Created
October 7, 2015 15:56
-
-
Save jthandy/43fa2ac56bd7ffc181f1 to your computer and use it in GitHub Desktop.
The query we used in the RJMetrics benchmark report "The State of Data Science" to identify data scientist profiles.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| /* | |
| Look for Data Scientists in the following 9 languages: | |
| -- English | |
| -- Spanish | |
| -- French | |
| -- German | |
| -- Dutch | |
| -- Swedish | |
| -- Italian | |
| -- Portuguese | |
| -- Turkish | |
| */ | |
| drop table if exists linkedin_people.data_scientists_pid; | |
| create table linkedin_people.data_scientists_pid distkey(li_person_id) as | |
| ( | |
| /* | |
| Add levels: | |
| -- executive | |
| Chief DS, Chief Data Officer (not Digital Officer), CMO, COO, | |
| CEO, CTO, founder, co-founder, owner, SVP, VP, president | |
| -- senior | |
| director, manager, lead, head, senior data scientist, principal | |
| -- junior | |
| everybody else, but not in academia | |
| -- academic | |
| professor, lecturer | |
| -- questionable | |
| have words "hiring", "looking for" in the headline | |
| */ | |
| select li_person_id, li_company_id, company_name, first_name, last_name, title, headline, | |
| case | |
| when | |
| ( | |
| headline like '%chief%' or | |
| headline like '%president%' or | |
| headline like '%ceo%' or | |
| (headline like '%amministratore delegato%' and country_code = 'IT') /* Italian */ or | |
| (headline like '%verkst%llande direkt%r%' and country_code = 'SE') /* Swedish */ or | |
| headline like '%director ejecutivo%' /* Spanish */ or | |
| headline like '%cmo%' or | |
| headline like 'coo %' or | |
| headline like '% coo' or | |
| headline like '% coo %' or | |
| headline like '%/coo' or | |
| (headline like '%pr%sident directeur g%n%ral%' and country_code = 'FR') /* French */ or | |
| (headline like '%algemeen directeur%' and country_code = 'NL') /* Dutch */ or | |
| (headline like '%ba% i%letme g%revlisi%' and country_code = 'TR') /* Turkish */ or | |
| (headline like '%diretor de opera%es%' and (country_code = 'BR' or country_code = 'PT')) /* Portuguese */ or | |
| headline like '%director de operaciones%' /* Spanish */ or | |
| headline like 'cto %' /* English, German, Italian, Swedish */ or | |
| headline like '% cto' or | |
| headline like '% cto %' or | |
| headline like '%/cto' or | |
| (headline like '%directeur de la technologie%' and country_code = 'FR') /* French */ or | |
| (headline like '%diretor de tecnologia%' and (country_code = 'BR' or country_code = 'PT')) /* Portuguese */ or | |
| (headline like '%hoofd technologie%' and country_code = 'NL') /* Dutch */ or | |
| (headline like '%teknolojiden sorumlu ba%kan%' and country_code = 'TR') /* Turkish */ or | |
| headline like '%director tecnol%gico%' /* Spanish */ or | |
| (headline like '%founder%' and headline not like '%group%') /* English */ or | |
| (headline like '%fondateur%' and country_code = 'FR') /* French */ or | |
| (headline like '%gr%nder%' and country_code = 'DE') /* German */ or | |
| (headline like '%oprichter%' and country_code = 'NL') /* Dutch */ or | |
| (headline like '%fondatore%' and country_code = 'IT') /* Italian */ or | |
| (headline like '%grundare%' and country_code = 'SE') /* Swedish */ or | |
| (headline like '%kurucu%' and country_code = 'TR') /* Turkish */ or | |
| headline like '%fundador%' /* Portuguese, Spanish */ or | |
| headline like '%owner %' or | |
| headline like '% owner%' or | |
| headline like '%propri%ta%r%' /* French, Italian, Portuguese */ or | |
| (headline like '%inhaber%' and country_code = 'DE') /* German */ or | |
| (headline like '%eigenaar%' and country_code = 'NL') /* Dutch */ or | |
| (headline like '%sahip%' and country_code = 'TR') /* Turkish */ or | |
| headline like '%propietario%' /* Spanish */ or | |
| (headline like '%vp%' and headline not like '%mvp%') or | |
| headline like '%vice%president%' /* English, French, Dutch, Italian, Swedish, Portuguese, Spanish */ or | |
| (headline like '%vizepr%sident%' and country_code = 'DE') /* German */ or | |
