5b48f9a9c097d26d395873044ceaa1a0b886682a,solutionbox/code_free_ml/mltoolbox/code_free_ml/analyze.py,,run_local_analysis,#Any#Any#Any#Any#,291

Before Change

                  float(parsed_line[col_name])))
            numerical_results[col_name]["count"] += 1
            numerical_results[col_name]["sum"] += float(parsed_line[col_name])
          elif transform == constant.IMAGE_TRANSFORM:
            pass
          elif transform == constant.KEY_TRANSFORM:
            pass
          else:
            raise ValueError("Unknown transform %s" % transform)

  // Write the vocab files. Each label is on its own line.
  vocab_sizes = {}

After Change

        parsed_line = dict(zip(header, line))
        num_examples += 1

        for col_name, transform_set in six.iteritems(inverted_features_target):
          // All transforms in transform_set require the same analysis. So look
          // at the first transform.
          transform_name = next(iter(transform_set))
          if transform_name in constant.TEXT_TRANSFORMS:
            split_strings = parsed_line[col_name].split(" ")

            // If a label is in the row N times, increase it"s vocab count by 1.
            // This is needed for TFIDF, but it"s also an interesting stat.
            for one_label in set(split_strings):
              // Filter out empty strings
              if one_label:
                vocabs[col_name][one_label] += 1
          elif transform_name in constant.CATEGORICAL_TRANSFORMS:
            if parsed_line[col_name]:
              vocabs[col_name][parsed_line[col_name]] += 1
          elif transform_name in constant.NUMERIC_TRANSFORMS:
            if not parsed_line[col_name].strip():
              continue

            numerical_results[col_name]["min"] = (
              min(numerical_results[col_name]["min"],
                  float(parsed_line[col_name])))
            numerical_results[col_name]["max"] = (
              max(numerical_results[col_name]["max"],
                  float(parsed_line[col_name])))
            numerical_results[col_name]["count"] += 1
            numerical_results[col_name]["sum"] += float(parsed_line[col_name])

  // Write the vocab files. Each label is on its own line.
  vocab_sizes = {}
  for name, label_count in six.iteritems(vocabs):
    // Labels is now the string:
    // label1,count

Instances