Transform data and update validation tests

src/pudl/extract/eia923.py

@@ -38,7 +38,6 @@ def __init__(self, *args, **kwargs):
 
     def process_raw(self, df, page, **partition):
         """Drops reserved columns."""
-        logger.info(df)
         to_drop = [c for c in df.columns if c[:8] == "reserved"]
         df = df.drop(to_drop, axis=1)
         df = df.rename(columns=self._metadata.get_column_map(page, **partition))

src/pudl/transform/eia923.py

@@ -1351,7 +1351,7 @@ def cooling_system_information_continuity(csi):  # pragma: no cover
             "monthly_total_withdrawal_volume_gallons": 0.3,
         },
         groupby_col="report_date",
-        n_outliers_allowed=1,
+        n_outliers_allowed=2,
     )
 
 

test/validate/eia_test.py

@@ -46,13 +46,13 @@ def test_no_null_cols_eia(pudl_out_eia, live_dbs, cols, df_name):
 @pytest.mark.parametrize(
     "df_name,raw_rows,monthly_rows,annual_rows",
     [
-        ("bf_eia923", 1_661_460, 1_661_460, 135_980),
-        ("bga_eia860", 153_487, 153_487, 153_487),
-        ("boil_eia860", 89_053, 89_053, 89_053),
-        ("frc_eia923", 676_851, 276_108, 26_709),
-        ("gen_eia923", None, 5_753_883, 479_379),
+        ("bf_eia923", 1_670_698, 1_670_698, 136_757),
+        ("bga_eia860", 154_378, 154_378, 154_378),
+        ("boil_eia860", 89_121, 89_121, 89_121),
+        ("frc_eia923", 681_764, 277_763, 26_781),
+        ("gen_eia923", None, 5_756_595, 479_605),
         ("gens_eia860", 591_645, 591_645, 591_645),
-        ("gf_eia923", 3_074_782, 3_074_782, 260_840),
+        ("gf_eia923", 3_105_223, 3_105_223, 263_056),
         ("own_eia860", 95_118, 95_118, 95_118),
         ("plants_eia860", 216_513, 216_513, 216_513),
         ("pu_eia860", 215_596, 215_596, 215_596),

test/validate/mcoe_test.py

@@ -94,11 +94,11 @@ def test_no_null_rows_mcoe(pudl_out_mcoe, live_dbs, df_name, thresh):
 @pytest.mark.parametrize(
     "df_name,monthly_rows,annual_rows",
     [
-        ("hr_by_unit", 413_173, 34_427),
-        ("hr_by_gen", 644_616, 53_707),
-        ("fuel_cost", 644_616, 53_707),
-        ("capacity_factor", 5_753_883, 479_379),
-        ("mcoe", 5_753_954, 479_383),
+        ("hr_by_unit", 415_117, 34_589),
+        ("hr_by_gen", 648_072, 53_995),
+        ("fuel_cost", 648_072, 53_995),
+        ("capacity_factor", 5_756_595, 479_605),
+        ("mcoe", 5_756_666, 479_609),
     ],
 )
 def test_minmax_rows_mcoe(pudl_out_mcoe, live_dbs, monthly_rows, annual_rows, df_name):