From f8342c232cafa140c46045bb8c995fe2fd42bdc8 Mon Sep 17 00:00:00 2001 From: martinforejt Date: Wed, 18 Dec 2024 11:15:05 +0100 Subject: [PATCH 1/8] feat(api): dataset fields statistics --- .../datasets/DatasetFieldStatistics.yaml | 19 +++++++ .../GetDatasetFieldStatisticsResponse.yaml | 21 +++++++ apify-api/openapi/components/tags.yaml | 4 ++ .../openapi/components/x-tag-groups.yaml | 1 + apify-api/openapi/openapi.yaml | 2 + ...datasets@{datasetId}@field-statistics.yaml | 55 +++++++++++++++++++ package-lock.json | 2 +- 7 files changed, 103 insertions(+), 1 deletion(-) create mode 100644 apify-api/openapi/components/schemas/datasets/DatasetFieldStatistics.yaml create mode 100644 apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml create mode 100644 apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml diff --git a/apify-api/openapi/components/schemas/datasets/DatasetFieldStatistics.yaml b/apify-api/openapi/components/schemas/datasets/DatasetFieldStatistics.yaml new file mode 100644 index 000000000..44b0e5dd7 --- /dev/null +++ b/apify-api/openapi/components/schemas/datasets/DatasetFieldStatistics.yaml @@ -0,0 +1,19 @@ +title: DatasetFieldStatistics +type: object +properties: + min: + type: number + description: 'Minimum value of the field. For numbers, this is calculated directly. For strings, this is the length of the shortest string. For arrays, this is the length of the shortest array. For objects, this is the number of keys in the smallest object.' + nullable: true + max: + type: number + description: 'Maximum value of the field. For numbers, this is calculated directly. For strings, this is the length of the longest string. For arrays, this is the length of the longest array. For objects, this is the number of keys in the largest object.' + nullable: true + nullCount: + type: number + description: 'How many items in the dataset have a null value for this field.' + nullable: true + emptyCount: + type: number + description: 'How many items in the dataset are `undefined`, meaning that for example empty string is not considered empty.' + nullable: true diff --git a/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml b/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml new file mode 100644 index 000000000..e69a88ec3 --- /dev/null +++ b/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml @@ -0,0 +1,21 @@ +title: GetDatasetFieldStatisticsResponse +required: + - data +type: object +properties: + data: + type: object + required: + - fields + - statistics + properties: + fields: + type: array + items: + type: string + description: 'Keys of the fields for which the statistics are provided.' + statistics: + type: object + additionalProperties: + $ref: ./DatasetFieldStatistics.yaml + description: 'Statistics for each field. The keys are the same as in the `fields` array.' diff --git a/apify-api/openapi/components/tags.yaml b/apify-api/openapi/components/tags.yaml index 90c85c876..c5c6eb003 100644 --- a/apify-api/openapi/components/tags.yaml +++ b/apify-api/openapi/components/tags.yaml @@ -758,6 +758,10 @@ x-legacy-doc-urls: - '#/reference/datasets/item-collection' x-trait: 'true' +- name: Datasets/Field statistics + x-displayName: Field statistics + x-parent-tag-name: Datasets + x-trait: 'true' - name: Request queues x-displayName: Request queues x-legacy-doc-urls: diff --git a/apify-api/openapi/components/x-tag-groups.yaml b/apify-api/openapi/components/x-tag-groups.yaml index c52de15a6..fbb05fb66 100644 --- a/apify-api/openapi/components/x-tag-groups.yaml +++ b/apify-api/openapi/components/x-tag-groups.yaml @@ -62,6 +62,7 @@ - Datasets/Dataset collection - Datasets/Dataset - Datasets/Item collection + - Datasets/Field statistics - name: Request queues tags: - Request queues diff --git a/apify-api/openapi/openapi.yaml b/apify-api/openapi/openapi.yaml index 4d0c6d021..75f0a1a90 100644 --- a/apify-api/openapi/openapi.yaml +++ b/apify-api/openapi/openapi.yaml @@ -566,6 +566,8 @@ paths: $ref: 'paths/datasets/datasets@{datasetId}.yaml' '/v2/datasets/{datasetId}/items': $ref: 'paths/datasets/datasets@{datasetId}@items.yaml' + '/v2/datasets/{datasetId}/field-statistics': + $ref: 'paths/datasets/datasets@{datasetId}@field-statistics.yaml' /v2/request-queues: $ref: paths/request-queues/request-queues.yaml '/v2/request-queues/{queueId}': diff --git a/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml b/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml new file mode 100644 index 000000000..5995de0ee --- /dev/null +++ b/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml @@ -0,0 +1,55 @@ +get: + tags: + - Datasets/Field statistics + summary: Get field statistics + description: | + Returns field statistics for given dataset. + When you configure the dataset [fields schema](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation), we generate a field list and measure the statistics such as `min`, `max`, `nullCount` and `emptyCount`. + + See [documentation](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation#dataset-field-statistics) for more information. + + operationId: dataset_field_statistics_get + parameters: + - name: datasetId + in: path + description: Dataset ID or `username~dataset-name`. + required: true + style: simple + schema: + type: string + example: WkzbQMuFYuamGv3YF + - name: token + in: query + description: | + API authentication token. It is required only when using the `username~dataset-name` format for `datasetId`. + style: form + explode: true + schema: + type: string + example: soSkq9ekdmfOslopH + responses: + '200': + description: '' + content: + application/json: + schema: + $ref: "../../components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml" + example: + data: + fields: ["name", "price"] + statistics: { + name: { + nullCount: 122 + }, + price: { + min: 59, + max: 89 + } + } +# TODO: add clients methods +# x-js-parent: DatasetClient +# x-js-name: fieldStatistics +# x-js-doc-url: https://docs.apify.com/api/client/js/reference/class/DatasetClient#fieldStatistics +# x-py-parent: DatasetClientAsync +# x-py-name: field_statistics +# x-py-doc-url: https://docs.apify.com/api/client/python/reference/class/DatasetClientAsync#field_statistics diff --git a/package-lock.json b/package-lock.json index d1864da3c..86a7d3482 100644 --- a/package-lock.json +++ b/package-lock.json @@ -74,7 +74,7 @@ }, "apify-docs-theme": { "name": "@apify/docs-theme", - "version": "1.0.146", + "version": "1.0.148", "license": "ISC", "dependencies": { "@apify/docs-search-modal": "^1.1.1", From a8237f4d84282f8fb101843332bcbb2733376deb Mon Sep 17 00:00:00 2001 From: martinforejt Date: Wed, 18 Dec 2024 11:20:54 +0100 Subject: [PATCH 2/8] update link in description --- .../paths/datasets/datasets@{datasetId}@field-statistics.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml b/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml index 5995de0ee..ba5e3c23c 100644 --- a/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml +++ b/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml @@ -6,7 +6,7 @@ get: Returns field statistics for given dataset. When you configure the dataset [fields schema](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation), we generate a field list and measure the statistics such as `min`, `max`, `nullCount` and `emptyCount`. - See [documentation](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation#dataset-field-statistics) for more information. + See dataset fields schema [documentation](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation#dataset-field-statistics) for more information. operationId: dataset_field_statistics_get parameters: From 060b2450fdc7104918cdaf0c9a64c303250cc312 Mon Sep 17 00:00:00 2001 From: martinforejt Date: Wed, 18 Dec 2024 18:13:39 +0100 Subject: [PATCH 3/8] remove redundant fields --- .../GetDatasetFieldStatisticsResponse.yaml | 17 +++-------------- .../datasets@{datasetId}@field-statistics.yaml | 15 +++++---------- 2 files changed, 8 insertions(+), 24 deletions(-) diff --git a/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml b/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml index e69a88ec3..29365bd3e 100644 --- a/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml +++ b/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml @@ -5,17 +5,6 @@ type: object properties: data: type: object - required: - - fields - - statistics - properties: - fields: - type: array - items: - type: string - description: 'Keys of the fields for which the statistics are provided.' - statistics: - type: object - additionalProperties: - $ref: ./DatasetFieldStatistics.yaml - description: 'Statistics for each field. The keys are the same as in the `fields` array.' + additionalProperties: + $ref: ./DatasetFieldStatistics.yaml + description: 'Statistics for each field from fields dataset schema.' diff --git a/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml b/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml index ba5e3c23c..ed120df4c 100644 --- a/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml +++ b/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml @@ -36,16 +36,11 @@ get: $ref: "../../components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml" example: data: - fields: ["name", "price"] - statistics: { - name: { - nullCount: 122 - }, - price: { - min: 59, - max: 89 - } - } + name: + nullCount: 122 + price: + min: 59 + max: 89 # TODO: add clients methods # x-js-parent: DatasetClient # x-js-name: fieldStatistics From fb348583c0e5991a17bc9320b500ca49a8d67f52 Mon Sep 17 00:00:00 2001 From: martinforejt Date: Wed, 18 Dec 2024 18:15:56 +0100 Subject: [PATCH 4/8] update endpoint description --- .../paths/datasets/datasets@{datasetId}@field-statistics.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml b/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml index ed120df4c..fd666df79 100644 --- a/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml +++ b/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml @@ -4,7 +4,7 @@ get: summary: Get field statistics description: | Returns field statistics for given dataset. - When you configure the dataset [fields schema](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation), we generate a field list and measure the statistics such as `min`, `max`, `nullCount` and `emptyCount`. + When you configure the dataset [fields schema](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation), we measure the statistics such as `min`, `max`, `nullCount` and `emptyCount` for each field. See dataset fields schema [documentation](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation#dataset-field-statistics) for more information. From 425bbbc8286e0e520d946af12d2dfdf5ec7a208c Mon Sep 17 00:00:00 2001 From: martinforejt Date: Wed, 18 Dec 2024 18:16:19 +0100 Subject: [PATCH 5/8] update response description --- .../schemas/datasets/GetDatasetFieldStatisticsResponse.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml b/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml index 29365bd3e..c0801a85e 100644 --- a/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml +++ b/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml @@ -7,4 +7,4 @@ properties: type: object additionalProperties: $ref: ./DatasetFieldStatistics.yaml - description: 'Statistics for each field from fields dataset schema.' + description: 'Statistics for each field from dataset fields schema.' From 4cc52db14e2304150b5934ac83cc40053d112b7c Mon Sep 17 00:00:00 2001 From: martinforejt Date: Fri, 20 Dec 2024 22:40:14 +0100 Subject: [PATCH 6/8] use /v2/datasets/{datasetId}/statistics approach --- .../GetDatasetFieldStatisticsResponse.yaml | 10 ---- .../GetDatasetStatisticsResponse.yaml | 15 ++++++ apify-api/openapi/components/tags.yaml | 4 +- .../openapi/components/x-tag-groups.yaml | 2 +- apify-api/openapi/openapi.yaml | 4 +- ...datasets@{datasetId}@field-statistics.yaml | 50 ------------------- .../datasets@{datasetId}@statistics.yaml | 49 ++++++++++++++++++ 7 files changed, 69 insertions(+), 65 deletions(-) delete mode 100644 apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml create mode 100644 apify-api/openapi/components/schemas/datasets/GetDatasetStatisticsResponse.yaml delete mode 100644 apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml create mode 100644 apify-api/openapi/paths/datasets/datasets@{datasetId}@statistics.yaml diff --git a/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml b/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml deleted file mode 100644 index c0801a85e..000000000 --- a/apify-api/openapi/components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml +++ /dev/null @@ -1,10 +0,0 @@ -title: GetDatasetFieldStatisticsResponse -required: - - data -type: object -properties: - data: - type: object - additionalProperties: - $ref: ./DatasetFieldStatistics.yaml - description: 'Statistics for each field from dataset fields schema.' diff --git a/apify-api/openapi/components/schemas/datasets/GetDatasetStatisticsResponse.yaml b/apify-api/openapi/components/schemas/datasets/GetDatasetStatisticsResponse.yaml