Move bug classification code from run.py into a separate script (#829)

run.py

@@ -6,8 +6,6 @@
 import argparse
 import sys
 
-import numpy as np
-
 from bugbug import bugzilla, db, repository
 from bugbug.models import MODELS, get_model_class
 
@@ -43,7 +41,6 @@ def parse_args(args):
         choices=["default", "nn"],
         default="default",
     )
-    parser.add_argument("--classify", help="Perform evaluation", action="store_true")
     parser.add_argument(
         "--historical",
         help="""Analyze historical bugs. Only used for defect, bugtype,
@@ -54,10 +51,6 @@ def parse_args(args):
 
 
 def main(args):
-    model_file_name = "{}{}model".format(
-        args.goal, "" if args.classifier == "default" else args.classifier
-    )
-
     if args.goal == "component":
         if args.classifier == "default":
             model_class_name = "component"
@@ -88,33 +81,6 @@ def main(args):
         else:
             model = model_class(args.lemmatization)
         model.train()
-    else:
-        model = model_class.load(model_file_name)
-
-    if args.classify:
-        for bug in bugzilla.get_bugs():
-            print(
-                f'https://bugzilla.mozilla.org/show_bug.cgi?id={ bug["id"] } - { bug["summary"]} '
-            )
-
-            if model.calculate_importance:
-                probas, importance = model.classify(
-                    bug, probabilities=True, importances=True
-                )
-
-                feature_names = model.get_human_readable_feature_names()
-
-                model.print_feature_importances(
-                    importance["importances"], feature_names, class_probabilities=probas
-                )
-            else:
-                probas = model.classify(bug, probabilities=True, importances=False)
-
-            if np.argmax(probas) == 1:
-                print(f"Positive! {probas}")
-            else:
-                print(f"Negative! {probas}")
-            input()
 
 
 if __name__ == "__main__":

scripts/bug_classifier.py

@@ -0,0 +1,71 @@
+# -*- coding: utf-8 -*-
+
+import argparse
+import os
+
+import numpy as np
+
+from bugbug import bugzilla
+from bugbug.models import get_model_class
+
+MODELS_WITH_TYPE = ("component",)
+
+
+def classify_bugs(model_name, classifier):
+    if classifier != "default":
+        assert (
+            model_name in MODELS_WITH_TYPE
+        ), f"{classifier} is not a valid classifier type for {model_name}"
+
+        model_file_name = f"{model_name}{classifier}model"
+        model_name = f"{model_name}_{classifier}"
+    else:
+        model_file_name = f"{model_name}model"
+
+    assert os.path.exists(
+        model_file_name
+    ), f"{model_file_name} does not exist. Train the model with trainer.py first."
+
+    model_class = get_model_class(model_name)
+    model = model_class.load(model_file_name)
+
+    for bug in bugzilla.get_bugs():
+        print(
+            f'https://bugzilla.mozilla.org/show_bug.cgi?id={bug["id"]} - {bug["summary"]} '
+        )
+
+        if model.calculate_importance:
+            probas, importance = model.classify(
+                bug, probabilities=True, importances=True
+            )
+
+            feature_names = model.get_human_readable_feature_names()
+
+            model.print_feature_importances(
+                importance["importances"], feature_names, class_probabilities=probas
+            )
+        else:
+            probas = model.classify(bug, probabilities=True, importances=False)
+
+        if np.argmax(probas) == 1:
+            print(f"Positive! {probas}")
+        else:
+            print(f"Negative! {probas}")
+        input()
+
+
+def main():
+    description = "Perform evaluation on bugs using the specified model"
+    parser = argparse.ArgumentParser(description=description)
+
+    parser.add_argument("model", help="Which model to use for evaluation")
+    parser.add_argument(
+        "--classifier",
+        help="Type of the classifier. Only used for component classification.",
+        choices=["default", "nn"],
+        default="default",
+    )
+
+    args = parser.parse_args()
+
+    classify_bugs(args.model, args.classifier)

setup.py

@@ -49,6 +49,7 @@ setup(
             "bugbug-check = scripts.check:main",
             "bugbug-microannotate-generate = scripts.microannotate_generator:main",
             "bugbug-classify-commit = scripts.commit_classifier:main",
+            "bugbug-classify-bug = scripts.bug_classifier:main",
             "bugbug-regressor-finder = scripts.regressor_finder:main",
         ]
     },