| (headline like '%ba%kan yard%mc%s%' and country_code = 'TR') /* Turkish */ or | |
| title like '%chief%' or | |
| title like '%vp%' or | |
| title like '%president%' or | |
| title like '%ceo%' or | |
| (title like '%amministratore delegato%' and country_code = 'IT') /* Italian */ or | |
| (title like '%verkst%llande direkt%r%' and country_code = 'SE') /* Swedish */ or | |
| title like '%director ejecutivo%' /* Spanish */ or | |
| title like '%cmo%' or | |
| title like 'coo %' or | |
| title like '% coo' or | |
| title like '% coo %' or | |
| title like '%/coo' or | |
| (title like '%pr%sident directeur g%n%ral%' and country_code = 'FR') /* French */ or | |
| (title like '%algemeen directeur%' and country_code = 'NL') /* Dutch */ or | |
| (title like '%ba% i%letme g%revlisi%' and country_code = 'TR') /* Turkish */ or | |
| (title like '%diretor de opera%es%' and (country_code = 'BR' or country_code = 'PT')) /* Portuguese */ or | |
| title like '%director de operaciones%' /* Spanish */ or | |
| title like 'cto %' /* English, German, Italian, Swedish */ or | |
| title like '% cto' or | |
| title like '% cto %' or | |
| title like '%/cto' or | |
| (title like '%directeur de la technologie%' and country_code = 'FR') /* French */ or | |
| (title like '%diretor de tecnologia%' and (country_code = 'BR' or country_code = 'PT')) /* Portuguese */ or | |
| (title like '%hoofd technologie%' and country_code = 'NL') /* Dutch */ or | |
| (title like '%teknolojiden sorumlu ba%kan%' and country_code = 'TR') /* Turkish */ or | |
| title like '%director tecnol%gico%' /* Spanish */ or | |
| (title like '%founder%' and title not like '%group%') /* English */ or | |
| (title like '%fondateur%' and country_code = 'FR') /* French */ or | |
| (title like '%gr%nder%' and country_code = 'DE') /* German */ or | |
| (title like '%oprichter%' and country_code = 'NL') /* Dutch */ or | |
| (title like '%fondatore%' and country_code = 'IT') /* Italian */ or | |
| (title like '%grundare%' and country_code = 'SE') /* Swedish */ or | |
| (title like '%kurucu%' and country_code = 'TR') /* Turkish */ or | |
| title like '%fundador%' /* Portuguese, Spanish */ or | |
| title like '%owner %' or | |
| title like '% owner%' or | |
| title like '%propri%ta%r%' /* French, Italian, Portuguese */ or | |
| (title like '%inhaber%' and country_code = 'DE') /* German */ or | |
| (title like '%eigenaar%' and country_code = 'NL') /* Dutch */ or | |
| (title like '%sahip%' and country_code = 'TR') /* Turkish */ or | |
| title like '%propietario%' /* Spanish */ or | |
| title like '%vice%president%' /* English, French, Dutch, Italian, Swedish, Portuguese, Spanish */ or | |
| (title like '%vizepr%sident%' and country_code = 'DE') /* German */ or | |
| (title like '%ba%kan yard%mc%s%' and country_code = 'TR') /* Turkish */ or | |
| /* | |
| Explicit Chief Data Scientist titles | |
| */ | |
| headline like '%chief data%scientist%' /* English, Dutch */ or | |
| headline like '%jefe cient%fico de datos%' /* Spanish */ or | |
| headline like '%scientifique%chef de donn%es%' /* French */ or | |
| headline like '%chef%daten%wissenschaftler%' /* German */ or | |
| headline like '%cientista%chefe dados%' /* Portuguese */ or | |
| headline like '%scienziato%dati capo%' /* Italian */ or | |
| headline like '%ba%veri bilimci%' /* Turkish */ or | |
| title like '%chief data%scientist%' /* English, Dutch */ or | |
| title like '%jefe cient%fico de datos%' /* Spanish */ or | |
| title like '%scientifique%chef de donn%es%' /* French */ or | |
| title like '%chef%daten%wissenschaftler%' /* German */ or | |
| title like '%cientista%chefe dados%' /* Portuguese */ or | |
| title like '%scienziato%dati capo%' /* Italian */ or | |
| title like '%ba%veri bilimci%' /* Turkish */ or | |
| /* | |
| Explicit Chief Data Officer titles | |
| */ | |
| headline like '%chief data%officer%' /* English, Dutch, German, French */ or | |
| headline like '%director de los datos%' /* Spanish */ or | |
| headline like '%directeur des donn%es%' /* French */ or | |
