查看数据清洗任务详情
更新时间：2024-11-14
功能介绍
本接口用于查看数据清洗任务详情。
注意事项
（1）通过API查看数据清洗任务，和千帆控制台页面展示字段不同：
- 本文API参数有的字段，可能在千帆控制台页面无
- 千帆控制台页面的部分字段，可能在本文API参数中无
- 后续会持续完善API功能，请关注API文档更新
（2）本文API支持通过Python SDK、Go SDK、Java SDK 和 Node.js SDK调用，调用流程请参考SDK安装及使用流程。
SDK调用
调用示例
import os
from qianfan.resources import Data
# 使用安全认证AK/SK鉴权，通过环境变量方式初始化；替换下列示例中参数，安全认证Access Key替换your_iam_ak，Secret Key替换your_iam_sk
os.environ["QIANFAN_ACCESS_KEY"] = "your_iam_ak"
os.environ["QIANFAN_SECRET_KEY"] = "your_iam_sk"
resp = Data.get_dataset_etl_task_info("task-9tff1q3h7ngdmgh4")
print(resp)package main
import (
"context"
"fmt"
"os"
"github.com/baidubce/bce-qianfan-sdk/go/qianfan"
)
func main() {
// 使用安全认证AK/SK鉴权，通过环境变量初始化；替换下列示例中参数，安全认证Access Key替换your_iam_ak，Secret Key替换your_iam_sk
os.Setenv("QIANFAN_ACCESS_KEY", "your_iam_ak")
os.Setenv("QIANFAN_SECRET_KEY", "your_iam_sk")
ca := qianfan.NewConsoleAction()
res, err := ca.Call(context.TODO(),
// 调用本文API，该参数值为固定值，无需修改；对应本文HTTP调用-请求说明-请求地址的后缀
"/wenxinworkshop/etl/detail", "",
// 对应本文HTTP调用-请求说明-请求参数-Body参数，具体使用请查看Body参数说明，根据实际使用选择参数
map[string]interface{}{
"etlId": "task-9tff1q3h7ngdmgh4",
})
if err != nil {
panic(err)
}
fmt.Println(string(res.Body))
}import com.baidubce.qianfan.Qianfan;
import com.baidubce.qianfan.model.console.ConsoleResponse;
import com.baidubce.qianfan.util.CollUtils;
import com.baidubce.qianfan.util.Json;
import java.util.Map;
public class Dome {
public static void main(String args[]){
// 使用安全认证AK/SK鉴权，替换下列示例中参数，安全认证Access Key替换your_iam_ak，Secret Key替换your_iam_sk
Qianfan qianfan = new Qianfan("your_iam_ak", "your_iam_sk");
ConsoleResponse<Map<String, Object>> response = qianfan.console()
// 调用本文API，该参数值为固定值，无需修改；对应本文HTTP调用-请求说明-请求地址的后缀
.route("/wenxinworkshop/etl/detail")
// 需要传入参数的场景，可以自行封装请求类，或者使用Map.of()来构建请求Body
// Java 8可以使用SDK提供的CollUtils.mapOf()来替代Map.of()
// 对应本文HTTP调用-请求说明-请求参数-Body参数，具体使用请查看Body参数说明，根据实际使用选择参数
.body(CollUtils.mapOf(
"etlId", "task-9tff1q3h7ngdmgh4"
))
.execute();
System.out.println(Json.serialize(response));
}
}import {consoleAction, setEnvVariable} from "@baiducloud/qianfan";
// 使用安全认证AK/SK鉴权，通过环境变量初始化；替换下列示例中参数，安全认证Access Key替换your_iam_ak，Secret Key替换your_iam_sk
setEnvVariable('QIANFAN_ACCESS_KEY','your_iam_ak');
setEnvVariable('QIANFAN_SECRET_KEY','your_iam_sk');
async function main() {
//base_api_route:调用本文API，该参数值为固定值，无需修改；对应本文HTTP调用-请求说明-请求地址的后缀
//data:对应本文HTTP调用-请求说明-请求参数-Body参数，具体使用请查看Body参数说明，根据实际使用选择参数
const res = await consoleAction({base_api_route: '/wenxinworkshop/etl/detail', data: {
"etlId": "task-9tff1q3h7ngdmgh4"
}
});
console.log(res);
}
main();返回示例
QfResponse(
code=200,
headers={...},
body={
"log_id": "h6ccwgig4r3q6vyd",
"result": {
"id": 10,
"etlTaskId": "task-7bynx9aaa1qyex2s",
"userId": 20,
"projectId": "",
"sourceDatasetId": 111,
"destDatasetId": 111,
"taskId": 10,
"entityCount": 2,
"entityType": 2,
"operationsV2": {
"clean": [],
"deduplication": [],
"desensitization": [],
"filter": [],
},
"result": {
"RET_OK": 0,
"pipeline_stage_result": None,
"export_entity_num": 0,
"remaining_entity": 0,
"unprocessed_entity": 0,
"remove_emoji": {"processed_entity": 0},
"remove_url": {"processed_entity": 0},
