Dataset Cleaner & Deduplicator
Pricing
from $0.30 / 1,000 item cleaneds
Clean, normalize and deduplicate any dataset: field names, whitespace, empty values, numbers, plus exact and fuzzy duplicate removal.
You can access the Dataset Cleaner & Deduplicator programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "3yNOzOAIAyMsMzuYQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/luminous_i~dataset-cleaner-deduplicator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-luminous_i-dataset-cleaner-deduplicator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/luminous_i~dataset-cleaner-deduplicator/runs": { "post": { "operationId": "runs-sync-luminous_i-dataset-cleaner-deduplicator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/luminous_i~dataset-cleaner-deduplicator/run-sync": { "post": { "operationId": "run-sync-luminous_i-dataset-cleaner-deduplicator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "inputDatasetId": { "title": "Dataset ID to clean", "type": "string", "description": "ID of a dataset produced by any other Actor. Leave empty if you paste data below." }, "items": { "title": "Or paste your data (JSON)", "type": "array", "description": "Array of JSON objects. Only used when no Dataset ID is provided." }, "normalizeFieldNames": { "title": "Normalize field names", "type": "boolean", "description": "Turns 'First Name', 'firstName' and 'FIRST_NAME' into a single 'first_name' key.", "default": true }, "trimWhitespace": { "title": "Trim whitespace", "type": "boolean", "description": "Removes leading and trailing spaces, collapses repeated spaces.", "default": true }, "normalizeEmptyValues": { "title": "Unify empty values", "type": "boolean", "description": "Converts 'N/A', 'null', '-' and 'unknown' into real null values.", "default": true }, "lowercaseEmails": { "title": "Lowercase emails", "type": "boolean", "description": "Converts all email fields to lowercase so 'John@X.com' and 'john@x.com' are treated as one address.", "default": true }, "normalizePhones": { "title": "Normalize phone numbers", "type": "boolean", "description": "Strips spaces, dots and dashes while keeping the international prefix.", "default": true }, "coerceNumbers": { "title": "Convert text to numbers", "type": "boolean", "description": "Turns '1 234,56' and '1,234.56' into real numeric values. Handles both European and US formats.", "default": false }, "dropEmptyFields": { "title": "Drop empty fields", "type": "boolean", "description": "Shrinks output size by removing keys with no value.", "default": false }, "requiredFields": { "title": "Required fields", "type": "array", "description": "Any row missing one of these fields is discarded.", "default": [], "items": { "type": "string" } }, "dedupeMode": { "title": "Deduplication mode", "enum": [ "none", "exact", "fuzzy" ], "type": "string", "description": "Exact compares values literally. Fuzzy catches near-duplicates like 'Société Dupont' and 'SOCIETE DUPONT', whatever the accents or casing.", "default": "exact" }, "dedupeFields": { "title": "Fields to compare (exact mode)", "type": "array", "description": "Leave empty to compare the entire row.", "default": [], "items": { "type": "string" } }, "fuzzyField": { "title": "Field to compare (fuzzy mode)", "type": "string", "description": "Name of the field to match on, for example 'company_name'." }, "fuzzyThreshold": { "title": "Similarity threshold", "minimum": 50, "maximum": 100, "type": "integer", "description": "50 to 100. Above 95 is strict, below 80 becomes aggressive. 90 is a safe default; use 80 to also merge legal suffixes like SARL, Ltd or Inc.", "default": 90 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Dataset Cleaner & Deduplicator from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: