Add Mishra_model README.md

Benchmark-Models/Mishra_MetabEng2023/README-petab-files.md

@@ -4,9 +4,15 @@ import pandas as pd
 import matplotlib.pyplot as plt
 from matplotlib import cm
 
+from matplotlib import cm  # Import cm for colormaps
+import matplotlib.pyplot as plt
+from sklearn.metrics import r2_score, mean_squared_error
+
+
 def plot_measurements_vs_simulation(simulation_df, measurement_df, output_file=None):
     """
-    Generates a logarithmic scatter plot comparing measurements and simulations.
+    Generates a logarithmic scatter plot comparing measurements and simulations, 
+    with R² and MSE displayed on the plot.
 
     Parameters:
         simulation_df (pd.DataFrame): DataFrame containing simulation data.
@@ -28,33 +34,43 @@ def plot_measurements_vs_simulation(simulation_df, measurement_df, output_file=N
 
     # Map unique colors to each datasetId
     unique_datasets = df_merged['datasetId'].unique()
-    colors = cm.get_cmap('tab10', len(unique_datasets))  # Using 'tab10' color map
-
-    # Initialize the plot
+    colors = colormaps['tab10']  # Use the updated colormap API
+    color_list = [colors(i) for i in range(len(unique_datasets))]
+
+    # Plotting
     plt.figure(figsize=(8, 8))
     plt.xscale('log')
     plt.yscale('log')
-
-    # Scatter plot with color mapping for each datasetId
+
     for i, dataset in enumerate(unique_datasets):
         subset = df_merged[df_merged['datasetId'] == dataset]
-        plt.scatter(subset['measurement'], subset['simulation'], color=colors(i), label=dataset)
-
-    # Add bisectrix (y=x line)
+        plt.scatter(subset['measurement'], subset['simulation'], color=color_list[i], label=dataset)
+
+    # Calculate R² and MSE
+    r2 = r2_score(df_merged['measurement'], df_merged['simulation'])
+    mse = mean_squared_error(df_merged['measurement'], df_merged['simulation'])
+
+    # Add R² and MSE to the plot
     x_min, x_max = df_merged['measurement'].min(), df_merged['measurement'].max()
     plt.plot([x_min, x_max], [x_min, x_max], 'k--')
-
-    # Labels, title, and legend
+    plt.text(
+        x_min * 1.2, x_max / 2,
+        f"$R^2$: {r2:.3f}\nMSE: {mse:.3e}",
+        fontsize=10, bbox=dict(facecolor='white', alpha=0.8, edgecolor='gray')
+    )
+
+    # Add labels and legend
     plt.xlabel("Measurement (log scale)")
     plt.ylabel("Simulation (log scale)")
-    plt.title("Logarithmic Measurement vs Simulation by Dataset")
     plt.legend(title="Dataset ID")
+    plt.show()
 
     # Show or save the plot
     if output_file:
         plt.savefig(output_file, dpi=300, bbox_inches='tight')
     else:
         plt.show()
+
 
 # Assuming `simulation_df` and `measurement_df` are predefined dataframes
 plot_measurements_vs_simulation(simulation_df, measurement_df)