diff --git a/DESCRIPTION b/DESCRIPTION index 6b82f8f..9a79318 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -5,6 +5,10 @@ Version: 2.0.0 Authors@R: c( person("Thiyanga S.", "Talagala", email = "ttalagala@sjp.ac.lk", role = c("aut", "cre"), comment=c(ORCID = "0000-0002-0656-9789")), person("Janith C.", "Wanniarachchi", role = c("aut")), + person("Hansani", "Piyumika", role = c("ctb")), + person("Jayani", "Lakshika", role = c("ctb")), + person("Chammika", "R De Mel", role = c("ctb")), + person("Randi", "Shashikala", role = c("ctb")), person("HLS", "Perera", role = c("ctb")), person("S", "Dissanayake", role = c("ctb")), person("MB", "Senanayake", role = c("ctb")), @@ -17,6 +21,8 @@ LazyData: true LazyDataCompression: xz RoxygenNote: 7.2.3 Roxygen: list(markdown = TRUE) +Depends: + R (>= 3.5.0) Suggests: knitr, rmarkdown, diff --git a/R/datatidy.R b/R/datatidy.R index 7625cac..5648846 100644 --- a/R/datatidy.R +++ b/R/datatidy.R @@ -1,125 +1,125 @@ -#' Data Scientists/Data Analyst/ Statistician Job Advertisements in the year 2020 -#' Job advertisements +#' Data scientists, data analyst, and statistician job advertisements from 2020 to 2023 +#' +#' A dataset with 1172 rows and 109 variables #' -#' A data frame with 1172 rows and 109 variables #' \itemize{ -#' \item{ID}{row id} -#' \item{Consultant}{Name of the consultant} -#' \item{DateRetrieved}{ Date of Data Retrieved } -#' \item{DatePublished}{Published Date of the Advertisement } -#' \item{Job_title}{ Name of the job category} -#' \item{Company}{Name of the Company} -#' \item{R}{If R is required -> 1 ,If not mentioned -> 0} -#' \item{SAS}{If SAS is required -> 1 , If not mentioned -> 0} -#' \item{SPSS}{If SPSS is required -> 1 , If not mentioned -> 0} -#' \item{Python}{If Python is required -> 1 , If not mentioned -> 0} -#' \item{MAtlab}{If Matlab is required -> 1 , If not mentioned -> 0} -#' \item{Scala}{If Scala is required -> 1 , If not mentioned -> 0} -#' \item{C#}{If C# is required -> 1 , If not mentioned -> 0} -#' \item{MS Word}{If knowledge in MS Word is required -> 1 , If not mentioned -> 0} -#' \item{Ms Excel}{If knowledge in MS Excel is required -> 1 , If not mentioned -> 0} -#' \item{OLE/DB}{If knowledge in OLE/DB is required -> 1 , If not mentioned -> 0} -#' \item{Ms Access}{If Ms Access is required -> 1 , If not mentioned -> 0} -#' \item{Ms PowerPoint}{If knowledge in Ms Powerpoint is required -> 1 , If not mentioned -> 0} -#' \item{Spreadsheets}{If knowledge in Spreadsheets is required -> 1 , If not mentioned -> 0} -#' \item{Data_visualization}{If knowledge inData Visualization is required -> 1 , If not mentioned -> 0} -#' \item{Presentation_Skills}{If Presentation Skills are required -> 1 , If not mentioned -> 0} -#' \item{Communication}{If Communication skills are required -> 1 , If not mentioned -> 0} -#' \item{BigData}{If knowledge in Big Data analysis is required -> 1 , If not mentioned -> 0} -#' \item{Data_warehouse}{If knowledge in Data Warehouse is required -> 1 , If not mentioned -> 0} -#' \item{cloud_storage}{If knowledge in Cloud Storage is required -> 1 , If not mentioned -> 0} -#' \item{Google_Cloud}{If knowledge in Google Cloud is required -> 1 , If not mentioned -> 0} -#' \item{AWS}{If knowledge in AWS is required -> 1 , If not mentioned -> 0} -#' \item{Machine_Learning}{If knowledge in Machine Learning is required -> 1 , If not mentioned -> 0} -#' \item{Deep Learning}{If knowledge in Deep Learning is required -> 1 , If not entioned -> 0} -#' \item{Computer_vision}{If knowledge in Computer Vision is required -> 1 , If not mentioned -> 0} -#' \item{Java}{If Java is required -> 1 , If not mentioned -> 0} -#' \item{C++}{If C++ is required -> 1 , If not mentioned -> 0} -#' \item{C}{If C is required -> 1 , If not mentioned -> 0} -#' \item{Linux/Unix}{If knowledge in Linux/Unix is required -> 1 , If not mentioned -> 0} -#' \item{SQL}{If SQL is required -> 1 , If not mentioned -> 0} -#' \item{NoSQL}{If NoSQL is required -> 1 , If not mentioned -> 0} -#' \item{RDBMS}{If knowledge in RDBMS is required -> 1 , If not mentioned -> 0} -#' \item{Oracle}{If knowledge in Oracle is required -> 1 , If not mentioned -> 0} -#' \item{MySQL}{If MYSQL is required -> 1 , If not mentioned -> 0} -#' \item{PHP}{If PHP is required -> 1 , If not mentioned -> 0} -#' \item{Flash_Actionscript}{If knowledge in Flash Action Script is required -> 1 , If not mentioned -> 0} -#' \item{SPL}{If knowledge in SPL is required -> 1 , If not mentioned -> 0} -#' \item{web_design_and_development_tools}{If knowledge in Web Design and Development Tools is required -> 1 , If not mentioned -> 0} -#' \item{Wordpress}{If knowledge in Wordpress is required -> 1 , If not mentioned -> 0} -#' \item{AI}{If Artificial Intelligence is required -> 1 , If not mentioned -> 0} -#' \item{Natural_Language_Processing(NLP)}{If knowledge in NLP is required -> 1 , If not mentioned -> 0} -#' \item{Microsoft Power BI}{If knowledge in Microsoft Power BI is required -> 1 , If not mentioned -> 0} -#' \item{Google_Analytics}{If knowledge in Google Analytics is required -> 1 , If not mentioned -> 0} -#' \item{graphics_and_design_skills}{If Graphic and Design Skills are required -> 1 , If not mentioned -> 0} -#' \item{Data_marketing}{If Data Marketing abillity is required -> 1 , If not mentioned -> 0} -#' \item{SEO}{If knowledge in SEO is required -> 1 , If not mentioned -> 0} -#' \item{Content_Management}{If knowledge in Content Management is required -> 1 , If not mentioned -> 0} -#' \item{Tableau}{If knowledge in Tableau is required -> 1 , If not mentioned -> 0} -#' \item{D3}{If knowledge in D3 is required -> 1 , If not mentioned -> 0} -#' \item{Alteryx}{If knowledge in Alteryx is required -> 1 , If not mentioned -> 0} -#' \item{KNIME}{If knowledge in KNIME is required -> 1 , If not mentioned -> 0} -#' \item{Spotfire}{If knowledge in Spotfire is required -> 1 , If not mentioned -> 0} -#' \item{Spark}{If knowledge in Spark is required -> 1 , If not mentioned -> 0} -#' \item{S3}{If knowledge in S3 is required -> 1 , If not mentioned -> 0} -#' \item{Redshift}{If knowledge in Redshift is required -> 1 , If not mentioned -> 0} -#' \item{DigitalOcean}{If knowledge in Digital Ocean is required -> 1 , If not mentioned -> 0} -#' \item{Javascript}{If Java Script is required -> 1 , If not mentioned -> 0} -#' \item{Kafka}{If knowledge in Kafka is required -> 1 , If not mentioned -> 0} -#' \item{Storm}{If knowledge in Storm is required -> 1 , If not mentioned -> 0} -#' \item{Bash}{If knowledge in Bash is required -> 1 , If not mentioned -> 0} -#' \item{Hadoop}{If knowledge in Hadoop is required -> 1 , If not mentioned -> 0} -#' \item{Data_Pipelines}{If knowledge in Data Pipelines