add pygrep-hooks and flake8-pytest-style Ruff linting (#214)

* remove useless pragmas

* enable pytest style checks

acro/acro_tables.py

@@ -145,7 +145,7 @@ def crosstab(  # pylint: disable=too-many-arguments,too-many-locals
         agg_func = get_aggfuncs(aggfunc)
 
         # requested table
-        table: DataFrame = pd.crosstab(  # type: ignore
+        table: DataFrame = pd.crosstab(
             index,
             columns,
             values,
@@ -321,33 +321,33 @@ def pivot_table(  # pylint: disable=too-many-arguments,too-many-locals
 
         # threshold check
         agg = [agg_threshold] * n_agg if n_agg > 1 else agg_threshold
-        t_values = pd.pivot_table(  # type: ignore
+        t_values = pd.pivot_table(
             data, values, index, columns, aggfunc=agg, margins=margins
         )
         masks["threshold"] = t_values
 
         if aggfunc is not None:
             # check for negative values -- currently unsupported
             agg = [agg_negative] * n_agg if n_agg > 1 else agg_negative
-            negative = pd.pivot_table(  # type: ignore
+            negative = pd.pivot_table(
                 data, values, index, columns, aggfunc=agg, margins=margins
             )
             if negative.to_numpy().sum() > 0:
                 masks["negative"] = negative
             # p-percent check
             agg = [agg_p_percent] * n_agg if n_agg > 1 else agg_p_percent
-            masks["p-ratio"] = pd.pivot_table(  # type: ignore
+            masks["p-ratio"] = pd.pivot_table(
                 data, values, index, columns, aggfunc=agg, margins=margins
             )
             # nk values check
             agg = [agg_nk] * n_agg if n_agg > 1 else agg_nk
-            masks["nk-rule"] = pd.pivot_table(  # type: ignore
+            masks["nk-rule"] = pd.pivot_table(
                 data, values, index, columns, aggfunc=agg, margins=margins
             )
             # check for missing values -- currently unsupported
             if CHECK_MISSING_VALUES:
                 agg = [agg_missing] * n_agg if n_agg > 1 else agg_missing
-                masks["missing"] = pd.pivot_table(  # type: ignore
+                masks["missing"] = pd.pivot_table(
                     data, values, index, columns, aggfunc=agg, margins=margins
                 )
 
@@ -782,7 +782,7 @@ def create_crosstab_masks(  # pylint: disable=too-many-arguments,too-many-locals
             logger.info(
                 "If there are multiple modes, one of them is randomly selected and displayed."
             )
-            masks["all-values-are-same"] = pd.crosstab(  # type: ignore
+            masks["all-values-are-same"] = pd.crosstab(
                 index,
                 columns,
                 values,
@@ -791,7 +791,7 @@ def create_crosstab_masks(  # pylint: disable=too-many-arguments,too-many-locals
                 dropna=dropna,
             )
         else:
-            t_values = pd.crosstab(  # type: ignore
+            t_values = pd.crosstab(
                 index,
                 columns,
                 values=values,
@@ -815,13 +815,13 @@ def create_crosstab_masks(  # pylint: disable=too-many-arguments,too-many-locals
             t_values = t_values < THRESHOLD
             masks["threshold"] = t_values
             # check for negative values -- currently unsupported
-            negative = pd.crosstab(  # type: ignore
+            negative = pd.crosstab(
                 index, columns, values, aggfunc=neg_funcs, margins=margins
             )
             if negative.to_numpy().sum() > 0:
                 masks["negative"] = negative
             # p-percent check
-            masks["p-ratio"] = pd.crosstab(  # type: ignore
+            masks["p-ratio"] = pd.crosstab(
                 index,
                 columns,
                 values,
@@ -830,17 +830,17 @@ def create_crosstab_masks(  # pylint: disable=too-many-arguments,too-many-locals
                 dropna=dropna,
             )
             # nk values check
-            masks["nk-rule"] = pd.crosstab(  # type: ignore
+            masks["nk-rule"] = pd.crosstab(
                 index, columns, values, aggfunc=nk_funcs, margins=margins, dropna=dropna
             )
             # check for missing values -- currently unsupported
             if CHECK_MISSING_VALUES:
-                masks["missing"] = pd.crosstab(  # type: ignore
+                masks["missing"] = pd.crosstab(
                     index, columns, values, aggfunc=missing_funcs, margins=margins
                 )
     else:
         # threshold check- doesn't matter what we pass for value
-        t_values = pd.crosstab(  # type: ignore
+        t_values = pd.crosstab(
             index,
             columns,
             values=None,
@@ -1499,7 +1499,7 @@ def crosstab_with_totals(  # pylint: disable=too-many-arguments,too-many-locals
         if crosstab:
             index_new, columns_new = get_index_columns(index, columns, data)
             # apply the crosstab with the new index and columns
-            table = pd.crosstab(  # type: ignore
+            table = pd.crosstab(
                 index_new,
                 columns_new,
                 values=values,
@@ -1534,7 +1534,7 @@ def crosstab_with_totals(  # pylint: disable=too-many-arguments,too-many-locals
             logger.setLevel(previous_level)
 
