Update examples/plot_variable_importance_classif_classes.py

Co-authored-by: bthirion <[email protected]>

examples/plot_variable_importance_classif_classes.py

@@ -43,7 +43,7 @@
 # of the features. To make the problem more intuitive, we generate a non-linear
 # combination of the features inspired by the Body Mass Index (BMI) formula.
 # The BMI can be obtained by :math:`\text{BMI} = \frac{\text{weight}}{\text{height}^2}`.
-# And we simply mimic the weight and height variables by rescalling 2 correlated
+# And we simply mimic the weight and height variables by rescaling 2 correlated
 # features. The binary target is then generated using the formula:
 # :math:`y = \beta_1 \exp\left(\frac{|\text{bmi} - \text{mean(bmi)}|}{\text{std(bmi)}}\right) + \beta_2 \exp\left(|\text{weight}| \times 1\left[|\text{weight} - \text{mean(weight)}| > \text{quantile(weight, 0.80)}\right] \right) + \beta_3 \cdot \text{age} + \epsilon` where :math:`\epsilon`` is a Gaussian noise.
 # The first and second term are non-linear functions of the features, corresponding to