is required -> 1 , If not mentioned -> 0} -#' \item{MPP_Platforms}{If MPP Platforms is required ->1,If not mentioned-0} -#' \item{Qlik}{If Qlik is required ->1,If not mentioned ->0} -#' \item{Pig}{If Pig is required ->1,If not mentioned ->0} -#' \item{Hive}{If Hive is required ->1,If not mentioned ->0} -#' \item{Tensorflow}{If Tensorflow is required ->1,If not mentioned ->0} -#' \item{Map/Reduce}{If Map/Reduce is required ->1,If not mentioned ->0} -#' \item{Impala}{If Impala is required ->1,If not mentioned ->0} -#' \item{Solr}{If Sloris required ->1,If not mentioned ->0} -#' \item{Teradata}{If Teradata is required ->1,If not mentioned ->0} -#' \item{MongoDB}{If MonoDB is required ->1,If not mentioned ->0} -#' \item{Elasticsearch}{If Elasticsearch is required ->1,If not mentioned ->0} -#' \item{YOLO}{If YOLO is required-1 ,If not mentioned-0} -#' \item{agile execution}{If agile execution is required->1 ,If not mentioned->0} -#' \item{Data_management}{If the knowledge in data management is required->1 ,If not mentioned->0} -#' \item{pyspark}{If pyspark is required->1 ,If not mentioned->0 } -#' \item{Data_mining}{If the knowledge in data mining is required->1 ,If not mentioned->0} -#' \item{Data_science}{If the knowledge in data science is required->1 ,If not mentioned->0} -#' \item{Web_Analytic_tools}{If the knowledge in Web Analytic tools is required->1 ,If not mentioned->0} -#' \item{IOT}{If IOT is required->1 ,If not mentioned->0} -#' \item{Numerical_Analysis}{If the knowledge in Numerical Analysis is required->1 ,If not mentioned->0} -#' \item{Economic}{If the knowledge in Economic is required->1 ,If not mentioned->0} -#' \item{Finance_Knowledge}{If Finance\_Knowledge is required->1 ,If not mentioned->0} -#' \item{Investment_Knowledge}{If Investment Knowledge is required->1 ,If not mentioned->0} -#' \item{Problem_Solving}{If the ability of Problem Solving is required->1 ,If not mentioned->0} -#' \item{Team_Handling}{If the ability of Team Handling is required->1 ,If not mentioned->0} -#' \item{Debtor_reconcilation}{If the ability of Debtor reconcilation is required->1 ,If not mentioned->0} -#' \item{Payroll_management}{If Payroll management is required->1 ,If not mentioned->0} -#' \item{Bayesian}{If Bayesian is required->1 ,If not mentioned->0} -#' \item{Optimization}{If Optimization knowledge is required-1 ,If not mentioned-0} -#' \item{Knowledge_in}{Required knowledge to do a particular job ,If not mentioned->NA} -#' \item{City}{City where the company is located in } -#' \item{Educational_qualifications}{Required educational qualifications} -#' \item{Salary}{Amount of salary} -#' \item{URL}{Web address of a particular job advertisement} -#' \item{Search_Term}{web search term of a particular job advertisement} -#' \item{Job_Category}{Category of the job (i.e. "Data Science","Data Analyst" etc.)} -#' \item{Team_Handling}{If the ability of Team Handling is required-1 ,If not mentioned-0} -#' \item{Debtor_reconcilation}{If the ability of Debtor reconciliation is required-1 ,If not mentioned-0} -#' \item{Payroll_management}{If the ability of Payroll management is required-1 ,If not mentioned-0} -#' \item{Bayesian}{If Bayesian knowledge is required-1 ,If not mentioned-0} -#' \item{Bahasa_Malaysia}{If Bahasa Malaysia is required-1 ,If not mentioned-0 } -#' \item{English_proficiency}{If English proficiency is required-1 ,If not mentioned-0} -#' \item{Experience_Category}{Number of years of experience in binned into categories} -#' \item{Location}{Location} -#' \item{Payment Frequency}{Payment frequency} -#' \item{BSc_needed}{If BSc is required-1 ,If not mentioned-0} -#' \item{MSc_needed}{If MSc is required-1 ,If not mentioned-0} -#' \item{PhD_needed}{If PhD is required-1 ,If not mentioned-0} -#' \item{English Needed}{If English is required-1 ,If not mentioned-0} -#' \item{year}{Survey year} +#' \item ID. row id +#' \item Consultant. Name of the consultant +#' \item DateRetrieved. Date of Data Retrieved +#' \item DatePublished. Published Date of the Advertisement +#' \item Job_title. Name of the job category +#' \item Company. Name of the Company +#' \item R. If R is required -> 1 ,If not mentioned -> 0 +#' \item SAS. If SAS is required -> 1 , If not mentioned -> 0 +#' \item SPSS. If SPSS is required -> 1 , If not mentioned -> 0 +#' \item Python. If Python is required -> 1 , If not mentioned -> 0 +#' \item MAtlab. If Matlab is required -> 1 , If not mentioned -> 0 +#' \item Scala. If Scala is required -> 1 , If not mentioned -> 0 +#' \item C#. If C# is required -> 1 , If not mentioned -> 0 +#' \item MS Word. If knowledge in MS Word is required -> 1 , If not mentioned -> 0 +#' \item Ms Excel. If knowledge in MS Excel is required -> 1 , If not mentioned -> 0 +#' \item OLE/DB. If knowledge in OLE/DB is required -> 1 , If not mentioned -> 0 +#' \item Ms Access. If Ms Access is required -> 1 , If not mentioned -> 0 +#' \item Ms PowerPoint. If knowledge in Ms Powerpoint is required -> 1 , If not mentioned -> 0 +#' \item Spreadsheets. If knowledge in Spreadsheets is required -> 1 , If not mentioned -> 0 +#' \item Data_visualization. If knowledge in Data Visualization is required -> 1 , If not mentioned -> 0 +#' \item Presentation_Skills. If Presentation Skills are required -> 1 , If not mentioned -> 0 +#' \item Communication. If Communication skills are required -> 1 , If not mentioned -> 0 +#' \item BigData. If knowledge in Big Data analysis is required -> 1 , If not mentioned -> 0 +#' \item Data_warehouse. If knowledge in Data Warehouse is required -> 1 , If not mentioned -> 0 +#' \item cloud_storage. If knowledge in Cloud Storage is required -> 1 , If not mentioned -> 0 +#' \item Google_Cloud. If knowledge in Google Cloud is required -> 1 , If not mentioned -> 0 +#' \item AWS. If knowledge in AWS is required -> 1 , If not mentioned -> 0 +#' \item Machine_Learning. If knowledge in Machine Learning is required -> 1 , If not mentioned -> 0 +#' \item Deep Learning. If knowledge in Deep Learning is required -> 1 , If not entioned -> 0 +#' \item Computer_vision. If knowledge in Computer Vision is required -> 1 , If not mentioned -> 0 +#' \item Java. If Java is required -> 1 , If not mentioned -> 0 +#' \item C++. If C++ is required -> 1 , If not mentioned -> 0 +#' \item C. If C is required -> 1 , If not mentioned -> 0 +#' \item Linux/Unix. If knowledge in Linux/Unix is required -> 1 , If not mentioned -> 0 +#' \item SQL. If SQL is required -> 1 , If not mentioned -> 0 +#' \item NoSQL. If NoSQL is required -> 1 , If not mentioned -> 0 +#' \item RDBMS. If knowledge in RDBMS is required -> 1 , If not mentioned -> 0 +#' \item Oracle. If knowledge in Oracle is required -> 1 , If not mentioned -> 0 +#' \item MySQL. If MYSQL is required -> 1 , If not mentioned -> 0 +#' \item PHP. If PHP is required -> 1 , If not mentioned -> 0 +#' \item Flash_Actionscript. If knowledge in Flash Action Script is required -> 1 , If not mentioned -> 0 +#' \item SPL. If knowledge in SPL is required -> 1 , If not mentioned -> 0 +#' \item web_design_and_development_tools. If knowledge in Web Design and Development Tools is required -> 1 , If not mentioned -> 0 +#' \item Wordpress. If knowledge in Wordpress is required -> 1 , If not mentioned -> 0 +#' \item AI. If Artificial Intelligence is required -> 1 , If not mentioned -> 0 +#' \item Natural_Language_Processing(NLP). If knowledge in NLP is required -> 1 , If not mentioned -> 0 +#' \item Microsoft Power BI. If knowledge in Microsoft Power BI is required -> 1 , If not mentioned -> 0 +#' \item Google_Analytics. If knowledge in Google Analytics is required -> 1 , If not mentioned -> 0 +#' \item graphics_and_design_skills. If Graphic and Design Skills are required -> 1 , If not mentioned -> 0 +#' \item Data_marketing. If Data Marketing abillity is required -> 1 , If not mentioned -> 0 +#' \item SEO. If knowledge in SEO is required -> 1 , If not mentioned -> 0 +#' \item Content_Management. If knowledge in Content Management is required -> 1 , If not mentioned -> 0 +#' \item Tableau. If knowledge in Tableau is required -> 1 , If not mentioned -> 0 +#' \item D3. If knowledge in D3 is required -> 1 , If not mentioned -> 0 +#' \item Alteryx. If knowledge in Alteryx is required -> 1 , If not mentioned -> 0 +#' \item KNIME. If knowledge in KNIME is required -> 1 , If not mentioned -> 0 +#' \item Spotfire. If knowledge in Spotfire is required -> 1 , If not mentioned -> 0 +#' \item Spark. If knowledge in Spark is required -> 1 , If not mentioned -> 0 +#' \item S3. If knowledge in S3 is required -> 1 , If not mentioned -> 0 +#' \item Redshift. If knowledge in Redshift is required -> 1 , If not mentioned -> 0 +#' \item DigitalOcean. If knowledge in Digital Ocean is required -> 1 , If not mentioned -> 0 +#' \item Javascript. If Java Script is required -> 1 , If not mentioned -> 0 +#' \item Kafka. If knowledge in Kafka is required -> 1 , If not mentioned -> 0 +#' \item Storm. If knowledge in Storm is required -> 1 , If not mentioned -> 0 +#' \item Bash. If knowledge in Bash is required -> 1 , If not mentioned -> 0 +#' \item Hadoop. If knowledge in Hadoop is required -> 1 , If not mentioned -> 0 +#' \item Data_Pipelines. If knowledge in Data Pipelines is required -> 1 , If not mentioned -> 0 +#' \item MPP_Platforms. If MPP Platforms is required ->1,If not mentioned-0 +#' \item Qlik. If Qlik is required ->1,If not mentioned ->0 +#' \item Pig. If Pig is required ->1,If not mentioned ->0 +#' \item Hive. If Hive is required ->1,If not mentioned ->0 +#' \item Tensorflow. If Tensorflow is required ->1,If not mentioned ->0 +#' \item Map/Reduce. If Map/Reduce is required ->1,If not mentioned ->0 +#' \item Impala. If Impala is required ->1,If not mentioned ->0 +#' \item Solr. If Sloris required ->1,If not mentioned ->0 +#' \item Teradata. If Teradata is required ->1,If not mentioned ->0 +#' \item MongoDB. If MonoDB is required ->1,If not mentioned ->0 +#' \item Elasticsearch. If Elasticsearch is required ->1,If not mentioned ->0 +#' \item YOLO. If YOLO is required-1 ,If not mentioned-0 +#' \item agile execution. If agile execution is required->1 ,If not mentioned->0 +#' \item Data_management. If the knowledge in data management is required->1 ,If not mentioned->0 +#' \item pyspark. If pyspark is required->1 ,If not mentioned->0 +#' \item Data_mining. If the knowledge in data mining is required->1 ,If not mentioned->0 +#' \item Data_science. If the knowledge in data science is required->1 ,If not mentioned->0 +#' \item Web_Analytic_tools. If the knowledge in Web Analytic tools is required->1 ,If not mentioned->0 +#' \item IOT. If IOT is required->1 ,If not mentioned->0 +#' \item Numerical_Analysis. If the knowledge in Numerical Analysis is required->1 ,If not mentioned->0 +#' \item Economic. If the knowledge in Economic is required->1 ,If not mentioned->0 +#' \item Finance_Knowledge. If Finance_Knowledge is required->1 ,If not mentioned->0 +#' \item Investment_Knowledge. If Investment Knowledge is required->1 ,If not mentioned->0 +#' \item Problem_Solving. If the ability of Problem Solving is required->1 ,If not mentioned->0 +#' \item Team_Handling. If the ability of Team Handling is required->1 ,If not mentioned->0 +#' \item Debtor_reconcilation. If the ability of Debtor reconcilation is required->1 ,If not mentioned->0 +#' \item Payroll_management. If Payroll management is required->1 ,If not mentioned->0 +#' \item Bayesian. If Bayesian is required->1 ,If not mentioned->0 +#' \item Optimization. If Optimization knowledge is required-1 ,If not mentioned-0 +#' \item Knowledge_in. Required knowledge to do a particular job ,If not mentioned->NA +#' \item City. City where the company is located in +#' \item Educational_qualifications. Required educational qualifications +#' \item Salary. Amount of salary +#' \item URL. Web address of a particular job advertisement +#' \item Search_Term. web search term of a particular job advertisement +#' \item Job_Category. Category of the job (i.e. "Data Science","Data Analyst" etc.) +#' \item Team_Handling. If the ability of Team Handling is required-1 ,If not mentioned-0 +#' \item Debtor_reconcilation. If the ability of Debtor reconciliation is required-1 ,If not mentioned-0 +#' \item Payroll_management. If the ability of Payroll management is required-1 ,If not mentioned-0 +#' \item Bayesian. If Bayesian knowledge is required-1 ,If not mentioned-0 +#' \item Bahasa_Malaysia. If Bahasa Malaysia is required-1 ,If not mentioned-0 +#' \item English_proficiency. If English proficiency is required-1 ,If not mentioned-0 +#' \item Experience_Category. Number of years of experience in binned into categories +#' \item Location. Location +#' \item Payment Frequency. Payment frequency +#' \item BSc_needed. If BSc is required-1 ,If not mentioned-0 +#' \item MSc_needed. If MSc is required-1 ,If not mentioned-0 +#' \item PhD_needed. If PhD is required-1 ,If not mentioned-0 +#' \item English Needed. If English is required-1 ,If not mentioned-0 +#' \item year. Survey year #' } #' @docType data #' @keywords datasets diff --git a/R/datatidy2020.R b/R/datatidy2020.R index 68d173d..09d645d 100644 --- a/R/datatidy2020.R +++ b/R/datatidy2020.R @@ -1,6 +1,7 @@ -#' Data Scientists/Data Analyst/ Statistician Job Advertisements in the year 2021 -#' Job advertisements collected in the year 2021 -#' A data frame with 430 rows and 115 columns +#' Data scientists, data