Added function for getting the ratio of improvement

The ratio of improvement is a very useful metric, so we add it to the
way we compute the input data.

train_model.py

@@ -136,6 +136,14 @@ def load_jmh_data(filename):
 
 #%%
 
+def compute_sample_ratios(jmh_data):
+    """
+    Takes a DataFrame with columns "Lowest score_best" and "Lowest score"
+    and returns the ratio of improvement.
+    """
+    return jmh_data["Lowest score_best"] / jmh_data["Lowest score"]
+
+
 def compute_sample_weights(jmh_data):
     """
     Takes a DataFrame with columns "Lowest score_best" and "Lowest score"
@@ -143,7 +151,7 @@ def compute_sample_weights(jmh_data):
     The weight is computer by computing the ratio of improvement,
     and adding it's log to 1/N, where N is the number of samples
     """
-    ratios = jmh_data["Lowest score_best"] / jmh_data["Lowest score"]
+    ratios = compute_sample_ratios(jmh_data)
     sample_weights = (1 / ratios.shape[0]) + numpy.log(ratios)
     return sample_weights
 
@@ -285,6 +293,7 @@ def load_training_data(jmh_results_filename,
 
     # Ok here we go
     jmh_with_best = load_jmh_data(jmh_results_filename)
+    jmh_with_best["Ratio improvement"] = compute_sample_ratios(jmh_with_best)
     jmh_with_best["Sample weight"] = compute_sample_weights(jmh_with_best)
     software_data = load_software_counters(software_counters_filename)
     software_with_jmh = merge_jmh_software(jmh_with_best, software_data)