地球资源数据云——数据资源详情
该数据集《Indeed job (Data science /data analyst/ ML)》主要用于监督学习任务,数据形态以文本为主。 题目说明:These job posted on Indeed India (July 2022), Make use of your NLP knowledge 任务类型:文本监督学习。 建议流程:先做文本清洗与分词,再比较 TF - IDF+线性模型 与 预训练语言模型。 评估建议:使用分层切分或交叉验证,优先关注 F1、Recall、AUC 等分类指标。 可用文件:job_dataset.csv。 This dataset contains over approximate 1600 job information records. The jobs are mainly relate to either 'Data Engineer', 'Data Analyst' or 'Data Scientist' or 'ML engineer' etc . there are eight column in this dataset The dataset contains the job Title, Company name, Job summary, Job Location and Expected Salary, post date, today , job Url. Task You can clean the dataset and remove the column if required What are the most in - demand skills? How are the jobs distributed geographically?

该数据集《Indeed job (Data science /data analyst/ ML)》主要用于监督学习任务,数据形态以文本为主。 题目说明:These job posted on Indeed India (July 2022), Make use of your NLP knowledge
任务类型:文本监督学习。
建议流程:先做文本清洗与分词,再比较 TF - IDF+线性模型 与 预训练语言模型。
评估建议:使用分层切分或交叉验证,优先关注 F1、Recall、AUC 等分类指标。
可用文件:job_dataset.csv。
This dataset contains over approximate 1600 job information records. The jobs are mainly relate to either 'Data Engineer', 'Data Analyst' or 'Data Scientist' or 'ML engineer' etc .
there are eight column in this dataset The dataset contains the job Title, Company name, Job summary, Job Location and Expected Salary, post date, today , job Url. Task
You can clean the dataset and remove the column if required
What are the most in - demand skills?
How are the jobs distributed geographically?