minor fixes and notes

2d.py

@@ -18,7 +18,7 @@ def filter_for_2d(df: pd.DataFrame, group: int):
 
 
 reference_dir = Path(base_dir / f"shannon_512_100")
-df_ref, _ = read_file(reference_dir/ "output_0004.hdf5")
+df_ref, _ = read_file(reference_dir / "output_0004.hdf5")
 
 df = df_ref.loc[df_ref["FOFGroupIDs"] == 1]
 df2 = df_ref.loc[df_ref["FOFGroupIDs"] == 4]

cic.py

@@ -78,11 +78,14 @@ if __name__ == '__main__':
     ax: Axes = fig.gca()
 
     print("start cic")
-    rho, extent = cic_from_radius(df_ref.X.to_numpy(), df_ref.Y.to_numpy(), 2000, 48.85, 56.985, 2, periodic=False)
-    # rho, extent = cic_range(df_ref.X.to_numpy(), df_ref.Y.to_numpy(), 1000, 30, 70, 30, 70, periodic=False)
+    # rho, extent = cic_from_radius(df_ref.X.to_numpy(), df_ref.Y.to_numpy(), 2000, 48.85, 56.985, 2, periodic=False)
+    rho, extent = cic_from_radius(df_ref.X.to_numpy(), df_ref.Y.to_numpy(), 500, 56, 49.5, 5, periodic=False)
+    # rho, extent = cic_range(df_ref.X.to_numpy(), df_ref.Y.to_numpy(), 1000, 0, 100, 0, 100, periodic=False)
     print("finished cic")
     data = 1.1 + rho
     i = ax.imshow(data.T, norm=LogNorm(), extent=extent, origin="lower")
+    ax.set_title(str(input_file.relative_to(input_file.parent.parent)))
+
     fig.colorbar(i)
     plt.show()
 

compare_halos.py

@@ -56,7 +56,7 @@ def compare_halo_resolutions(
     df_ref, ref_meta = read_file(reference_dir / "output_0004.hdf5")
     if velo_halos:
         df_ref_halo, ref_halo_lookup, ref_unbound = read_velo_halo_particles(reference_dir, recursivly=False)
-        # TODO: clarify if unbound particles should be ignored
+        # TODO: clarify if unbound particles should be ignored -> yes
         for k, v in ref_halo_lookup.items():
             v.update(ref_unbound[k])
     else:

halo_mass_functions.py

@@ -9,9 +9,11 @@ from read_vr_files import read_velo_halos
 fig: Figure = plt.figure()
 ax: Axes = fig.gca()
 
-num_bins = 100
+num_bins = 30
 sim_volume = 100 ** 3
 
+# notes: shannon + db2
+
 linestyles = ["solid", "dashed", "dotted"]
 colors = ["C1", "C2", "C3", "C4"]
 
@@ -21,7 +23,7 @@ for i, waveform in enumerate(["DB2", "DB4", "DB8", "shannon"]):
         dir = base_dir / f"{waveform}_{resolution}_100"
         halos = read_velo_halos(dir)
 
-        # halos = halos[halos["Mvir"] > 2]  # there seem to be multiple halos with a mass of 1.88196993
+        halos = halos[halos["Mvir"] > 2]  # there seem to be multiple halos with a mass of 1.88196993
 
         # halos.to_csv("weird_halos.csv")
 

readfiles.py

@@ -20,21 +20,24 @@ def read_file(file: Path) -> Tuple[pd.DataFrame, ParticlesMeta]:
     meta_cache_file = file.with_suffix(".cache_meta.pickle")
     if not (cache_file.exists() and meta_cache_file.exists()):
         reference_file = h5py.File(file)
+        has_fof=        "FOFGroupIDs" in reference_file["PartType1"]
 
         masses = reference_file["PartType1"]["Masses"]
         if not np.all(masses == masses[0]):
             raise ValueError("only equal mass particles are supported for now")
         df = pd.DataFrame(reference_file["PartType1"]["Coordinates"], columns=["X", "Y", "Z"])
-        df2 = pd.DataFrame(reference_file["PartType1"]["FOFGroupIDs"], columns=["FOFGroupIDs"]).astype("category")
-        df = df.merge(df2, "outer", left_index=True, right_index=True)
-        del df2
+        if has_fof:
+            df2 = pd.DataFrame(reference_file["PartType1"]["FOFGroupIDs"], columns=["FOFGroupIDs"]).astype("category")
+            df = df.merge(df2, "outer", left_index=True, right_index=True)
+            del df2
         df3 = pd.DataFrame(reference_file["PartType1"]["ParticleIDs"], columns=["ParticleIDs"])
 
         df = df.merge(df3, "outer", left_index=True, right_index=True)
         del df3
         df.set_index("ParticleIDs", inplace=True)
-        print("sorting")
-        df.sort_values("FOFGroupIDs",inplace=True)
+        if has_fof:
+            print("sorting")
+            df.sort_values("FOFGroupIDs",inplace=True)
         meta = ParticlesMeta(
             particle_mass=masses[0]
         )

sizes.py

@@ -16,9 +16,10 @@ with pd.option_context('display.max_rows', None):
 
 fig: Figure = plt.figure()
 ax: Axes = fig.gca()
+# hist2d, log?
 
-x_col = "ref_Mvir"
-y_col = "comp_Mvir"
+x_col = "ref_Mass_200mean"
+y_col = "comp_Mass_200mean"
 
 # ax.scatter(df["ref_sizes"], df["comp_sizes"], s=1, alpha=.3)
 ax.scatter(df[x_col], df[y_col], s=1, alpha=.3)
@@ -31,7 +32,7 @@ ax.set_ylabel(y_col)
 min_x = min([min(df[x_col]), min(df[y_col])])
 max_x = max([max(df[x_col]), max(df[y_col])])
 
-ax.plot([min_x, max_x], [min_x, max_x], linewidth=1, color="C2")
+ax.loglog([min_x, max_x], [min_x, max_x], linewidth=1, color="C2")
 
 fig2: Figure = plt.figure()
 ax2: Axes = fig2.gca()