"trad_to_simp": {"processed_entity": 0},
"remove_id_card": {"processed_entity": 0},
"remove_phone_number": {"processed_entity": 0},
"remove_exception_char": {"processed_entity": 0},
"replace_sim2trad": {"processed_entity": 0},
"replace_trad2sim": {"processed_entity": 0},
"replace_upper2lower": {"processed_entity": 0},
"cut": {"remaining_entity": 0, "unprocessed_entity": 0},
"failReason": "",
"pauseReason": "",
},
"processStatus": 4,
"status": 0,
"createTime": "2023-11-24T14:54:13+08:00",
"finishTime": "0001-01-01T00:00:00Z",
"creatorName": "xx",
"sourceDatasetName": "xxx",
"sourceDatasetStrId": "ds-xarnkxxxxfjky2q",
"destDatasetName": "xxx",
"destDatasetStrId": "ds-9tf91xxxx3dm7h4",
"etlResult": "",
"remainingEntity": 0,
"exceptionResult": "",
"startTime": "2023-11-24 14:54:13",
"endTime": "-",
"modifyTime": "2023-11-24 14:54:51",
"logPath": "xxxx",
},
"status": 200,
"success": True,
},
){
"log_id": "44k3yj73ms178179",
"result": {
"id": 273,
"etlTaskId": "task-7bynx9aaa1qyex2s",
"userId": 113,
"sourceDatasetId": 2235,
"destDatasetId": 2230,
"taskId": 5331,
"entityCount": 1,
"entityType": 2,
"operationsV2": {
"clean": [
{
"name": "remove_invisible_character",
"args": {}
},
{
"name": "replace_uniform_whitespace",
"args": {}
},
{
"name": "remove_non_meaning_characters",
"args": {}
},
{
"name": "replace_traditional_chinese_to_simplified",
"args": {}
},
{
"name": "remove_web_identifiers",
"args": {}
},
{
"name": "remove_emoji",
"args": {}
},
{
"name": "save_pipeline_clean",
"args": {}
}
],
"deduplication": [
{
"name": "deduplication_simhash",
"args": {
"distance": 5.6511
}
},
{
"name": "save_pipeline_deduplication",
"args": {}
}
],
"desensitization": [
{
"name": "replace_emails",
"args": {}
},
{
"name": "replace_ip",
"args": {}
},
{
"name": "replace_identifier",
"args": {}
},
{
"name": "save_pipeline_desensitization",
"args": {}
}
],
"filter": [
{
"name": "filter_check_number_words",
"args": {
"number_words_max_cutoff": 10000,
"number_words_min_cutoff": 2.2
}
},
{
"name": "filter_check_character_repetition_removal",
"args": {
"default_character_repetition_max_cutoff": 0.2
}
},
{
"name": "filter_check_word_repetition_removal",
"args": {
"word_repetition_max_cutoff": 0.6
}
},
{
"name": "filter_check_special_characters",
"args": {
"special_characters_max_cutoff": 0.3
}
},
{
"name": "filter_check_flagged_words",
"args": {
"flagged_words_max_cutoff": 0.50556
}
},
{
"name": "filter_check_lang_id",
"args": {
"lang_id_min_cutoff": 0.5
}
},
{
"name": "filter_check_perplexity",
"args": {
"perplexity_max_cutoff": 1110
}
},
{
"name": "save_pipeline_filter",
"args": {}
}
]
},
"result": {
"RET_OK": 0,
"pipeline_stage_result": {
"clean": {
"status": "Success",
"operator_count": 6,
"entity_match_count": 1,
"each_operator_result": [
{
"name": "remove_invisible_character",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "replace_uniform_whitespace",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "remove_non_meaning_characters",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "replace_traditional_chinese_to_simplified",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "remove_web_identifiers",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "remove_emoji",
"remaining_count": 1,
"drop_count": 0
}
]
},
"deduplication": {
"status": "Success",
"operator_count": 1,
"entity_match_count": 0,
"each_operator_result": [
{
"name": "deduplication_simhash",
"remaining_count": 0,
"drop_count": 0
}
]
},
"desensitization": {
"status": "Success",
"operator_count": 3,
"entity_match_count": 0,
"each_operator_result": [
{
"name": "replace_emails",
"remaining_count": 0,
"drop_count": 0
},
{
"name": "replace_ip",
"remaining_count": 0,
"drop_count": 0
},
{
"name": "replace_identifier",
"remaining_count": 0,
"drop_count": 0
}
]
},
"filter": {
"status": "Success",
"operator_count": 7,
"entity_match_count": 1,
"each_operator_result": [
{
"name": "filter_check_number_words",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "filter_check_character_repetition_removal",
"remaining_count": 0,
"drop_count": 1
},
{
"name": "filter_check_word_repetition_removal",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "filter_check_special_characters",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "filter_check_flagged_words",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "filter_check_lang_id",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "filter_check_perplexity",
"remaining_count": 1,
"drop_count": 0
}
]
}
},
"export_entity_num": 0,
"remaining_entity": 0,
"unprocessed_entity": 0,
"remove_emoji": {
"processed_entity": 0
},
"remove_url": {
"processed_entity": 0
},
"trad_to_simp": {
"processed_entity": 0
},
"remove_id_card": {
"processed_entity": 0
},
"remove_phone_number": {
"processed_entity": 0
},
"remove_exception_char": {
"processed_entity": 0
},
"replace_sim2trad": {
"processed_entity": 0
},
"replace_trad2sim": {
"processed_entity": 0
},
"replace_upper2lower": {
"processed_entity": 0
},
"cut": {
"remaining_entity": 0,
"unprocessed_entity": 0
},
"failReason": "",
"pauseReason": ""
},
"processStatus": 2,
"status": 0,
"createTime": "2023-11-06T14:31:03+08:00",
"finishTime": "2023-11-06T14:32:11+08:00",
"creatorName": "yyw02",
"sourceDatasetName": "zy_泛文本5-V1",
"sourceDatasetStrId": "ds-xarnk5tdirfjky2q",
"destDatasetName": "g423423-V2",
"destDatasetStrId": "ds-9tf91q1h7n3dm7h4",
"etlResult": "",
"remainingEntity": 0,
"exceptionResult": "",
"startTime": "2023-11-06 14:31:03",
"endTime": "2023-11-06 14:32:11",
"modifyTime": "2023-11-06 14:32:11",
"logPath": "https://bj.bcebos.com/easydata-qabosqa/qianfan/qianfan1019/_system_/dataset/ds-u7898jqx2aabjp38/cleaning/2235-2230-273-20231106143103.txt?x-bce-security-token=ZjkyZmQ2YmQxZTQ3NDxxxxxZp70QaweY1MNyT32OKRGNCew%3D%3D\u0026authorization=bce-auth-v1%2F24ec282b7c6d11eexxxxx4d33b5123"
},
"status": 200,
"success": true
}{
"log_id": "44k3yj73ms178179",
"result": {
"id": 273,
"etlTaskId": "task-7bynx9aaa1qyex2s",
"userId": 113,
"sourceDatasetId": 2235,
"destDatasetId": 2230,
"taskId": 5331,
"entityCount": 1,
"entityType": 2,
"operationsV2": {
"clean": [
{
"name": "remove_invisible_character",
"args": {}
},
{
"name": "replace_uniform_whitespace",
"args": {}
},
{
"name": "remove_non_meaning_characters",
