fix linting issues

Author: margovskiy_merck

obsidian/experiment/advanced_design.py

@@ -22,7 +22,7 @@ class AdvExpDesigner:
     """
 
     def __init__(
-        self, continuous_params=None, conditional_subparameters=None, subparam_mapping=None, design_df = None
+        self, continuous_params=None, conditional_subparameters=None, subparam_mapping=None, design_df=None
     ):
         """
         Initializes the AdvExpDesigner with experimental parameters and optional subparameter mappings.
@@ -37,17 +37,18 @@ def __init__(
 
         if design_df is not None and not design_df.empty:
             self.design = design_df
-            self.continuous_keys = list(self.continuous_params.keys()) if continuous_params else design_df.select_dtypes(include=['number']).columns.tolist()
             self.categorical_keys = design_df.select_dtypes(exclude=['number']).columns.tolist()
-        else: 
+            if continuous_params:
+                self.continuous_keys = list(self.continuous_params.keys())
+            else:
+                self.continuous_keys = design_df.select_dtypes(include=['number']).columns.tolist()
+        else:
             self.continuous_keys = list(self.continuous_params.keys()) if continuous_params else []
             self.categorical_keys = list(self.conditional_subparameters.keys()) if conditional_subparameters else []
 
         self.subparam_mapping = subparam_mapping or infer_subparam_mapping(self.conditional_subparameters)
         self.subparam_key = (list(self.subparam_mapping.values())[0] if self.subparam_mapping else None)
 
-    #consider adding a constructor function with DataFrame of design preloaded
-    #include subparameter mapping schema, buffer_type -> pH, catalyst -> loading_range
 
     def generate_design(self, seed, n_samples, optimize_categories=True):
         """
@@ -433,7 +434,8 @@ def assign_conditional_subparameter(
 
 def infer_subparam_mapping(conditional_subparameters):
     mapping = {}
-    if len(conditional_subparameters) == 0: return mapping
+    if len(conditional_subparameters) == 0:
+        return mapping
     else:
         for cat_param, levels in conditional_subparameters.items():
             subparam_candidates = set()
@@ -923,7 +925,6 @@ def find_best_design_parallel(
 def plot_design_quality_evolution(metrics_df):
     metrics_df = metrics_df.sort_values("seed")
 
-
     fig, axes = plt.subplots(2, 3, figsize=(15, 10))
     metrics = metrics_df.columns
 

obsidian/experiment/sampling.py

@@ -1,10 +1,11 @@
-import numpy as np 
+import numpy as np
 import pandas as pd
 import matplotlib.pyplot as plt
 
+
 def generate_weights(df, n, bias, plot_weights=False, enforce=False):
     """
-    Generates a Pandas series of weights for each datum given a particular bias. 
+    Generates a Pandas series of weights for each datum given a particular bias.
 
     df: DataFrame of candidates
     n:  size of the design to pick
@@ -15,7 +16,7 @@ def generate_weights(df, n, bias, plot_weights=False, enforce=False):
     plot_weights: boolean, whether to plot distribution of weights, default False
     enforce: boolean, whether to force biases, default False
 
-    Returns: Pandas Series of normalized row weights. 
+    Returns: Pandas Series of normalized row weights.
     """
     weights = pd.Series(1.0, index=df.index)
     for col, params in bias.items():
@@ -29,7 +30,7 @@ def generate_weights(df, n, bias, plot_weights=False, enforce=False):
     if enforce:
         if (weights > 0).sum() < n:
             raise ValueError(f"Not enough rows ({(weights > 0).sum()}) satisfy all enforce conditions for n={n}.")
-        
+       
     weights = weights / weights.sum()
 
     print("Weights min:", weights.min(), "max:", weights.max())
@@ -43,10 +44,11 @@ def generate_weights(df, n, bias, plot_weights=False, enforce=False):
         plt.show()
 
     return weights
-    
+
+
 def sample_with_bias(df, n, replace=False, seed=None, bias=None, enforce=False, plot_weights=False):
     """
-    Returns a random Pandas DataFrame sample of data points from a population with or without bias. 
+    Returns a random Pandas DataFrame sample of data points from a population with or without bias.
 
     df: DataFrame of candidates
     n:  int, size of the design to pick
@@ -58,14 +60,15 @@ def sample_with_bias(df, n, replace=False, seed=None, bias=None, enforce=False,
     enforce: boolean, whether to force biases, default False
     plot_weights: boolean, whether to plot distribution of weights, default False
 
-    Returns: Pandas DataFrame of sampled data points. 
+    Returns: Pandas DataFrame of sampled data points.
     """
     if bias:
         w = generate_weights(df, n, bias, plot_weights, enforce)
         return df.sample(n=n, replace=replace, random_state=seed, weights=w)
     else:
         return df.sample(n=n, replace=replace, random_state=seed)
 
+
 def _space_filling_score(Z, metric="hybrid"):
     """
     Z: (k, d) standardized features of the candidate sample
@@ -87,6 +90,7 @@ def _space_filling_score(Z, metric="hybrid"):
         return 0.6 * d_min + 0.4 * d_mnn
     raise ValueError("Unknown metric")
 
+
 def best_sample(df, k, feature_cols, *, n_trials=500, bias=None, plot_weights=False, enforce=False,
                 random_state=None, standardize=True, dropna=True, metric="hybrid"):
     """
@@ -103,7 +107,7 @@ def best_sample(df, k, feature_cols, *, n_trials=500, bias=None, plot_weights=Fa
     dfv = df.loc[idx]
     Xfull = base.loc[idx].to_numpy(dtype=float)
 
-    if bias: 
+    if bias:
         weights = generate_weights(df, k, bias, plot_weights, enforce)
     else:
         weights = None
@@ -137,4 +141,4 @@ def toZ(X): return X
             best_score = s
             best_df = cand
 
-    return best_df, {"score": best_score, "metric": metric, "n_trials": n_trials}
+    return best_df, {"score": best_score, "metric": metric, "n_trials": n_trials}