Merge branch 'master' into feature/interaction_plot_improvment

MAIF · Jul 4, 2024 · b350f12 · b350f12
2 parents a467eaa + b568987
commit b350f12
Show file tree

Hide file tree

Showing 2 changed files with 18 additions and 9 deletions.
diff --git a/shapash/explainer/smart_plotter.py b/shapash/explainer/smart_plotter.py
@@ -374,9 +374,8 @@ def plot_scatter(
                 val_inter = feature_values_max - feature_values_min
                 from sklearn.neighbors import KernelDensity
 
-                feature_np = np.array(feature_values_array)[:, None]
-                median_value = np.nanmedian(feature_np)
-                feature_np = np.where(np.isnan(feature_np), median_value, feature_np)
+                feature_np = np.array(feature_values_array)
+                feature_np = feature_np[~np.isnan(feature_np)][:, None]
                 kde = KernelDensity(bandwidth=val_inter / 100, kernel="epanechnikov").fit(feature_np)
                 xs = np.linspace(feature_values_min, feature_values_max, 1000)
                 log_dens = kde.score_samples(xs[:, None])
@@ -3708,9 +3707,20 @@ def _prediction_regression_plot(
             if len(y_target) > 500:
                 lower_quantile = y_target.iloc[:, 0].quantile(0.005)
                 upper_quantile = y_target.iloc[:, 0].quantile(0.995)
-                y_target = y_target.iloc[:, 0][
+                y_target_tmp = y_target.iloc[:, 0][
                     (y_target.iloc[:, 0] > lower_quantile) & (y_target.iloc[:, 0] < upper_quantile)
                 ]
+                if len(y_target_tmp) > 0.95 * len(y_target):
+                    y_target = y_target_tmp
+                else:
+                    y_target_tmp = y_target.iloc[:, 0][(y_target.iloc[:, 0] < upper_quantile)]
+                    if len(y_target_tmp) > 0.95 * len(y_target):
+                        y_target = y_target_tmp
+                    else:
+                        y_target_tmp = y_target.iloc[:, 0][(y_target.iloc[:, 0] > lower_quantile)]
+                        if len(y_target_tmp) > 0.95 * len(y_target):
+                            y_target = y_target_tmp
+
             y_target_values = y_target.values.flatten()
 
             y_pred = self.explainer.y_pred.loc[y_target.index]
@@ -3727,9 +3737,8 @@ def _prediction_regression_plot(
                 val_inter = feature_values_max - feature_values_min
                 from sklearn.neighbors import KernelDensity
 
-                feature_np = np.array(feature_values_array)[:, None]
-                median_value = np.nanmedian(feature_np)
-                feature_np = np.where(np.isnan(feature_np), median_value, feature_np)
+                feature_np = np.array(feature_values_array)
+                feature_np = feature_np[~np.isnan(feature_np)][:, None]
                 kde = KernelDensity(bandwidth=val_inter / 300, kernel="epanechnikov").fit(feature_np)
                 xs = np.linspace(feature_values_min, feature_values_max, 1000)
                 log_dens = kde.score_samples(xs[:, None])

diff --git a/shapash/webapp/smart_app.py b/shapash/webapp/smart_app.py
@@ -4,7 +4,7 @@
 import copy
 import random
 import re
-from math import log10
+from math import isfinite, log10
 
 import dash
 import dash_bootstrap_components as dbc
@@ -193,7 +193,7 @@ def init_data(self, rows=None):
             typ = self.dataframe[col].dtype
             if typ == float:
                 std = self.dataframe[col].std()
-                if std != 0:
+                if isfinite(std) and std != 0:
                     digit = max(round(log10(1 / std) + 1) + 2, 0)
                     self.round_dataframe[col] = self.dataframe[col].map(f"{{:.{digit}f}}".format).astype(float)