"args": {}
},
{
"name": "replace_traditional_chinese_to_simplified",
"args": {}
},
{
"name": "remove_web_identifiers",
"args": {}
},
{
"name": "remove_emoji",
"args": {}
},
{
"name": "save_pipeline_clean",
"args": {}
}
],
"deduplication": [
{
"name": "deduplication_simhash",
"args": {
"distance": 5.6511
}
},
{
"name": "save_pipeline_deduplication",
"args": {}
}
],
"desensitization": [
{
"name": "replace_emails",
"args": {}
},
{
"name": "replace_ip",
"args": {}
},
{
"name": "replace_identifier",
"args": {}
},
{
"name": "save_pipeline_desensitization",
"args": {}
}
],
"filter": [
{
"name": "filter_check_number_words",
"args": {
"number_words_max_cutoff": 10000,
"number_words_min_cutoff": 2.2
}
},
{
"name": "filter_check_character_repetition_removal",
"args": {
"default_character_repetition_max_cutoff": 0.2
}
},
{
"name": "filter_check_word_repetition_removal",
"args": {
"word_repetition_max_cutoff": 0.6
}
},
{
"name": "filter_check_special_characters",
"args": {
"special_characters_max_cutoff": 0.3
}
},
{
"name": "filter_check_flagged_words",
"args": {
"flagged_words_max_cutoff": 0.50556
}
},
{
"name": "filter_check_lang_id",
"args": {
"lang_id_min_cutoff": 0.5
}
},
{
"name": "filter_check_perplexity",
"args": {
"perplexity_max_cutoff": 1110
}
},
{
"name": "save_pipeline_filter",
"args": {}
}
]
},
"result": {
"RET_OK": 0,
"pipeline_stage_result": {
"clean": {
"status": "Success",
"operator_count": 6,
"entity_match_count": 1,
"each_operator_result": [
{
"name": "remove_invisible_character",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "replace_uniform_whitespace",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "remove_non_meaning_characters",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "replace_traditional_chinese_to_simplified",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "remove_web_identifiers",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "remove_emoji",
"remaining_count": 1,
"drop_count": 0
}
]
},
"deduplication": {
"status": "Success",
"operator_count": 1,
"entity_match_count": 0,
"each_operator_result": [
{
"name": "deduplication_simhash",
"remaining_count": 0,
"drop_count": 0
}
]
},
"desensitization": {
"status": "Success",
"operator_count": 3,
"entity_match_count": 0,
"each_operator_result": [
{
"name": "replace_emails",
"remaining_count": 0,
"drop_count": 0
},
{
"name": "replace_ip",
"remaining_count": 0,
"drop_count": 0
},
{
"name": "replace_identifier",
"remaining_count": 0,
"drop_count": 0
}
]
},
"filter": {
"status": "Success",
"operator_count": 7,
"entity_match_count": 1,
"each_operator_result": [
{
"name": "filter_check_number_words",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "filter_check_character_repetition_removal",
"remaining_count": 0,
"drop_count": 1
},
{
"name": "filter_check_word_repetition_removal",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "filter_check_special_characters",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "filter_check_flagged_words",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "filter_check_lang_id",
"remaining_count": 1,
"drop_count": 0
},
{
