fix path issue on case-sensitive file systems

Author: janosh

mb_discovery/plot_scripts/plot_funcs.py

@@ -55,6 +55,10 @@ def hist_classified_stable_as_func_of_hull_dist(
     e_above_hull_vals = df[e_above_hull_col]
     residuals = error + e_above_hull_vals
 
+    if stability_crit not in get_args(StabilityCriterion):
+        raise ValueError(
+            f"Invalid {stability_crit=} must be one of {get_args(StabilityCriterion)}"
+        )
     if stability_crit == "energy":
         test = residuals
     elif "std" in stability_crit:

mb_discovery/plot_scripts/precision_recall_vs_calc_count.py

@@ -20,15 +20,15 @@
 
 
 # %%
-df_hull = pd.read_csv(
-    f"{ROOT}/data/2022-06-11-from-rhys/wbm-e-above-mp-hull.csv"
-).set_index("material_id")
+DATA_DIR = f"{ROOT}/data/2022-06-11-from-rhys"
+df_hull = pd.read_csv(f"{DATA_DIR}/wbm-e-above-mp-hull.csv").set_index("material_id")
 
 dfs: dict[str, pd.DataFrame] = {}
 for model_name in ("Wren", "CGCNN", "Voronoi"):
-    dfs[model_name] = pd.read_csv(
-        f"{ROOT}/data/2022-06-11-from-rhys/{model_name}-mp-initial-structures.csv"
+    df = pd.read_csv(
+        f"{DATA_DIR}/{model_name.lower()}-mp-initial-structures.csv"
     ).set_index("material_id")
+    dfs[model_name] = df
 
 # dfs["M3GNet"] = pd.read_json(
 #     f"{ROOT}/data/2022-08-16-m3gnet-wbm-relax-results-IS2RE.json.gz"

tests/test_plot_funcs.py

@@ -9,15 +9,14 @@
 from mb_discovery.plot_scripts.plot_funcs import precision_recall_vs_calc_count
 
 
-df_hull = pd.read_csv(
-    f"{ROOT}/data/2022-06-11-from-rhys/wbm-e-above-mp-hull.csv"
-).set_index("material_id")
+DATA_DIR = f"{ROOT}/data/2022-06-11-from-rhys"
+
+df_hull = pd.read_csv(f"{DATA_DIR}/wbm-e-above-mp-hull.csv").set_index("material_id")
 
 test_dfs: dict[str, pd.DataFrame] = {}
 for model_name in ("Wren", "CGCNN", "Voronoi"):
     df = pd.read_csv(
-        f"{ROOT}/data/2022-06-11-from-rhys/{model_name}-mp-initial-structures.csv",
-        nrows=100,
+        f"{DATA_DIR}/{model_name.lower()}-mp-initial-structures.csv", nrows=100
     ).set_index("material_id")
 
     df["e_above_mp_hull"] = df_hull.e_above_mp_hull