Merge branch 'main' into NPI-3683-sp3-consistency-check-streamlining

gnssanalysis/filenames.py

@@ -593,7 +593,7 @@ def determine_snx_name_props(file_path: pathlib.Path) -> Dict[str, Any]:
             if blk:
                 soln_df = pd.read_csv(
                     io.BytesIO(blk[0]),
-                    delim_whitespace=True,
+                    sep="\\s+",  # delim_whitespace is deprecated
                     comment="*",
                     names=["CODE", "PT", "SOLN", "T", "START_EPOCH", "END_EPOCH", "MEAN_EPOCH"],
                     converters={

gnssanalysis/gn_frame.py

@@ -17,7 +17,7 @@ def _get_core_list(core_list_path):
     # need to check if solution numbers are consistent with discontinuities selection
     core_df = _pd.read_csv(
         core_list_path,
-        delim_whitespace=True,
+        sep="\\s+",  # delim_whitespace is deprecated
         skiprows=4,
         comment="-",
         usecols=[0, 1, 2, 3],

gnssanalysis/gn_io/blq.py

@@ -28,7 +28,7 @@ def read_blq(path, as_complex=True):
     sites = blq_file_read[:, 0].astype("<U4")
     constituents = ["M2", "S2", "N2", "K2", "K1", "O1", "P1", "Q1", "MF", "MM", "SSA"]
 
-    blq_df = _pd.read_csv(_BytesIO(b"\n".join(blq_file_read[:, 1:].reshape((-1)))), delim_whitespace=True, header=None)
+    blq_df = _pd.read_csv(_BytesIO(b"\n".join(blq_file_read[:, 1:].reshape((-1)))), sep="\\s+", header=None)
     if as_complex:
         # convert extracted A and P to complex phasors X + jY so the comparison of several blq files could be done
         b = blq_df.values.reshape(-1, 11 * 3)

gnssanalysis/gn_io/clk.py

@@ -34,7 +34,7 @@ def read_clk(clk_path):
 
     clk_df = _pd.read_csv(
         _BytesIO(data),
-        delim_whitespace=True,
+        sep="\\s+",  # delim_whitespace is deprecated
         header=None,
         usecols=clk_cols,
         names=clk_names,  # type:ignore

gnssanalysis/gn_io/discon.py

@@ -18,7 +18,7 @@ def _read_discontinuities(path):
     out_df = _pd.read_csv(
         filepath_or_buffer=_BytesIO(block),
         usecols=[0, 1, 2, 4, 5, 6],
-        delim_whitespace=True,
+        sep="\\s+",  # delim_whitespace is deprecated
         header=None,
         names=["CODE", "PT", "SOLN", "START", "END", "MODEL"],
         dtype={0: object, 1: object, 2: int, 4: object, 5: object, 6: MODEL_CATEGORY},

gnssanalysis/gn_io/erp.py

@@ -260,7 +260,7 @@ def read_erp(
     data_of_interest = content[start_of_data:]  # data block
     erp_df = _pd.read_csv(
         _BytesIO(data_of_interest),
-        delim_whitespace=True,
+        sep="\\s+",  # delim_whitespace is deprecated
         names=headers,
         index_col=False,
     )

gnssanalysis/gn_io/igslog.py

@@ -463,12 +463,13 @@ def gather_metadata(
         gather_id_loc, columns=["CODE", "DOMES_N", "CITY", "COUNTRY", "X", "Y", "Z", "LAT", "LON", "HEI", "PATH"]
     )
 
-    id_loc_df.CITY[id_loc_df.CITY == ""] = "N/A"
+    id_loc_df.loc[id_loc_df.CITY == "", "CITY"] = "N/A"
     id_loc_df.CITY = id_loc_df.CITY.str.rstrip().str.upper()
     id_loc_df.COUNTRY = translate_series(
         id_loc_df.COUNTRY.str.rstrip().str.upper(), _gn_io.aux_dicts.translation_country
     ).values
-    id_loc_df.DOMES_N[id_loc_df.DOMES_N == ""] = "---------"
+
+    id_loc_df.loc[id_loc_df.DOMES_N == "", "DOMES_N"] = "---------"
 
     xyz_array = (
         id_loc_df[["X", "Y", "Z"]].stack().str.replace(",", ".").replace({"": None}).unstack().values.astype(float)
@@ -504,7 +505,7 @@ def gather_metadata(
     ant_df.RADOME2 = ant_df.RADOME2.str.rstrip().str.upper()
 