"name": "filter_check_perplexity",
"remaining_count": 1,
"drop_count": 0
}
]
}
},
"export_entity_num": 0,
"remaining_entity": 0,
"unprocessed_entity": 0,
"remove_emoji": {
"processed_entity": 0
},
"remove_url": {
"processed_entity": 0
},
"trad_to_simp": {
"processed_entity": 0
},
"remove_id_card": {
"processed_entity": 0
},
"remove_phone_number": {
"processed_entity": 0
},
"remove_exception_char": {
"processed_entity": 0
},
"replace_sim2trad": {
"processed_entity": 0
},
"replace_trad2sim": {
"processed_entity": 0
},
"replace_upper2lower": {
"processed_entity": 0
},
"cut": {
"remaining_entity": 0,
"unprocessed_entity": 0
},
"failReason": "",
"pauseReason": ""
},
"processStatus": 2,
"status": 0,
"createTime": "2023-11-06T14:31:03+08:00",
"finishTime": "2023-11-06T14:32:11+08:00",
"creatorName": "yyw02",
"sourceDatasetName": "zy_泛文本5-V1",
"sourceDatasetStrId": "ds-xarnk5tdirfjky2q",
"destDatasetName": "g423423-V2",
"destDatasetStrId": "ds-9tf91q1h7n3dm7h4",
"etlResult": "",
"remainingEntity": 0,
"exceptionResult": "",
"startTime": "2023-11-06 14:31:03",
"endTime": "2023-11-06 14:32:11",
"modifyTime": "2023-11-06 14:32:11",
"logPath": "https://bj.bcebos.com/easydata-qabosqa/qianfan/qianfan1019/_system_/dataset/ds-u7898jqx2aabjp38/cleaning/2235-2230-273-20231106143103.txt?x-bce-security-token=ZjkyZmQ2YmQxZTQ3NDxxxxxZp70QaweY1MNyT32OKRGNCew%3D%3D\u0026authorization=bce-auth-v1%2F24ec282b7c6d11eexxxxx4d33b5123"
},
"status": 200,
"success": true
}{
log_id: '44k3yj73ms178179',
result: {
id: 273,
etlTaskId: 'task-7bynx9aaa1qyex2s',
userId: 113,
sourceDatasetId: 2235,
destDatasetId: 2230,
taskId: 5331,
entityCount: 1,
entityType: 2,
operationsV2: {
clean: [
{
name: 'remove_invisible_character',
args: {}
},
{
name: 'replace_uniform_whitespace',
args: {}
},
{
name: 'remove_non_meaning_characters',
args: {}
},
{
name: 'replace_traditional_chinese_to_simplified',
args: {}
},
{
name: 'remove_web_identifiers',
args: {}
},
{
name: 'remove_emoji',
args: {}
},
{
name: 'save_pipeline_clean',
args: {}
}
],
deduplication: [
{
name: 'deduplication_simhash',
args: {
distance: 5.6511
}
},
{
name: 'save_pipeline_deduplication',
args: {}
}
],
desensitization: [
{
name: 'replace_emails',
args: {}
},
{
name: 'replace_ip',
args: {}
},
{
name: 'replace_identifier',
args: {}
},
{
name: 'save_pipeline_desensitization',
args: {}
}
],
filter: [
{
name: 'filter_check_number_words',
args: {
number_words_max_cutoff: 10000,
number_words_min_cutoff: 2.2
}
},
{
name: 'filter_check_character_repetition_removal',
args: {
default_character_repetition_max_cutoff: 0.2
}
},
{
name: 'filter_check_word_repetition_removal',
args: {
word_repetition_max_cutoff: 0.6
}
},
{
name: 'filter_check_special_characters',
args: {
special_characters_max_cutoff: 0.3
}
},
{
name: 'filter_check_flagged_words',
args: {
flagged_words_max_cutoff: 0.50556
}
},
{
name: 'filter_check_lang_id',
args: {
lang_id_min_cutoff: 0.5
}
},
{
name: 'filter_check_perplexity',
args: {
perplexity_max_cutoff: 1110
}
},
{
name: 'save_pipeline_filter',
args: {}
}
]
},
result: {
RET_OK: 0,
pipeline_stage_result: {
clean: {
status: 'Success',
operator_count: 6,
