Merge branch 'feat_fixture'

src/alchemlyb/__init__.py

@@ -54,6 +54,8 @@ def concat(objs, *args, **kwargs):
 
 
     .. versionadded:: 0.5.0"""
+    if isinstance(objs, pd.DataFrame):
+        return objs
     # Sanity check
     try:
         attrs = objs[0].attrs

src/alchemlyb/tests/conftest.py

@@ -0,0 +1,267 @@
+import pytest
+from alchemtest.amber import load_bace_example, load_simplesolvated
+from alchemtest.gmx import (
+    load_benzene,
+    load_expanded_ensemble_case_1,
+    load_expanded_ensemble_case_2,
+    load_expanded_ensemble_case_3,
+    load_water_particle_with_total_energy,
+    load_water_particle_with_potential_energy,
+    load_water_particle_without_energy,
+    load_ABFE,
+)
+from alchemtest.gomc import load_benzene as gomc_load_benzene
+from alchemtest.namd import (
+    load_tyr2ala,
+    load_idws,
+    load_restarted,
+    load_restarted_reversed,
+)
+
+from alchemlyb.parsing import gmx, amber, gomc, namd
+
+
+@pytest.fixture
+def gmx_benzene():
+    dataset = load_benzene()
+    return dataset["data"]
+
+
+@pytest.fixture
+def gmx_benzene_Coulomb_dHdl(gmx_benzene):
+    return [gmx.extract_dHdl(file, T=300) for file in gmx_benzene["Coulomb"]]
+
+
+@pytest.fixture
+def gmx_benzene_VDW_dHdl(gmx_benzene):
+    return [gmx.extract_dHdl(file, T=300) for file in gmx_benzene["VDW"]]
+
+
+@pytest.fixture
+def gmx_benzene_Coulomb_u_nk(gmx_benzene):
+    return [gmx.extract_u_nk(file, T=300) for file in gmx_benzene["Coulomb"]]
+
+
+@pytest.fixture
+def gmx_benzene_VDW_u_nk(gmx_benzene):
+    return [gmx.extract_u_nk(file, T=300) for file in gmx_benzene["VDW"]]
+
+
+@pytest.fixture
+def gmx_benzene_VDW_dHdl(gmx_benzene):
+    return [gmx.extract_dHdl(file, T=300) for file in gmx_benzene["VDW"]]
+
+
+@pytest.fixture
+def gmx_ABFE():
+    dataset = load_ABFE()
+    return dataset["data"]
+
+
+@pytest.fixture
+def gmx_ABFE_complex_n_uk(gmx_ABFE):
+    return [gmx.extract_u_nk(file, T=300) for file in gmx_ABFE["complex"]]
+
+
+@pytest.fixture
+def gmx_ABFE_complex_dHdl(gmx_ABFE):
+    return [gmx.extract_dHdl(file, T=300) for file in gmx_ABFE["complex"]]
+
+
+@pytest.fixture
+def gmx_expanded_ensemble_case_1():
+    dataset = load_expanded_ensemble_case_1()
+
+    return [
+        gmx.extract_u_nk(filename, T=300, filter=False)
+        for filename in dataset["data"]["AllStates"]
+    ]
+
+
+@pytest.fixture
+def gmx_expanded_ensemble_case_1_dHdl():
+    dataset = load_expanded_ensemble_case_1()
+
+    return [
+        gmx.extract_dHdl(filename, T=300, filter=False)
+        for filename in dataset["data"]["AllStates"]
+    ]
+
+
+@pytest.fixture
+def gmx_expanded_ensemble_case_2():
+    dataset = load_expanded_ensemble_case_2()
+
+    return [
+        gmx.extract_u_nk(filename, T=300, filter=False)
+        for filename in dataset["data"]["AllStates"]
+    ]
+
+
+@pytest.fixture
+def gmx_expanded_ensemble_case_2_dHdl():
+    dataset = load_expanded_ensemble_case_2()
+
+    return [
+        gmx.extract_dHdl(filename, T=300, filter=False)
+        for filename in dataset["data"]["AllStates"]
+    ]
+
+
+@pytest.fixture
+def gmx_expanded_ensemble_case_3():
+    dataset = load_expanded_ensemble_case_3()
+
+    return [
+        gmx.extract_u_nk(filename, T=300, filter=False)
+        for filename in dataset["data"]["AllStates"]
+    ]
+
+
+@pytest.fixture
+def gmx_expanded_ensemble_case_3_dHdl():
+    dataset = load_expanded_ensemble_case_3()
+
+    return [
+        gmx.extract_dHdl(filename, T=300, filter=False)