new file mode 100644 index 000000000..9b659ad5c --- /dev/null +++ b/apify-api/openapi/components/schemas/datasets/GetDatasetStatisticsResponse.yaml @@ -0,0 +1,15 @@ +title: GetDatasetStatisticsResponse +required: + - data +type: object +properties: + data: + type: object + properties: + fieldStatistics: + type: object + additionalProperties: + $ref: ./DatasetFieldStatistics.yaml + description: 'When you configure the dataset [fields schema](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation), we measure the statistics such as `min`, `max`, `nullCount` and `emptyCount` for each field. + This property provides statistics for each field from dataset fields schema. +

See dataset field statistics [documentation](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation#dataset-field-statistics) for more information.' diff --git a/apify-api/openapi/components/tags.yaml b/apify-api/openapi/components/tags.yaml index c5c6eb003..dfa8659c0 100644 --- a/apify-api/openapi/components/tags.yaml +++ b/apify-api/openapi/components/tags.yaml @@ -758,8 +758,8 @@ x-legacy-doc-urls: - '#/reference/datasets/item-collection' x-trait: 'true' -- name: Datasets/Field statistics - x-displayName: Field statistics +- name: Datasets/Statistics + x-displayName: Statistics x-parent-tag-name: Datasets x-trait: 'true' - name: Request queues diff --git a/apify-api/openapi/components/x-tag-groups.yaml b/apify-api/openapi/components/x-tag-groups.yaml index fbb05fb66..8e578a4fa 100644 --- a/apify-api/openapi/components/x-tag-groups.yaml +++ b/apify-api/openapi/components/x-tag-groups.yaml @@ -62,7 +62,7 @@ - Datasets/Dataset collection - Datasets/Dataset - Datasets/Item collection - - Datasets/Field statistics + - Datasets/Statistics - name: Request queues tags: - Request queues diff --git a/apify-api/openapi/openapi.yaml b/apify-api/openapi/openapi.yaml index 75f0a1a90..377ae251e 100644 --- a/apify-api/openapi/openapi.yaml +++ b/apify-api/openapi/openapi.yaml @@ -566,8 +566,8 @@ paths: $ref: 'paths/datasets/datasets@{datasetId}.yaml' '/v2/datasets/{datasetId}/items': $ref: 'paths/datasets/datasets@{datasetId}@items.yaml' - '/v2/datasets/{datasetId}/field-statistics': - $ref: 'paths/datasets/datasets@{datasetId}@field-statistics.yaml' + '/v2/datasets/{datasetId}/statistics': + $ref: 'paths/datasets/datasets@{datasetId}@statistics.yaml' /v2/request-queues: $ref: paths/request-queues/request-queues.yaml '/v2/request-queues/{queueId}': diff --git a/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml b/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml deleted file mode 100644 index fd666df79..000000000 --- a/apify-api/openapi/paths/datasets/datasets@{datasetId}@field-statistics.yaml +++ /dev/null @@ -1,50 +0,0 @@ -get: - tags: - - Datasets/Field statistics - summary: Get field statistics - description: | - Returns field statistics for given dataset. - When you configure the dataset [fields schema](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation), we measure the statistics such as `min`, `max`, `nullCount` and `emptyCount` for each field. - - See dataset fields schema [documentation](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation#dataset-field-statistics) for more information. - - operationId: dataset_field_statistics_get - parameters: - - name: datasetId - in: path - description: Dataset ID or `username~dataset-name`. - required: true - style: simple - schema: - type: string - example: WkzbQMuFYuamGv3YF - - name: token - in: query - description: | - API authentication token. It is required only when using the `username~dataset-name` format for `datasetId`. - style: form - explode: true - schema: - type: string - example: soSkq9ekdmfOslopH - responses: - '200': - description: '' - content: - application/json: - schema: - $ref: "../../components/schemas/datasets/GetDatasetFieldStatisticsResponse.yaml" - example: - data: - name: - nullCount: 122 - price: - min: 59 - max: 89 -# TODO: add clients methods -# x-js-parent: DatasetClient -# x-js-name: fieldStatistics -# x-js-doc-url: https://docs.apify.com/api/client/js/reference/class/DatasetClient#fieldStatistics -# x-py-parent: DatasetClientAsync -# x-py-name: field_statistics -# x-py-doc-url: https://docs.apify.com/api/client/python/reference/class/DatasetClientAsync#field_statistics diff --git a/apify-api/openapi/paths/datasets/datasets@{datasetId}@statistics.yaml