Merge pull request #43 from MSDLLCpapers/plotting

Added MDS plot

CHANGELOG.md

@@ -4,6 +4,8 @@
 ### Added
 - Default values for NParEGO scalarization_weights
 - SHAP PDP ICE plots now work with categorical values
+- Added scikit-learn to dependencies, for MDS
+- Added MDS plot
 
 ### Modified
 - SHAP PDP ICE plots must now have color and x-axis indices that are distinct

obsidian/campaign/campaign.py

@@ -99,6 +99,7 @@ def add_data(self, df: pd.DataFrame):
     def clear_data(self):
         """Clears campaign data"""
         self.data = pd.DataFrame()
+        self.iter = 0
 
     @property
     def optimizer(self) -> Optimizer:

obsidian/plotting/plotly.py

@@ -8,11 +8,61 @@
 
 import plotly.graph_objects as go
 from plotly.graph_objects import Figure
+from sklearn.manifold import MDS
 
 import pandas as pd
 import numpy as np
 
 
+def MDS_plot(campaign: Campaign) -> Figure:
+    """
+    Creates a Multi-Dimensional Scaling (MDS) plot of the campaign data,
+    colored by iteration.
+    
+    This plot is helpful to visualize the convergence of the optimizer on a 2D plane.
+    
+    Args:
+        campaign (Campaign): The campaign object containing the data.
+        
+    Returns:
+        fig (Figure): The MDS plot
+    """
+    mds = MDS(n_components=2)
+    X_mds = mds.fit_transform(campaign.X_space.encode(campaign.X))
+
+    iter_max = campaign.data['Iteration'].max()
+    iter_vals = campaign.data['Iteration'].values
+
+    if campaign.data['Iteration'].nunique() == 1:
+        iter_vals = np.zeros_like(iter_vals)
+        iter_max = 0
+        cbar = None
+    else:
+        cbar = dict(title=dict(text='Iteration', font=dict(size=10)))
+
+    fig = go.Figure()
+
+    fig.add_trace(go.Scatter(x=X_mds[:, 0], y=X_mds[:, 1],
+                             mode='markers',
+                             name='Observations',
+                             marker={'color': iter_vals, 'size': 10,
+                                     'cmax': iter_max, 'cmin': 0,
+                                     'colorscale': [[0, obsidian_colors.rich_blue],
+                                                    [0.5, obsidian_colors.teal],
+                                                    [1, obsidian_colors.lemon]],
+                                     'colorbar': cbar
+                                     },
+                             showlegend=False
+                             ))
+
+    fig.update_xaxes(title_text='Component 1')
+    fig.update_yaxes(title_text='Component 2')
+    fig.update_layout(template='ggplot2', title='Multi-Dimensional Scaling (MDS) Plot',
+                      autosize=False, height=400, width=500)
+
+    return fig
+
+
 def parity_plot(optimizer: Optimizer,
                 f_transform: bool = False,
                 response_id: int = 0) -> Figure:

obsidian/tests/test_plotting.py

@@ -6,7 +6,8 @@
     factor_plot,
     surface_plot,
     visualize_inputs,
-    optim_progress
+    optim_progress,
+    MDS_plot
 )
 
 from obsidian.objectives import Scalar_WeightedSum
@@ -75,6 +76,19 @@ def test_optim_progress_plot():
     obj = Scalar_WeightedSum(weights=[1, 1])
     campaign.set_objective(obj)
     fig = optim_progress(campaign, X_suggest=X_suggest)
+
+
+@pytest.mark.fast
+def test_MDS_plot():
+    # Test with default data
+    fig = MDS_plot(campaign)
+
+    # Test with no iteration data
+    data = campaign.data
+    data = data.drop(columns='Iteration')
+    campaign.clear_data()
+    campaign.add_data(data)
+    fig = MDS_plot(campaign)
 
 
 if __name__ == '__main__':

pyproject.toml

@@ -58,6 +58,7 @@ sphinx = { version =  "^7.3.7", optional = true}
 myst-parser = { version =  "^3.0.1", optional = true}
 pydata-sphinx-theme = { version =  "^0.15.4", optional = true}
 linkify-it-py = { version =  "^2.0.3", optional = true}
+scikit-learn = "^1.5.1"
 
 
 [tool.poetry.extras]