+        for filename in dataset["data"]["AllStates"]
+    ]
+
+
+@pytest.fixture
+def gmx_water_particle_with_total_energy():
+    dataset = load_water_particle_with_total_energy()
+
+    return [
+        gmx.extract_u_nk(filename, T=300) for filename in dataset["data"]["AllStates"]
+    ]
+
+
+@pytest.fixture
+def gmx_water_particle_with_total_energy_dHdl():
+    dataset = load_water_particle_with_total_energy()
+
+    return [
+        gmx.extract_dHdl(filename, T=300) for filename in dataset["data"]["AllStates"]
+    ]
+
+
+@pytest.fixture
+def gmx_water_particle_with_potential_energy():
+    dataset = load_water_particle_with_potential_energy()
+
+    return [
+        gmx.extract_u_nk(filename, T=300) for filename in dataset["data"]["AllStates"]
+    ]
+
+
+@pytest.fixture
+def gmx_water_particle_with_potential_energy_dHdl():
+    dataset = load_water_particle_with_potential_energy()
+
+    return [
+        gmx.extract_dHdl(filename, T=300) for filename in dataset["data"]["AllStates"]
+    ]
+
+
+@pytest.fixture
+def gmx_water_particle_without_energy():
+    dataset = load_water_particle_without_energy()
+
+    return [
+        gmx.extract_u_nk(filename, T=300) for filename in dataset["data"]["AllStates"]
+    ]
+
+
+@pytest.fixture
+def gmx_water_particle_without_energy_dHdl():
+    dataset = load_water_particle_without_energy()
+
+    return [
+        gmx.extract_dHdl(filename, T=300) for filename in dataset["data"]["AllStates"]
+    ]
+
+
+@pytest.fixture
+def amber_simplesolvated():
+    dataset = load_simplesolvated()
+    return dataset["data"]
+
+
+@pytest.fixture
+def amber_simplesolvated_charge_dHdl(amber_simplesolvated):
+    return [
+        amber.extract_dHdl(filename, T=298.0)
+        for filename in amber_simplesolvated["charge"]
+    ]
+
+
+@pytest.fixture
+def amber_simplesolvated_vdw_dHdl(amber_simplesolvated):
+    return [
+        amber.extract_dHdl(filename, T=298.0)
+        for filename in amber_simplesolvated["vdw"]
+    ]
+
+
+@pytest.fixture
+def amber_bace_example_complex_vdw():
+    dataset = load_bace_example()
+
+    return [
+        amber.extract_u_nk(filename, T=298.0)
+        for filename in dataset["data"]["complex"]["vdw"]
+    ]
+
+
+@pytest.fixture
+def gomc_benzene():
+    dataset = gomc_load_benzene()
+    return dataset["data"]
+
+
+@pytest.fixture
+def gomc_benzene_u_nk(gomc_benzene):
+    return [gomc.extract_u_nk(filename, T=298) for filename in gomc_benzene]
+
+
+@pytest.fixture
+def gomc_benzene_dHdl(gomc_benzene):
+    return [gomc.extract_dHdl(filename, T=298) for filename in gomc_benzene]
+
+
+@pytest.fixture
+def namd_tyr2ala():
+    dataset = load_tyr2ala()
+    u_nk1 = namd.extract_u_nk(dataset["data"]["forward"][0], T=300)
+    u_nk2 = namd.extract_u_nk(dataset["data"]["backward"][0], T=300)
+
+    # combine dataframes of fwd and rev directions
+    u_nk1[u_nk1.isna()] = u_nk2
+    u_nk = u_nk1.sort_index(level=u_nk1.index.names[1:])
+
+    return u_nk
+
+
+@pytest.fixture
+def namd_idws():
+    dataset = load_idws()
+    u_nk = namd.extract_u_nk(dataset["data"]["forward"], T=300)
+
+    return u_nk
+
+
+@pytest.fixture
+def namd_idws_restarted():
+    dataset = load_restarted()
+    u_nk = namd.extract_u_nk(dataset["data"]["both"], T=300)
+
+    return u_nk
+
+
+@pytest.fixture
+def namd_idws_restarted_reversed():
+    dataset = load_restarted_reversed()
+    u_nk = namd.extract_u_nk(dataset["data"]["both"], T=300)
+
+    return u_nk