| (headline like '%direttore dati%' and headline not like '%foundation%')/* Italian */ or | |
| headline like '%de dados principal%' /* Portuguese */ or | |
| title like '%chief data%officer%' /* English, Dutch, German, French */ or | |
| title like '%director de los datos%' /* Spanish */ or | |
| title like '%directeur des donn%es%' /* French */ or | |
| (title like '%direttore dati%' and title not like '%foundation%') /* Italian */ or | |
| title like '%de dados principal%' /* Portuguese */ | |
| ) then 'executive' | |
| when | |
| ( | |
| headline like '%director%' /* English, Spanish */ or | |
| (headline like '%directeur%' and (country_code = 'FR' or country_code = 'NL')) /* French, Dutch */ or | |
| (headline like '%direttore%' and country_code = 'IT') /* Italian */ or | |
| (headline like '%direkt%r%' and (country_code = 'NL' or country_code = 'SE')) /* German, Swedish */ or | |
| (headline like '%diretor%' and (country_code = 'BR' or country_code = 'PT')) /* Portuguese */ or | |
| headline like '%pr%sident%' /* English, French, German, Dutch, Italian, Swedish, Portuguese, Spanish */ or | |
| headline like '%manager%' /* English, French, German, Italian, Dutch */ or | |
| (headline like '%responsabile%' and country_code = 'IT') /* Italian */ or | |
| (headline like '%ledare%' and country_code = 'SE') /* Swedish */ or | |
| (headline like '%m%d%r%' and country_code = 'TR') /* Turkish */ or | |
| headline like '%gerente%' /* Portuguese, Spanish */ or | |
| headline like '%principal%' or | |
| headline like '%senior%' or | |
| (headline like '%sr %' and headline not like '%sr base%' and headline not like '%sr. base%') or | |
| (headline like '%sr. %' and headline not like '%sr. base%') or | |
| headline like '%lead %' or | |
| headline like '%lead,%' or | |
| headline like '%head %' or | |
| headline like '%head,%' or | |
| (headline like '%hoofd%' and country_code = 'NL') /* Dutch */ or | |
| (headline like '%ba%kan%' and country_code = 'TR') /* Turkish */ or | |
| title like '%director%' /* English, Spanish */ or | |
| (title like '%directeur%' and (country_code = 'FR' or country_code = 'NL')) /* French, Dutch */ or | |
| (title like '%direttore%' and country_code = 'IT') /* Italian */ or | |
| (title like '%direkt%r%' and (country_code = 'NL' or country_code = 'SE')) /* German, Swedish */ or | |
| (title like '%diretor%' and (country_code = 'BR' or country_code = 'PT')) /* Portuguese */ or | |
| title like '%pr%sident%' /* English, French, German, Dutch, Italian, Swedish, Portuguese, Spanish */ or | |
| title like '%manager%' /* English, French, German, Italian, Dutch */ or | |
| (title like '%responsabile%' and country_code = 'IT') /* Italian */ or | |
| (title like '%ledare%' and country_code = 'SE') /* Swedish */ or | |
| (title like '%m%d%r%' and country_code = 'TR') /* Turkish */ or | |
| title like '%gerente%' /* Portuguese, Spanish */ or | |
| title like '%principal%' or | |
| title like '%senior%' or | |
| (title like '%sr %' and title not like '%sr base%' and title not like '%sr. base%') or | |
| (title like '%sr. %' and title not like '%sr. base%') or | |
| title like '%lead %' or | |
| title like '%lead,%' or | |
| title like '%head %' or | |
| title like '%head,%' or | |
| (title like '%hoofd%' and country_code = 'NL') /* Dutch */ or | |
| (title like '%ba%kan%' and country_code = 'TR') /* Turkish */ | |
| ) | |
| and | |
| ( | |
| (headline not like '%academic%' or headline is null) and | |
| (title not like '%academic%' or title is null) | |
| ) then 'senior' | |
| when | |
| ( | |
| headline like '%professor%' /* English, Dutch, German, Portuguese, Italian */ or | |
| headline like '%profesor%' /* Spanish */ or | |
| headline like '%professeur%' /* French */ or | |
| headline similar to '%profes_r%' /* Turkish */ or | |
| title like '%professor%' /* English, Dutch, German, Portuguese, Italian */ or | |
| title like '%profesor%' /* Spanish */ or | |
| title like '%professeur%' /* French */ or | |
| title similar to '%profes_r%' /* Turkish */ or | |
