run black

NNPDF · Jul 29, 2024 · 4d78845 · 4d78845
1 parent ddf1139
commit 4d78845
Show file tree

Hide file tree

Showing 17 changed files with 137 additions and 129 deletions.
diff --git a/validphys2/src/validphys/lhaindex.py b/validphys2/src/validphys/lhaindex.py
@@ -125,7 +125,7 @@ def infofilename(name):
 @lru_cache()
 def parse_info(name):
     with open(infofilename(name)) as infofile:
-        result=yaml.YAML(typ='safe', pure=True).load(infofile)
+        result = yaml.YAML(typ='safe', pure=True).load(infofile)
     return result
 
 

diff --git a/validphys2/src/validphys/tests/__init__.py b/validphys2/src/validphys/tests/__init__.py
@@ -1 +1 @@
-#
+#
diff --git a/validphys2/src/validphys/tests/test_arclengths.py b/validphys2/src/validphys/tests/test_arclengths.py
@@ -2,6 +2,7 @@
 from validphys.tableloader import sane_load
 from validphys.tests.test_regressions import make_table_comp
 
+
 @make_table_comp(sane_load)
 def test_arclength_mc(mc_pdf_config):
     """Integration test that ``arc_length_table`` action matches expected value
@@ -14,6 +15,7 @@ def test_arclength_mc(mc_pdf_config):
     table = API.arc_length_table(**mc_pdf_config)
     return table
 
+
 @make_table_comp(sane_load)
 def test_arclength_hessian(hessian_pdf_config):
     """Like ``test_arclength_mc`` except uses a hessian ``PDF``. Checks that

diff --git a/validphys2/src/validphys/tests/test_calcutils.py b/validphys2/src/validphys/tests/test_calcutils.py
@@ -6,17 +6,17 @@
 
 from validphys import calcutils
 
-sane_floats = floats(
-    min_value=-1, max_value=1, allow_nan=False, allow_infinity=False)
+sane_floats = floats(min_value=-1, max_value=1, allow_nan=False, allow_infinity=False)
 diffs = arrays(dtype=float, shape=10, elements=sane_floats)
 sqrtcov = arrays(dtype=float, shape=(10, 10), elements=sane_floats)
 
+
 @given(sqrtcov, diffs)
 def test_calc_chi2(s, d):
-    cov = s@s.T
-    #Handle zero matrices and so on
+    cov = s @ s.T
+    # Handle zero matrices and so on
     np.fill_diagonal(cov, np.diag(cov) + 1)
-    chi2 = d@la.inv(cov)@d
+    chi2 = d @ la.inv(cov) @ d
     chol = la.cholesky(cov, lower=True)
     calc = calcutils.calc_chi2(chol, d)
     assert np.allclose(chi2, calc)

diff --git a/validphys2/src/validphys/tests/test_closuretest.py b/validphys2/src/validphys/tests/test_closuretest.py
@@ -9,57 +9,46 @@
 
 from validphys.closuretest import bias_dataset, variance_dataset
 
+
 class TestResult:
     """class for testing base level estimators which expect a results object"""
+
     def __init__(self, central_value, rawdata=None):
         self.central_value = central_value
         self.rawdata = rawdata
         self.error_members = rawdata
         self.ndata = len(central_value)
         self.sqrtcovmat = np.identity(self.ndata)
 
-    def __len__(self,):
+    def __len__(self):
         return self.ndata
 
+
 N_DATA = 5
 N_REPLICAS = 10
 
-#TODO: make these fixtures?
+# TODO: make these fixtures?
 # these are proxies for results tuples of data and theory
-ones_results = 2*[TestResult(np.ones(N_DATA), np.ones((N_DATA, N_REPLICAS)))]
-twos_results = 2*[TestResult(2*np.ones(N_DATA), 2*np.ones((N_DATA, N_REPLICAS)))]
+ones_results = 2 * [TestResult(np.ones(N_DATA), np.ones((N_DATA, N_REPLICAS)))]
+twos_results = 2 * [TestResult(2 * np.ones(N_DATA), 2 * np.ones((N_DATA, N_REPLICAS)))]
+
+replicas = np.arange(N_REPLICAS)[np.newaxis, :] * np.ones((N_DATA, 1))
+replicas_result = 2 * [TestResult(replicas.mean(axis=1), replicas)]
 