         else:
-            table = pd.pivot_table(  # type: ignore
+            table = pd.pivot_table(
                 data=data,
                 values=values,
                 index=index,
@@ -1618,7 +1618,7 @@ def manual_crossstab_with_totals(  # pylint: disable=too-many-arguments
         table = recalculate_margin(table, margins_name)
 
     elif aggfunc == "mean":
-        count_table = pd.crosstab(  # type: ignore
+        count_table = pd.crosstab(
             index=index,
             columns=columns,
             values=values,

pyproject.toml

@@ -23,14 +23,14 @@ lint.select = [
   "ICN",  # flake8-import-conventions
   "N",   # pep8-naming
 #  "PD",  # pandas-vet
-#  "PGH", # pygrep-hooks
+  "PGH", # pygrep-hooks
   "PIE",  # flake8-pie
 #  "PL",  # Pylint
   "PLC", # Pylint
   "PLE", # Pylint
 #  "PLR", # Pylint
 #  "PLW", # Pylint
-#  "PT",  # flake8-pytest-style
+  "PT",  # flake8-pytest-style
   "Q",   # flake8-quotes
 #  "RET", # flake8-return
   "RUF100",  # Ruff-specific

test/test_initial.py

@@ -17,15 +17,15 @@
 PATH: str = "RES_PYTEST"
 
 
-@pytest.fixture
+@pytest.fixture()
 def data() -> pd.DataFrame:
     """Load test data."""
     path = os.path.join("data", "test_data.dta")
     data = pd.read_stata(path)
     return data
 
 
-@pytest.fixture
+@pytest.fixture()
 def acro() -> ACRO:
     """Initialise ACRO."""
     return ACRO(suppress=True)
@@ -334,14 +334,14 @@ def test_output_removal(data, acro, monkeypatch):
     assert output_1.summary == correct_summary
     acro.print_outputs()
     # remove something that is not there
-    with pytest.raises(ValueError):
+    with pytest.raises(ValueError, match="unable to remove 123, key not found"):
         acro.remove_output("123")
     shutil.rmtree(PATH)
 
 
 def test_load_output():
     """Empty array when loading output."""
-    with pytest.raises(ValueError):
+    with pytest.raises(ValueError, match="error loading output"):
         record.load_output(PATH, [])
 
 
@@ -350,7 +350,7 @@ def test_finalise_invalid(data, acro):
     _ = acro.crosstab(data.year, data.grant_type)
     output_0 = acro.results.get_index(0)
     output_0.exception = "Let me have it"
-    with pytest.raises(ValueError):
+    with pytest.raises(ValueError, match="Invalid file extension.*"):
         _ = acro.finalise(PATH, "123")
 
 
@@ -405,10 +405,10 @@ def test_rename_output(data, acro):
     assert orig_name not in results.get_keys()
     assert os.path.exists(f"{PATH}/{new_name}_0.csv")
     # rename an output that doesn't exist
-    with pytest.raises(ValueError):
+    with pytest.raises(ValueError, match="unable to rename 123, key not found"):
         acro.rename_output("123", "name")
     # rename an output to another that already exists
-    with pytest.raises(ValueError):
+    with pytest.raises(ValueError, match="unable to rename, cross_table .* exists"):
         acro.rename_output("output_1", "cross_table")
     shutil.rmtree(PATH)
 
@@ -427,7 +427,7 @@ def test_add_comments(data, acro):
     acro.add_comments(output_0.uid, comment_1)
     assert output_0.comments == [comment, comment_1]
     # add a comment to something that is not there
-    with pytest.raises(ValueError):
+    with pytest.raises(ValueError, match="unable to find 123, key not found"):
         acro.add_comments("123", "comment")
     shutil.rmtree(PATH)
 
@@ -480,7 +480,7 @@ def test_suppression_error(caplog):
 
 def test_adding_exception(acro):
     """Adding an exception to an output that doesn't exist test."""
-    with pytest.raises(ValueError):
+    with pytest.raises(ValueError, match="unable to add exception: output_0 .*"):
         acro.add_exception("output_0", "Let me have it")
 
 
@@ -597,14 +597,14 @@ def test_hierachical_aggregation(data, acro):
 
 def test_single_values_column(data, acro):
     """Pandas does not allows multiple arrays for values."""
-    with pytest.raises(ValueError):
+    with pytest.raises(ValueError, match=".*specify a single values column.*"):
         _ = acro.crosstab(
             data.year,
             data.grant_type,
             values=[data.inc_activity, data.inc_activity],
             aggfunc="mean",
         )
-    with pytest.raises(ValueError):
+    with pytest.raises(ValueError, match=".*specify a single values column.*"):
         _ = acro.crosstab(data.year, data.grant_type, values=None, aggfunc="mean")
 
 

test/test_stata17_interface.py

@@ -25,7 +25,7 @@
 #    return ACRO()
 
 
-@pytest.fixture
+@pytest.fixture()
 def data() -> pd.DataFrame:
     """Load test data."""
     path = os.path.join("data", "test_data.dta")

test/test_stata_interface.py

@@ -26,7 +26,7 @@
 #    return ACRO()
 
 
-@pytest.fixture
+@pytest.fixture()
 def data() -> pd.DataFrame:
     """Load test data."""
     path = os.path.join("data", "test_data.dta")