     no_rad2_mask = ~ant_df.RADOME.isin(_gn_io.aux_dicts.atx_rad_tbl)
-    ant_df.RADOME[no_rad2_mask] = ant_df.RADOME2[no_rad2_mask]
+    ant_df.loc[no_rad2_mask, "RADOME"] = ant_df.RADOME2[no_rad2_mask]
     # translation_ant.index.name= None
     antennas = translate_series(ant_df.ANTENNA, _gn_io.aux_dicts.translation_ant)
     invalid_ant_mask = ~antennas.index.isin(_gn_io.aux_dicts.atx_ant_tbl)

gnssanalysis/gn_io/pea.py

@@ -13,7 +13,7 @@ def read_pea_partials(path):
     df = _pd.read_csv(
         _BytesIO(partials[begin:]),
         header=None,
-        delim_whitespace=True,
+        sep="\\s+",  # delim_whitespace is deprecated
         usecols=[0, 1, 2, 9, 10, 11],
         names=[None, "MJD", "TOD", "X", "Y", "Z"],
     )

gnssanalysis/gn_io/sinex.py

@@ -461,7 +461,7 @@ def _get_snx_matrix(path_or_bytes, stypes=("APR", "EST"), verbose=True, snx_head
     else:
         return None  # not found
 
-    matrix_raw = _pd.read_csv(snx_buffer, delim_whitespace=True, dtype={0: _np.int16, 1: _np.int16})
+    matrix_raw = _pd.read_csv(snx_buffer, sep="\\s+", dtype={0: _np.int16, 1: _np.int16})
     # can be 4 and 5 columns; only 2 first int16
 
     output = []

gnssanalysis/gn_io/trace.py

@@ -168,7 +168,7 @@ def _find_trace(output_path: str) -> tuple:
 #     LC_bytes = b''.join(trace_LC_list)
 #     LC_bytes = LC_bytes.replace(b'=',b'') #getting rif of '='
 
-#     df_LC = _pd.read_csv(_BytesIO(LC_bytes),delim_whitespace=True,header=None,usecols=[1,2,4,6,8,9,10,11,12,13]).astype(
+#     df_LC = _pd.read_csv(_BytesIO(LC_bytes),sep="\\s+",header=None,usecols=[1,2,4,6,8,9,10,11,12,13]).astype(
 #         {
 #             1: _np.int16, 2:_np.int32, 4: '<U3',
 #             6: '<U1', 8: '<U4',

requirements.txt

@@ -1,6 +1,7 @@
 boto3
 click
 hatanaka
+jinja2
 matplotlib
 numpy
 pandas

tests/test_sp3.py

@@ -154,14 +154,24 @@ def test_read_sp3_correct_svs_read_when_ev_ep_present(self, mock_file):
     # TODO Add test(s) for correctly reading header fundamentals (ACC, ORB_TYPE, etc.)
     # TODO add tests for correctly reading the actual content of the SP3 in addition to the header.
     # TODO add tests for correctly generating sp3 output content with gen_sp3_content() and gen_sp3_header()
-
-    @patch("builtins.open", new_callable=mock_open, read_data=input_data)
-    def test_gen_sp3_content_velocity_exception_handling(self, mock_file):
+    # These tests should include:
+    # - Correct alignment of POS, CLK, STDPOS STDCLK, (not velocity yet), FLAGS
+    # - Correct alignment of the above when nodata and infinite values are present
+    # - Inclusion of HLM orbit_type in header, after applying Helmert trainsformation (if not covered elsewhere?
+    #   Probably should be covered elsewhere)
+    # - Not including column names (can just test that output matches expected format)
+    # - Not including any NaN value *anywhere*
+
+    def test_gen_sp3_content_velocity_exception_handling(self):
         """
         gen_sp3_content() velocity output should raise exception (currently unsupported).\
             If asked to continue with warning, it should remove velocity columns before output.
         """
-        sp3_df = sp3.read_sp3("mock_path", pOnly=False)
+        # Input data passed as bytes here, rather than using a mock file, because the mock file setup seems to break
+        # part of Pandas Styler, which is used by gen_sp3_content(). Specifically, some part of Styler's attempt to
+        # load style config files leads to a crash, despite some style config files appearing to read successfully)
+        input_data_fresh = input_data + b""  # Lazy attempt at not passing a reference
+        sp3_df = sp3.read_sp3(bytes(input_data_fresh), pOnly=False)
         with self.assertRaises(NotImplementedError):
             generated_sp3_content = sp3.gen_sp3_content(sp3_df, continue_on_unhandled_velocity_data=False)