-replicas = np.arange(N_REPLICAS)[np.newaxis, :]*np.ones((N_DATA, 1))
-replicas_result = 2*[TestResult(replicas.mean(axis=1), replicas)]
 
 def test_bias_function():
     bias_ones = bias_dataset(
-        ones_results,
-        [ones_results], # need list of length one to emulate collect
-        None,
-        None,
+        ones_results, [ones_results], None, None  # need list of length one to emulate collect
     )
     assert np.allclose(0, bias_ones.bias)
-    bias_one_two = bias_dataset(
-        ones_results,
-        [twos_results],
-        None,
-        None,
-    )
+    bias_one_two = bias_dataset(ones_results, [twos_results], None, None)
     assert np.allclose(N_DATA, bias_one_two.bias)
 
+
 def test_variance_function():
-    vardata = variance_dataset(
-        ones_results,
-        None,
-        None,
-    )
+    vardata = variance_dataset(ones_results, None, None)
     assert np.allclose(0, vardata.variance)
-    var_reps = variance_dataset(
-        replicas_result,
-        None,
-        None,
-    )
+    var_reps = variance_dataset(replicas_result, None, None)
     # calc explicitly what variance should be
-    expected = np.sum(((np.arange(N_REPLICAS) - 4.5)**2)*N_DATA/N_REPLICAS)
+    expected = np.sum(((np.arange(N_REPLICAS) - 4.5) ** 2) * N_DATA / N_REPLICAS)
     assert np.allclose(expected, var_reps.variance)
diff --git a/validphys2/src/validphys/tests/test_core.py b/validphys2/src/validphys/tests/test_core.py
@@ -5,6 +5,7 @@
 from validphys import core
 from validphys.tests.conftest import PDF, HESSIAN_PDF
 
+
 @pytest.mark.parametrize("pdf_name", [PDF, HESSIAN_PDF])
 def test_pdf(pdf_name):
     """Check that the given PDF and their relevant attributes can be read

diff --git a/validphys2/src/validphys/tests/test_fitveto.py b/validphys2/src/validphys/tests/test_fitveto.py
@@ -2,9 +2,8 @@
 import pytest
 import itertools
 from hypothesis import given
-from hypothesis.strategies import (floats, integers, tuples, lists,
-    booleans)
-from hypothesis.extra.numpy import arrays,  array_shapes
+from hypothesis.strategies import floats, integers, tuples, lists, booleans
+from hypothesis.extra.numpy import arrays, array_shapes
 
 from validphys.fitveto import distribution_veto, determine_vetoes
 from validphys.fitveto import NSIGMA_DISCARD_ARCLENGTH, NSIGMA_DISCARD_CHI2, INTEG_THRESHOLD
@@ -14,15 +13,21 @@
 nicefloats = floats(allow_nan=False, allow_infinity=False)
 integ_floats = floats(allow_nan=False, max_value=0.4)
 
-fitinfos = tuples(integers(min_value=1),
-        nicefloats, nicefloats, nicefloats,
-        booleans(),
-        arrays(float, shape=7, elements=nicefloats),
-        arrays(float, shape=5, elements=integ_floats)).map(FitInfo._make)
+fitinfos = tuples(
+    integers(min_value=1),
+    nicefloats,
+    nicefloats,
+    nicefloats,
+    booleans(),
+    arrays(float, shape=7, elements=nicefloats),
+    arrays(float, shape=5, elements=integ_floats),
+).map(FitInfo._make)
 
 
 thresholds = floats(min_value=1, max_value=10)
 distributions = arrays(float, shape=shape1d, elements=nicefloats)
+
+
 # Ignore over- and underflow warnings.
 @pytest.mark.filterwarnings("ignore")
 @given(distributions, thresholds)
@@ -32,18 +37,24 @@ def test_distribution_veto(arr, threshold):
     assert np.all(masked - np.mean(arr) <= threshold * np.std(arr))
 
 
-#The case where the list is empty is handled in postfit
+# The case where the list is empty is handled in postfit
 @pytest.mark.filterwarnings('ignore')
 @given(lists(fitinfos, min_size=1))
 def test_determine_vetoes(fitinfos):
-    vetoes = determine_vetoes(fitinfos, NSIGMA_DISCARD_CHI2, NSIGMA_DISCARD_ARCLENGTH, INTEG_THRESHOLD)
+    vetoes = determine_vetoes(
+        fitinfos, NSIGMA_DISCARD_CHI2, NSIGMA_DISCARD_ARCLENGTH, INTEG_THRESHOLD
+    )
     assert np.all(vetoes['Positivity'] == np.array([info.is_positive for info in fitinfos]))
     tot = vetoes['Total']
     assert all(np.all(tot & val == tot) for val in vetoes.values())
-    single_replica_veto = determine_vetoes([fitinfos[0]], NSIGMA_DISCARD_CHI2, NSIGMA_DISCARD_ARCLENGTH, INTEG_THRESHOLD)
+    single_replica_veto = determine_vetoes(
+        [fitinfos[0]], NSIGMA_DISCARD_CHI2, NSIGMA_DISCARD_ARCLENGTH, INTEG_THRESHOLD
+    )
     assert single_replica_veto['Total'][0] == single_replica_veto['Positivity'][0]
     # distribution_vetoes applied a second time should veto nothing
     if sum(tot) > 0:
         passing_fitinfos = list(itertools.compress(fitinfos, tot))
-        second_vetoes = determine_vetoes(passing_fitinfos, NSIGMA_DISCARD_CHI2, NSIGMA_DISCARD_ARCLENGTH, INTEG_THRESHOLD)
+        second_vetoes = determine_vetoes(
+            passing_fitinfos, NSIGMA_DISCARD_CHI2, NSIGMA_DISCARD_ARCLENGTH, INTEG_THRESHOLD
+        )
         assert sum(vetoes["Total"]) == sum(second_vetoes["Total"])
diff --git a/validphys2/src/validphys/tests/test_mc2hessian.py b/validphys2/src/validphys/tests/test_mc2hessian.py
@@ -6,6 +6,7 @@
 
 NEIG = 5
 
+
 def test_mc2hessian(data_config, tmp):
     """Tests that the generated hessian PDF is indeed marked as such
     and that the metadata is not obviously broken

diff --git a/validphys2/src/validphys/tests/test_metaexps.py b/validphys2/src/validphys/tests/test_metaexps.py
@@ -23,9 +23,5 @@ def test_no_systematic_overlaps():
     # TODO: when we have dataset defaults it would be nice to check that none
     # of the default systematics overlap - should be fine for now.
     ds_inputs = [{"dataset": ds} for ds in ds_names]
-    res = API.print_systype_overlap(
-        dataset_inputs=ds_inputs, metadata_group="experiment"
-    )
-    assert isinstance(
-        res, str
-    ), f"Overlap found between metadata experiments {res[0]} {res[1]}"
+    res = API.print_systype_overlap(dataset_inputs=ds_inputs, metadata_group="experiment")
+    assert isinstance(res, str), f"Overlap found between metadata experiments {res[0]} {res[1]}"
diff --git a/validphys2/src/validphys/tests/test_plots.py b/validphys2/src/validphys/tests/test_plots.py
@@ -97,7 +97,12 @@ def test_plot_xq2_custom():
     dataset_inputs = [
         {'dataset': 'NMC_NC_NOTFIXED_P_EM-SIGMARED', 'variant': 'legacy', 'custom_group': 'one'},
         {'dataset': 'ATLAS_TTBAR_7TEV_TOT_X-SEC', 'variant': 'legacy', 'custom_group': 'one'},
-        {'dataset': 'CMS_Z0J_8TEV_PT-Y', 'cfac': ['NRM'], 'variant': 'legacy', 'custom_group': 'two'},
+        {
+            'dataset': 'CMS_Z0J_8TEV_PT-Y',
+            'cfac': ['NRM'],
+            'variant': 'legacy',
+            'custom_group': 'two',
+        },
     ]
 
