5b48f9a9c097d26d395873044ceaa1a0b886682a,solutionbox/code_free_ml/test_mltoolbox/test_analyze.py,TestCloudAnalyzeFromCSVFiles,test_numerics,#TestCloudAnalyzeFromCSVFiles#,299

Before Change

      input_file_path,
      "\n".join(["%s,%s" % (i, 10 * i + 0.5) for i in range(100)]))

    analyze.run_cloud_analysis(
        output_dir=output_folder,
        csv_file_pattern=input_file_path,
        bigquery_table=None,
        schema=[{"name": "col1", "type": "INTEGER"},
                {"name": "col2", "type": "FLOAT"}],
        features={"col1": {"transform": "scale"},
                  "col2": {"transform": "identity"}})
    stats = json.loads(
        file_io.read_file_to_string(
            os.path.join(output_folder, analyze.constant.STATS_FILE)).decode())

After Change

      input_file_path,
      "\n".join(["%s,%s" % (i, 10 * i + 0.5) for i in range(100)]))

    schema = [{"name": "col1", "type": "INTEGER"},
              {"name": "col2", "type": "FLOAT"}]
    features = {"col1": {"transform": "scale", "source_column": "col1"},
                "col2": {"transform": "identity", "source_column": "col2"}}
    analyze.run_cloud_analysis(
        output_dir=output_folder,
        csv_file_pattern=input_file_path,
        bigquery_table=None,
        schema=schema,
        inverted_features=analyze.invert_features(features))

    stats = json.loads(
        file_io.read_file_to_string(
            os.path.join(output_folder, analyze.constant.STATS_FILE)).decode())

Instances