| headline like '%lecturer%' /*English */ or | |
| headline like '%lector%' /* Dutch */ or | |
| headline like '%charg%de cours%' /* French */ or | |
| headline like '%dozent%' /* German */ or | |
| headline like '%docente%' /* Italian */ or | |
| headline like '%okutman%' /* Turkish */ or | |
| title like '%lecturer%' or | |
| title like '%lector%' /* Dutch */ or | |
| title like '%charg%de cours%' /* French */ or | |
| title like '%dozent%' /* German */ or | |
| title like '%docente%' /* Italian */ or | |
| title like '%okutman%' /* Turkish */ | |
| ) then 'academic' | |
| when | |
| ( | |
| headline like '%hiring%' or | |
| headline like '%looking%' or | |
| title like '%hiring%' or | |
| title like '%looking%' | |
| ) then 'questionable' | |
| else 'junior' | |
| end | |
| as level, | |
| location, country_code, raw_date_started, month_started, year_started, date_started, | |
| position_duration, person_industry, num_connections, date_last_visited, date_updated | |
| from | |
| ( | |
| select li_person_id, li_company_id, company_name, first_name, last_name, title, headline, | |
| location, country_code, raw_date_started, month_started, year_started, date_started, | |
| position_duration, person_industry, num_connections, date_last_visited, date_updated | |
| from linkedin_people.all_employees_pid | |
| where | |
| ( | |
| /* | |
| Lecturers and Professors of Data Science | |
| */ | |
| ( | |
| ( | |
| headline like '%professor%' /* English, Dutch, German, Portuguese, Italian */ or | |
| headline like '%profesor%' /* Spanish */ or | |
| headline like '%professeur%' /* French */ or | |
| headline similar to '%profes_r%' /* Turkish */ or | |
| title like '%professor%' /* English, Dutch, German, Portuguese, Italian */ or | |
| title like '%profesor%' /* Spanish */ or | |
| title like '%professeur%' /* French */ or | |
| title similar to '%profes_r%' /* Turkish */ or | |
| headline like '%lecturer%' /*English */ or | |
| headline like '%lector%' /* Dutch */ or | |
| headline like '%charg%de cours%' /* French */ or | |
| headline like '%dozent%' /* German */ or | |
| headline like '%docente%' /* Italian */ or | |
| headline like '%okutman%' /* Turkish */ or | |
| title like '%lecturer%' or | |
| title like '%lector%' /* Dutch */ or | |
| title like '%charg%de cours%' /* French */ or | |
| title like '%dozent%' /* German */ or | |
| title like '%docente%' /* Italian */ or | |
| title like '%okutman%' /* Turkish */ | |
| ) | |
| and | |
| ( | |
| headline like '%data science%' /* English, Dutch, */ or | |
| headline like '%ciencia de datos%' /* Spanish */ or | |
| headline like '%science des donn%es%' /* French */ or | |
| headline like '%daten%wissenschaft%' /* German */ or | |
| headline like '%ci%ncia dados%' /* Portuguese */ or | |
| headline like '%scienza dati%' /* Italian */ or | |
| headline like '%veri bilimi%' /* Turkish */ or | |
| title like '%data science%' /* English, Dutch, */ or | |
| title like '%ciencia de datos%' /* Spanish */ or | |
| title like '%science des donn%es%' /* French */ or | |
| title like '%daten%wissenschaft%' /* German */ or | |
| title like '%ci%ncia dados%' /* Portuguese */ or | |
| title like '%scienza dati%' /* Italian */ or | |
| title like '%veri bilimi%' /* Turkish */ | |
| ) | |
| ) | |
| or | |
| /* | |
| Executive Level | |
| */ | |
| ( | |
| ( | |
| headline like '%chief%' or | |
| headline like '%president%' or | |
| headline like '%ceo%' or | |
| (headline like '%amministratore delegato%' and country_code = 'IT') /* Italian */ or | |
| (headline like '%verkst%llande direkt%r%' and country_code = 'SE') /* Swedish */ or | |
| headline like '%director ejecutivo%' /* Spanish */ or | |
| headline like '%cmo%' or | |
| headline like 'coo %' or | |
| headline like '% coo' or | |
| headline like '% coo %' or | |
| headline like '%/coo' or | |
| (headline like '%pr%sident directeur g%n%ral%' and country_code = 'FR') /* French */ or | |
| (headline like '%algemeen directeur%' and country_code = 'NL') /* Dutch */ or | |
| (headline like '%ba% i%letme g%revlisi%' and country_code = 'TR') /* Turkish */ or | |