     return API.plot_xq2(

diff --git a/validphys2/src/validphys/tests/test_postfit.py b/validphys2/src/validphys/tests/test_postfit.py
@@ -74,10 +74,7 @@ def test_postfit(tmp):
     for x in range(1, nrep + 1):
         repnos = set()
         # [File in PDF set, file in fit]
-        files = [
-            pdfsetpath / f"{TMPFIT}_{x:04d}.dat",
-            postfitpath / f"replica_{x}/{TMPFIT}.dat",
-        ]
+        files = [pdfsetpath / f"{TMPFIT}_{x:04d}.dat", postfitpath / f"replica_{x}/{TMPFIT}.dat"]
         for file in files:
             with open(file, "r") as f:
                 data = yaml.safe_load_all(f)

diff --git a/validphys2/src/validphys/tests/test_pyfkdata.py b/validphys2/src/validphys/tests/test_pyfkdata.py
@@ -100,7 +100,10 @@ def test_positivity(pdf_name):
         assert_allclose(preds.values, core_predictions.rawdata)
         # Now do the same with the API
         api_predictions = API.positivity_predictions_data_result(
-            theoryid=THEORYID, use_cuts="internal", pdf=pdf_name, posdataset={"dataset": posset, "maxlambda": 1e6}
+            theoryid=THEORYID,
+            use_cuts="internal",
+            pdf=pdf_name,
+            posdataset={"dataset": posset, "maxlambda": 1e6},
         )
         assert_allclose(preds.values, api_predictions.rawdata)
         # And now check that the results are correct for any kind of PDF

