computer/computer-dist/src/assembly/dataset/struct.json

{
  "version": "2.0",
  "structs": [
    {
      "id": "1",
      "skip": false,
      "input": {
        "type": "FILE",
        "path": "/dataset/ml-latest-small/ratings.csv",
        "file_filter": {
          "extensions": [
            "*"
          ]
        },
        "format": "CSV",
        "delimiter": ",",
        "date_format": "yyyy-MM-dd HH:mm:ss",
        "time_zone": "GMT+8",
        "skipped_line": {
          "regex": "(^#|^//).*|"
        },
        "compression": "NONE",
        "batch_size": 500,
        "header": [
          "userId",
          "movieId",
          "rating",
          "timestamp"
        ],
        "charset": "UTF-8",
        "list_format": null
      },
      "vertices": [
        {
          "label": "user",
          "skip": false,
          "id": null,
          "unfold": false,
          "field_mapping": {
            "userId": "id"
          },
          "value_mapping": {},
          "selected": [
            "userId"
          ],
          "ignored": [],
          "null_values": [
            ""
          ],
          "update_strategies": {}
        }
      ],
      "edges": [
        {
          "label": "rating",
          "skip": false,
          "source": [
            "userId"
          ],
          "unfold_source": false,
          "target": [
            "movieId"
          ],
          "unfold_target": false,
          "field_mapping": {
            "userId": "id",
            "movieId": "id",
            "rating": "rate",
            "timestamp": "timestamp"
          },
          "value_mapping": {},
          "selected": [],
          "ignored": [],
          "null_values": [
            ""
          ],
          "update_strategies": {}
        }
      ]
    },
    {
      "id": "2",
      "skip": false,
      "input": {
        "type": "FILE",
        "path": "/dataset/ml-latest-small/tags.csv",
        "file_filter": {
          "extensions": [
            "*"
          ]
        },
        "format": "CSV",
        "delimiter": ",",
        "date_format": "yyyy-MM-dd HH:mm:ss",
        "time_zone": "GMT+8",
        "skipped_line": {
          "regex": "(^#|^//).*|"
        },
        "compression": "NONE",
        "batch_size": 500,
        "header": [
          "userId",
          "movieId",
          "tag",
          "timestamp"
        ],
        "charset": "UTF-8",
        "list_format": null
      },
      "vertices": [
        {
          "label": "user",
          "skip": false,
          "id": null,
          "unfold": false,
          "field_mapping": {
            "userId": "id"
          },
          "value_mapping": {},
          "selected": [
            "userId"
          ],
          "ignored": [],
          "null_values": [
            ""
          ],
          "update_strategies": {}
        }
      ],
      "edges": [
        {
          "label": "taged",
          "skip": false,
          "source": [
            "userId"
          ],
          "unfold_source": false,
          "target": [
            "movieId"
          ],
          "unfold_target": false,
          "field_mapping": {
            "userId": "id",
            "movieId": "id",
            "tag": "tag",
            "timestamp": "timestamp"
          },
          "value_mapping": {},
          "selected": [],
          "ignored": [],
          "null_values": [
            ""
          ],
          "update_strategies": {}
        }
      ]
    },
    {
      "id": "3",
      "skip": false,
      "input": {
        "type": "FILE",
        "path": "/dataset/ml-latest-small/movies.csv",
        "file_filter": {
          "extensions": [
            "*"
          ]
        },
        "format": "CSV",
        "delimiter": ",",
        "date_format": "yyyy-MM-dd HH:mm:ss",
        "time_zone": "GMT+8",
        "skipped_line": {
          "regex": "(^#|^//).*|"
        },
        "compression": "NONE",
        "batch_size": 500,
        "header": [
          "movieId",
          "title",
          "genres"
        ],
        "charset": "UTF-8",
        "list_format": {
          "start_symbol": "",
          "elem_delimiter": "|",
          "end_symbol": ""
        }
      },
      "vertices": [
        {
          "label": "movie",
          "skip": false,
          "id": null,
          "unfold": false,
          "field_mapping": {
            "movieId": "id"
          },
          "value_mapping": {},
          "selected": [],
          "ignored": [],
          "null_values": [
            ""
          ],
          "update_strategies": {}
        }
      ],
      "edges": []
    }
  ]
}