Added function for loading training data in model training script

This function is made so that it can be used to load and have nicely
prepared training data.

train_model.py

@@ -7,6 +7,8 @@ import pandas as pd
 import numpy
 import pickle
 
+import os.path # Checking existence of paths
+
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import confusion_matrix
 from sklearn.metrics import matthews_corrcoef
@@ -255,23 +257,35 @@ def normalize_data(data, selected_columns, normalizing_column):
 #%%
 
 
-if __name__ == "__main__":
-    # The script takes a number of files as input
-    # Loads the JMH data, SW & HW performance counters
-    # Merges them to get a well built data file
-    # And train the classifier.
-
-    #%% 
-
-    print("Loading training data...")
-    jmh_with_best = load_jmh_data("data/jmh-results-34f6dc24.csv")
+def load_training_data(jmh_results_filename,
+                       software_counters_filename,
+                       hardware_counters_filename):
+    """ A function that loads the training data for training JBrainy
+        input: - The name of the file containing the JMH benchmark data
+               - The name of the software counters file 
+               - The name of the hardware counters filename
+        returns: A report containing the data
+            and some metadata, like the selected SW columns and HW columns
+            and the names of the data structures we will be dealing with
+    """
+    # Precondition: All the provided files must exist.
+    for file in [jmh_results_filename,
+                 software_counters_filename,
+                 hardware_counters_filename]:
+        if os.path.isfile(file):
+            # OK.
+            continue
+        else:
+            raise "The path '{0}' does not exist".format(file)
+
+    # Ok here we go
+    jmh_with_best = load_jmh_data(jmh_results_filename)
     jmh_with_best["Sample weight"] = compute_sample_weights(jmh_with_best)
-    software_data = load_software_counters("data/software-perf.csv")
+    software_data = load_software_counters(software_counters_filename)
     software_with_jmh = merge_jmh_software(jmh_with_best, software_data)
-    software_selected_columns = [c for c in software_with_jmh.columns if "run" in c]
+    software_selected_columns = software_data.columns
     software_features = software_with_jmh.get(software_selected_columns)
-    data_structure_names=software_with_jmh["Param: datastructureName_best"].sort_values().unique()
-    papi_data = load_hardware_counters("data/hardware-perf-50.csv")
+    papi_data = load_hardware_counters(hardware_counters_filename)
     papi_data['size'] = jmh_with_best['Param: applicationSize']
     hardware_selected_columns = [c for c in papi_data.columns if "PAPI" in c]
     hardware_features = papi_data.get(hardware_selected_columns)
@@ -280,10 +294,31 @@ if __name__ == "__main__":
     # apps where they were the best choice and apps where they were used.
     software_plus_hardware = software_with_jmh.join(hardware_features)
     sw_hw_cleaned = remove_weakmap_hashmap(software_plus_hardware)
+    return { "data" : sw_hw_cleaned,
+             "data_structure_names" : software_plus_hardware["Param: datastructureName_best"].sort_values().unique(),
+             "software_selected_columns": software_selected_columns,
+             "hardware_selected_columns": hardware_selected_columns }
+
+if __name__ == "__main__":
+    # The script takes a number of files as input
+    # Loads the JMH data, SW & HW performance counters
+    # Merges them to get a well built data file
+    # And train the classifier.
+
+    #%% 
+
+    print("Loading training data...")
+    training_data = load_training_data("data/jmh-results-9307f70f.csv",
+                                       "software-perf.csv",
+                                       "data/hardware-perf-data.csv")
     print("Training data loaded")
 
     #%%
 
+    sw_hw_cleaned = training_data["data"]
+    hardware_selected_columns = training_data["hardware_selected_columns"]
+    software_selected_columns = training_data["software_selected_columns"]
+
     print("Normalizing data")
     hw_normalized_data = normalize_data(sw_hw_cleaned,
                                         hardware_selected_columns,