60cd627b07e790aaf07016467c3911f22ceb7182,solutionbox/code_free_ml/test_mltoolbox/test_analyze_data.py,TestLocalAnalyze,test_categorical,#TestLocalAnalyze#,136
 
Before Change
      self.assertEqual(stats["column_stats"]["transport"]["vocab_size"], 6)
      // Color column.
      vocab_str = file_io.read_file_to_string(
        os.path.join(output_folder, analyze_data.VOCAB_ANALYSIS_FILE % "color"))
      vocab = pd.read_csv(six.StringIO(vocab_str),
                          header=None,
                          names=["color", "count"])
      expected_vocab = pd.DataFrame(
After Change
        {"color": {"transform": "one_hot"},
         "transport": {"transform": "embedding"}})
      stats = json.loads(
          file_io.read_file_to_string(
              os.path.join(output_folder, analyze_data.constant.STATS_FILE)).decode())
      self.assertEqual(stats["column_stats"]["color"]["vocab_size"], 3)
      self.assertEqual(stats["column_stats"]["transport"]["vocab_size"], 6)
      // Color column.

In pattern: SUPERPATTERN
Frequency: 4
Non-data size: 4
Instances
 Project Name: googledatalab/pydatalab
 Commit Name: 60cd627b07e790aaf07016467c3911f22ceb7182
 Time: 2017-06-06
 Author: brandondutra@google.com
 File Name: solutionbox/code_free_ml/test_mltoolbox/test_analyze_data.py
 Class Name: TestLocalAnalyze
 Method Name: test_categorical
 Project Name: googledatalab/pydatalab
 Commit Name: 60cd627b07e790aaf07016467c3911f22ceb7182
 Time: 2017-06-06
 Author: brandondutra@google.com
 File Name: solutionbox/code_free_ml/test_mltoolbox/test_analyze_data.py
 Class Name: TestCloudAnalyzeFromCSVFiles
 Method Name: test_text
 Project Name: googledatalab/pydatalab
 Commit Name: 60cd627b07e790aaf07016467c3911f22ceb7182
 Time: 2017-06-06
 Author: brandondutra@google.com
 File Name: solutionbox/code_free_ml/test_mltoolbox/test_analyze_data.py
 Class Name: TestLocalAnalyze
 Method Name: test_text
 Project Name: googledatalab/pydatalab
 Commit Name: 60cd627b07e790aaf07016467c3911f22ceb7182
 Time: 2017-06-06
 Author: brandondutra@google.com
 File Name: solutionbox/code_free_ml/test_mltoolbox/test_analyze_data.py
 Class Name: TestCloudAnalyzeFromCSVFiles
 Method Name: test_categorical