| (headline like '%diretor de opera%es%' and (country_code = 'BR' or country_code = 'PT')) /* Portuguese */ or | |
| headline like '%director de operaciones%' /* Spanish */ or | |
| headline like 'cto %' /* English, German, Italian, Swedish */ or | |
| headline like '% cto' or | |
| headline like '% cto %' or | |
| headline like '%/cto' or | |
| (headline like '%directeur de la technologie%' and country_code = 'FR') /* French */ or | |
| (headline like '%diretor de tecnologia%' and (country_code = 'BR' or country_code = 'PT')) /* Portuguese */ or | |
| (headline like '%hoofd technologie%' and country_code = 'NL') /* Dutch */ or | |
| (headline like '%teknolojiden sorumlu ba%kan%' and country_code = 'TR') /* Turkish */ or | |
| headline like '%director tecnol%gico%' /* Spanish */ or | |
| (headline like '%founder%' and headline not like '%group%') /* English */ or | |
| (headline like '%fondateur%' and country_code = 'FR') /* French */ or | |
| (headline like '%gr%nder%' and country_code = 'DE') /* German */ or | |
| (headline like '%oprichter%' and country_code = 'NL') /* Dutch */ or | |
| (headline like '%fondatore%' and country_code = 'IT') /* Italian */ or | |
| (headline like '%grundare%' and country_code = 'SE') /* Swedish */ or | |
| (headline like '%kurucu%' and country_code = 'TR') /* Turkish */ or | |
| headline like '%fundador%' /* Portuguese, Spanish */ or | |
| headline like '%owner %' or | |
| headline like '% owner%' or | |
| headline like '%propri%ta%r%' /* French, Italian, Portuguese */ or | |
| (headline like '%inhaber%' and country_code = 'DE') /* German */ or | |
| (headline like '%eigenaar%' and country_code = 'NL') /* Dutch */ or | |
| (headline like '%sahip%' and country_code = 'TR') /* Turkish */ or | |
| headline like '%propietario%' /* Spanish */ or | |
| (headline like '%vp%' and headline not like '%mvp%') or | |
| headline like '%vice%president%' /* English, French, Dutch, Italian, Swedish, Portuguese, Spanish */ or | |
| (headline like '%vizepr%sident%' and country_code = 'DE') /* German */ or | |
| (headline like '%ba%kan yard%mc%s%' and country_code = 'TR') /* Turkish */ or | |
| title like '%chief%' or | |
| title like '%vp%' or | |
| title like '%president%' or | |
| title like '%ceo%' or | |
| (title like '%amministratore delegato%' and country_code = 'IT') /* Italian */ or | |
| (title like '%verkst%llande direkt%r%' and country_code = 'SE') /* Swedish */ or | |
| title like '%director ejecutivo%' /* Spanish */ or | |
| title like '%cmo%' or | |
| title like 'coo %' or | |
| title like '% coo' or | |
| title like '% coo %' or | |
| title like '%/coo' or | |
| (title like '%pr%sident directeur g%n%ral%' and country_code = 'FR') /* French */ or | |
| (title like '%algemeen directeur%' and country_code = 'NL') /* Dutch */ or | |
| (title like '%ba% i%letme g%revlisi%' and country_code = 'TR') /* Turkish */ or | |
| (title like '%diretor de opera%es%' and (country_code = 'BR' or country_code = 'PT')) /* Portuguese */ or | |
| title like '%director de operaciones%' /* Spanish */ or | |
| title like 'cto %' /* English, German, Italian, Swedish */ or | |
| title like '% cto' or | |
| title like '% cto %' or | |
| title like '%/cto' or | |
| (title like '%directeur de la technologie%' and country_code = 'FR') /* French */ or | |
| (title like '%diretor de tecnologia%' and (country_code = 'BR' or country_code = 'PT')) /* Portuguese */ or | |
| (title like '%hoofd technologie%' and country_code = 'NL') /* Dutch */ or | |
| (title like '%teknolojiden sorumlu ba%kan%' and country_code = 'TR') /* Turkish */ or | |
| title like '%director tecnol%gico%' /* Spanish */ or | |
| (title like '%founder%' and title not like '%group%') /* English */ or | |
| (title like '%fondateur%' and country_code = 'FR') /* French */ or | |
| (title like '%gr%nder%' and country_code = 'DE') /* German */ or | |
| (title like '%oprichter%' and country_code = 'NL') /* Dutch */ or | |
| (title like '%fondatore%' and country_code = 'IT') /* Italian */ or | |
