Include more value types to describe field's precision more accurately (#820)

Include more precise value types.

Also included one example datasets,
https://huggingface.co/datasets/pollen-robotics/apple_storage, to
showcase the differences between 1.0 (same Croissant as in:
https://huggingface.co/api/datasets/pollen-robotics/apple_storage/croissant)
and the proposed modifications that would go into 1.1 (see the relative
output folders). The fields' precision was taken from:
https://datasets-server.huggingface.co/info?dataset=pollen-robotics/apple_storage

Author: ccl-core

datasets/1.0/huggingface-pollen-robotics-apple-storage/metadata.json

@@ -0,0 +1,250 @@
+{
+  "@context": {
+    "@language": "en",
+    "@vocab": "https://schema.org/",
+    "citeAs": "cr:citeAs",
+    "column": "cr:column",
+    "conformsTo": "dct:conformsTo",
+    "cr": "http://mlcommons.org/croissant/",
+    "data": {
+      "@id": "cr:data",
+      "@type": "@json"
+    },
+    "dataBiases": "cr:dataBiases",
+    "dataCollection": "cr:dataCollection",
+    "dataType": {
+      "@id": "cr:dataType",
+      "@type": "@vocab"
+    },
+    "dct": "http://purl.org/dc/terms/",
+    "extract": "cr:extract",
+    "field": "cr:field",
+    "fileProperty": "cr:fileProperty",
+    "fileObject": "cr:fileObject",
+    "fileSet": "cr:fileSet",
+    "format": "cr:format",
+    "includes": "cr:includes",
+    "isLiveDataset": "cr:isLiveDataset",
+    "jsonPath": "cr:jsonPath",
+    "key": "cr:key",
+    "md5": "cr:md5",
+    "parentField": "cr:parentField",
+    "path": "cr:path",
+    "personalSensitiveInformation": "cr:personalSensitiveInformation",
+    "recordSet": "cr:recordSet",
+    "references": "cr:references",
+    "regex": "cr:regex",
+    "repeated": "cr:repeated",
+    "replace": "cr:replace",
+    "sc": "https://schema.org/",
+    "separator": "cr:separator",
+    "source": "cr:source",
+    "subField": "cr:subField",
+    "transform": "cr:transform"
+  },
+  "@type": "sc:Dataset",
+  "distribution": [
+    {
+      "@type": "cr:FileObject",
+      "@id": "repo",
+      "name": "repo",
+      "description": "The Hugging Face git repository.",
+      "contentUrl": "https://huggingface.co/datasets/pollen-robotics/apple_storage/tree/refs%2Fconvert%2Fparquet",
+      "encodingFormat": "git+https",
+      "sha256": "https://github.com/mlcommons/croissant/issues/80"
+    },
+    {
+      "@type": "cr:FileSet",
+      "@id": "parquet-files-for-config-default",
+      "name": "parquet-files-for-config-default",
+      "description": "The underlying Parquet files as converted by Hugging Face (see: https://huggingface.co/docs/dataset-viewer/parquet).",
+      "containedIn": {
+        "@id": "repo"
+      },
+      "encodingFormat": "application/x-parquet",
+      "includes": "default/*/*.parquet"
+    }
+  ],
+  "recordSet": [
+    {
+      "@type": "cr:RecordSet",
+      "dataType": "cr:Split",
+      "key": {
+        "@id": "default_splits/split_name"
+      },
+      "@id": "default_splits",
+      "name": "default_splits",
+      "description": "Splits for the default config.",
+      "field": [
+        {
+          "@type": "cr:Field",
+          "@id": "default_splits/split_name",
+          "name": "split_name",
+          "description": "The name of the split.",
+          "dataType": "sc:Text"
+        }
+      ],
+      "data": {
+        "default_splits/split_name": "train"
+      }
+    },
+    {
+      "@type": "cr:RecordSet",
+      "@id": "default",
+      "name": "default",
+      "description": "pollen-robotics/apple_storage - 'default' subset",
+      "field": [
+        {
+          "@type": "cr:Field",
+          "@id": "default/split",
+          "name": "default/split",
+          "description": "Split to which the example belongs to.",
+          "dataType": "sc:Text",
+          "source": {
+            "fileSet": {
+              "@id": "parquet-files-for-config-default"
+            },
+            "extract": {
+              "fileProperty": "fullpath"
+            },
+            "transform": {
+              "regex": "default/(?:partial-)?(train)/.+parquet$"
+            }
+          },
+          "references": {
+            "field": {
+              "@id": "default_splits/split_name"
+            }
+          }
+        },
+        {
+          "@type": "cr:Field",
+          "@id": "default/observation.state",
+          "name": "default/observation.state",
+          "description": "Column 'observation.state' from the Hugging Face parquet file.",
+          "dataType": "sc:Float",
+          "source": {
+            "fileSet": {
+              "@id": "parquet-files-for-config-default"
+            },
+            "extract": {
+              "column": "observation.state"
+            }
+          },
+          "repeated": true
+        },
+        {
+          "@type": "cr:Field",
+          "@id": "default/action",
+          "name": "default/action",
+          "description": "Column 'action' from the Hugging Face parquet file.",
+          "dataType": "sc:Float",
+          "source": {
+            "fileSet": {
+              "@id": "parquet-files-for-config-default"
+            },
+            "extract": {
+              "column": "action"
+            }
+          },
+          "repeated": true
+        },
+        {
+          "@type": "cr:Field",
+          "@id": "default/timestamp",
+          "name": "default/timestamp",
+          "description": "Column 'timestamp' from the Hugging Face parquet file.",
+          "dataType": "sc:Float",
+          "source": {
+            "fileSet": {
+              "@id": "parquet-files-for-config-default"
+            },
+            "extract": {
+              "column": "timestamp"
+            }
+          }
+        },
+        {
+          "@type": "cr:Field",
+          "@id": "default/frame_index",
+          "name": "default/frame_index",
+          "description": "Column 'frame_index' from the Hugging Face parquet file.",
+          "dataType": "sc:Integer",
+          "source": {
+            "fileSet": {
+              "@id": "parquet-files-for-config-default"
+            },
+            "extract": {
+              "column": "frame_index"
+            }
+          }
+        },
+        {
+          "@type": "cr:Field",
+          "@id": "default/episode_index",
+          "name": "default/episode_index",
+          "description": "Column 'episode_index' from the Hugging Face parquet file.",
+          "dataType": "sc:Integer",
+          "source": {
+            "fileSet": {
+              "@id": "parquet-files-for-config-default"
+            },
+            "extract": {
+              "column": "episode_index"
+            }
+          }
+        },
+        {
+          "@type": "cr:Field",
+          "@id": "default/index",
+          "name": "default/index",
+          "description": "Column 'index' from the Hugging Face parquet file.",
+          "dataType": "sc:Integer",
+          "source": {
+            "fileSet": {
+              "@id": "parquet-files-for-config-default"
+            },
+            "extract": {
+              "column": "index"
+            }
+          }
+        },
+        {
+          "@type": "cr:Field",
+          "@id": "default/task_index",
+          "name": "default/task_index",
+          "description": "Column 'task_index' from the Hugging Face parquet file.",
+          "dataType": "sc:Integer",
+          "source": {
+            "fileSet": {
+              "@id": "parquet-files-for-config-default"
+            },
+            "extract": {
+              "column": "task_index"
+            }
+          }
+        }
+      ]
+    }
+  ],
+  "conformsTo": "http://mlcommons.org/croissant/1.0",
+  "name": "apple_storage",
+  "description": "This dataset was created using LeRobot.\n\n\t\n\t\t\n\t\n\t\n\t\tDataset Structure\n\t\n\nmeta/info.json:\n{\n    \"codebase_version\": \"v2.0\",\n    \"robot_type\": \"reachy2\",\n    \"total_episodes\": 50,\n    \"total_frames\": 14983,\n    \"total_tasks\": 1,\n    \"total_videos\": 50,\n    \"total_chunks\": 1,\n    \"chunks_size\": 1000,\n    \"fps\": 30,\n    \"splits\": {\n        \"train\": \"0:50\"\n    },\n    \"data_path\": \"data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet\",\n    \"video_path\":… See the full description on the dataset page: https://huggingface.co/datasets/pollen-robotics/apple_storage.",
+  "keywords": [
+    "robotics",
+    "apache-2.0",
+    "10K - 100K",
+    "parquet",
+    "Tabular",
+    "Time-series",
+    "Video",
+    "Datasets",
+    "Dask",
+    "Croissant",
+    "Polars",
+    "🇺🇸 Region: US",
+    "LeRobot"
+  ],
+  "license": "https://choosealicense.com/licenses/apache-2.0/",
+  "url": "https://huggingface.co/datasets/pollen-robotics/apple_storage"
+}