diff --git a/validphys2/src/validphys/tests/test_tableloader.py b/validphys2/src/validphys/tests/test_tableloader.py
@@ -8,66 +8,65 @@
 def test_min_combination():
     nan = np.nan
     dfdicts = [
-            {('NNPDF31_nlo_as_0130_uncorr__combined',
-              'chi2'): {('NMC', 'NMC', 204, 394): nan, ('NMC',
-               'NMC',
-               204,
-               400): 679.78465060721771, ('NMC', 'NMCPD', 121, 394): nan, ('NMC',
-               'NMCPD',
-               121,
-               400): 226.73557951005108, ('NMC', 'Total', 325, 394): nan, ('NMC',
-               'Total',
-               325,
-               400): 906.52023011726862, ('SLAC', 'SLACD', 34, 394): nan, ('SLAC',
-               'SLACD',
-               34,
-               400): 55.48265988454024, ('SLAC', 'SLACP', 33, 394): nan, ('SLAC',
-               'SLACP',
-               33,
-               400): 56.765548408772041, ('SLAC', 'Total', 67, 394): nan, ('SLAC',
-               'Total',
-               67,
-               400): 110.50940462648715}},
-
-          {('NNPDF31_nlo_as_0130_uncorr__combined', 'chi2'):
-              {('NMC', 'NMC', 204, 394): 572.89990139102679, ('NMC','NMC', 204,
-           400): 643.10896957499369, ('NMC',
-           'NMCPD',
-           121,
-           394): 228.66185589823439, ('NMC', 'NMCPD', 121, 400): 232.87411189255329, ('NMC',
-           'Total',
-           325,
-           394): 801.56175728926098, ('NMC',
-           'Total',
-           325,
-           400): 875.98308146754709, ('SLAC', 'SLACD', 34, 394): 62.071957514383364, ('SLAC',
-           'SLACD',
-           34,
-           400): 44.278821773436725, ('SLAC',
-           'SLACP',
-           33,
-           394): 70.465557968855123, ('SLAC', 'SLACP', 33, 400): 57.213453384186352, ('SLAC',
-           'Total',
-           67,
-           394): 126.25943979466223, ('SLAC', 'Total', 67, 400): 101.69776217874313}},
+        {
+            ('NNPDF31_nlo_as_0130_uncorr__combined', 'chi2'): {
+                ('NMC', 'NMC', 204, 394): nan,
+                ('NMC', 'NMC', 204, 400): 679.78465060721771,
+                ('NMC', 'NMCPD', 121, 394): nan,
+                ('NMC', 'NMCPD', 121, 400): 226.73557951005108,
+                ('NMC', 'Total', 325, 394): nan,
+                ('NMC', 'Total', 325, 400): 906.52023011726862,
+                ('SLAC', 'SLACD', 34, 394): nan,
+                ('SLAC', 'SLACD', 34, 400): 55.48265988454024,
+                ('SLAC', 'SLACP', 33, 394): nan,
+                ('SLAC', 'SLACP', 33, 400): 56.765548408772041,
+                ('SLAC', 'Total', 67, 394): nan,
+                ('SLAC', 'Total', 67, 400): 110.50940462648715,
+            }
+        },
+        {
+            ('NNPDF31_nlo_as_0130_uncorr__combined', 'chi2'): {
+                ('NMC', 'NMC', 204, 394): 572.89990139102679,
+                ('NMC', 'NMC', 204, 400): 643.10896957499369,
+                ('NMC', 'NMCPD', 121, 394): 228.66185589823439,
+                ('NMC', 'NMCPD', 121, 400): 232.87411189255329,
+                ('NMC', 'Total', 325, 394): 801.56175728926098,
+                ('NMC', 'Total', 325, 400): 875.98308146754709,
+                ('SLAC', 'SLACD', 34, 394): 62.071957514383364,
+                ('SLAC', 'SLACD', 34, 400): 44.278821773436725,
+                ('SLAC', 'SLACP', 33, 394): 70.465557968855123,
+                ('SLAC', 'SLACP', 33, 400): 57.213453384186352,
+                ('SLAC', 'Total', 67, 394): 126.25943979466223,
+                ('SLAC', 'Total', 67, 400): 101.69776217874313,
+            }
+        },
     ]
     dfs = [pd.DataFrame.from_dict(df) for df in dfdicts]
-    res = tableloader.combine_pseudorreplica_tables(dfs, ['NNPDF31_nlo_as_0130_uncorr__combined'],  )
-    assert pd.isnull(res.loc[pd.IndexSlice[:,:,:,394],:]).all().all()
-    assert (res.loc[pd.IndexSlice[:,:,:,400],:] == dfs[1].loc[pd.IndexSlice[:,:,:,400],:]).all().all()
+    res = tableloader.combine_pseudorreplica_tables(dfs, ['NNPDF31_nlo_as_0130_uncorr__combined'])
+    assert pd.isnull(res.loc[pd.IndexSlice[:, :, :, 394], :]).all().all()
+    assert (
+        (res.loc[pd.IndexSlice[:, :, :, 400], :] == dfs[1].loc[pd.IndexSlice[:, :, :, 400], :])
+        .all()
+        .all()
+    )
     res2 = tableloader.combine_pseudorreplica_tables(
-            dfs, ['NNPDF31_nlo_as_0130_uncorr__combined'], min_points_required=1)
-    assert not pd.isnull(res2.loc[pd.IndexSlice[:,:,:,394],:]).all().all()
-    assert (res2.loc[pd.IndexSlice[:,:,:,400],:] == dfs[1].loc[pd.IndexSlice[:,:,:,400],:]).all().all()
+        dfs, ['NNPDF31_nlo_as_0130_uncorr__combined'], min_points_required=1
+    )
+    assert not pd.isnull(res2.loc[pd.IndexSlice[:, :, :, 394], :]).all().all()
+    assert (
+        (res2.loc[pd.IndexSlice[:, :, :, 400], :] == dfs[1].loc[pd.IndexSlice[:, :, :, 400], :])
+        .all()
+        .all()
+    )
 
 
 def test_extrasum_slice():
     l = Loader()
-    f =  l.check_vp_output_file('ljzWOixPQfmq5dA1-EUocg==/tables/fits_chi2_table.csv')
+    f = l.check_vp_output_file('ljzWOixPQfmq5dA1-EUocg==/tables/fits_chi2_table.csv')
     d, l = tableloader.load_adapted_fits_chi2_table(f)
     components = ['LHCb Total', 'ATLASTTBARTOT', 'LHCBZ940PB']
     sliced = tableloader.get_extrasum_slice(d, components)
     slicel = tableloader.get_extrasum_slice(d, components)
-    assert sliced.shape == (3,1)
-    assert sliced.loc[('LHCb', 'Total'),:].shape == (1,)
+    assert sliced.shape == (3, 1)
+    assert sliced.loc[('LHCb', 'Total'), :].shape == (1,)
     assert slicel.size == 3