv file."""
+
+    # Put the columsn with "-" first
+    cols = df.columns.tolist()
+    cols_sorted = sorted(cols, key=lambda x: (x[0] != "-", x))
+    df = df[cols_sorted]
     df.to_csv(path, index=False, date_format=date_format, **kwargs)
 
 

{avoca-0.16.0 → avoca-0.17.0}/avoca/testing/utils.py

@@ -3,7 +3,7 @@ import pandas as pd
 
 def make_dt_index(df: pd.DataFrame | pd.Index) -> pd.DataFrame | pd.Index:
     """Create a datetime index for the dataframe."""
-    index = pd.date_range(start="2023-01-01", periods=len(df), freq="h")
+    index = pd.date_range(start="2023-01-01", periods=len(df), freq="h", unit="s")
     if isinstance(df, pd.Index):
         return index
     return df.set_index(index)

{avoca-0.16.0 → avoca-0.17.0}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "avoca"
-version = "0.16.0"
+version = "0.17.0"
 authors = [
   { name="Lionel Constantin", email="lionel.constantin@empa.ch" },
 ]

avoca-0.17.0/tests/bindings/gcwerks_with_flags.dat

@@ -0,0 +1,7 @@
+Created:  6 May 21 07:53 GMT
+     -    -      -       -   methane    ethane    ethene   propane   propene
+  date time volume    type      area      area      area      area      area
+210101 0025    1.0    air   1506527    187333     54226    124023      9004
+210101 0126    1.1    air       nan    191969     72289    124942     14789
+210101 0226    1.0    air  1445250H    175597     39373    104478      6643
+210101 0327    0.9    air  1434459*    171817     38493     99796      5926

avoca-0.17.0/tests/bindings/test_gcwerks.py

@@ -0,0 +1,32 @@
+from pathlib import Path
+
+import pandas as pd
+
+from avoca.bindings.gcwerks import read_gcwerks
+from avoca.flags import QA_Flag
+
+this_dir = Path(__file__).parent
+
+
+def test_read_gcwerks():
+    path = this_dir / "gcwerks.dat"
+    df = read_gcwerks(path)
+    assert len(df) == 4
+
+
+def test_read_gcwerks_with_flags():
+    path = this_dir / "gcwerks_with_flags.dat"
+    df = read_gcwerks(path)
+    assert len(df) == 4
+
+    assert df[("methane", "area")].iloc[0] == 1506527
+    assert df[("methane", "flag")].iloc[0] == 0
+    assert df[("methane", "area")].iloc[2] == 1445250
+    assert df[("methane", "flag")].iloc[2] == QA_Flag.HEIGHT_INTEGRATION.value
+    assert pd.isna(df[("methane", "area")].iloc[1])
+    assert df[("methane", "flag")].iloc[1] == QA_Flag.MISSING.value
+    assert pd.isna(df[("methane", "area")].iloc[3])
+    assert (
+        df[("methane", "flag")].iloc[3]
+        == QA_Flag.INVALIDATED_EXT.value + QA_Flag.MISSING.value
+    )

{avoca-0.16.0 → avoca-0.17.0}/tests/test_io.py

@@ -1,3 +1,5 @@
+import pandas as pd
+
 from avoca import io
 from avoca.testing import testdata_dir
 from avoca.testing.df import simple_df
@@ -8,8 +10,13 @@ def test_from_to_csv():
     io.to_csv(simple_df, "simple_df.csv")
     # Read the dataframe
     df = io.from_csv("simple_df.csv")
+
+    # Columns will be sorted differently
+    cols_sorted = sorted(simple_df.columns, key=lambda x: (x[0] != "-", x))
+    simple_df_sorted = simple_df[cols_sorted]
+
     # Check if the dataframes are equal
-    assert simple_df.equals(df)
+    pd.testing.assert_frame_equal(simple_df_sorted, df)
 
 
 def test_missing_area():

avoca-0.16.0/tests/bindings/test_gcwerks.py

@@ -1,11 +0,0 @@
-from pathlib import Path
-
-from avoca.bindings.gcwerks import read_gcwerks
-
-this_dir = Path(__file__).parent
-
-
-def test_read_gcwerks():
-    path = this_dir / "gcwerks.dat"
-    df = read_gcwerks(path)
-    assert len(df) == 4