Fix n_bins to num_bins

Author: stefanradev93

bayesflow/diagnostics/plots/calibration_histogram.py

@@ -102,7 +102,7 @@ def calibration_histogram(
             "Confidence intervals might be unreliable!"
         )
 
-    # Set n_bins automatically, if nothing provided
+    # Set num_bins automatically, if nothing provided
     if num_bins is None:
         num_bins = int(ratio / 2)
         # Attempt a fix if a single bin is determined so plot still makes sense

bayesflow/diagnostics/plots/mc_calibration.py

@@ -18,7 +18,7 @@ def mc_calibration(
     pred_models: dict[str, np.ndarray] | np.ndarray,
     true_models: dict[str, np.ndarray] | np.ndarray,
     model_names: Sequence[str] = None,
-    n_bins: int = 10,
+    num_bins: int = 10,
     label_fontsize: int = 16,
     title_fontsize: int = 18,
     metric_fontsize: int = 14,
@@ -41,12 +41,12 @@ def mc_calibration(
         The one-hot-encoded true model indices per data set.
     model_names       : list or None, optional, default: None
         The model names for nice plot titles. Inferred if None.
-    n_bins          : int, optional, default: 10
+    num_bins          : int, optional, default: 10
         The number of bins to use for the calibration curves (and marginal histograms).
     label_fontsize    : int, optional, default: 16
         The font size of the y-label and y-label texts
-    legend_fontsize   : int, optional, default: 14
-        The font size of the legend text (ECE value)
+    metric_fontsize   : int, optional, default: 14
+        The font size of the metric (e.g., ECE)
     title_fontsize    : int, optional, default: 18
         The font size of the title text. Only relevant if `stacked=False`
     tick_fontsize     : int, optional, default: 12
@@ -83,7 +83,7 @@ def mc_calibration(
         estimates=pred_models,
         targets=true_models,
         model_names=plot_data["variable_names"],
-        n_bins=n_bins,
+        num_bins=num_bins,
         return_probs=True,
     )
 
@@ -92,7 +92,7 @@ def mc_calibration(
         ax.plot(ece["probs_pred"][j], ece["probs_true"][j], "o-", color=color)
 
         # Plot PMP distribution over bins
-        uniform_bins = np.linspace(0.0, 1.0, n_bins + 1)
+        uniform_bins = np.linspace(0.0, 1.0, num_bins + 1)
         norm_weights = np.ones_like(plot_data["estimates"]) / len(plot_data["estimates"])
         ax.hist(plot_data["estimates"][:, j], bins=uniform_bins, weights=norm_weights[:, j], color="grey", alpha=0.3)
 

bayesflow/utils/classification/calibration_curve.py

@@ -27,8 +27,8 @@ def calibration_curve(
     num_bins : int, default=5
         Number of bins to discretize the [0, 1] interval. A bigger number
         requires more data. Bins with no samples (i.e. without
-        corresponding values in `y_prob`) will not be returned, thus the
-        returned arrays may have less than `n_bins` values.
+        corresponding values in `estimates`) will not be returned, thus the
+        returned arrays may have less than `num_bins` values.
     strategy : {'uniform', 'quantile'}, default='uniform'
         Strategy used to define the widths of the bins.
 
@@ -39,11 +39,11 @@ def calibration_curve(
 
     Returns
     -------
-    prob_true : ndarray of shape (n_bins,) or smaller
+    prob_true : ndarray of shape (num_bins,) or smaller
         The proportion of samples whose class is the positive class, in each
         bin (fraction of positives).
 
-    prob_pred : ndarray of shape (n_bins,) or smaller
+    prob_pred : ndarray of shape (num_bins,) or smaller
         The mean estimated probability in each bin.
 
     References