f1522f7930a7dd101bca96c76db291647d2d5de4,solutionbox/structured_data/mltoolbox/_structured_data/preprocess/local_preprocess.py,,run_numerical_categorical_analysis,#Any#Any#,69

Before Change

  for input_file in input_files:
    with file_io.FileIO(input_file, "r") as f:
      for line in f:
        parsed_line = dict(zip(header, line.strip().split(",")))

        for col_schema in schema_list:
          col_name = col_schema["name"]

After Change

    // label2,count
    // ...
    // where label1 is the most frequent label, and label2 is the 2nd most, etc.
    labels = "\n".join(["%s,%d" % (label, count)
                        for label, count in sorted(six.iteritems(label_count),
                                                   key=lambda x: x[1],
                                                   reverse=True)])
    file_io.write_string_to_file(
        os.path.join(args.output_dir, CATEGORICAL_ANALYSIS_FILE % name),
        labels)

Instances