entity_match_count: 1,
each_operator_result: [
{
name: 'remove_invisible_character',
remaining_count: 1,
drop_count: 0
},
{
name: 'replace_uniform_whitespace',
remaining_count: 1,
drop_count: 0
},
{
name: 'remove_non_meaning_characters',
remaining_count: 1,
drop_count: 0
},
{
name: 'replace_traditional_chinese_to_simplified',
remaining_count: 1,
drop_count: 0
},
{
name: 'remove_web_identifiers',
remaining_count: 1,
drop_count: 0
},
{
name: 'remove_emoji',
remaining_count: 1,
drop_count: 0
}
]
},
deduplication: {
status: 'Success',
operator_count: 1,
entity_match_count: 0,
each_operator_result: [
{
name: 'deduplication_simhash',
remaining_count: 0,
drop_count: 0
}
]
},
desensitization: {
status: 'Success',
operator_count: 3,
entity_match_count: 0,
each_operator_result: [
{
name: 'replace_emails',
remaining_count: 0,
drop_count: 0
},
{
name: 'replace_ip',
remaining_count: 0,
drop_count: 0
},
{
name: 'replace_identifier',
remaining_count: 0,
drop_count: 0
}
]
},
filter: {
status: 'Success',
operator_count: 7,
entity_match_count: 1,
each_operator_result: [
{
name: 'filter_check_number_words',
remaining_count: 1,
drop_count: 0
},
{
name: 'filter_check_character_repetition_removal',
remaining_count: 0,
drop_count: 1
},
{
name: 'filter_check_word_repetition_removal',
remaining_count: 1,
drop_count: 0
},
{
name: 'filter_check_special_characters',
remaining_count: 1,
drop_count: 0
},
{
name: 'filter_check_flagged_words',
remaining_count: 1,
drop_count: 0
},
{
name: 'filter_check_lang_id',
remaining_count: 1,
drop_count: 0
},
{
name: 'filter_check_perplexity',
remaining_count: 1,
drop_count: 0
}
]
}
},
export_entity_num: 0,
remaining_entity: 0,
unprocessed_entity: 0,
remove_emoji: {
processed_entity: 0
},
remove_url: {
processed_entity: 0
},
trad_to_simp: {
processed_entity: 0
},
remove_id_card: {
processed_entity: 0
},
remove_phone_number: {
processed_entity: 0
},
remove_exception_char: {
processed_entity: 0
},
replace_sim2trad: {
processed_entity: 0
},
replace_trad2sim: {
processed_entity: 0
},
replace_upper2lower: {
processed_entity: 0
},
cut: {
remaining_entity: 0,
unprocessed_entity: 0
},
failReason: '',
pauseReason: ''
},
processStatus: 2,
status: 0,
createTime: '2023-11-06T14:31:03+08:00',
finishTime: '2023-11-06T14:32:11+08:00',
creatorName: 'yyw02',
sourceDatasetName: 'zy_泛文本5-V1',
sourceDatasetStrId: 'ds-xarnk5tdirfjky2q',
destDatasetName: 'g423423-V2',
destDatasetStrId: 'ds-9tf91q1h7n3dm7h4',
etlResult: '',
remainingEntity: 0,
exceptionResult: '',
startTime: '2023-11-06 14:31:03',
endTime: '2023-11-06 14:32:11',
modifyTime: '2023-11-06 14:32:11',
logPath: 'https://bj.bcebos.com/easydata-qabosqa/qianfan/qianfan1019/_system_/dataset/ds-u7898jqx2aabjp38/cleaning/2235-2230-273-20231106143103.txt?x-bce-security-token=ZjkyZmQ2YmQxZTQ3NDxxxxxZp70QaweY1MNyT32OKRGNCew==\u0026authorization=bce-auth-v1/24ec282b7c6d11eexxxxx4d33b5123'
},
status: 200,
success: true
}请求参数
注意：不同语言SDK的请求参数不同，请根据实际调用选择对应参数。
- Python SDK请求参数说明
| 名称 | 类型 | 必填 | 描述 |
|---|---|---|---|