Analyst, and statistician related job advertisements in 2020 +#' +#' A dataset with 430 rows and 115 columns +#' #' \itemize{ #' \item ID. Row id #' \item Consultant. Name of the consultant @@ -14,11 +15,11 @@ #' \item Python. If Python is required -> 1 , If not mentioned -> 0 #' \item MAtlab. If MAtlab is required -> 1 , If not mentioned -> 0 #' \item Scala. If Scala is required -> 1 , If not mentioned -> 0 -#' \item C_Sharp. If C\_Sharp is required -> 1 , If not mentioned -> 0 -#' \item Ms_Excel. If Ms\_Excel is required -> 1 , If not mentioned -> 0 +#' \item C_Sharp. If C_Sharp is required -> 1 , If not mentioned -> 0 +#' \item Ms_Excel. If Ms_Excel is required -> 1 , If not mentioned -> 0 #' \item OLE_DB. If OLE_DB is required -> 1 , If not mentioned -> 0 -#' \item Ms_Access. If Ms\_Access is required -> 1 , If not mentioned -> 0 -#' \item Ms_PowerPoint. If Ms\_PowerPoint is required -> 1 , If not mentioned -> 0 +#' \item Ms_Access. If Ms_Access is required -> 1 , If not mentioned -> 0 +#' \item Ms_PowerPoint. If Ms_PowerPoint is required -> 1 , If not mentioned -> 0 #' \item Spreadsheets. If Spreadsheets is required -> 1 , If not mentioned -> 0 #' \item Data_visualization. If knowledge in Data Visualization is required -> 1 , If not mentioned -> 0 #' \item Presentation_Skills. If Presentation Skills are required -> 1 , If not mentioned -> 0 @@ -41,7 +42,7 @@ #' \item Oracle. If knowledge in Oracle is required -> 1 , If not mentioned -> 0 #' \item MySQL. If MYSQL is required -> 1 , If not mentioned -> 0 #' \item PHP. If PHP is required -> 1 , If not mentioned -> 0 -#' \item Flash_Actionscript. If Flash\_Actionscript is required -> 1 , If not mentioned -> 0 +#' \item Flash_Actionscript. If Flash_Actionscript is required -> 1 , If not mentioned -> 0 #' \item SPL. If knowledge in SPL is required -> 1 , If not mentioned -> 0 #' \item web_design_and_development_tools. If knowledge in Web Design and Development Tools is required -> 1 , If not mentioned -> 0 #' \item Wordpress. If Wordpress is required -> 1 , If not mentioned -> 0 @@ -99,7 +100,7 @@ #' \item Payroll_management. If the ability of Payroll management is required -> 1 , If not mentioned -> 0 #' \item Bayesian. If Bayesian knowledge is required -> 1 , If not mentioned -> 0 #' \item Optimization. If Optimization knowledge is required -> 1 ,If not mentioned -> 0 -#' \item Bahasa_Malaysia. If Bahasa\_Malaysia knowledge is required -> 1 ,If not mentioned -> 0 +#' \item Bahasa_Malaysia. If Bahasa_Malaysia knowledge is required -> 1 ,If not mentioned -> 0 #' \item Knowledge_in. Required knowledge to do a particular job , If not mentioned -> NA #' \item City. City where the company is located in , If not mentioned -> NA #' \item Location. Country where the company is located in diff --git a/man/DStidy.Rd b/man/DStidy.Rd index 82f99c5..1f63ebd 100644 --- a/man/DStidy.Rd +++ b/man/DStidy.Rd @@ -3,8 +3,7 @@ \docType{data} \name{DStidy} \alias{DStidy} -\title{Data Scientists/Data Analyst/ Statistician Job Advertisements in the year 2020 -Job advertisements} +\title{Data scientists, data analyst, and statistician job advertisements from 2020 to 2023} \source{ Data collection was done, BSc (Hons)Staistics, University of Sri Jayewardenepura under the statistical consultancy service from 2020 to 2023. @@ -13,125 +12,127 @@ Jayewardenepura under the statistical consultancy service from 2020 to 2023. data(DStidy) } \description{ -A data frame with 1172 rows and 109 variables +A dataset with 1172 rows and 109 variables +} +\details{ \itemize{ -\item{ID}{row id} -\item{Consultant}{Name of the consultant} -\item{DateRetrieved}{ Date of Data Retrieved } -\item{DatePublished}{Published Date of the Advertisement } -\item{Job_title}{ Name of the job category} -\item{Company}{Name of the Company} -\item{R}{If R is required -> 1 ,If not mentioned -> 0} -\item{SAS}{If SAS is required -> 1 , If not mentioned -> 0} -\item{SPSS}{If SPSS is required -> 1 , If not mentioned -> 0} -\item{Python}{If Python is required -> 1 , If not mentioned -> 0} -\item{MAtlab}{If Matlab is required -> 1 , If not mentioned -> 0} -\item{Scala}{If Scala is required -> 1 , If not mentioned -> 0} -\item{C#}{If C# is required -> 1 , If not mentioned -> 0} -\item{MS Word}{If knowledge in MS Word is required -> 1 , If not mentioned -> 0} -\item{Ms Excel}{If knowledge in MS Excel is required -> 1 , If not mentioned -> 0} -\item{OLE/DB}{If knowledge in OLE/DB is required -> 1 , If not mentioned -> 0} -\item{Ms Access}{If Ms Access is required -> 1 , If not mentioned -> 0} -\item{Ms PowerPoint}{If knowledge in Ms Powerpoint is required -> 1 , If not mentioned -> 0} -\item{Spreadsheets}{If knowledge in Spreadsheets is required -> 1 , If not mentioned -> 0} -\item{Data_visualization}{If knowledge inData Visualization is required -> 1 , If not mentioned -> 0} -\item{Presentation_Skills}{If Presentation Skills are required -> 1 , If not mentioned -> 0} -\item{Communication}{If Communication skills are required -> 1 , If not mentioned -> 0} -\item{BigData}{If knowledge in Big Data analysis is required -> 1 , If not mentioned -> 0} -\item{Data_warehouse}{If knowledge in Data Warehouse is required -> 1 , If not mentioned -> 0} -\item{cloud_storage}{If knowledge in Cloud Storage is required -> 1 , If not mentioned -> 0} -\item{Google_Cloud}{If knowledge in Google Cloud is required -> 1 , If not mentioned -> 0} -\item{AWS}{If knowledge in AWS is required -> 1 , If not mentioned -> 0} -\item{Machine_Learning}{If knowledge in Machine Learning is required -> 1 , If not mentioned -> 0} -\item{Deep Learning}{If knowledge in Deep Learning is required -> 1 , If not entioned -> 0} -\item{Computer_vision}{If knowledge in Computer Vision is required -> 1 , If not mentioned -> 0} -\item{Java}{If Java is required -> 1 , If not mentioned -> 0} -\item{C++}{If C++ is required -> 1 , If not mentioned -> 0} -\item{C}{If C is required -> 1 , If not mentioned -> 0} -\item{Linux/Unix}{If knowledge in Linux/Unix is required -> 1 , If not mentioned -> 0} -\item{SQL}{If SQL is required -> 1 , If not mentioned -> 0} -\item{NoSQL}{If NoSQL is required -> 1 , If not mentioned -> 0} -\item{RDBMS}{If knowledge in RDBMS is required -> 1 , If not mentioned -> 0} -\item{Oracle}{If knowledge in Oracle is required -> 1 , If not mentioned -> 0} -\item{MySQL}{If MYSQL is required -> 1 , If not mentioned -> 0} -\item{PHP}{If PHP is required -> 1 , If not mentioned -> 0} -\item{Flash_Actionscript}{If knowledge in Flash Action Script is required -> 1 , If not mentioned -> 0} -\item{SPL}{If knowledge in SPL is required -> 1 , If not mentioned -> 0} -\item{web_design_and_development_tools}{If knowledge in Web Design and Development Tools is required -> 1 , If not mentioned -> 0} -\item{Wordpress}{If knowledge in Wordpress is required -> 1 , If not mentioned -> 0} -\item{AI}{If Artificial Intelligence is required -> 1 , If not mentioned -> 0} -\item{Natural_Language_Processing(NLP)}{If knowledge in NLP is required -> 1 , If not mentioned -> 0} -\item{Microsoft Power BI}{If knowledge in Microsoft Power BI is required -> 1 , If not mentioned -> 0} -\item{Google_Analytics}{If knowledge in Google Analytics is required -> 1 , If not mentioned -> 0} -\item{graphics_and_design_skills}{If Graphic and Design Skills are required -> 1 , If not mentioned -> 0} -\item{Data_marketing}{If Data Marketing abillity is required -> 1 , If not mentioned -> 0} -\item{SEO}{If knowledge in SEO is required -> 1 , If not mentioned -> 0} -\item{Content_Management}{If knowledge in Content Management is required -> 1 , If not mentioned -> 0} -\item{Tableau}{If knowledge in Tableau is required -> 1 , If not mentioned -> 0} -\item{D3}{If knowledge in D3 is required -> 1 , If not mentioned -> 0} -\item{Alteryx}{If knowledge in Alteryx is required -> 1 , If not mentioned -> 0} -\item{KNIME}{If knowledge in KNIME is required -> 1 , If not mentioned -> 0} -\item{Spotfire}{If knowledge in Spotfire is required -> 1 , If not mentioned -> 0} -\item{Spark}{If knowledge in Spark is required -> 1 , If not mentioned -> 0} -\item{S3}{If knowledge in S3 is required -> 1 , If not mentioned -> 0} -\item{Redshift}{If knowledge in Redshift is required -> 1 , If not mentioned -> 0} -\item{DigitalOcean}{If knowledge in Digital Ocean is required -> 1 , If not mentioned -> 0} -\item{Javascript}{If Java Script is required -> 1 , If not mentioned -> 0} -\item{Kafka}{If knowledge in Kafka is required -> 1 , If not mentioned -> 0} -\item{Storm}{If knowledge in Storm is required -> 1 , If not mentioned -> 0} -\item{Bash}{If knowledge in Bash is required -> 1 , If not mentioned -> 0} -\item{Hadoop}{If knowledge in Hadoop is required -> 1 , If not mentioned -> 0} -\item{Data_Pipelines}{If knowledge in Data Pipelines is required -> 1 , If not mentioned -> 0} -\item{MPP_Platforms}{If MPP Platforms is required ->1,If not mentioned-0} -\item{Qlik}{If Qlik is required ->1,If not mentioned ->0} -\item{Pig}{If Pig is required ->1,If not mentioned ->0} -\item{Hive}{If Hive is required ->1,If not mentioned ->0} -\item{Tensorflow}{If Tensorflow is required ->1,If not mentioned ->0} -\item{Map/Reduce}{If Map/Reduce is required ->1,If not mentioned ->0} -\item{Impala}{If Impala is required ->1,If not mentioned ->0} -\item{Solr}{If Sloris required ->1,If not mentioned ->0} -\item{Teradata}{If Teradata is required ->1,If not mentioned ->0} -\item{MongoDB}{If MonoDB is required ->1,If not mentioned ->0} -\item{Elasticsearch}{If Elasticsearch is required ->1,If not mentioned ->0} -\item{YOLO}{If YOLO is required-1 ,If not mentioned-0} -\item{agile execution}{If agile execution is required->1 ,If not mentioned->0} -\item{Data_management}{If the knowledge in data management is required->1 ,If not mentioned->0} -\item{pyspark}{If pyspark is required->1 ,If not mentioned->0 } -\item{Data_mining}{If the knowledge in data mining is required->1 ,If not mentioned->0} -\item{Data_science}{If the knowledge in data science is required->1 ,If not mentioned->0} -\item{Web_Analytic_tools}{If the knowledge in Web Analytic tools is required->1 ,If not mentioned->0} -\item{IOT}{If IOT is required->1 ,If not mentioned->0} -\item{Numerical_Analysis}{If the knowledge in Numerical Analysis is required->1 ,If not mentioned->0} -\item{Economic}{If the knowledge in Economic is required->1 ,If not mentioned->0} -\item{Finance_Knowledge}{If Finance\_Knowledge is required->1 ,If not mentioned->0} -\item{Investment_Knowledge}{If Investment Knowledge is required->1 ,If not mentioned->0} -\item{Problem_Solving}{If the ability of Problem Solving is required->1 ,If not mentioned->0} -\item{Team_Handling}{If the ability of Team Handling is required->1 ,If not mentioned->0} -\item{Debtor_reconcilation}{If the ability of Debtor reconcilation is required->1 ,If not mentioned->0} -\item{Payroll_management}{If Payroll management is required->1 ,If not mentioned->0} -\item{Bayesian}{If Bayesian is required->1 ,If not mentioned->0} -\item{Optimization}{If Optimization knowledge is required-1 ,If not mentioned-0} -\item{Knowledge_in}{Required knowledge to do a particular job ,If not mentioned->NA} -\item{City}{City where the company is located in } -\item{Educational_qualifications}{Required educational qualifications} -\item{Salary}{Amount of salary} -\item{URL}{Web address of a particular job advertisement} -\item{Search_Term}{web search term of a particular job advertisement} -\item{Job_Category}{Category of the job (i.e. "Data Science","Data Analyst" etc.)} -\item{Team_Handling}{If the ability of Team Handling is required-1 ,If not mentioned-0} -\item{Debtor_reconcilation}{If the ability of Debtor reconciliation is required-1 ,If not mentioned-0} -\item{Payroll_management}{If the ability of Payroll management is required-1 ,If not mentioned-0} -\item{Bayesian}{If Bayesian knowledge is required-1 ,If not mentioned-0} -\item{Bahasa_Malaysia}{If Bahasa Malaysia is required-1 ,If not mentioned-0 } -\item{English_proficiency}{If English proficiency is required-1 ,If not mentioned-0} -\item{Experience_Category}{Number of years of experience in binned into categories} -\item{Location}{Location} -\item{Payment Frequency}{Payment frequency} -\item{BSc_needed}{If BSc is required-1 ,If not mentioned-0} -\item{MSc_needed}{If MSc is required-1 ,If not mentioned-0} -\item{PhD_needed}{If PhD is required-1 ,If not mentioned-0} -\item{English Needed}{If English is required-1 ,If not mentioned-0} -\item{year}{Survey year} +\item ID. row id +\item Consultant. Name of the consultant +\item DateRetrieved. Date of Data Retrieved +\item DatePublished. Published Date of the Advertisement +\item Job_title. Name of the job category +\item Company. Name of the Company +\item R. If R is required -> 1 ,If not mentioned -> 0 +\item SAS. If SAS is required -> 1 , If not mentioned -> 0 +\item SPSS. If SPSS is required -> 1 , If not mentioned -> 0 +\item Python. If Python is required -> 1 , If not mentioned -> 0 +\item MAtlab. If Matlab is required -> 1 , If not mentioned -> 0 +\item Scala. If Scala is required -> 1 , If not mentioned -> 0 +\item C#. If C# is required -> 1 , If not mentioned -> 0 +\item MS Word. If knowledge in MS Word is required -> 1 , If not mentioned -> 0 +\item Ms Excel. If knowledge in MS Excel is required -> 1 , If not mentioned -> 0 +\item OLE/DB. If knowledge in OLE/DB is required -> 1 , If not mentioned -> 0 +\item Ms Access. If Ms Access is required -> 1 , If not mentioned -> 0 +\item Ms PowerPoint. If knowledge in Ms Powerpoint is required -> 1 , If not mentioned -> 0 +\item Spreadsheets. If knowledge in Spreadsheets is required -> 1 , If not mentioned -> 0 +\item Data_visualization. If knowledge in Data Visualization is required -> 1 , If not mentioned -> 0 +\item Presentation_Skills. If Presentation Skills are required -> 1 , If not mentioned -> 0 +\item Communication. If Communication skills are required -> 1 , If not mentioned -> 0 +\item BigData. If knowledge in Big Data analysis is required -> 1 , If not mentioned -> 0 +\item Data_warehouse. If knowledge in Data Warehouse is required -> 1 , If not mentioned -> 0 +\item cloud_storage. If knowledge in Cloud Storage is required -> 1 , If not mentioned -> 0 +\item Google_Cloud. If knowledge in Google Cloud is required -> 1 , If not mentioned -> 0 +\item AWS. If knowledge in AWS is required -> 1 , If not mentioned -> 0 +\item Machine_Learning. If knowledge in Machine Learning is required -> 1 , If not mentioned -> 0 +\item Deep Learning. If knowledge in Deep Learning is required -> 1 , If not entioned -> 0 +\item Computer_vision. If knowledge in Computer Vision is required -> 1 , If not mentioned -> 0 +\item Java. If Java is required -> 1 , If not mentioned -> 0 +\item C++. If C++ is required -> 1 , If not mentioned -> 0 +\item C. If C is required -> 1 , If not mentioned -> 0 +\item Linux/Unix. If knowledge in Linux/Unix is required -> 1 , If not mentioned -> 0 +\item SQL. If SQL is required -> 1 , If not mentioned -> 0 +\item NoSQL. If NoSQL is required -> 1 , If not mentioned -> 0 +\item RDBMS. If knowledge in RDBMS is required -> 1 , If not mentioned -> 0 +\item Oracle. If knowledge in Oracle is required -> 1 , If not mentioned -> 0 +\item MySQL. If MYSQL is required -> 1 , If not mentioned -> 0 +\item PHP. If PHP is required -> 1 , If not mentioned -> 0 +\item Flash_Actionscript. If knowledge in Flash Action Script is required -> 1 , If not mentioned -> 0 +\item SPL. If knowledge in SPL is required -> 1 , If not mentioned -> 0 +\item web_design_and_development_tools. If knowledge in Web Design and Development Tools is required -> 1 , If not mentioned -> 0 +\item Wordpress. If knowledge in Wordpress is required -> 1 , If not mentioned -> 0 +\item AI. If Artificial Intelligence is required -> 1 , If not mentioned -> 0 +\item Natural_Language_Processing(NLP). If knowledge in NLP is required -> 1 , If not mentioned -> 0 +\item Microsoft Power BI. If knowledge in Microsoft Power BI is required -> 1 , If not mentioned -> 0 +\item Google_Analytics. If knowledge in Google Analytics is required -> 1 , If not mentioned -> 0 +\item graphics_and_design_skills. If Graphic and Design Skills are required -> 1 , If not mentioned -> 0 +\item Data_marketing. If Data Marketing abillity is required -> 1 , If not mentioned -> 0 +\item SEO. If knowledge in SEO is required -> 1 , If not mentioned -> 0 +\item Content_Management. If knowledge in Content Management is required -> 1 , If not mentioned -> 0 +\item Tableau. If knowledge in Tableau is required -> 1 , If not mentioned -> 0 +\item D3. If knowledge in D3 is required -> 1 , If not mentioned -> 0 +\item Alteryx. If knowledge in Alteryx is required -> 1 , If not mentioned -> 0 +\item KNIME. If knowledge in KNIME is required -> 1 , If not mentioned -> 0 +\item Spotfire. If knowledge in Spotfire is required -> 1 , If not mentioned -> 0 +\item Spark. If knowledge in Spark is required -> 1 , If not mentioned -> 0 +\item S3. If knowledge in S3 is required -> 1 , If not mentioned -> 0 +\item Redshift. If knowledge in Redshift is required -> 1 , If not mentioned -> 0 +\item DigitalOcean. If knowledge in Digital Ocean is required -> 1 , If not mentioned -> 0 +\item Javascript. If Java Script is required -> 1 , If not mentioned -> 0 +\item Kafka. If knowledge in Kafka is required -> 1 , If not mentioned -> 0 +\item Storm. If knowledge in Storm is required -> 1 , If not mentioned -> 0 +\item Bash. If knowledge in Bash is required -> 1 , If not mentioned -> 0 +\item Hadoop. If knowledge in Hadoop is required -> 1 , If not mentioned -> 0 +\item Data_Pipelines. If knowledge in Data Pipelines is required -> 1 , If not mentioned -> 0 +\item MPP_Platforms. If MPP Platforms is required ->1,If not mentioned-0 +\item Qlik. If Qlik is required ->1,If not mentioned ->0 +\item Pig. If Pig is required ->1,If not mentioned ->0 +\item Hive. If Hive is required ->1,If not mentioned ->0 +\item Tensorflow. If Tensorflow is required ->1,If not mentioned ->0 +\item Map/Reduce. If Map/Reduce is required ->1,If not mentioned ->0 +\item Impala. If Impala is required ->1,If not mentioned ->0 +\item Solr. If Sloris required ->1,If not mentioned ->0 +\item Teradata. If Teradata is required ->1,If not mentioned ->0 +\item MongoDB. If MonoDB is required ->1,If not mentioned ->0 +\item Elasticsearch. If Elasticsearch is required ->1,If not mentioned ->0 +\item YOLO. If YOLO is required-1 ,If not mentioned-0 +\item agile execution. If agile execution is required->1 ,If not mentioned->0 +\item Data_management. If the knowledge in data management is required->1 ,If not mentioned->0 +\item pyspark. If pyspark is required->1 ,If not mentioned->0 +\item Data_mining. If the knowledge in data mining is required->1 ,If not mentioned->0 +\item Data_science. If the knowledge in data science is required->1 ,If not mentioned->0 +\item Web_Analytic_tools. If the knowledge in Web Analytic tools is required->1 ,If not mentioned->0 +\item IOT. If IOT is required->1 ,If not mentioned->0 +\item Numerical_Analysis. If the knowledge in Numerical Analysis is required->1 ,If not mentioned->0 +\item Economic. If the knowledge in Economic is required->1 ,If not mentioned->0 +\item Finance_Knowledge. If Finance_Knowledge is required->1 ,If not mentioned->0 +\item Investment_Knowledge. If Investment Knowledge is required->1 ,If not mentioned->0 +\item Problem_Solving. If the ability of Problem Solving is required->1 ,If not mentioned->0 +\item Team_Handling. If the ability of Team Handling is required->1 ,If not mentioned->0 +\item Debtor_reconcilation. If the ability of Debtor reconcilation is required->1 ,If not mentioned->0 +\item Payroll_management. If Payroll management is required->1 ,If not mentioned->0 +\item Bayesian. If Bayesian is required->1 ,If not mentioned->0 +\item Optimization. If Optimization knowledge is required-1 ,If not mentioned-0 +\item Knowledge_in. Required knowledge to do a particular job ,If not mentioned->NA +\item City. City where the company is located in +\item Educational_qualifications. Required educational qualifications +\item Salary. Amount of salary +\item URL. Web address of a particular job advertisement +\item Search_Term. web search term of a particular job advertisement +\item Job_Category. Category of the job (i.e. "Data Science","Data Analyst" etc.) +\item Team_Handling. If the ability of Team Handling is required-1 ,If not mentioned-0 +\item Debtor_reconcilation. If the ability of Debtor reconciliation is required-1 ,If not mentioned-0 +\item Payroll_management. If the ability of Payroll management is required-1 ,If not mentioned-0 +\item Bayesian. If Bayesian knowledge is required-1 ,If not mentioned-0 +\item Bahasa_Malaysia. If Bahasa Malaysia is required-1 ,If not mentioned-0 +\item English_proficiency. If English proficiency is required-1 ,If not mentioned-0 +\item Experience_Category. Number of years of experience in binned into categories +\item Location. Location +\item Payment Frequency. Payment frequency +\item BSc_needed. If BSc is required-1 ,If not mentioned-0 +\item MSc_needed. If MSc is required-1 ,If not mentioned-0 +\item PhD_needed. If PhD is required-1 ,If not mentioned-0 +\item English Needed. If English is required-1 ,If not mentioned-0 +\item year. Survey year } } \keyword{datasets} diff --git a/man/DStidy_2020.Rd b/man/DStidy_2020.Rd index 592be7e..09d19b9 100644 --- a/man/DStidy_2020.Rd +++ b/man/DStidy_2020.Rd @@ -3,125 +3,7 @@ \docType{data} \name{DStidy_2020} \alias{DStidy_2020} -\title{Data Scientists/Data Analyst/ Statistician Job Advertisements in the year 2021 -Job advertisements collected in the year 2021 -A data frame with 430 rows and 115 columns -\itemize{ -\item ID. Row id -\item Consultant. Name of the consultant -\item DateRetrieved. Date of data retrieved -\item DatePublished. Published date of the advertisement -\item Job_title. Name of the job category -\item Company. Name of the company -\item R. If R is required -> 1 , If not mentioned -> 0 -\item SAS. If SAS is required -> 1 , If not mentioned -> 0 -\item SPSS. If SPSS is required -> 1 , If not mentioned -> 0 -\item Python. If Python is required -> 1 , If not mentioned -> 0 -\item MAtlab. If MAtlab is required -> 1 , If not mentioned -> 0 -\item Scala. If Scala is required -> 1 , If not mentioned -> 0 -\item C_Sharp. If C\_Sharp is required -> 1 , If not mentioned -> 0 -\item Ms_Excel. If Ms\_Excel is required -> 1 , If not mentioned -> 0 -\item OLE_DB. If OLE_DB is required -> 1 , If not mentioned -> 0 -\item Ms_Access. If Ms\_Access is required -> 1 , If not mentioned -> 0 -\item Ms_PowerPoint. If Ms\_PowerPoint is required -> 1 , If not mentioned -> 0 -\item Spreadsheets. If Spreadsheets is required -> 1 , If not mentioned -> 0 -\item Data_visualization. If knowledge in Data Visualization is required -> 1 , If not mentioned -> 0 -\item Presentation_Skills. If Presentation Skills are required -> 1 , If not mentioned -> 0 -\item Communication. If Communication skills are required -> 1 , If not mentioned -> 0 -\item BigData. If knowledge in Big Data analysis is required -> 1 , If not mentioned -> 0 -\item Data_warehouse. If knowledge in Data Warehouse is required -> 1 , If not mentioned -> 0 -\item cloud_storage. If knowledge in Cloud Storage is required -> 1 , If not mentioned -> 0 -\item Google_Cloud. If knowledge in Google Cloud is required -> 1 , If not mentioned -> 0 -\item AWS. If knowledge in AWS is required -> 1 , If not mentioned -> 0 -\item Machine_Learning. If knowledge in Machine Learning is required -> 1 , If not mentioned -> 0 -\item Deep_Learning. If knowledge in Deep Learning is required -> 1 , If not mentioned -> 0 -\item Computer_vision. If knowledge in Computer Vision is required -> 1 , If not mentioned -> 0 -\item Java. If Java is required -> 1 , If not mentioned -> 0 -\item Cpp. If Cpp is required -> 1 , If not mentioned -> 0 -\item C. If C is required -> 1 , If not mentioned -> 0 -\item Linux_Unix. If knowledge in Linux/Unix is required -> 1 , If not mentioned -> 0 -\item SQL. If SQL is required -> 1 , If not mentioned -> 0 -\item NoSQL. If NoSQL is required -> 1 , If not mentioned -> 0 -\item RDBMS. If knowledge in RDBMS is required -> 1 , If not mentioned -> 0 -\item Oracle. If knowledge in Oracle is required -> 1 , If not mentioned -> 0 -\item MySQL. If MYSQL is required -> 1 , If not mentioned -> 0 -\item PHP. If PHP is required -> 1 , If not mentioned -> 0 -\item Flash_Actionscript. If Flash\_Actionscript is required -> 1 , If not mentioned -> 0 -\item SPL. If knowledge in SPL is required -> 1 , If not mentioned -> 0 -\item web_design_and_development_tools. If knowledge in Web Design and Development Tools is required -> 1 , If not mentioned -> 0 -\item Wordpress. If Wordpress is required -> 1 , If not mentioned -> 0 -\item AI. If AI is required 1 , If not mentioned 0 -\item Natural_Language_Processing(NLP). If knowledge in NLP is required -> 1 , If not mentioned -> 0 -\item Microsoft_Power_BI. If knowledge in Microsoft Power BI is required -> 1 , If not mentioned -> 0 -\item Google_Analytics. If knowledge in Google Analytics is required -> 1 , If not mentioned -> 0 -\item graphics_and_design_skills. If Graphic and Design Skills are required -> 1 , If not mentioned -> 0 -\item Data_marketing. If Data Marketing abillity is required -> 1 , If not mentioned -> 0 -\item SEO. If knowledge in SEO is required -> 1 , If not mentioned -> 0 -\item Content_Management. If knowledge in Content Management is required -> 1 , If not mentioned -> 0 -\item Tableau. If knowledge in Tableau is required -> 1 , If not mentioned -> 0 -\item D3. If knowledge in D3 is required -> 1 , If not mentioned -> 0 -\item Alteryx. If knowledge in Alteryx is required -> 1 , If not mentioned -> 0 -\item KNIME. If knowledge in KNIME is required -> 1 , If not mentioned -> 0 -\item Spotfire. If knowledge in Spotfire is required -> 1 , If not mentioned -> 0 -\item Spark. If knowledge in Spark is required -> 1 , If not mentioned -> 0 -\item S3. If knowledge in S3 is required -> 1 , If not mentioned -> 0 -\item Redshift. If knowledge in Redshift is required -> 1 , If not mentioned -> 0 -\item DigitalOcean. If knowledge in Digital Ocean is required -> 1 , If not mentioned -> 0 -\item Javascript. If Java Script is required -> 1 , If not mentioned -> 0 -\item Kafka. If knowledge in Kafka is required -> 1 , If not mentioned -> 0 -\item Storm. If knowledge in Storm is required -> 1 , If not mentioned -> 0 -\item Bash. If knowledge in Bash is required -> 1 , If not mentioned -> 0 -\item Hadoop. If knowledge in Hadoop is required -> 1 , If not mentioned -> 0 -\item Data_Pipelines. If knowledge in Data Pipelines is required -> 1 , If not mentioned -> 0 -\item MPP_Platforms. If MPP Platforms is required -> 1 , If not mentioned -> 0 -\item Qlik. If Qlik is required -> 1 , If not mentioned -> 0 -\item Pig. If Pig is required -> 1 , If not mentioned -> 0 -\item Hive. If Hive is required -> 1 , If not mentioned -> 0 -\item Tensorflow. If Tensorflow is required -> 1 , If not mentioned -> 0 -\item Map_Reduce. If Map/Reduce is required -> 1 , If not mentioned -> 0 -\item Impala. If Impala is required -> 1 ,If not mentioned -> 0 -\item Solr. If Sloris required -> 1 , If not mentioned -> 0 -\item Teradata. If Teradata is required -> 1 , If not mentioned -> 0 -\item MongoDB. If MonoDB is required -> 1 , If not mentioned -> 0 -\item Elasticsearch. If Elasticsearch is required -> 1, If not mentioned -> 0 -\item YOLO. If YOLO is required -> 1, If not mentioned -> 0 -\item agile_execution. If agile execution is required -> 1 , If not mentioned -> 0 -\item Data_management. If the knowledge in Data Management is required -> 1 , If not mentioned -> 0 -\item pyspark. If pyspark is required -> 1 , If not mentioned -> 0 -\item Data_mining. If the knowledge in Data Mining is required -> 1 , If not mentioned -> 0 -\item Data_science. If the knowledge in Data Science is required -> 1 , If not mentioned -> 0 -\item Web_Analytic_tools. If the knowledge in Web Analytic tools is required -> 1 , If not mentioned -> 0 -\item IOT. If IOT is required -> 1 , If not mentioned -> 0 -\item Numerical_Analysis. If the knowledge in Numerical Analysis is required -> 1 , If not mentioned -> 0 -\item Economic. If the knowledge in Economic is required -> 1 , If not mentioned -> 0 -\item Finance_Knowledge. If Finance_Knowledge is required -> 1 , If not mentioned -> 0 -\item Investment_Knowledge. If Investment Knowledge is required -> 1 , If not mentioned -> 0 -\item Problem_Solving. If the ability of Problem Solving is required -> 1 , If not mentioned -> 0 -\item Korean_language. If the ability of Korean language is required -> 1 , If not mentioned -> 0 -\item Bash_Linux_Scripting. If Bash Linux Scripting is required -> 1 , If not mentioned -> 0 -\item Team_Handling. If the ability of Team Handling is required -> 1 , If not mentioned -> 0 -\item Debtor_reconcilation. If the ability of Debtor reconciliation is required -> 1 , If not mentioned -> 0 -\item Payroll_management. If the ability of Payroll management is required -> 1 , If not mentioned -> 0 -\item Bayesian. If Bayesian knowledge is required -> 1 , If not mentioned -> 0 -\item Optimization. If Optimization knowledge is required -> 1 ,If not mentioned -> 0 -\item Bahasa_Malaysia. If Bahasa\_Malaysia knowledge is required -> 1 ,If not mentioned -> 0 -\item Knowledge_in. Required knowledge to do a particular job , If not mentioned -> NA -\item City. City where the company is located in , If not mentioned -> NA -\item Location. Country where the company is located in -\item Educational_qualifications. Required educational qualifications -\item Salary. Salary -\item English_proficiency. English proficiency -\item URL. URL of the job advertisement -\item Search_Term. Search Term -\item Job_Category. Name of the job category -\item Minimum_Years_of_experience. Minimum years of experience needed for the job , If not mentioned -> NA -\item Experience. Experience -\item Experience_Category. Experience category -\item Job_Country. Job country -\item Edu_Category. Education category -\item Minimum_Salary. Minimum salary -\item Salary_BasisSalary. basis -}} +\title{Data scientists, data Analyst, and statistician related job advertisements in 2020} \source{ Data wrangling part was done by Janith C. Wanniarachchie, BSc (Hons)Staistics, University of Sri Jayewardenepura and description file was prepared by Randi Shashikala. @@ -130,9 +12,9 @@ Jayewardenepura and description file was prepared by Randi Shashikala. data(DStidy_2020) } \description{ -Data Scientists/Data Analyst/ Statistician Job Advertisements in the year 2021 -Job advertisements collected in the year 2021 -A data frame with 430 rows and 115 columns +A dataset with 430 rows and 115 columns +} +\details{ \itemize{ \item ID. Row id \item Consultant. Name of the consultant @@ -146,11 +28,11 @@ A data frame with 430 rows and 115 columns \item Python. If Python is required -> 1 , If not mentioned -> 0 \item MAtlab. If MAtlab is required -> 1 , If not mentioned -> 0 \item Scala. If Scala is required -> 1 , If not mentioned -> 0 -\item C_Sharp. If C\_Sharp is required -> 1 , If not mentioned -> 0 -\item Ms_Excel. If Ms\_Excel is required -> 1 , If not mentioned -> 0 +\item C_Sharp. If C_Sharp is required -> 1 , If not mentioned -> 0 +\item Ms_Excel. If Ms_Excel is required -> 1 , If not mentioned -> 0 \item OLE_DB. If OLE_DB is required -> 1 , If not mentioned -> 0 -\item Ms_Access. If Ms\_Access is required -> 1 , If not mentioned -> 0 -\item Ms_PowerPoint. If Ms\_PowerPoint is required -> 1 , If not mentioned -> 0 +\item Ms_Access. If Ms_Access is required -> 1 , If not mentioned -> 0 +\item Ms_PowerPoint. If Ms_PowerPoint is required -> 1 , If not mentioned -> 0 \item Spreadsheets. If Spreadsheets is required -> 1 , If not mentioned -> 0 \item Data_visualization. If knowledge in Data Visualization is required -> 1 , If not mentioned -> 0 \item Presentation_Skills. If Presentation Skills are required -> 1 , If not mentioned -> 0 @@ -173,7 +55,7 @@ A data frame with 430 rows and 115 columns \item Oracle. If knowledge in Oracle is required -> 1 , If not mentioned -> 0 \item MySQL. If MYSQL is required -> 1 , If not mentioned -> 0 \item PHP. If PHP is required -> 1 , If not mentioned -> 0 -\item Flash_Actionscript. If Flash\_Actionscript is required -> 1 , If not mentioned -> 0 +\item Flash_Actionscript. If Flash_Actionscript is required -> 1 , If not mentioned -> 0 \item SPL. If knowledge in SPL is required -> 1 , If not mentioned -> 0 \item web_design_and_development_tools. If knowledge in Web Design and Development Tools is required -> 1 , If not mentioned -> 0 \item Wordpress. If Wordpress is required -> 1 , If not mentioned -> 0 @@ -231,7 +113,7 @@ A data frame with 430 rows and 115 columns \item Payroll_management. If the ability of Payroll management is required -> 1 , If not mentioned -> 0 \item Bayesian. If Bayesian knowledge is required -> 1 , If not mentioned -> 0 \item Optimization. If Optimization knowledge is required -> 1 ,If not mentioned -> 0 -\item Bahasa_Malaysia. If Bahasa\_Malaysia knowledge is required -> 1 ,If not mentioned -> 0 +\item Bahasa_Malaysia. If Bahasa_Malaysia knowledge is required -> 1 ,If not mentioned -> 0 \item Knowledge_in. Required knowledge to do a particular job , If not mentioned -> NA \item City. City where the company is located in , If not mentioned -> NA \item Location. Country where the company is located in