| (title like '%grundare%' and country_code = 'SE') /* Swedish */ or | |
| (title like '%kurucu%' and country_code = 'TR') /* Turkish */ or | |
| title like '%fundador%' /* Portuguese, Spanish */ or | |
| title like '%owner %' or | |
| title like '% owner%' or | |
| title like '%propri%ta%r%' /* French, Italian, Portuguese */ or | |
| (title like '%inhaber%' and country_code = 'DE') /* German */ or | |
| (title like '%eigenaar%' and country_code = 'NL') /* Dutch */ or | |
| (title like '%sahip%' and country_code = 'TR') /* Turkish */ or | |
| title like '%propietario%' /* Spanish */ or | |
| title like '%vice%president%' /* English, French, Dutch, Italian, Swedish, Portuguese, Spanish */ or | |
| (title like '%vizepr%sident%' and country_code = 'DE') /* German */ or | |
| (title like '%ba%kan yard%mc%s%' and country_code = 'TR') /* Turkish */ | |
| ) | |
| and | |
| ( | |
| ( | |
| headline like '%data science%' and | |
| lower(company_name) not like '%data science%' and | |
| headline not like '% at %data%science%' | |
| ) /* English, Dutch, */ | |
| or | |
| headline like '%ciencia de datos%' /* Spanish */ or | |
| headline like '%science des donn%es%' /* French */ or | |
| headline like '%daten%wissenschaft%' /* German */ or | |
| headline like '%ci%ncia dados%' /* Portuguese */ or | |
| headline like '%scienza dati%' /* Italian */ or | |
| headline like '%veri bilimi%' /* Turkish */ or | |
| title like '%data science%' /* English, Dutch, */ or | |
| title like '%ciencia de datos%' /* Spanish */ or | |
| title like '%science des donn%es%' /* French */ or | |
| title like '%daten%wissenschaft%' /* German */ or | |
| title like '%ci%ncia dados%' /* Portuguese */ or | |
| title like '%scienza dati%' /* Italian */ or | |
| title like '%veri bilimi%' /* Turkish */ | |
| ) | |
| ) | |
| or | |
| /* | |
| Senior Level | |
| */ | |
| ( | |
| ( | |
| headline like '%director%' /* English, Spanish */ or | |
| (headline like '%directeur%' and (country_code = 'FR' or country_code = 'NL')) /* French, Dutch */ or | |
| (headline like '%direttore%' and country_code = 'IT') /* Italian */ or | |
| (headline like '%direkt%r%' and (country_code = 'NL' or country_code = 'SE')) /* German, Swedish */ or | |
| (headline like '%diretor%' and (country_code = 'BR' or country_code = 'PT')) /* Portuguese */ or | |
| headline like '%pr%sident%' /* English, French, German, Dutch, Italian, Swedish, Portuguese, Spanish */ or | |
| headline like '%manager%' /* English, French, German, Italian, Dutch */ or | |
| (headline like '%responsabile%' and country_code = 'IT') /* Italian */ or | |
| (headline like '%ledare%' and country_code = 'SE') /* Swedish */ or | |
| (headline like '%m%d%r%' and country_code = 'TR') /* Turkish */ or | |
| headline like '%gerente%' /* Portuguese, Spanish */ or | |
| headline like '%principal%' or | |
| headline like '%senior%' or | |
| (headline like '%sr %' and headline not like '%sr base%' and headline not like '%sr. base%') or | |
| (headline like '%sr. %' and headline not like '%sr. base%') or | |
| headline like '%lead %' or | |
| headline like '%lead,%' or | |
| headline like '%head %' or | |
| headline like '%head,%' or | |
| (headline like '%hoofd%' and country_code = 'NL') /* Dutch */ or | |
| (headline like '%ba%kan%' and country_code = 'TR') /* Turkish */ or | |
| title like '%director%' /* English, Spanish */ or | |
| (title like '%directeur%' and (country_code = 'FR' or country_code = 'NL')) /* French, Dutch */ or | |
| (title like '%direttore%' and country_code = 'IT') /* Italian */ or | |
| (title like '%direkt%r%' and (country_code = 'NL' or country_code = 'SE')) /* German, Swedish */ or | |
| (title like '%diretor%' and (country_code = 'BR' or country_code = 'PT')) /* Portuguese */ or | |
| title like '%pr%sident%' /* English, French, German, Dutch, Italian, Swedish, Portuguese, Spanish */ or | |
| title like '%manager%' /* English, French, German, Italian, Dutch */ or | |
| (title like '%responsabile%' and country_code = 'IT') /* Italian */ or | |