| etl_id | string | 是 | 数据清洗任务ID，说明： （1）可以通过以下任一方式获取该字段值： · 方式一，通过调用创建数据清洗任务接口，返回的字段result获取 · 方式二，通过调用查看清洗任务列表接口，返回的字段etlStrId获取 · 方式三，在控制台-数据处理-数据清洗页面，查看任务序号，如下图所示：  （2）该字段新增支持string类型，如果之前使用的是int类型，建议变更为string类型，后续可能将逐步废弃int类型；例如之前获取数据清洗任务序号，是调用查看清洗任务列表接口，返回的etlId字段获取，请替换为接口返回的etlStrId字段获取 |
- 其它SDK请求参数说明
| 名称 | 类型 | 必填 | 描述 |
|---|---|---|---|
| etlId | string | 是 | 数据清洗任务序号，说明： （1）可以通过以下任一方式获取该字段值： · 方式一，通过调用创建数据清洗任务接口，返回的字段result获取 · 方式二，通过调用查看清洗任务列表接口，返回的字段etlStrId获取 · 方式三，在控制台-数据处理-数据清洗页面，查看任务序号，如下图所示： （2）该字段新增支持string类型，如果之前使用的是int类型，建议变更为string类型，后续可能将逐步废弃int类型；例如之前获取数据清洗任务序号，是调用查看清洗任务列表接口，返回的etlId字段获取，请替换为接口返回的etlStrId字段获取 |
返回参数
说明：返回的部分字段如下，未说明的字段暂无需关注。
| 名称 | 类型 | 描述 |
|---|---|---|
| log_id | string | 操作记录id |
| result | object | 返回结果 |
| status | int | 状态码 |
| success | bool | 是否操作成功，说明： · true：成功 · false：失败 |
返回结果result说明
| 名称 | 类型 | 描述 |
|---|---|---|
| id | int | 任务序号，注意：该字段后续将废弃，如果有使用此字段，建议变更为etlTaskId字段 |
| etlTaskId | string | 任务序号 |
| userId | int | 用户ID |
| sourceDatasetId | int | 清洗前的源数据集版本ID，注意：该字段后续将废弃，如果有使用此字段，建议变更为sourceDatasetStrId字段 |
| sourceDatasetStrId | string | 清洗前的源数据集版本ID |
| destDatasetId | int | 清洗后的目标数据集版本ID，注意： 该字段后续将废弃，如果有使用此字段，建议变更为destDatasetStrId字段 |
| destDatasetStrId | string | 清洗后的目标数据集版本ID |
| taskId | int | 数据清洗任务ID |
| entityCount | int | 样本个数 |
| entityType | int | 样本类型，说明： 1：图片 2：文本 3：音频 4：视频 |
| operationsV2 | map[string][]operationV2 | 清洗配置 ，说明： （1）key为string，有以下值： · 清洗：clean · 过滤：filter · 去重：deduplication · 去隐私：desensitization （2）value为list，值为单个阶段用户所选择的所有算子组成的列表 · 列表中的每个元素，对应某个算子的配置，格式参考operationsV2说明 · 如果用户没有在对应阶段选择任何算子，则value为空列表 |
| result | object | 清洗结果 |
| processStatus | int | 清洗状态信息，说明： · 0：无状态，表示没有任务 · 1：进行中 · 2：已完成 · 3：已终止 · 4：清洗失败 · 5：任务暂停 |
| status | int | 清洗任务状态，说明： · 0：正常 · 1：删除 |
| createTime | string | 创建时间 |
| finishTime | string | 完成时间 |
| creatorName | string | 创建者名称 |
| sourceDatasetName | string | 源数据集名称 |
| destDatasetName | string | 目标数据集名称 |
| etlResult | string | 清洗结果 |
| remainingEntity | int | 清洗后剩余的样本数量 |
| exceptionResult | string | 异常原因 |
| startTime | string | 任务启动时间 |
| endTime | string | 任务结束时间 |
| modifyTime | string | 更改时间 |
| logPath | string | 清洗日志文件路径，如/minio/v-abc/some/path/1-2-1-20231010181818.txt |
operationV2说明
| 名称 | 类型 | 描述 |
|---|---|---|
| name | string | 算子名称，见各阶段name值和args值 （1）Clean清洗阶段算子 · remove_emoji：去除文档中的表情 · remove_invisible_character：移除ASCII中的一些不可见字符, 如0-32 和127-160这两个范围 · replace_uniform_whitespace：将不同的unicode空格比如 u2008，转成正常的空格 · remove_non_meaning_characters：去除乱码和无意义的unicode · replace_traditional_chinese_to_simplified：繁体转简体，如“不經意，妳的笑容”清洗成“不经意，你的笑容” · remove_web_identifiers：移除文档中的html标签，如 <html>,<dev>,<p>等（2）Filter过滤阶段算子 · filter_check_number_words：检查文档的词数目，词数目不在指定范围会被过滤掉，如中文[1,10000] · filter_check_word_repetition_removal：检查文档的词重复率，如果词重复率太高，意味着文档中重复的词太多，文档会被过滤掉 · filter_check_character_repetition_removal：检查文档的字重复率，如果字重复率太高，意味着文档中重复的字太多，文档会被过滤掉 · filter_check_special_characters：检查文档的特殊字符率，如果特殊字符率太高，意味着文档中特殊字符太多，文档会被过滤掉 ·filter_check_flagged_words：检查文档的色情暴力词率,如果色情暴力词率太高，文档会被过滤掉 · filter_check_lang_id：检查文档的语言概率,如果语言概率太低，文档会被过滤掉 · filter_check_perplexity：检查文档的困惑度,如果困惑度太高，文档会被过滤掉 （3）Deduplication去重阶段算子 · deduplication_simhash：根据海明距离计算文档相似度, 相似度<=海明距离，认为两个文档相似。 （4）Desensitization 去隐私阶段算子 · replace_emails：去除email地址 · replace_ip：去除IPv4 或者 IPv6 地址 · replace_identifier：去除数字和字母数字标识符，如电话号码、信用卡号、十六进制散列等，同时跳过年份和简单数字的实例 |
