more code clean up

.pre-commit-config.yaml

@@ -12,7 +12,7 @@ repos:
       - id: isort
 
   - repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 22.6.0
     hooks:
       - id: black
 
@@ -22,7 +22,7 @@ repos:
       - id: flake8
 
   - repo: https://github.com/asottile/pyupgrade
-    rev: v2.31.1
+    rev: v2.34.0
     hooks:
       - id: pyupgrade
         args: [--py39-plus]
@@ -33,7 +33,7 @@ repos:
       - id: format-ipy-cells
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.1.0
+    rev: v4.3.0
     hooks:
       - id: check-case-conflict
       - id: check-symlinks
@@ -44,7 +44,7 @@ repos:
       - id: trailing-whitespace
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.942
+    rev: v0.961
     hooks:
       - id: mypy
         additional_dependencies: [types-pyyaml]

ml_stability/hist_clf_vary.py

@@ -23,21 +23,22 @@
 # %%
 fig, ax = plt.subplots(1, 1, figsize=(10, 9))
 
-df_hull = pd.read_csv(f"{ROOT}/data/wbm_e_above_mp.csv")
+df_hull = pd.read_csv(f"{ROOT}/data/wbm_e_above_mp_hull.csv").set_index("material_id")
 
-e_hull_dict = dict(zip(df_hull.material_id, df_hull.e_above_hull))
 
 for model_name, color in zip(
     # ["wren", "cgcnn", "cgcnn-d"],
     # ["tab:blue", "tab:red", "tab:purple"],
     ["wren", "voronoi", "cgcnn"],
     ["tab:blue", "tab:orange", "tab:red"],
 ):
-    df = pd.read_csv(f"{ROOT}/data/{model_name}-mp-initial-structures.csv")
+    df = pd.read_csv(f"{ROOT}/data/{model_name}-mp-initial-structures.csv").set_index(
+        "material_id"
+    )
 
-    df["e_above_hull"] = pd.to_numeric(df["material_id"].map(e_hull_dict))
+    df["e_above_hull"] = df_hull.e_above_hull
 
-    df = df.dropna(axis=0, subset=["e_above_hull"])
+    df = df.dropna(subset=["e_above_hull"])
 
     rare = "all"