training-data.hf/dataset_info.json

{
  "builder_name": "csv",
  "citation": "",
  "config_name": "default",
  "dataset_name": "csv",
  "dataset_size": 371565,
  "description": "",
  "download_checksums": {
    "/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Yersinia-enterocolitica/scaffold-split-train.csv.gz": {
      "num_bytes": 61567,
      "checksum": null
    }
  },
  "download_size": 61567,
  "features": {
    "smiles": {
      "feature": {
        "dtype": "string",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "inputs": {
      "V_d": {
        "dtype": "null",
        "_type": "Value"
      },
      "gt_mask": {
        "dtype": "null",
        "_type": "Value"
      },
      "lt_mask": {
        "dtype": "null",
        "_type": "Value"
      },
      "mg": {
        "E": {
          "feature": {
            "feature": {
              "dtype": "float32",
              "_type": "Value"
            },
            "_type": "Sequence"
          },
          "_type": "Sequence"
        },
        "V": {
          "feature": {
            "feature": {
              "dtype": "float32",
              "_type": "Value"
            },
            "_type": "Sequence"
          },
          "_type": "Sequence"
        },
        "edge_index": {
          "feature": {
            "feature": {
              "dtype": "float32",
              "_type": "Value"
            },
            "_type": "Sequence"
          },
          "_type": "Sequence"
        },
        "rev_edge_index": {
          "feature": {
            "dtype": "float32",
            "_type": "Value"
          },
          "_type": "Sequence"
        }
      },
      "weight": {
        "dtype": "float32",
        "_type": "Value"
      },
      "x_d": {
        "feature": {
          "dtype": "float32",
          "_type": "Value"
        },
        "_type": "Sequence"
      },
      "y": {
        "feature": {
          "dtype": "float32",
          "_type": "Value"
        },
        "_type": "Sequence"
      }
    },
    "labels": {
      "feature": {
        "dtype": "float64",
        "_type": "Value"
      },
      "_type": "Sequence"
    },
    "extra_features": {
      "feature": {
        "dtype": "float32",
        "_type": "Value"
      },
      "_type": "Sequence"
    }
  },
  "homepage": "",
  "license": "",
  "size_in_bytes": 433132,
  "splits": {
    "train": {
      "name": "train",
      "num_bytes": 371565,
      "num_examples": 984,
      "dataset_name": "csv"
    }
  },
  "version": {
    "version_str": "0.0.0",
    "major": 0,
    "minor": 0,
    "patch": 0
  }
}