Analysis of hh.kz
Komashev Daniyar Arzamekov Alisher
25.12.2016 г
1 Step. Collection data
- Problem : the collection and analysis of labor market in Kazakhstan.
- Solution : To solve this problem, we have collected data from most major sites, such as hh.kz, which collected data from all cities and in all spheres.
2 step. Read all of data
- After collecting data, we save it in csv format
- As we can see we have 16215 obs. and 24 variables
vacancy=read.csv("vacancy.csv")
str(vacancy)## 'data.frame': 16215 obs. of 24 variables:
## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ specialization_id: int 1 1 1 1 1 1 1 1 1 1 ...
## $ vacancy_name : Factor w/ 6084 levels "'Менеджер по консолидированным авто отправкам",..: 4882 4882 984 3309 4695 3845 3116 6015 221 2108 ...
## $ salary_to : int NA NA NA 150000 300000 NA 500000 NA NA NA ...
## $ salary_from : int NA NA NA 70000 150000 NA 120000 NA NA 100000 ...
## $ salary_currency : Factor w/ 6 levels "EUR","KGS","KZT",..: NA NA NA 3 3 NA 3 NA NA 3 ...
## $ requirement : Factor w/ 10639 levels "1- знание английского и русского языков, умение писать официальные письма, креатив.",..: 3598 3598 4591 1112 10081 5996 1638 3181 398 9275 ...
## $ responsibility : Factor w/ 10133 levels "# установи_ контакт с покупателем.",..: 2064 2064 7041 7835 8476 6074 7123 6994 489 8723 ...
## $ area_id : int 159 159 160 160 159 174 160 160 160 160 ...
## $ area_name : Factor w/ 54 levels "Акколь","Аксай (Казахстан)",..: 9 9 7 7 9 29 7 7 7 7 ...
## $ created_at : Factor w/ 11966 levels "2016-11-17T01:03:52+0300",..: 11941 11941 11920 11916 11889 11886 11886 11883 11878 11871 ...
## $ vacancy_url : Factor w/ 12384 levels "https://hh.ru/applicant/vacancy_response?vacancyId=11617814",..: 9546 9546 7796 12367 5790 9423 6988 7708 6972 566 ...
## $ employer_id : int 942300 942300 984620 1491586 2271389 60607 1288140 60607 39474 1065869 ...
## $ employer_name : Factor w/ 5399 levels "(1 st) ТМ Aviator",..: 1611 1611 3886 4332 1338 3832 1797 3832 1475 1896 ...
## $ employer_url : Factor w/ 5399 levels "https://hh.ru/employer/1000042",..: 5277 5277 5371 1111 2935 4615 652 4615 4446 165 ...
## $ employer_checked : logi TRUE TRUE TRUE TRUE TRUE TRUE ...
## $ address_city : Factor w/ 95 levels "Абай","Аксай",..: 8 8 7 7 NA NA NA NA NA 7 ...
## $ address_building : Factor w/ 694 levels " 2/14","1","1 ",..: 183 183 445 584 NA NA NA NA NA 108 ...
## $ address_street : Factor w/ 762 levels "1-й микрорайон",..: 472 472 421 264 NA NA NA NA NA 626 ...
## $ address_lat : num 51.1 51.1 43.2 43.2 NA ...
## $ address_long : num 71.4 71.4 76.9 76.9 NA ...
## $ vacancy_id : int 19161263 19161263 19125118 19224792 19066750 19157842 19109433 19123608 19109088 18545370 ...
## $ vacancy_type : Factor w/ 3 levels "anonymous","direct",..: 3 3 3 3 3 3 3 3 3 3 ...
## $ vacancy_alter_url: Factor w/ 12384 levels "https://career.ru/vacancy/11617814",..: 9851 9851 8242 12372 6398 9736 7505 8160 7489 1703 ...3 step. Start analysis
- 1. We all share the data by city. In order to make the analysis for each city separately. Each city has its own id. Example: Almaty id is 160.
almaty=subset(vacancy,vacancy$area_id==160)And so on all the city
2. Next comes the separation specialization. And each specialization also has its own id. Example: IT and Telecamunication id is 1
itTelecom=subset(almaty, almaty$specialization_id==1)
marketing=subset(almaty, almaty$specialization_id==3)
bugalteria=subset(almaty, almaty$specialization_id==2)
adminpersonal=subset(almaty, almaty$specialization_id==4)
bank=subset(almaty, almaty$specialization_id==5)
build=subset(almaty, almaty$specialization_id==20)
transport=subset(almaty, almaty$specialization_id==21)And so on all the specialization
3. Next, we decided to find out what is the average of the minimum wage offered. To this end, we have brought all of the data About salary and took their mean values
*This is the average minimum salary proposed for each specialization
salaryIt=na.omit(itTelecom$salary_from)
meanOfSalaryIt=round(mean(salaryIt),0)
salaryMarket=na.omit(marketing$salary_from)
meanOfSalaryMarket=round(mean(salaryMarket),0)
salarybugalteria=na.omit(bugalteria$salary_from)
meanOfSalarybugalteria=round(mean(salarybugalteria),0)
salaryAdmin=na.omit(adminpersonal$salary_from)
meanOfSalaryAdmin=round(mean(salaryAdmin),0)
salarybank=na.omit(bank$salary_from)
meanOfSalarybank=round(mean(salarybank),0)
salarybuild=na.omit(build$salary_from)
meanOfSalarybuild=round(mean(salarybuild),0)
salaryTransport=na.omit(transport$salary_from)
meanOfSalaryTransport=round(mean(salaryTransport),0)
meanOfSalary<-c(meanOfSalarybank,meanOfSalaryAdmin,meanOfSalarybugalteria,meanOfSalaryMarket,meanOfSalaryIt,meanOfSalaryTransport,meanOfSalarybuild)
namesSalary<-c("банк","управ","бугал","продажи","ит","транс","строит")
print(meanOfSalary)## [1] 118473 89441 119957 106611 135691 109817 157345a=data.frame(namesSalary,meanOfSalary)- This graph shows the average minimum salary offered in various specializations in Almaty
plot(a)
* 4. Further analysis explores these moments: * In some cities, the biggest and the minimum wage * The most popular profession in Kazakhstan and most popular profession each city separately * In which specialization wage the biggest * And so on * to be continued…