b/apify-api/openapi/paths/datasets/datasets@{datasetId}@statistics.yaml new file mode 100644 index 000000000..52ce3ea06 --- /dev/null +++ b/apify-api/openapi/paths/datasets/datasets@{datasetId}@statistics.yaml @@ -0,0 +1,49 @@ +get: + tags: + - Datasets/Statistics + summary: Get dataset statistics + description: | + Returns statistics for given dataset. + Currently provides only [field statistics](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation#dataset-field-statistics). + + operationId: dataset_statistics_get + parameters: + - name: datasetId + in: path + description: Dataset ID or `username~dataset-name`. + required: true + style: simple + schema: + type: string + example: WkzbQMuFYuamGv3YF + - name: token + in: query + description: | + API authentication token. It is required only when using the `username~dataset-name` format for `datasetId`. + style: form + explode: true + schema: + type: string + example: soSkq9ekdmfOslopH + responses: + '200': + description: '' + content: + application/json: + schema: + $ref: "../../components/schemas/datasets/GetDatasetStatisticsResponse.yaml" + example: + data: + fieldStatistics: + name: + nullCount: 122 + price: + min: 59 + max: 89 +# TODO: add clients methods +# x-js-parent: DatasetClient +# x-js-name: statistics +# x-js-doc-url: https://docs.apify.com/api/client/js/reference/class/DatasetClient#statistics +# x-py-parent: DatasetClientAsync +# x-py-name: statistics +# x-py-doc-url: https://docs.apify.com/api/client/python/reference/class/DatasetClientAsync#statistics From 2fb28065efddbf86ff62fe3d0aa87203dbdccfc5 Mon Sep 17 00:00:00 2001 From: martinforejt Date: Fri, 20 Dec 2024 22:43:35 +0100 Subject: [PATCH 7/8] fix indent --- .../datasets/GetDatasetStatisticsResponse.yaml | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/apify-api/openapi/components/schemas/datasets/GetDatasetStatisticsResponse.yaml b/apify-api/openapi/components/schemas/datasets/GetDatasetStatisticsResponse.yaml index 9b659ad5c..27d09d681 100644 --- a/apify-api/openapi/components/schemas/datasets/GetDatasetStatisticsResponse.yaml +++ b/apify-api/openapi/components/schemas/datasets/GetDatasetStatisticsResponse.yaml @@ -6,10 +6,10 @@ properties: data: type: object properties: - fieldStatistics: - type: object - additionalProperties: - $ref: ./DatasetFieldStatistics.yaml - description: 'When you configure the dataset [fields schema](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation), we measure the statistics such as `min`, `max`, `nullCount` and `emptyCount` for each field. - This property provides statistics for each field from dataset fields schema. -

See dataset field statistics [documentation](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation#dataset-field-statistics) for more information.' + fieldStatistics: + type: object + additionalProperties: + $ref: ./DatasetFieldStatistics.yaml + description: 'When you configure the dataset [fields schema](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation), we measure the statistics such as `min`, `max`, `nullCount` and `emptyCount` for each field. + This property provides statistics for each field from dataset fields schema. +

See dataset field statistics [documentation](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation#dataset-field-statistics) for more information.' From c431a15f807dfdf7be7ed6fd8113f08be097dfce Mon Sep 17 00:00:00 2001 From: martinforejt Date: Sat, 21 Dec 2024 22:15:10 +0100 Subject: [PATCH 8/8] fieldStatistics nullable --- .../schemas/datasets/GetDatasetStatisticsResponse.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/apify-api/openapi/components/schemas/datasets/GetDatasetStatisticsResponse.yaml b/apify-api/openapi/components/schemas/datasets/GetDatasetStatisticsResponse.yaml index 27d09d681..9a5b675ff 100644 --- a/apify-api/openapi/components/schemas/datasets/GetDatasetStatisticsResponse.yaml +++ b/apify-api/openapi/components/schemas/datasets/GetDatasetStatisticsResponse.yaml @@ -8,6 +8,7 @@ properties: properties: fieldStatistics: type: object + nullable: true additionalProperties: $ref: ./DatasetFieldStatistics.yaml description: 'When you configure the dataset [fields schema](https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema/validation), we measure the statistics such as `min`, `max`, `nullCount` and `emptyCount` for each field.