| (title like '%ledare%' and country_code = 'SE') /* Swedish */ or | |
| (title like '%m%d%r%' and country_code = 'TR') /* Turkish */ or | |
| title like '%gerente%' /* Portuguese, Spanish */ or | |
| title like '%principal%' or | |
| title like '%senior%' or | |
| (title like '%sr %' and title not like '%sr base%' and title not like '%sr. base%') or | |
| (title like '%sr. %' and title not like '%sr. base%') or | |
| title like '%lead %' or | |
| title like '%lead,%' or | |
| title like '%head %' or | |
| title like '%head,%' or | |
| (title like '%hoofd%' and country_code = 'NL') /* Dutch */ or | |
| (title like '%ba%kan%' and country_code = 'TR') /* Turkish */ | |
| ) | |
| and | |
| ( | |
| ( | |
| headline like '%data science%' and | |
| lower(company_name) not like '%data science%' and | |
| headline not like '% at %data%science%' | |
| ) /* English, Dutch, */ or | |
| headline like '%ciencia de datos%' /* Spanish */ or | |
| headline like '%science des donn%es%' /* French */ or | |
| headline like '%daten%wissenschaft%' /* German */ or | |
| headline like '%ci%ncia dados%' /* Portuguese */ or | |
| headline like '%scienza dati%' /* Italian */ or | |
| headline like '%veri bilimi%' /* Turkish */ or | |
| title like '%data science%' /* English, Dutch, */ or | |
| title like '%ciencia de datos%' /* Spanish */ or | |
| title like '%science des donn%es%' /* French */ or | |
| title like '%daten%wissenschaft%' /* German */ or | |
| title like '%ci%ncia dados%' /* Portuguese */ or | |
| title like '%scienza dati%' /* Italian */ or | |
| title like '%veri bilimi%' /* Turkish */ | |
| ) | |
| ) | |
| or | |
| /* | |
| Explicit Chief Data Scientist titles | |
| */ | |
| headline like '%chief data%scientist%' /* English, Dutch */ or | |
| headline like '%jefe cient%fico de datos%' /* Spanish */ or | |
| headline like '%scientifique%chef de donn%es%' /* French */ or | |
| headline like '%chef%daten%wissenschaftler%' /* German */ or | |
| headline like '%cientista%chefe dados%' /* Portuguese */ or | |
| headline like '%scienziato%dati capo%' /* Italian */ or | |
| headline like '%ba%veri bilimci%' /* Turkish */ or | |
| title like '%chief data%scientist%' /* English, Dutch */ or | |
| title like '%jefe cient%fico de datos%' /* Spanish */ or | |
| title like '%scientifique%chef de donn%es%' /* French */ or | |
| title like '%chef%daten%wissenschaftler%' /* German */ or | |
| title like '%cientista%chefe dados%' /* Portuguese */ or | |
| title like '%scienziato%dati capo%' /* Italian */ or | |
| title like '%ba%veri bilimci%' /* Turkish */ or | |
| /* | |
| Explicit Chief Data Officer titles | |
| */ | |
| headline like '%chief data%officer%' /* English, Dutch, German, French */ or | |
| headline like '%director de los datos%' /* Spanish */ or | |
| headline like '%directeur des donn%es%' /* French */ or | |
| (headline like '%direttore dati%' and headline not like '%foundation%')/* Italian */ or | |
| headline like '%de dados principal%' /* Portuguese */ or | |
| title like '%chief data%officer%' /* English, Dutch, German, French */ or | |
| title like '%director de los datos%' /* Spanish */ or | |
| title like '%directeur des donn%es%' /* French */ or | |
| (title like '%direttore dati%' and title not like '%foundation%') /* Italian */ or | |
| title like '%de dados principal%' /* Portuguese */ or | |
| /* | |
| Plain Data Scientists | |
| */ | |
| headline like '%data scientist%' /* English, Dutch */ or | |
| headline like '%cient%fico de datos%' /* Spanish */ or | |
| headline like '%scientifique de donn%es%' /* French */ or | |
| headline like '%daten%wis%enschaftler%' /* German */ or | |
| headline like '%cientista de dados%' /* Portuguese */ or | |
| headline like '%scienziato dati%' /* Italian */ or | |
| headline like '%veri bilimci%' /* Turkish */ or | |
| title like '%data scientist%' /* English, Dutch */ or | |
| title like '%cient%fico de datos%' /* Spanish */ or | |
| title like '%scientifique de donn%es%' /* French */ or | |
| title like '%daten%wis%enschaftler%' /* German */ or | |