src/alchemlyb/tests/test_convergence.py

@@ -8,17 +8,8 @@
 from alchemlyb.parsing import gmx
 
 
-@pytest.fixture()
-def gmx_benzene():
-    dataset = load_benzene()
-    return [gmx.extract_dHdl(dhdl, T=300) for dhdl in dataset["data"]["Coulomb"]], [
-        gmx.extract_u_nk(dhdl, T=300) for dhdl in dataset["data"]["Coulomb"]
-    ]
-
-
-def test_convergence_ti(gmx_benzene):
-    dHdl, u_nk = gmx_benzene
-    convergence = forward_backward_convergence(dHdl, "TI")
+def test_convergence_ti(gmx_benzene_Coulomb_dHdl):
+    convergence = forward_backward_convergence(gmx_benzene_Coulomb_dHdl, "TI")
     assert convergence.shape == (10, 5)
 
     assert convergence.loc[0, "Forward"] == pytest.approx(3.07, 0.01)
@@ -28,31 +19,29 @@ def test_convergence_ti(gmx_benzene):
 
 
 @pytest.mark.parametrize("estimator", ["MBAR", "BAR"])
-def test_convergence_fep(gmx_benzene, estimator):
-    dHdl, u_nk = gmx_benzene
-    convergence = forward_backward_convergence(u_nk, estimator)
+def test_convergence_fep(gmx_benzene_Coulomb_u_nk, estimator):
+    convergence = forward_backward_convergence(gmx_benzene_Coulomb_u_nk, estimator)
     assert convergence.shape == (10, 5)
     assert convergence.loc[0, "Forward"] == pytest.approx(3.02, 0.01)
     assert convergence.loc[0, "Backward"] == pytest.approx(3.06, 0.01)
     assert convergence.loc[9, "Forward"] == pytest.approx(3.05, 0.01)
     assert convergence.loc[9, "Backward"] == pytest.approx(3.04, 0.01)
 
 
-def test_convergence_wrong_estimator(gmx_benzene):
-    dHdl, u_nk = gmx_benzene
+def test_convergence_wrong_estimator(gmx_benzene_Coulomb_dHdl):
     with pytest.raises(ValueError, match="is not available in"):
-        forward_backward_convergence(u_nk, "WWW")
+        forward_backward_convergence(gmx_benzene_Coulomb_dHdl, "WWW")
 
 
-def test_convergence_wrong_cases(gmx_benzene):
-    dHdl, u_nk = gmx_benzene
+def test_convergence_wrong_cases(gmx_benzene_Coulomb_u_nk):
     with pytest.warns(DeprecationWarning, match="Using lower-case strings for"):
-        forward_backward_convergence(u_nk, "mbar")
+        forward_backward_convergence(gmx_benzene_Coulomb_u_nk, "mbar")
 
 
-def test_convergence_method(gmx_benzene):
-    dHdl, u_nk = gmx_benzene
-    convergence = forward_backward_convergence(u_nk, "MBAR", num=2, method="adaptive")
+def test_convergence_method(gmx_benzene_Coulomb_u_nk):
+    convergence = forward_backward_convergence(
+        gmx_benzene_Coulomb_u_nk, "MBAR", num=2, method="adaptive"
+    )
     assert len(convergence) == 2
 
 
@@ -75,12 +64,7 @@ def test_cummean_long_none_integter():
 
 
 def test_R_c_converged():
-    data = pd.Series(
-        data=[
-            0,
-        ]
-        * 100
-    )
+    data = pd.Series(data=[0] * 100)
     data.attrs["temperature"] = 310
     data.attrs["energy_unit"] = "kcal/mol"
     value, running_average = fwdrev_cumavg_Rc(data)
@@ -96,42 +80,16 @@ def test_R_c_notconverged():
 
 
 def test_R_c_real():
-    data = pd.Series(
-        data=np.hstack(
-            (
-                range(10),
-                [
-                    4.5,
-                ]
-                * 10,
-            )
-        )
-    )
+    data = pd.Series(data=np.hstack((range(10), [4.5] * 10)))
     data.attrs["temperature"] = 310
     data.attrs["energy_unit"] = "kcal/mol"
     value, running_average = fwdrev_cumavg_Rc(data, tol=2.0)
     np.testing.assert_allclose(value, 0.35)
 
 
 def test_A_c_real():
-    data = pd.Series(
-        data=np.hstack(
-            (
-                range(10),
-                [
-                    4.5,
-                ]
-                * 10,
-            )
-        )
-    )
+    data = pd.Series(data=np.hstack((range(10), [4.5] * 10)))
     data.attrs["temperature"] = 310
     data.attrs["energy_unit"] = "kcal/mol"
-    value = A_c(
-        [
-            data,
-        ]
-        * 2,
-        tol=2.0,
-    )
+    value = A_c([data] * 2, tol=2.0)
     np.testing.assert_allclose(value, 0.65)