def test_generate_summary(self):
"""Various test cases for summarizer.generate_summary."""
summarizer_simple = Summarizer(self.simple_dataframe, self.config)
output_df_simple = summarizer_simple.generate_summary()
self.assertEqual(len(output_df_simple), 3)
self.assertIn(1, output_df_simple['Size'].values)
self.assertIn('test', output_df_simple['Text'].values)
self.assertIn('test2', output_df_simple['Text'].values)
self.assertIn('test3', output_df_simple['Text'].values)
self.assertIn('', output_df_simple['ClassLines'].values)
summarizer_stack_lines = Summarizer(self.stack_lines_dataframe,
self.config)
output_df_stack_lines = summarizer_stack_lines.generate_summary()
self.assertIn('some.class.java',
output_df_stack_lines['ClassLines'].values)
self.assertIn('some.class2.java',
output_df_stack_lines['ClassLines'].values)
self.assertIn('some.class3.java',
output_df_stack_lines['ClassLines'].values)
self.assertIn('', output_df_stack_lines['Text'].values)
summarizer_multi_cluster = Summarizer(self.multi_cluster_dataframe,
self.config)
output_df_multi_cluster = summarizer_multi_cluster.generate_summary()
self.assertEqual(len(output_df_multi_cluster), 2)
self.assertIn(2, output_df_multi_cluster['Size'].values)
self.assertIn(1, output_df_multi_cluster['Size'].values)
def run_classification_summary(df, classifier_config):
"""Runs the various classification algorithms outputting a summary dataframe.
Args:
df: pandas dataframe containing the error information we wish to classify and summarize
classifier_config: config_pb2 proto specified by the configuration file
Returns:
pandas dataframe that summarizes the information obtained from the classification algorithms
run on the input dataframe
"""
# Running our classifiers
error_code_matcher = ErrorCodeMatcher(df, classifier_config)
error_code_matcher.match_informative_errors()
k_means_classifier = KMeansClusterer(df, classifier_config)
k_means_classifier.cluster_errors()
# Running the summarizer
summarizer = Summarizer(df, classifier_config)
return summarizer.generate_summary()
