pipelines/components/ml_metrics/Calculate_regression_metrics/from_CSV/component.yaml

name: Calculate regression metrics from csv
description: |-
  Calculates regression metrics.

      Annotations:
          author: Alexey Volkov <alexey.volkov@ark-kun.com>  
inputs:
- {name: true_values}
- {name: predicted_values}
outputs:
- {name: number_of_items, type: Integer}
- {name: max_absolute_error, type: Float}
- {name: mean_absolute_error, type: Float}
- {name: mean_squared_error, type: Float}
- {name: root_mean_squared_error, type: Float}
- {name: metrics, type: JsonObject}
implementation:
  container:
    image: python:3.7
    command:
    - sh
    - -c
    - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
      'numpy==1.19.0' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet
      --no-warn-script-location 'numpy==1.19.0' --user) && "$0" "$@"
    - python3
    - -u
    - -c
    - |
      def calculate_regression_metrics_from_csv(
          true_values_path,
          predicted_values_path,
      ):
          '''Calculates regression metrics.

          Annotations:
              author: Alexey Volkov <alexey.volkov@ark-kun.com>
          '''
          import math
          import numpy

          true_values = numpy.loadtxt(true_values_path, dtype=numpy.float64)
          predicted_values = numpy.loadtxt(predicted_values_path, dtype=numpy.float64)

          if len(predicted_values.shape) != 1:
              raise NotImplemented('Only single prediction values are supported.')
          if len(true_values.shape) != 1:
              raise NotImplemented('Only single true values are supported.')

          if predicted_values.shape != true_values.shape:
              raise ValueError('Input shapes are different: {} != {}'.format(predicted_values.shape, true_values.shape))

          number_of_items = true_values.size
          errors = (true_values - predicted_values)
          abs_errors = numpy.abs(errors)
          squared_errors = errors ** 2
          max_absolute_error = numpy.max(abs_errors)
          mean_absolute_error = numpy.average(abs_errors)
          mean_squared_error = numpy.average(squared_errors)
          root_mean_squared_error = math.sqrt(mean_squared_error)
          metrics = dict(
              number_of_items=number_of_items,
              max_absolute_error=max_absolute_error,
              mean_absolute_error=mean_absolute_error,
              mean_squared_error=mean_squared_error,
              root_mean_squared_error=root_mean_squared_error,
          )

          return (
              number_of_items,
              max_absolute_error,
              mean_absolute_error,
              mean_squared_error,
              root_mean_squared_error,
              metrics,
          )

      def _serialize_json(obj) -> str:
          if isinstance(obj, str):
              return obj
          import json
          def default_serializer(obj):
              if hasattr(obj, 'to_struct'):
                  return obj.to_struct()
              else:
                  raise TypeError("Object of type '%s' is not JSON serializable and does not have .to_struct() method." % obj.__class__.__name__)
          return json.dumps(obj, default=default_serializer, sort_keys=True)

      def _serialize_float(float_value: float) -> str:
          if isinstance(float_value, str):
              return float_value
          if not isinstance(float_value, (float, int)):
              raise TypeError('Value "{}" has type "{}" instead of float.'.format(str(float_value), str(type(float_value))))
          return str(float_value)

      def _serialize_int(int_value: int) -> str:
          if isinstance(int_value, str):
              return int_value
          if not isinstance(int_value, int):
              raise TypeError('Value "{}" has type "{}" instead of int.'.format(str(int_value), str(type(int_value))))
          return str(int_value)

      import argparse
      _parser = argparse.ArgumentParser(prog='Calculate regression metrics from csv', description='Calculates regression metrics.\n\n    Annotations:\n        author: Alexey Volkov <alexey.volkov@ark-kun.com>')
      _parser.add_argument("--true-values", dest="true_values_path", type=str, required=True, default=argparse.SUPPRESS)
      _parser.add_argument("--predicted-values", dest="predicted_values_path", type=str, required=True, default=argparse.SUPPRESS)
      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=6)
      _parsed_args = vars(_parser.parse_args())
      _output_files = _parsed_args.pop("_output_paths", [])

      _outputs = calculate_regression_metrics_from_csv(**_parsed_args)

      _output_serializers = [
          _serialize_int,
          _serialize_float,
          _serialize_float,
          _serialize_float,
          _serialize_float,
          _serialize_json,

      ]

      import os
      for idx, output_file in enumerate(_output_files):
          try:
              os.makedirs(os.path.dirname(output_file))
          except OSError:
              pass
          with open(output_file, 'w') as f:
              f.write(_output_serializers[idx](_outputs[idx]))      
    args:
    - --true-values
    - {inputPath: true_values}
    - --predicted-values
    - {inputPath: predicted_values}
    - '----output-paths'
    - {outputPath: number_of_items}
    - {outputPath: max_absolute_error}
    - {outputPath: mean_absolute_error}
    - {outputPath: mean_squared_error}
    - {outputPath: root_mean_squared_error}
    - {outputPath: metrics}