datasets/1.0/huggingface-pollen-robotics-apple-storage/output/default.jsonl

@@ -0,0 +1,2 @@
+{"default/split": "train", "default/observation.state": "[0.10541590303182602, 0.17775288224220276, -0.034828223288059235, -1.779552698135376, 0.19387680292129517, 0.23834092915058136, 0.5736730694770813, 2.2687575817108154, 0.3638584017753601, -0.10709299892187119, 0.17650286853313446, -1.7178312540054321, -0.23304715752601624, -0.01350467000156641, -0.23764093220233917, 0.7148351669311523, 0.30428069829940796, 0.4503992199897766, -0.3561597168445587]", "default/action": "[0.10364092141389847, 0.17767426371574402, -0.03599759191274643, -1.7781453132629395, 0.19254662096500397, 0.23872801661491394, 0.5728810429573059, 2.268928050994873, 0.337989866733551, -0.1228933185338974, 0.12340744584798813, -1.7406771183013916, -0.21982413530349731, -0.007903007790446281, -0.23672595620155334, 2.268928050994873, 0.30656060576438904, 0.45012393593788147, -0.35880979895591736]", "default/timestamp": 0.0, "default/frame_index": 0, "default/episode_index": 0, "default/index": 0, "default/task_index": 0}
+{"default/split": "train", "default/observation.state": "[0.10533513873815536, 0.17774134874343872, -0.03509356081485748, -1.779287338256836, 0.193406343460083, 0.23852363228797913, 0.5733709931373596, 2.2687575817108154, 0.3596370220184326, -0.10983806848526001, 0.16703356802463531, -1.7218334674835205, -0.22976867854595184, -0.011929522268474102, -0.23680514097213745, 0.89737868309021, 0.30457937717437744, 0.4505760371685028, -0.3568390905857086]", "default/action": "[0.10363447666168213, 0.17763693630695343, -0.03626960888504982, -1.7790641784667969, 0.191580668091774, 0.2376576066017151, 0.5730078816413879, 2.268928050994873, 0.3229674994945526, -0.1312551498413086, 0.09607468545436859, -1.7481365203857422, -0.20632752776145935, -0.004209509119391441, -0.2362600415945053, 2.268928050994873, 0.3067648112773895, 0.4495879113674164, -0.3593738079071045]", "default/timestamp": 0.03333333507180214, "default/frame_index": 1, "default/episode_index": 0, "default/index": 1, "default/task_index": 0}