| args | object | 算子参数，格式随参数名称而变化，见各阶段name值对应的args说明： · 当name为Clean清洗阶段算子，args值为空 · 当name为Desensitization 去隐私阶段算子，args值为空 · 当name为Deduplication或Desensitization，请查看args说明 |
args说明
- 当name为Clean清洗阶段算子，args值为空
- 当name为Desensitization 去隐私阶段算子，args值为空
- 当name为Deduplication去重阶段算子，args说明如下
| 名称 | 类型 | 描述 |
|---|---|---|
| distance | int | 范围4-6 |
- 当name为Filter过滤阶段算子，args说明如下
| 名称 | 类型 | 描述 |
|---|---|---|
| number_words_min_cutoff | float | 最小词数目 · 范围为[1,10000] · 当name=filter_check_number_words，该字段必填 |
| number_words_max_cutoff | float | 最大词数目 · 范围为[1,10000] · 当name=filter_check_number_words，该字段必填 |
| word_repetition_max_cutoff | float | 文档的词重复率 · 范围为0-1 · 当name=filter_check_word_repetition_removal，该字段必填 |
| default_character_repetition_max_cutoff | float | 文档的字重复率 · 范围为0-1 · 当name=filter_check_character_repetition_removal，该字段必填 |
| special_characters_max_cutoff | float | 检查文档的特殊字符率，如果特殊字符率太高，意味着文档中特殊字符太多，文档会被过滤掉 · 范围为0-1 · 当name=filter_check_special_characters，该字段必填 |
| flagged_words_max_cutoff | float | 检查文档的色情暴力词率,如果色情暴力词率太高，文档会被过滤掉 ·范围为0-1 · 当name=filter_check_flagged_words，该字段必填 |
| lang_id_min_cutoff | float | 检查文档的语言概率,如果语言概率太低，文档会被过滤掉 · 范围为0-1 · 当name=filter_check_lang_id，该字段必填 |
| perplexity_max_cutoff | float | 检查文档的困惑度,如果困惑度太高，文档会被过滤掉 ·范围为1-5000 · 当name=filter_check_perplexity，该字段必填 |
清洗结果result说明
| 名称 | 类型 | 描述 |
|---|---|---|
| RET_OK | int | 清洗结果 |
| pipeline_stage_result | object | pipeline状态结果 |
| export_entity_num | int | 导出样本数量 |
| remaining_entity | int | 剩余样本 |
| unprocessed_entity | int | 尚未清洗样本 |
| remove_emoji | object | 里面只有一个int字段，processed_entity：某个算子被执行的行数 |
| remove_url | object | 只有一个int字段，processed_entity：某个算子被执行的行数 |
| trad_to_simp | object | 只有一个int字段，processed_entity：某个算子被执行的行数 |
| remove_id_card | object | 只有一个int字段，processed_entity：某个算子被执行的行数 |
| remove_phone_number | object | 只有一个int字段，processed_entity：某个算子被执行的行数 |
| remove_exception_char | object | 只有一个int字段，processed_entity：某个算子被执行的行数 |
| replace_sim2trad | object | 只有一个int字段，processed_entity：某个算子被执行的行数 |
| replace_trad2sim | object | 只有一个int字段，processed_entity：某个算子被执行的行数 |
| replace_upper2lower | object | 只有一个int字段，processed_entity：某个算子被执行的行数 |
| cut | object | 裁剪，说明： · remaining_entity：剩余样本数量 · unprocessed_entity：尚未清洗样本 |
| failReason | string | 失败原因 |
| pauseReason | string | 暂停原因 |
pipeline_stage_result说明
| 名称 | 类型 | 描述 |
|---|---|---|
| clean | object | 数据清洗clean阶段执行结果 |
| deduplication | object | 数据清洗deduplication阶段执行结果 |
| desensitization | object | 数据清洗desensitization阶段执行结果 |
| filter | object | 数据清洗filter阶段执行结果 |
执行结果说明
clean、deduplication、desensitization、filter 阶段执行结果字段相同，如下
| 名称 | 类型 | 描述 |
|---|---|---|
| status | string | 数据清洗某阶段执行结果，例："Success" |
| operator_count | int | 该阶段算子数 |
| entity_match_count | int | 匹配到的样本数量 |
| each_operator_result | object[] | 具体到算子的清洗结果列表 |
each_operator_result 说明
| 名称 | 类型 | 描述 |
|---|---|---|
| name | string | 算子名称 |
| remaining_count | int | 通过该算子清洗后剩余样本数 |
| drop_count | int | 通过该算子清洗掉的样本数 |