| title like '%cientista de dados%' /* Portuguese */ or | |
| title like '%scienziato dati%' /* Italian */ or | |
| title like '%veri bilimci%' /* Turkish */ | |
| ) | |
| and | |
| ( | |
| /* | |
| Chief DS and CDO exceptions | |
| */ | |
| (headline not like '%office%of%chief%data%' or headline is null) and | |
| (headline not like '%coordonnat%' or headline is null) and | |
| (headline not like '%bases de donn%' or headline is null) and | |
| (headline not like '%scientifiques et donn%es%' or headline is null) and | |
| (headline not like '%scientifique sp%cialis%' or headline is null) and | |
| (headline not like '%r%dactrice scientifique%' or headline is null) and | |
| (headline not like '%qualit% des donn%es%' or headline is null) and | |
| (title not like '%office%of%' or title is null) and | |
| (title not like '%coordonnat%' or title is null) and | |
| (title not like '%bases de donn%' or title is null) and | |
| (title not like '%scientifiques et donn%es%' or title is null) and | |
| (title not like '%scientifique sp%cialis%' or title is null) and | |
| (title not like '%r%dactrice scientifique%' or title is null) and | |
| (title not like '%qualit% des donn%es%' or title is null) and | |
| /* | |
| Exclude analysts listing data scientist titles | |
| */ | |
| (headline not like '%analyst%' or headline is null) /* English, Dutch, German, French */ and | |
| (headline not like '%analist%' or headline is null) /* Spanish, Portuguese, Italian, Turkish */ and | |
| (title not like '%analyst%' or title is null) /* English, Dutch, German, French */ and | |
| (title not like '%analist%' or title is null) /* Spanish, Portuguese, Italian, Turkish */ and | |
| /* | |
| Exclude people listing DS incubators in their headline | |
| */ | |
| (headline not like '%insight data science%' or headline is null) and | |
| (headline not like '%data incubator%' or headline is null) and | |
| (headline not like '%metis%' or headline is null) and | |
| (headline not like '%general assemb%' or headline is null) | |
| /* | |
| Other exceptions | |
| */ | |
| (headline not like '%coordonnat%' or headline is null) and | |
| (headline not like '%bases de donn%' or headline is null) and | |
| (headline not like '%scientifiques et donn%es%' or headline is null) and | |
| (headline not like '%scientifique sp%cialis%' or headline is null) and | |
| (headline not like '%r%dactrice scientifique%' or headline is null) and | |
| (title not like '%coordonnat%' or title is null) and | |
| (title not like '%bases de donn%' or title is null) and | |
| (title not like '%scientifiques et donn%es%' or title is null) and | |
| (title not like '%scientifique sp%cialis%' or title is null) and | |
| (title not like '%r%dactrice scientifique%' or title is null) and | |
| (headline not like '%hr%' or headline is null) and | |
| (headline not like '%recruiter%' or headline is null) and | |
| (headline not like '%exec search%' or headline is null) and | |
| (headline not like '%buyer%' or headline is null) and | |
| (headline not like '%seller%' or headline is null) and | |
| (headline not like '%account dev%' or headline is null) and | |
| (headline not like '%student%' or headline is null) and | |
| (headline not like '%leading%' or headline is null) and | |
| (headline not like '%heading%' or headline is null) and | |
| (headline not like '%data science major%' or headline is null) and | |
| (title not like '%hr%' or title is null) and | |
| (title not like '%recruiter%' or title is null) and | |
| (title not like '%exec search%' or title is null) and | |
| (title not like '%buyer%' or title is null) and | |
| (title not like '%seller%' or title is null) and | |
| (title not like '%account dev%' or title is null) and | |
| (title not like '%student%' or title is null) and | |
| (title not like '%leading%' or title is null) and | |
| (title not like '%heading%' or title is null) and | |
| (title not like '%data science major%' or title is null) and | |
| ) | |
| ) | |
| ); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment