getURL <- "https://raw.githubusercontent.com/deepakmongia/Fall2018/master/Data-607-Project3/freeformResponses.csv"
free.form.response.df1 <- read.csv(getURL, header = TRUE, sep = ",")
dim(free.form.response.df1)## [1] 16716 62head(free.form.response.df1, 2)## GenderFreeForm KaggleMotivationFreeForm CurrentJobTitleFreeForm
## 1
## 2
## MLToolNextYearFreeForm MLMethodNextYearFreeForm
## 1
## 2
## LanguageRecommendationFreeForm PublicDatasetsFreeForm
## 1
## 2
## PersonalProjectsChallengeFreeForm
## 1 Data manipulation
## 2 I can't find time to practice consistently
## LearningPlatformCommunityFreeForm LearningPlatformFreeForm1
## 1
## 2
## LearningPlatformFreeForm2 LearningPlatformFreeForm3
## 1
## 2
## LearningPlatformUsefulnessCommunitiesFreeForm
## 1 NA
## 2 NA
## LearningPlatformUsefulnessFreeForm1Select
## 1
## 2
## LearningPlatformUsefulnessFreeForm1SelectFreeForm
## 1 NA
## 2 NA
## LearningPlatformUsefulnessFreeForm2Select
## 1
## 2
## LearningPlatformUsefulnessFreeForm2SelectFreeForm
## 1 NA
## 2 NA
## LearningPlatformUsefulnessFreeForm3Select
## 1
## 2
## LearningPlatformUsefulnessFreeForm3SelectFreeForm
## 1 NA
## 2 NA
## BlogsPodcastsNewslettersFreeForm JobSkillImportanceOtherSelect1FreeForm
## 1 None
## 2
## JobSkillImportanceOtherSelect2FreeForm
## 1
## 2
## JobSkillImportanceOtherSelect3FreeForm CoursePlatformFreeForm
## 1
## 2
## HardwarePersonalProjectsFreeForm ProveKnowledgeFreeForm
## 1
## 2
## ImpactfulAlgorithmFreeForm
## 1 It's not deployed yet, but hopefully a computationally efficient neural net package customized for the nielsen kilts database that will use interpretable neural nets approximated for probablistic graphical models explain and predict motivational drivers of consumer behavior.
## 2 Sentiment analysis of twitter data
## InterestingProblemFreeForm DataScienceIdentityFreeForm MajorFreeForm
## 1
## 2
## PastJobTitlesFreeForm FirstTrainingFreeForm
## 1
## 2
## LearningCategoryOtherFreeForm MLSkillsFreeForm MLTechniquesFreeform
## 1
## 2
## EmployerIndustryOtherFreeForm EmployerSearchMethodOtherFreeForm
## 1
## 2
## JobFunctionFreeForm WorkHardwareFreeForm WorkDataTypeFreeForm
## 1
## 2
## WorkLibrariesFreeForm WorkAlgorithmsFreeForm
## 1 Clustering Methods, association rules
## 2
## WorkToolsFreeForm1 WorkToolsFreeForm2 WorkToolsFreeForm3
## 1
## 2 Stata
## WorkToolsFrequencySelect1FreeForm WorkFrequencySelect2FreeForm
## 1 NA NA
## 2 NA NA
## WorkFrequencySelect3FreeForm WorkMethodsFreeForm1 WorkMethodsFreeForm2
## 1 NA
## 2 NA
## WorkMethodsFreeForm3 WorkMethodsFrequencySelect1FreeForm
## 1 NA
## 2 NA
## WorkMethodsFrequencySelect2FreeForm WorkMethodsFrequencySelect3FreeForm
## 1 NA NA
## 2 NA NA
## TimeOtherSelectFreeForm WorkChallengesFreeForm
## 1
## 2
## WorkChallengeFrequencyOtherFreeForm WorkMLTeamSeatFreeForm
## 1 NA
## 2 NA
## WorkDataStorageFreeForm WorkCodeSharingFreeForm SalaryChangeFreeForm
## 1
## 2
## JobSearchResourceFreeForm
## 1
## 2Removing the columns which have all NA values
free.form.response.df2 <- free.form.response.df1[, apply(free.form.response.df1, 2, function(x){any(!is.na(x))})]Checking the counts of valid data elements under all the columns in the new dataframe
sprintf("Total number of rows in the data.frame is: %s", nrow(free.form.response.df2))## [1] "Total number of rows in the data.frame is: 16716"apply(free.form.response.df2, 2, function(x){sum(!(x == ""), na.rm = TRUE)})## GenderFreeForm
## 134
## KaggleMotivationFreeForm
## 746
## CurrentJobTitleFreeForm
## 1143
## MLToolNextYearFreeForm
## 385
## MLMethodNextYearFreeForm
## 227
## LanguageRecommendationFreeForm
## 81
## PublicDatasetsFreeForm
## 262
## PersonalProjectsChallengeFreeForm
## 3523
## LearningPlatformCommunityFreeForm
## 179
## LearningPlatformFreeForm1
## 330
## LearningPlatformFreeForm2
## 54
## LearningPlatformFreeForm3
## 45
## LearningPlatformUsefulnessFreeForm1Select
## 369
## LearningPlatformUsefulnessFreeForm2Select
## 64
## LearningPlatformUsefulnessFreeForm3Select
## 54
## BlogsPodcastsNewslettersFreeForm
## 1116
## JobSkillImportanceOtherSelect1FreeForm
## 201
## JobSkillImportanceOtherSelect2FreeForm
## 87
## JobSkillImportanceOtherSelect3FreeForm
## 35
## CoursePlatformFreeForm
## 333
## HardwarePersonalProjectsFreeForm
## 120
## ProveKnowledgeFreeForm
## 122
## ImpactfulAlgorithmFreeForm
## 4379
## InterestingProblemFreeForm
## 4467
## DataScienceIdentityFreeForm
## 2417
## MajorFreeForm
## 809
## PastJobTitlesFreeForm
## 2094
## FirstTrainingFreeForm
## 244
## LearningCategoryOtherFreeForm
## 476
## MLSkillsFreeForm
## 672
## MLTechniquesFreeform
## 759
## EmployerIndustryOtherFreeForm
## 926
## EmployerSearchMethodOtherFreeForm
## 640
## JobFunctionFreeForm
## 504
## WorkHardwareFreeForm
## 121
## WorkDataTypeFreeForm
## 662
## WorkLibrariesFreeForm
## 4504
## WorkAlgorithmsFreeForm
## 415
## WorkToolsFreeForm1
## 664
## WorkToolsFreeForm2
## 133
## WorkToolsFreeForm3
## 80
## WorkMethodsFreeForm1
## 189
## WorkMethodsFreeForm2
## 33
## WorkMethodsFreeForm3
## 61
## TimeOtherSelectFreeForm
## 358
## WorkChallengesFreeForm
## 214
## WorkMLTeamSeatFreeForm
## 931
## WorkDataStorageFreeForm
## 256
## WorkCodeSharingFreeForm
## 375
## SalaryChangeFreeForm
## 101
## JobSearchResourceFreeForm
## 199KaggleMotivationFreeForm_vect <- free.form.response.df2$KaggleMotivationFreeForm[free.form.response.df2$KaggleMotivationFreeForm != ""]
length(KaggleMotivationFreeForm_vect)## [1] 746CurrentJobTitleFreeForm_vect <- free.form.response.df2$CurrentJobTitleFreeForm[free.form.response.df2$CurrentJobTitleFreeForm != ""]
length(CurrentJobTitleFreeForm_vect)## [1] 1143any(is.na(free.form.response.df2$CurrentJobTitleFreeForm))## [1] FALSEMLToolNextYearFreeForm_vect <- free.form.response.df2$MLToolNextYearFreeForm[free.form.response.df2$MLToolNextYearFreeForm != ""]
length(MLToolNextYearFreeForm_vect)## [1] 385MLToolNextYearFreeForm_vect## [1] PyTorch
## [2] Keras
## [3] Internal
## [4] pytorch
## [5] Python, SQL,Data Robot
## [6] keras
## [7] PyTorch,Scala,Go
## [8] pytorch
## [9] PyTorch
## [10] Government, have to support us joint venture application big data barter their Aadhar Card include (Unique Data with DNA History biometric)
## [11] Hadoop
## [12] F#
## [13] pytorch
## [14] Spark
## [15] I focus on methods not on tools: looking forward to learn more about active learning, transfer learning, domain adaptation, and reinforcement learning
## [16] PyTorch
## [17] Scala
## [18] I don't know yet
## [19] all
## [20] Keras
## [21] Scala
## [22] OpenCL
## [23] Power BI, d3.js
## [24] Everything depends on needs.
## [25] Clickhouse
## [26] PyTorch
## [27] I haven't decided exactly
## [28] Spark
## [29] SOM
## [30] Torch
## [31] MoBagel Decanter
## [32] DundasBI
## [33] PyTorch
## [34] Alteryx
## [35] Javascript
## [36] Dataiku
## [37] PyTorch
## [38] DSL development tools
## [39] C#
## [40] Gpu cuda
## [41] CNTK
## [42] PyTorch
## [43] PCL (point cloud library)
## [44] Pytorch
## [45] Lisp
## [46] I will learn something, just don't know what.
## [47] Python, SQL, NoSQL, etc
## [48] Keras
## [49] Go
## [50] D
## [51] Symbolic C
## [52] Common Lysp
## [53] VBA
## [54] simply mastering the tools I already use
## [55] Spark
## [56] Decentralization Applications
## [57] Flux.jl; Edward;
## [58] SAP HANA PAL
## [59] Proprietary tool
## [60] I learn the tools as I need them
## [61] PyTorch, MxNet
## [62] H2O
## [63] Apache Drill
## [64] MXnET
## [65] Alteryx
## [66] PyMC3
## [67] Theano
## [68] Deep Learning
## [69] Deep learning
## [70] scala
## [71] Kira
## [72] rust
## [73] Javascript
## [74] Go
## [75] anything realted to big data
## [76] H2O AI
## [77] Open CV
## [78] PowerBI
## [79] spacy
## [80] unbbayes
## [81] Alteryx
## [82] hopefully TensorFlow Research Cloud
## [83] tensorflow
## [84] Latex
## [85] I want to make my own, revolutionary content
## [86] pytorch
## [87] torch
## [88] TensorFlow
## [89] mxnet
## [90] pytorch
## [91] Swift; iOS app development
## [92] retired
## [93] Pytorch
## [94] Medical Image Analysis tools
## [95] Prevision.io
## [96] D3
## [97] Go
## [98] rust
## [99] Drake
## [100] Dremio, Beam, NiFi, Presto, Lambda
## [101] Keras
## [102] Pytorch
## [103] DL
## [104] Dual-Wield Light Saber
## [105] Microsoft Cognitive Tool Kit
## [106] Keras
## [107] Predix
## [108] PyMC3
## [109] Spark
## [110] what best fits my needs
## [111] Keras
## [112] keras
## [113] PyTorch
## [114] will wait and see
## [115] PyTorch
## [116] Classical, frequentist statistical methods
## [117] Shiny
## [118] Deep+Wide learning
## [119] Pytorch
## [120] TensorFlow!
## [121] Edward
## [122] PyTorch
## [123] Golang
## [124] Cloud Computing
## [125] Catboost
## [126] elastic search
## [127] Prefer not to say
## [128] pytorch
## [129] Javascript
## [130] security related technologies
## [131] Scala
## [132] OCaml
## [133] Don't know yet
## [134] MXNet
## [135] Tensorflow
## [136] cntk
## [137] Cassandra; Zeppelin
## [138] Cuda
## [139] R; Python; MS AZURE; and more
## [140] Hadoop/Hive/Impala
## [141] Keras
## [142] Azure
## [143] PyTorch
## [144] Pytorch
## [145] Robotics
## [146] Quantum machine learning
## [147] pytorch
## [148] Lisp
## [149] PyTorch
## [150] pytorch, coreML
## [151] Scala
## [152] Azure
## [153] Oracle BI
## [154] Haskell
## [155] Linux
## [156] Dataiku
## [157] Spark
## [158] PyTorch
## [159] I plan to improve my current skills on the technologies I know
## [160] pytorch
## [161] Apache Kafka
## [162] caffe2
## [163] Keras
## [164] Learn what I need as I go along
## [165] CUDA
## [166] DyNet
## [167] cuda
## [168] New technology in general
## [169] better unix / unix admin
## [170] Various Data Science disciplines
## [171] Scala
## [172] Go language
## [173] Pytorch
## [174] Spark
## [175] Haskell
## [176] H2O
## [177] TensorFlow Research Cloud
## [178] Scala
## [179] PyTorch
## [180] Data Science Studio
## [181] mxnet
## [182] BigML
## [183] SAS Vdmml
## [184] these are means to various ends so I don't think about it this way
## [185] AI
## [186] I learn because I have to - no excitement anymore
## [187] PyTorch
## [188] More statistical backgroun
## [189] Sonnet
## [190] The system where ever I land. Not as many jobs as we are led to believe hiring older workers.
## [191] SAS Viya
## [192] Scala
## [193] Many
## [194] all topics seems interesting.
## [195] wtf?
## [196] Incanter
## [197] Caffe2
## [198] Neo4J
## [199] Spark
## [200] PowerBI
## [201] GPU/Accelerator programming
## [202] Scala
## [203] Scala/Spark
## [204] H2O
## [205] Tools I learn on a need basis, and currently there is no specific need
## [206] Splunk
## [207] C# in Unity3D
## [208] dont know
## [209] D3
## [210] Keras
## [211] pymc3
## [212] Graph databases
## [213] spark
## [214] Databricks
## [215] Haskell
## [216] scala
## [217] Seeq Workbench
## [218] Sisense
## [219] Scala
## [220] Tensorflow
## [221] power BI
## [222] Scala / DeepLearning4J
## [223] Any machine learning!
## [224] Rust
## [225] Sparkling Water
## [226] Pytorch
## [227] New NN types
## [228] ANGLICAN(Probabilistic programming); Ray (reinforcement learning)
## [229] I am just a beginner so
## [230] Deepening what I currently use
## [231] I can't choose only one, sorry
## [232] Python
## [233] Kubernetes
## [234] Nengo and Pytorch
## [235] Einstein Analytics
## [236] Pytorch
## [237] Tensorflow
## [238] self driving car
## [239] Spark and TensorFlow and NLP and more SQL and noSQL
## [240] Pytorch
## [241] Azkaban
## [242] pytorch
## [243] Vertica
## [244] Kafka
## [245] H2O Deepwater and Driverless AI
## [246] Keras; PyTorch
## [247] You're a tool
## [248] TensorFlow
## [249] pytorch
## [250] scala
## [251] PyTorch
## [252] Scala
## [253] Zeppelin
## [254] Pytorch, dask
## [255] Edward - Python library for probabilistic modeling
## [256] Deep neural network
## [257] pytorch
## [258] Secret
## [259] dremio
## [260] Tensorflow
## [261] Keras, MXNet
## [262] D
## [263] PyTorch
## [264] pytorch
## [265] CNTK; pytorch
## [266] TIMi Suite
## [267] Keras
## [268] Keras
## [269] Cuda
## [270] Google Cloud AI
## [271] Tensorflow, Keras, Vertica
## [272] Various ll
## [273] pytorch
## [274] Azure
## [275] Elasticsearch
## [276] Don't know
## [277] pyTorch
## [278] blockchains
## [279] PredicSis
## [280] Unity
## [281] D3 JS
## [282] Math
## [283] Alteryx
## [284] javascript
## [285] PyTorch
## [286] pytorch
## [287] Flink
## [288] tensorflow
## [289] Dataiku DSS
## [290] Scala, Akka
## [291] Databricks
## [292] Keras
## [293] PyTorch
## [294] Haskell
## [295] Alteryx
## [296] More math and new algorithms
## [297] iOS / CoreML / ARKit
## [298] Alteryx
## [299] Airflow
## [300] https://keras.io/
## [301] pytorch
## [302] PyTorch
## [303] Docker
## [304] H2o
## [305] PyTorch
## [306] Tensorflow
## [307] OpenText Magellan
## [308] Keras
## [309] cannot predict
## [310] AI
## [311] keras
## [312] scala
## [313] Microsoft Power BI
## [314] Power BI
## [315] Amazon Alexa
## [316] PyTorch
## [317] mxnet
## [318] Haskell
## [319] Airflow
## [320] Ethereum
## [321] Keras; PyTorch
## [322] Pytorch
## [323] keras
## [324] Presto
## [325] Microsoft
## [326] KERAS
## [327] not sure
## [328] Coq or LaTeX
## [329] PyTorch
## [330] d3.js
## [331] CNTK
## [332] rust
## [333] Go
## [334] PyTorch
## [335] JavaScript
## [336] TensorFlow
## [337] Gurobi
## [338] I learn as needed
## [339] ownR platform
## [340] Apache Spark
## [341] Tensor Flow & Spark/Mathlib
## [342] Keras
## [343] Tensorflow
## [344] Caffe2
## [345] docker
## [346] Vulkan, I am looking into it as a possible replacement for OpenCL
## [347] scala
## [348] pytorch
## [349] Tesseract
## [350] MXNET
## [351] Akumen
## [352] Scala
## [353] NuPIC
## [354] pytorch
## [355] Genetic Programming
## [356] SAS, R
## [357] data "science" is bullshit
## [358] Pytorch
## [359] PyTorch
## [360] None. I'd rather focus on problem definition and knowing which tool to use in the right context.
## [361] caffe
## [362] Kotlin
## [363] QlikSense
## [364] CUDA
## [365] advanced CUDA methods
## [366] Dataiku
## [367] Latest AI and Deep Learning techniques
## [368] Automated Machine Learning (TPOT , AutoSklearn)
## [369] H2O
## [370] Pytorch
## [371] pentaho
## [372] Reversible Computing Design Flow
## [373] pytorch
## [374] Microsoft Power BI + Azure ML
## [375] PyTorch
## [376] i don't know, i wish i could learn them all.
## [377] SAS Viya
## [378] cntk
## [379] Rust
## [380] H2O
## [381] GNU/Linux
## [382] Cache
## [383] adjoint optimization
## [384] Prognoz Platform
## [385] Haskell
## 249 Levels: adjoint optimization advanced CUDA methods AI ... ZeppelinMLMethodNextYearFreeForm_vect <- free.form.response.df2$MLMethodNextYearFreeForm[free.form.response.df2$MLMethodNextYearFreeForm != ""]
length(MLMethodNextYearFreeForm_vect)## [1] 227LanguageRecommendationFreeForm_vect <- free.form.response.df2$LanguageRecommendationFreeForm[free.form.response.df2$LanguageRecommendationFreeForm != ""]
length(LanguageRecommendationFreeForm_vect)## [1] 81JobSkillImportanceOtherSelect1FreeForm_vect <- free.form.response.df2$JobSkillImportanceOtherSelect1FreeForm[free.form.response.df2$JobSkillImportanceOtherSelect1FreeForm != ""]
length(JobSkillImportanceOtherSelect1FreeForm_vect)## [1] 201JobSkillImportanceOtherSelect2FreeForm_vect <- free.form.response.df2$JobSkillImportanceOtherSelect2FreeForm[free.form.response.df2$JobSkillImportanceOtherSelect2FreeForm != ""]
JobSkillImportanceOtherSelect3FreeForm_vect <- free.form.response.df2$JobSkillImportanceOtherSelect3FreeForm[free.form.response.df2$JobSkillImportanceOtherSelect3FreeForm != ""]
PastJobTitlesFreeForm_vect <- free.form.response.df2$PastJobTitlesFreeForm[free.form.response.df2$PastJobTitlesFreeForm != ""]
length(PastJobTitlesFreeForm_vect)## [1] 2094WorkHardwareFreeForm_vect <- free.form.response.df2$WorkHardwareFreeForm[free.form.response.df2$WorkHardwareFreeForm != ""]
SalaryChangeFreeForm_vect <- free.form.response.df2$SalaryChangeFreeForm[free.form.response.df2$SalaryChangeFreeForm != ""]
TimeOtherSelectFreeForm_vect <- free.form.response.df2$TimeOtherSelectFreeForm[free.form.response.df2$TimeOtherSelectFreeForm != ""]
length(TimeOtherSelectFreeForm_vect)## [1] 359## counts for programming being devoted time and its data
sum(!is.na(str_extract(TimeOtherSelectFreeForm_vect, "(\\w*rogramming)|(\\w*oftware)|(\\w*lgorithm)|(\\w*coding)|(\\w*Coding)|(\\w*development)")))## [1] 42TimeOtherSelectFreeForm_vect[!is.na(str_extract(TimeOtherSelectFreeForm_vect, "(\\w*rogramming)|(\\w*oftware)|(\\w*lgorithm)|(\\w*Coding)|(\\w*development)"))]## [1] Programming
## [2] other software engineering
## [3] Business Logic Programming
## [4] software development
## [5] Coding
## [6] Coding
## [7] Software development
## [8] Software development
## [9] At this time, all my projects in ML development are done on my own (but not for my current job)
## [10] Algorithm programming
## [11] integrate tools, develop algorithms
## [12] Algorithm development
## [13] Application development
## [14] Programming
## [15] Algorithm development
## [16] Another software related tasks
## [17] Coding
## [18] Other development work
## [19] Coding other stuff
## [20] writing software
## [21] Analytics software product development
## [22] Coding
## [23] Database management, programming
## [24] Project and business development
## [25] Software Development
## [26] Other Programming
## [27] researching new techniques and devising new algorithms
## [28] Non-ML related software development
## [29] Software development
## [30] develop algorithm
## [31] Code development
## [32] Software Development
## [33] programming
## [34] Software development
## [35] Infrastructure programming
## [36] software development
## [37] Software development
## [38] modification of algorithms
## [39] Programming
## 314 Levels: ... writing software## counts for management being used based on time and its values
sum(!is.na(str_extract(TimeOtherSelectFreeForm_vect, "\\w*anage")))## [1] 29TimeOtherSelectFreeForm_vect[!is.na(str_extract(TimeOtherSelectFreeForm_vect, "\\w*anage"))]## [1] Management
## [2] Management
## [3] Business Management
## [4] Data validation, business process management, ...
## [5] Manager
## [6] management
## [7] Product Management
## [8] strategy/management
## [9] Project management
## [10] projectmanagement
## [11] Manager taks (managing the team, PM activities, dissemination and education, talking with business lines, ...)
## [12] Project Management
## [13] Project Management + Integration into end-to-end service
## [14] Management
## [15] Management
## [16] Project management
## [17] EDC Management
## [18] Project Management
## [19] Management
## [20] Managerial
## [21] Management
## [22] Database management, programming
## [23] management of others
## [24] Project Management
## [25] Project Management
## [26] Quallty management
## [27] Project management
## [28] project management
## [29] process management
## 314 Levels: ... writing softwareCreating a data.frame for just the non blank data from the relevant columns
FreeForm_List <- list(KaggleMotivationFreeForm = KaggleMotivationFreeForm_vect, CurrentJobTitleFreeForm = CurrentJobTitleFreeForm_vect, MLToolNextYearFreeForm = MLToolNextYearFreeForm_vect, MLMethodNextYearFreeForm = MLMethodNextYearFreeForm_vect, LanguageRecommendationFreeForm = LanguageRecommendationFreeForm_vect, JobSkillImportanceOtherSelect1FreeForm = JobSkillImportanceOtherSelect1FreeForm_vect, JobSkillImportanceOtherSelect2FreeForm = JobSkillImportanceOtherSelect2FreeForm_vect, JobSkillImportanceOtherSelect3FreeForm = JobSkillImportanceOtherSelect3FreeForm_vect, PastJobTitlesFreeForm = PastJobTitlesFreeForm_vect, WorkHardwareFreeForm = WorkHardwareFreeForm_vect, SalaryChangeFreeForm = SalaryChangeFreeForm_vect, TimeOtherSelectFreeForm = TimeOtherSelectFreeForm_vect)
FreeForm_df <- FreeForm_List %>% lapply(`length<-`, max(lengths(FreeForm_List))) %>% as.data.frame()
head(FreeForm_df)## KaggleMotivationFreeForm
## 1 Curious
## 2 Promote our data solutions
## 3 More knowledge and funny experience
## 4 Keep it touch with the data science evolution and keep challenging myself
## 5 machine learning and data science is my passion
## 6 Learn new skills and challenge myself
## CurrentJobTitleFreeForm MLToolNextYearFreeForm
## 1 teacher PyTorch
## 2 Hydrographic Surveyor Keras
## 3 mechanical engineer Internal
## 4 Technical support engineer pytorch
## 5 Quantitative Analyst Python, SQL,Data Robot
## 6 Market Analyst keras
## MLMethodNextYearFreeForm
## 1 recommendation engines
## 2 Natural Language Processing
## 3 Get a deeper understanding of Bayesian Methods
## 4 Natural Language Processing
## 5 GANs
## 6 Online learning
## LanguageRecommendationFreeForm
## 1 don't know
## 2 C only
## 3 Javascript
## 4 Cache
## 5 Weka to get a feel for what the basics, then Python for the Bread and Butter analysis, and finally C/C++ for really advanced techniques and to understand what is going on under the hood.
## 6 VBA Excel
## JobSkillImportanceOtherSelect1FreeForm
## 1 Prior experience of working on data
## 2 Visibility via platforms like GitHub
## 3 Related Blog
## 4 Fluent in Algorithms
## 5 understand the data tool ecosystem
## 6 Analytical thinking
## JobSkillImportanceOtherSelect2FreeForm
## 1 Mathematics for Machine Learning
## 2 Machine Learning theory
## 3 Data Cleaning
## 4 Business acumen
## 5 SPSS
## 6 Reinforcement learning
## JobSkillImportanceOtherSelect3FreeForm PastJobTitlesFreeForm
## 1 Time series analysis Director of Engineering
## 2 Domain Management Consultant
## 3 communication skills Knowledge Management
## 4 Communication skills Accountant
## 5 Able to write own code Lecturer
## 6 Data Analytics concepts Developer
## WorkHardwareFreeForm
## 1 pc
## 2 Supercomputing Services at BIOS, Colombia
## 3 Acer basic laptop
## 4 Hadoop cluster
## 5 <NA>
## 6 Hadoop as a Service Infrastructure
## SalaryChangeFreeForm
## 1 Came from a different industry in another country, so not comparable
## 2 Again I am a graduate student
## 3 hard to say, we have a 30-40% inflation rate in Argentina
## 4 no salary
## 5 I changed disciplines recently and cannot make a fair comparison.
## 6 Currently a doctoral student
## TimeOtherSelectFreeForm
## 1 Personal Development
## 2 Constructing and maintaining experimental systems
## 3 Unrelated
## 4 Fighting production fires
## 5 Pen & Paper analysis
## 6 ManagementNow checking the job titles of the people who selected the “other” option from the job title form, and hence fall under the free form - CurrentJobTitleFreeForm:
CurrentJobTitleFreeForm_vect <- tolower(CurrentJobTitleFreeForm_vect)
CurrentJobTitleFreeForm_vect %>% as.factor() %>% levels()## [1] " "
## [2] " system analyst"
## [3] "academician"
## [4] "academics"
## [5] "account coordinator"
## [6] "accountant"
## [7] "actuarial analyst"
## [8] "actuarial analyst "
## [9] "actuary"
## [10] "actuary "
## [11] "administration"
## [12] "administrative assistant"
## [13] "administrative assistant "
## [14] "administrative hr"
## [15] "administrator"
## [16] "advanced analytics architect"
## [17] "advanced analytics manager"
## [18] "ai engineer"
## [19] "air navigation engineer"
## [20] "algorithm developer"
## [21] "algorithms engineer "
## [22] "all of the above"
## [23] "all of the above "
## [24] "americorp member"
## [25] "analysis engineer"
## [26] "analysis intern"
## [27] "analyst"
## [28] "analytical lead"
## [29] "analytics consultant"
## [30] "analytics developer"
## [31] "analytics engineer"
## [32] "analytics engineer "
## [33] "analytics head"
## [34] "analytics manager"
## [35] "analytics specialist"
## [36] "application architect"
## [37] "application engineer"
## [38] "applications consultant"
## [39] "applications developer "
## [40] "applied researcher"
## [41] "apprentice in big data engineering"
## [42] "architect"
## [43] "architect and architectural engineer"
## [44] "assistant instructional designer"
## [45] "assistant manager retail"
## [46] "assistant professor"
## [47] "assitant professor"
## [48] "associate consultant"
## [49] "associate professor"
## [50] "associate professor in statistics"
## [51] "associate provost"
## [52] "associate software developer"
## [53] "attorney"
## [54] "auditor"
## [55] "automation engineer"
## [56] "avp"
## [57] "bank employee"
## [58] "banker"
## [59] "banking operations"
## [60] "benefits consultant"
## [61] "bi"
## [62] "bi "
## [63] "bi analyst"
## [64] "bi analyst "
## [65] "bi consultant"
## [66] "bi developer"
## [67] "bi manager"
## [68] "bi specialist"
## [69] "bi/dw project manager"
## [70] "big data analytics lead "
## [71] "big data developer"
## [72] "big data engineer"
## [73] "big data support engineer"
## [74] "bioinformatician"
## [75] "bioinformatics engineer"
## [76] "broadcast engineer"
## [77] "budget analyst"
## [78] "business "
## [79] "business consultant"
## [80] "business developer"
## [81] "business development"
## [82] "business development "
## [83] "business development associate"
## [84] "business development manager"
## [85] "business development specialist"
## [86] "business improvement"
## [87] "business intelligence"
## [88] "business intelligence analyst"
## [89] "business intelligence analyst "
## [90] "business intelligence architect"
## [91] "business intelligence consultant"
## [92] "business intelligence developer"
## [93] "business intelligence project manager"
## [94] "business intelligence specialist"
## [95] "business intelligence, data integration analyst"
## [96] "business operations"
## [97] "business process analyst"
## [98] "buyer"
## [99] "cashier :/"
## [100] "cdo"
## [101] "ceo"
## [102] "cfo"
## [103] "chemical engineer"
## [104] "chief data officer"
## [105] "chief marketing officer"
## [106] "chief product officer"
## [107] "chief science officer"
## [108] "chro"
## [109] "client owner"
## [110] "clinical analyst"
## [111] "cloud computing "
## [112] "cloud computing engineer"
## [113] "cloud developer advocate"
## [114] "cloud engineer"
## [115] "co-op student- you should have student as an employment status too.."
## [116] "commercial executive (digital service)"
## [117] "commodity market analyst"
## [118] "communications/information office chief"
## [119] "company consultant"
## [120] "competitive analyst "
## [121] "computer scientist"
## [122] "computer systems analyst"
## [123] "computer vision"
## [124] "computer vision engineer"
## [125] "consultant"
## [126] "consultant-supply chain"
## [127] "consultant "
## [128] "consultant business intelligente & big data"
## [129] "consultant metier"
## [130] "consulting architect"
## [131] "content developer"
## [132] "continuous improvement "
## [133] "contract officer"
## [134] "controller"
## [135] "coo"
## [136] "cook and student"
## [137] "copywriter"
## [138] "corporate "
## [139] "cpa"
## [140] "creative coder"
## [141] "credit risk analyst"
## [142] "crm coordinator"
## [143] "cto"
## [144] "cto & engineer"
## [145] "cto for media group"
## [146] "curriculum developer"
## [147] "customer experience manager"
## [148] "customer insights analyst "
## [149] "customer service"
## [150] "customer service rep"
## [151] "cv researcher"
## [152] "data analyst"
## [153] "data analytics executive"
## [154] "data analytics manager"
## [155] "data architect"
## [156] "data architect "
## [157] "data associate"
## [158] "data conversion specialist"
## [159] "data designer"
## [160] "data developer"
## [161] "data engineer"
## [162] "data engineer - the position near data scientist and including strong software development skills"
## [163] "data executive"
## [164] "data journalism"
## [165] "data manager"
## [166] "data miner, data analyst, text miner, text analyst, text graphics"
## [167] "data operations"
## [168] "data processor"
## [169] "data project manager"
## [170] "data quality analyst"
## [171] "data quality engineer"
## [172] "data science instructor"
## [173] "data science intern"
## [174] "data science practice lead"
## [175] "data science professor"
## [176] "data science project manager"
## [177] "data science project manager, co-founder, consultant"
## [178] "data scientist"
## [179] "data scientist & project manager"
## [180] "data scientist manager"
## [181] "data scientist teacher"
## [182] "data scientist/analyst/machine learning analyst"
## [183] "data scientist/software developper"
## [184] "data services director"
## [185] "data strategist"
## [186] "data strategy"
## [187] "data supporter"
## [188] "data warehouse specialist"
## [189] "data warehousing and bi"
## [190] "database executive"
## [191] "database quality assurance engineer"
## [192] "dataops engineer"
## [193] "datascience manager"
## [194] "datawarehouse tester"
## [195] "datawarehousing etl"
## [196] "date engineer"
## [197] "dba"
## [198] "dealer/trader"
## [199] "debug technician "
## [200] "decision scientist"
## [201] "deep learning engineer"
## [202] "delivery driver"
## [203] "design and technical support"
## [204] "design coordinator"
## [205] "designer"
## [206] "develop software and hardware"
## [207] "developer evangelist "
## [208] "development manager"
## [209] "devops"
## [210] "digital analyst"
## [211] "digital marketer"
## [212] "digital marketing"
## [213] "digital marketing analyst"
## [214] "digital marketing consultant"
## [215] "digital strategist"
## [216] "digitalization manager"
## [217] "director"
## [218] "director "
## [219] "director - technology and analytics"
## [220] "director "
## [221] "director it"
## [222] "director modelling and research"
## [223] "director of analytics"
## [224] "director of manufacturing technology"
## [225] "director of ml"
## [226] "director of r&d group"
## [227] "director, digital collaboration "
## [228] "doctorate student"
## [229] "domain consultant"
## [230] "driver"
## [231] "dsp/hw/asic engineer"
## [232] "dwh administrator"
## [233] "e-commerce manager"
## [234] "ecommerce director"
## [235] "econometrician"
## [236] "economist"
## [237] "ecosystem research analyst"
## [238] "editor"
## [239] "educational"
## [240] "educator"
## [241] "electrical design engineer"
## [242] "employee in university"
## [243] "energy analyst"
## [244] "engg project manager"
## [245] "engineer"
## [246] "engineering analyst"
## [247] "engineering manager"
## [248] "engineering manager "
## [249] "engineering student"
## [250] "english teacher"
## [251] "enterpreneur, consultant"
## [252] "enterprise architect"
## [253] "entrepreneur"
## [254] "entrepreneur "
## [255] "entrepreneur in residence"
## [256] "essbase analyst"
## [257] "etl developer"
## [258] "etl specialist"
## [259] "exec vp "
## [260] "executive"
## [261] "executive tech management"
## [262] "factory worker"
## [263] "faculty"
## [264] "faculty / professor"
## [265] "faculty/researcher/machine learning"
## [266] "farmer"
## [267] "finance"
## [268] "finance director"
## [269] "finance manager"
## [270] "finance specialist"
## [271] "financial analyst"
## [272] "financial controller"
## [273] "financial data analyst"
## [274] "financial quant analyst"
## [275] "financial services"
## [276] "financial stability analyst"
## [277] "firmware"
## [278] "forex trader"
## [279] "founder"
## [280] "fp&a"
## [281] "fraud specialist"
## [282] "fund manager"
## [283] "general management"
## [284] "general medicine"
## [285] "geologist"
## [286] "gis"
## [287] "gis analyst"
## [288] "gis/stats"
## [289] "global insights & strategic planning lead"
## [290] "global leader - finance bi coe"
## [291] "government"
## [292] "graduate assistant"
## [293] "graduate student"
## [294] "graduate student "
## [295] "hadoop developer"
## [296] "hardware engineering"
## [297] "head of ai research"
## [298] "head of analytics"
## [299] "head of bi and ops"
## [300] "head of department"
## [301] "head of digital solutions"
## [302] "head of education"
## [303] "head of engineering"
## [304] "head of erp center of excellence"
## [305] "head of it"
## [306] "head of monitoring"
## [307] "head of unit "
## [308] "head product implementation "
## [309] "hpc"
## [310] "hse consultant"
## [311] "human resources "
## [312] "hybrid big data/data science engineer"
## [313] "hydrographic surveyor"
## [314] "i don't know"
## [315] "i.t lecturer "
## [316] "implementation consultant"
## [317] "industrial engineer"
## [318] "info security analyst "
## [319] "information architect"
## [320] "information management consultant"
## [321] "information security "
## [322] "information security analyst "
## [323] "information security architect "
## [324] "information technology "
## [325] "information: architect / designer / analyst"
## [326] "informations management"
## [327] "infrastructure specialist "
## [328] "innovation expert"
## [329] "innovation manager"
## [330] "insight analyst"
## [331] "instructor"
## [332] "instrumentation technician"
## [333] "integration specialist"
## [334] "intern - data analytics and machine learning"
## [335] "internal audit executive"
## [336] "internal auditor"
## [337] "investigator"
## [338] "investment analyst"
## [339] "investor and program manager"
## [340] "it's kind of ml-engineer/researcher/scientist combined "
## [341] "it-consultant"
## [342] "it analyst"
## [343] "it architect"
## [344] "it coordinator "
## [345] "it direcctor"
## [346] "it director"
## [347] "it helpdesk"
## [348] "it manager"
## [349] "it operations"
## [350] "it risk consulting supervisor"
## [351] "it security admin"
## [352] "it security consulant"
## [353] "it support analyst "
## [354] "itc consultant"
## [355] "jedi"
## [356] "junior strategist / data analyst"
## [357] "key account manager"
## [358] "knowledge manager"
## [359] "lab manager"
## [360] "labops"
## [361] "laboratory technician"
## [362] "land lord!"
## [363] "lead/rm/support analyst/data analyst for bfs"
## [364] "lecturer"
## [365] "lecturer "
## [366] "lecturer in computer science"
## [367] "linguist"
## [368] "logistics"
## [369] "logistics consultant"
## [370] "maintenance & support"
## [371] "maintenance specialist"
## [372] "maintenance supervisor "
## [373] "manage it"
## [374] "management accountant"
## [375] "management consultant"
## [376] "management consultant "
## [377] "manager"
## [378] "manager "
## [379] "manager - consulting"
## [380] "manager / team lead"
## [381] "manager in financial services"
## [382] "manager of splunk, a big data platform"
## [383] "manager, software development"
## [384] "managing consultant"
## [385] "managing data scientist"
## [386] "managing director"
## [387] "managing partner"
## [388] "managing the mess"
## [389] "manufacturing associate"
## [390] "manufacturing engineer"
## [391] "market analyst"
## [392] "market researcher"
## [393] "marketer"
## [394] "marketing"
## [395] "marketing analyst"
## [396] "marketing applications consultant"
## [397] "marketing manager"
## [398] "marketing professional"
## [399] "marketing research analyst"
## [400] "marketing researcher"
## [401] "material controller "
## [402] "math professor"
## [403] "math teacher"
## [404] "mathematician"
## [405] "mathematics educator"
## [406] "mathematics professor"
## [407] "mdm & data governance sme"
## [408] "mechanical design engineer"
## [409] "mechanical developer"
## [410] "mechanical engineer"
## [411] "media & education manager"
## [412] "media officer "
## [413] "medical director of analytics"
## [414] "medical resident / researcher"
## [415] "medical student researcher"
## [416] "metrologis, cmm programmer"
## [417] "military communications specialist"
## [418] "mis"
## [419] "mix of data scientist, data engineering, and product"
## [420] "ml product manager"
## [421] "mobile developer"
## [422] "model validation"
## [423] "monkey"
## [424] "mortgage closer"
## [425] "multi-purpose"
## [426] "network administrator"
## [427] "network engineer"
## [428] "network engineer & devops"
## [429] "network operations/analyst engineer"
## [430] "networking"
## [431] "networks engineer"
## [432] "none of them"
## [433] "not-related-with ds"
## [434] "nsf"
## [435] "ocr for personal projects"
## [436] "officer"
## [437] "online marketer"
## [438] "operation manager"
## [439] "operations analyst"
## [440] "operations manager"
## [441] "operations research analyst"
## [442] "operations supervisor "
## [443] "orthopedic surgical navigation support"
## [444] "owner"
## [445] "pasta maker"
## [446] "performance analyst"
## [447] "performance engineer "
## [448] "petrophysicist"
## [449] "pharmacy manager"
## [450] "phd"
## [451] "phd student"
## [452] "physician"
## [453] "pizza guy"
## [454] "pmo"
## [455] "polygraphy"
## [456] "portfolio manager"
## [457] "portfolio manager "
## [458] "pr manager"
## [459] "practice lead"
## [460] "presalesenineering"
## [461] "president"
## [462] "pricing actuary"
## [463] "pricing manager"
## [464] "process associate"
## [465] "procurement specialist"
## [466] "product consultant"
## [467] "product designer"
## [468] "product engineering manager"
## [469] "product manager"
## [470] "product manager "
## [471] "product marketing"
## [472] "product onder data"
## [473] "product owner"
## [474] "production support"
## [475] "professor"
## [476] "professor "
## [477] "professor / researcher"
## [478] "professor and researcher"
## [479] "professor of statistics "
## [480] "professor/researcher"
## [481] "program coordinator"
## [482] "program director"
## [483] "program manager"
## [484] "programme manager"
## [485] "programmer / researcher"
## [486] "project accountant"
## [487] "project coordinator"
## [488] "project engineer"
## [489] "project management "
## [490] "project manager"
## [491] "project techinician"
## [492] "projectmanager "
## [493] "psychologist"
## [494] "psychometrician"
## [495] "public health"
## [496] "public heath specialist"
## [497] "publich health veterinarian"
## [498] "purchase"
## [499] "qa"
## [500] "qa analyst"
## [501] "qa engineer"
## [502] "qa tester"
## [503] "qa, big data components tester"
## [504] "quality analyst"
## [505] "quality assurance"
## [506] "quality assurance engineer"
## [507] "quality assurance lead"
## [508] "quality assurance manager"
## [509] "quality assurance technician"
## [510] "quality engineer"
## [511] "quality manager"
## [512] "quality manager 3"
## [513] "quality performance helpdesk"
## [514] "quant"
## [515] "quant (quantitative analyst)"
## [516] "quant analyst"
## [517] "quantitative analyst"
## [518] "quantitative risk analyst"
## [519] "quantitative strategist"
## [520] "quants"
## [521] "r&d mathematician"
## [522] "r&d specialist"
## [523] "receptionist"
## [524] "report developer"
## [525] "report specialist"
## [526] "reporter"
## [527] "reporting analyst "
## [528] "reporting workstream lead"
## [529] "research analyst"
## [530] "research and development "
## [531] "research assistant"
## [532] "research associate"
## [533] "research engineer"
## [534] "research executive"
## [535] "research scholar"
## [536] "research student"
## [537] "researcher"
## [538] "researcher + manager = professor ;)"
## [539] "resident entrepreneur"
## [540] "retail"
## [541] "retail assistant"
## [542] "risk analyst"
## [543] "risk manager"
## [544] "risk specialist"
## [545] "sa"
## [546] "sales"
## [547] "sales and marketing"
## [548] "sales associate"
## [549] "sales engineer"
## [550] "sales executive"
## [551] "sales professional"
## [552] "sales rep"
## [553] "sales/business development exec"
## [554] "sales/marketing"
## [555] "sap end user"
## [556] "scientific account manager/field appllication scientist"
## [557] "secretary"
## [558] "security analyst"
## [559] "security consultant "
## [560] "security engineer"
## [561] "security guard"
## [562] "security guard/ data administrator "
## [563] "seed science"
## [564] "senior assistant"
## [565] "senior consultant"
## [566] "senior data engineer"
## [567] "senior data software engineer"
## [568] "senior manager"
## [569] "senior manager, analytics"
## [570] "senior product owner"
## [571] "senior project manager"
## [572] "seo"
## [573] "seo manager"
## [574] "seo specialist "
## [575] "service delivery manager"
## [576] "service engineer"
## [577] "service manager"
## [578] "services engineer "
## [579] "services manager"
## [580] "seta support"
## [581] "sharepoint/tfs administrator"
## [582] "site reliability engineer"
## [583] "six sigma black belt"
## [584] "small business"
## [585] "social media marketing manager"
## [586] "social work"
## [587] "social worker"
## [588] "software analyst"
## [589] "software architect"
## [590] "software architect "
## [591] "software development director"
## [592] "software engineer analytics"
## [593] "software engineering consultant"
## [594] "software engineering intern"
## [595] "software manager"
## [596] "software project manager"
## [597] "software support"
## [598] "software test automation engineer"
## [599] "software test engineer "
## [600] "software tester"
## [601] "software testing"
## [602] "software testing engineer"
## [603] "solution archetect"
## [604] "solution architect"
## [605] "solution architect "
## [606] "solution designer"
## [607] "solutions architect"
## [608] "solutions architect "
## [609] "solutions engineer"
## [610] "sound engineer"
## [611] "spatial data analyst"
## [612] "spreadsheet trainer and consultant"
## [613] "sr director, data science"
## [614] "sr manager"
## [615] "sr manager of software engineering"
## [616] "sr security manager"
## [617] "sr. dircetor"
## [618] "sr. quantitative analyst"
## [619] "sr. technical architect"
## [620] "sr.consultant"
## [621] "statistical analyst"
## [622] "storeman"
## [623] "strategy and corporate development"
## [624] "strategy director"
## [625] "strategy manager"
## [626] "structurer"
## [627] "student"
## [628] "student "
## [629] "student of psychology"
## [630] "student, ta"
## [631] "summer tech analyst "
## [632] "supervisor"
## [633] "supply chain"
## [634] "supply chain solution"
## [635] "support analyst"
## [636] "support engineer"
## [637] "sustainability analyst"
## [638] "svp data & ai"
## [639] "svp, analytics"
## [640] "sw manager "
## [641] "sysadmin"
## [642] "system admin"
## [643] "system administrator"
## [644] "system administrator and space marine"
## [645] "system analyst"
## [646] "system and data analyst"
## [647] "system architect"
## [648] "system designer project manager"
## [649] "system engineer"
## [650] "systems analyst"
## [651] "systems engineer"
## [652] "systems operator"
## [653] "systems specialist"
## [654] "teacher"
## [655] "teacher "
## [656] "teacher assistant cs department"
## [657] "teaching assistant"
## [658] "team lead"
## [659] "tech manager"
## [660] "tech support "
## [661] "technical architect"
## [662] "technical company ceo"
## [663] "technical consultant"
## [664] "technical lead"
## [665] "technical specialist"
## [666] "technical support"
## [667] "technical support analyst"
## [668] "technical support engineer"
## [669] "technical support engineer "
## [670] "technical trainer"
## [671] "technical writer"
## [672] "technician"
## [673] "technician-ag technology"
## [674] "technology architect "
## [675] "telecommunication"
## [676] "telemetry "
## [677] "temp work in a non data science field. i graduated back in may of 2016 and haven't been able to get hired in the data science field yet"
## [678] "territory advisor"
## [679] "test analyst"
## [680] "test engineer"
## [681] "test manager"
## [682] "tester"
## [683] "testing analyst"
## [684] "text miner"
## [685] "ti business analyst "
## [686] "trader"
## [687] "trader, risk manager"
## [688] "trainer"
## [689] "transfer pricing analyst"
## [690] "translator"
## [691] "truck driver"
## [692] "underwriter"
## [693] "vice president"
## [694] "vice president, data analytics trainings"
## [695] "vp of product engineering"
## [696] "vp of technology"
## [697] "web analyst"
## [698] "web designer"
## [699] "web designing"
## [700] "web developer"
## [701] "web rater"
## [702] "well master"
## [703] "worker "
## [704] "worker on a mathematical theory of knowledge"
## [705] "workforce analytics"### Data related jobs
sum(!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*business intelligence)|(\\w*bi)|(\\w*data)|(\\w*analyst)|(\\w*big data)|(\\w*dba)")))## [1] 230CurrentJobTitleFreeForm_vect[!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*business intelligence)|(\\w*bi)|(\\w*data)|(\\w*analyst)|(\\w*big data)|(\\w*dba)"))]## [1] "quantitative analyst"
## [2] "market analyst"
## [3] "quant (quantitative analyst)"
## [4] "data developer"
## [5] "marketing analyst"
## [6] "quantitative analyst"
## [7] "data architect"
## [8] "quantitative analyst"
## [9] "data analyst"
## [10] "digital marketing analyst"
## [11] "big data engineer"
## [12] "web analyst"
## [13] "marketing analyst"
## [14] "data engineer"
## [15] "data science practice lead"
## [16] "data architect "
## [17] "bioinformatics engineer"
## [18] "data engineer"
## [19] "data engineer - the position near data scientist and including strong software development skills"
## [20] "gis analyst"
## [21] "test analyst"
## [22] "data operations"
## [23] "data engineer"
## [24] "system analyst"
## [25] "datawarehouse tester"
## [26] "data quality analyst"
## [27] "quantitative analyst"
## [28] "operations analyst"
## [29] "testing analyst"
## [30] "senior data engineer"
## [31] "ecosystem research analyst"
## [32] "actuarial analyst"
## [33] "security analyst"
## [34] "big data developer"
## [35] "data architect"
## [36] "data engineer"
## [37] "data engineer"
## [38] "data engineer"
## [39] "financial quant analyst"
## [40] "business intelligence"
## [41] "data science professor"
## [42] "customer insights analyst "
## [43] "lead/rm/support analyst/data analyst for bfs"
## [44] "data journalism"
## [45] "engineering analyst"
## [46] "quantitative analyst"
## [47] "actuarial analyst"
## [48] "data science project manager, co-founder, consultant"
## [49] "bi developer"
## [50] "hybrid big data/data science engineer"
## [51] "bi"
## [52] "bi analyst"
## [53] "mdm & data governance sme"
## [54] "data associate"
## [55] "reporting analyst "
## [56] "data engineer"
## [57] "business intelligence analyst"
## [58] "database executive"
## [59] "temp work in a non data science field. i graduated back in may of 2016 and haven't been able to get hired in the data science field yet"
## [60] "bi manager"
## [61] "network operations/analyst engineer"
## [62] "business intelligence consultant"
## [63] "system analyst"
## [64] "data architect"
## [65] "information: architect / designer / analyst"
## [66] "clinical analyst"
## [67] "database quality assurance engineer"
## [68] "business intelligence consultant"
## [69] "quantitative analyst"
## [70] "data engineer"
## [71] "bioinformatician"
## [72] "quantitative analyst"
## [73] "data scientist/analyst/machine learning analyst"
## [74] "spatial data analyst"
## [75] "data architect"
## [76] "essbase analyst"
## [77] "credit risk analyst"
## [78] "financial analyst"
## [79] "test analyst"
## [80] "data warehousing and bi"
## [81] "business intelligence, data integration analyst"
## [82] "data conversion specialist"
## [83] "business intelligence architect"
## [84] "data engineer"
## [85] "quantitative analyst"
## [86] "insight analyst"
## [87] "managing data scientist"
## [88] "research analyst"
## [89] "support analyst"
## [90] "data manager"
## [91] "bioinformatician"
## [92] "financial analyst"
## [93] "bioinformatician"
## [94] "data architect"
## [95] "business intelligence developer"
## [96] "business intelligence analyst "
## [97] "data scientist manager"
## [98] "dba"
## [99] "quant analyst"
## [100] "mobile developer"
## [101] "big data analytics lead "
## [102] "vice president, data analytics trainings"
## [103] "bi "
## [104] "bi specialist"
## [105] "risk analyst"
## [106] "data architect"
## [107] "data engineer"
## [108] "computer systems analyst"
## [109] " system analyst"
## [110] "data strategist"
## [111] "competitive analyst "
## [112] "data warehouse specialist"
## [113] "performance analyst"
## [114] "chief data officer"
## [115] "data engineer"
## [116] "data engineer"
## [117] "consultant business intelligente & big data"
## [118] "ti business analyst "
## [119] "analyst"
## [120] "data miner, data analyst, text miner, text analyst, text graphics"
## [121] "data science intern"
## [122] "quality analyst"
## [123] "information security analyst "
## [124] "business intelligence developer"
## [125] "qa analyst"
## [126] "financial data analyst"
## [127] "data scientist"
## [128] "bioinformatician"
## [129] "head of bi and ops"
## [130] "data manager"
## [131] "data services director"
## [132] "analyst"
## [133] "qa, big data components tester"
## [134] "business intelligence"
## [135] "big data engineer"
## [136] "data strategy"
## [137] "site reliability engineer"
## [138] "systems analyst"
## [139] "chief data officer"
## [140] "data scientist/software developper"
## [141] "data science project manager"
## [142] "risk analyst"
## [143] "energy analyst"
## [144] "it analyst"
## [145] "data manager"
## [146] "data analytics executive"
## [147] "bioinformatician"
## [148] "senior data software engineer"
## [149] "business intelligence specialist"
## [150] "datawarehousing etl"
## [151] "sr director, data science"
## [152] "data scientist & project manager"
## [153] "data engineer"
## [154] "junior strategist / data analyst"
## [155] "data manager"
## [156] "data processor"
## [157] "data analytics manager"
## [158] "data architect"
## [159] "marketing analyst"
## [160] "bioinformatician"
## [161] "business intelligence consultant"
## [162] "budget analyst"
## [163] "quantitative analyst"
## [164] "operations research analyst"
## [165] "statistical analyst"
## [166] "mix of data scientist, data engineering, and product"
## [167] "system analyst"
## [168] "software analyst"
## [169] "test analyst"
## [170] "data scientist"
## [171] "actuarial analyst "
## [172] "bi consultant"
## [173] "data quality engineer"
## [174] "financial analyst"
## [175] "sustainability analyst"
## [176] "business intelligence analyst"
## [177] "data executive"
## [178] "it's kind of ml-engineer/researcher/scientist combined "
## [179] "data engineer"
## [180] "technical support analyst"
## [181] "data supporter"
## [182] "operations analyst"
## [183] "investment analyst"
## [184] "commodity market analyst"
## [185] "bi/dw project manager"
## [186] "data project manager"
## [187] "info security analyst "
## [188] "financial analyst"
## [189] "data scientist teacher"
## [190] "manager of splunk, a big data platform"
## [191] "transfer pricing analyst"
## [192] "it support analyst "
## [193] "big data support engineer"
## [194] "security guard/ data administrator "
## [195] "data architect"
## [196] "business intelligence"
## [197] "dataops engineer"
## [198] "quantitative risk analyst"
## [199] "financial stability analyst"
## [200] "business intelligence developer"
## [201] "web analyst"
## [202] "svp data & ai"
## [203] "data designer"
## [204] "apprentice in big data engineering"
## [205] "system and data analyst"
## [206] "test analyst"
## [207] "digital analyst"
## [208] "quantitative analyst"
## [209] "global leader - finance bi coe"
## [210] "datascience manager"
## [211] "data engineer"
## [212] "business intelligence developer"
## [213] "marketing research analyst"
## [214] "data science instructor"
## [215] "business intelligence project manager"
## [216] "bioinformatician"
## [217] "system analyst"
## [218] "site reliability engineer"
## [219] "intern - data analytics and machine learning"
## [220] "data engineer"
## [221] "summer tech analyst "
## [222] "data architect"
## [223] "research analyst"
## [224] "bi analyst "
## [225] "bi manager"
## [226] "bi consultant"
## [227] "sr. quantitative analyst"
## [228] "data analyst"
## [229] "business process analyst"
## [230] "product onder data"### software related jobs
sum(!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*application)|(\\w*computer)|(\\w*software)|(^it)")))## [1] 64CurrentJobTitleFreeForm_vect[!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*application)|(\\w*computer)|(\\w*software)|(^it)"))]## [1] "software architect"
## [2] "software testing"
## [3] "it manager"
## [4] "it operations"
## [5] "software architect"
## [6] "it coordinator "
## [7] "software tester"
## [8] "it direcctor"
## [9] "it-consultant"
## [10] "it security admin"
## [11] "data engineer - the position near data scientist and including strong software development skills"
## [12] "it director"
## [13] "computer scientist"
## [14] "software architect "
## [15] "software manager"
## [16] "software architect"
## [17] "it manager"
## [18] "software tester"
## [19] "marketing applications consultant"
## [20] "software architect"
## [21] "it helpdesk"
## [22] "application engineer"
## [23] "applications developer "
## [24] "it manager"
## [25] "applications consultant"
## [26] "it risk consulting supervisor"
## [27] "software architect"
## [28] "computer vision"
## [29] "software test engineer "
## [30] "it manager"
## [31] "sr manager of software engineering"
## [32] "software tester"
## [33] "it manager"
## [34] "it architect"
## [35] "develop software and hardware"
## [36] "application engineer"
## [37] "it security consulant"
## [38] "computer systems analyst"
## [39] "software support"
## [40] "software engineering consultant"
## [41] "software engineering intern"
## [42] "software development director"
## [43] "lecturer in computer science"
## [44] "data scientist/software developper"
## [45] "it analyst"
## [46] "senior data software engineer"
## [47] "software architect"
## [48] "software manager"
## [49] "manager, software development"
## [50] "software analyst"
## [51] "it manager"
## [52] "itc consultant"
## [53] "it's kind of ml-engineer/researcher/scientist combined "
## [54] "associate software developer"
## [55] "it support analyst "
## [56] "software architect"
## [57] "software architect"
## [58] "software test automation engineer"
## [59] "computer vision engineer"
## [60] "it manager"
## [61] "software engineer analytics"
## [62] "software project manager"
## [63] "application architect"
## [64] "software testing engineer"### leadership using data science
sum(!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*director)|(\\w*cto)|(\\w*ceo)|(\\w*cfo)|(\\w*chief)|(\\w*vp)|(\\w*head of)")))## [1] 92CurrentJobTitleFreeForm_vect[!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*director)|(\\w*cto)|(\\w*ceo)|(\\w*cfo)|(\\w*chief)|(\\w*vp)|(\\w*head of)"))]## [1] "head of engineering"
## [2] "cto"
## [3] "director of ml"
## [4] "it direcctor"
## [5] "director"
## [6] "director"
## [7] "exec vp "
## [8] "director "
## [9] "director of r&d group"
## [10] "cto"
## [11] "it director"
## [12] "cto for media group"
## [13] "director"
## [14] "ecommerce director"
## [15] "director "
## [16] "finance director"
## [17] "factory worker"
## [18] "head of analytics"
## [19] "chief product officer"
## [20] "vp of technology"
## [21] "cto"
## [22] "cto"
## [23] "cto"
## [24] "head of analytics"
## [25] "ceo"
## [26] "svp, analytics"
## [27] "cto"
## [28] "instructor"
## [29] "cto"
## [30] "avp"
## [31] "cto"
## [32] "doctorate student"
## [33] "head of education"
## [34] "director"
## [35] "cfo"
## [36] "strategy director"
## [37] "program director"
## [38] "technical company ceo"
## [39] "cto"
## [40] "cto"
## [41] "managing director"
## [42] "cto"
## [43] "ceo"
## [44] "director"
## [45] "director"
## [46] "instructor"
## [47] "chief data officer"
## [48] "ceo"
## [49] "head of it"
## [50] "director of manufacturing technology"
## [51] "software development director"
## [52] "head of bi and ops"
## [53] "instructor"
## [54] "data services director"
## [55] "head of erp center of excellence"
## [56] "chief data officer"
## [57] "head of monitoring"
## [58] "ceo"
## [59] "director"
## [60] "vp of product engineering"
## [61] "sr director, data science"
## [62] "finance director"
## [63] "cto"
## [64] "cto"
## [65] "communications/information office chief"
## [66] "ceo"
## [67] "director of analytics"
## [68] "director it"
## [69] "cto"
## [70] "chief marketing officer"
## [71] "medical director of analytics"
## [72] "head of digital solutions"
## [73] "cto"
## [74] "director modelling and research"
## [75] "cto"
## [76] "head of ai research"
## [77] "chief science officer"
## [78] "ceo"
## [79] "cto"
## [80] "ceo"
## [81] "svp data & ai"
## [82] "head of unit "
## [83] "head of department"
## [84] "instructor"
## [85] "director"
## [86] "cto"
## [87] "data science instructor"
## [88] "cto & engineer"
## [89] "managing director"
## [90] "director - technology and analytics"
## [91] "director, digital collaboration "
## [92] "director"### Teching / Education
sum(!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*professor)|(\\w*teach)|(\\w*educat)|(\\w*faculty)")))## [1] 81CurrentJobTitleFreeForm_vect[!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*professor)|(\\w*teach)|(\\w*educat)|(\\w*faculty)"))]## [1] "teacher"
## [2] "professor"
## [3] "assistant professor"
## [4] "teacher"
## [5] "professor "
## [6] "teaching assistant"
## [7] "researcher + manager = professor ;)"
## [8] "teacher "
## [9] "teacher"
## [10] "math professor"
## [11] "teacher"
## [12] "professor and researcher"
## [13] "professor"
## [14] "professor"
## [15] "professor"
## [16] "educator"
## [17] "assistant professor"
## [18] "professor"
## [19] "data science professor"
## [20] "professor/researcher"
## [21] "professor"
## [22] "professor "
## [23] "teacher"
## [24] "media & education manager"
## [25] "teacher"
## [26] "teacher"
## [27] "professor"
## [28] "associate professor"
## [29] "head of education"
## [30] "faculty / professor"
## [31] "professor"
## [32] "professor"
## [33] "teacher"
## [34] "professor"
## [35] "professor"
## [36] "faculty"
## [37] "teacher"
## [38] "faculty"
## [39] "professor/researcher"
## [40] "assistant professor"
## [41] "professor"
## [42] "teacher"
## [43] "mathematics professor"
## [44] "professor"
## [45] "professor"
## [46] "professor"
## [47] "teacher"
## [48] "english teacher"
## [49] "math professor"
## [50] "teacher"
## [51] "teacher"
## [52] "associate professor"
## [53] "professor"
## [54] "assistant professor"
## [55] "teacher"
## [56] "mathematics educator"
## [57] "faculty/researcher/machine learning"
## [58] "math teacher"
## [59] "teacher assistant cs department"
## [60] "teacher"
## [61] "teacher"
## [62] "teacher"
## [63] "professor"
## [64] "professor of statistics "
## [65] "teacher"
## [66] "teacher"
## [67] "data scientist teacher"
## [68] "professor"
## [69] "professor / researcher"
## [70] "professor"
## [71] "professor"
## [72] "associate professor in statistics"
## [73] "professor"
## [74] "associate professor"
## [75] "professor"
## [76] "professor"
## [77] "professor"
## [78] "professor"
## [79] "assistant professor"
## [80] "assitant professor"
## [81] "educational"### Student
sum(!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*student)")))## [1] 26CurrentJobTitleFreeForm_vect[!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*student)"))]## [1] "engineering student"
## [2] "cook and student"
## [3] "student"
## [4] "student"
## [5] "phd student"
## [6] "student"
## [7] "doctorate student"
## [8] "phd student"
## [9] "medical student researcher"
## [10] "phd student"
## [11] "student of psychology"
## [12] "co-op student- you should have student as an employment status too.."
## [13] "student"
## [14] "graduate student "
## [15] "student"
## [16] "graduate student"
## [17] "student"
## [18] "phd student"
## [19] "student "
## [20] "student"
## [21] "phd student"
## [22] "graduate student"
## [23] "student"
## [24] "student"
## [25] "student, ta"
## [26] "research student"### Finance related
sum(!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*financ)")))## [1] 18CurrentJobTitleFreeForm_vect[!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*financ)"))]## [1] "finance manager" "finance director"
## [3] "financial quant analyst" "financial controller"
## [5] "finance" "manager in financial services"
## [7] "finance" "financial analyst"
## [9] "financial analyst" "finance manager"
## [11] "financial data analyst" "finance director"
## [13] "financial services" "financial analyst"
## [15] "financial analyst" "financial stability analyst"
## [17] "global leader - finance bi coe" "finance specialist"### Quant / maths related
sum(!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*quant)|(\\w*math)")))## [1] 28CurrentJobTitleFreeForm_vect[!is.na(str_extract(CurrentJobTitleFreeForm_vect, "(\\w*quant)|(\\w*math)"))]## [1] "quantitative analyst"
## [2] "quant (quantitative analyst)"
## [3] "quantitative analyst"
## [4] "quantitative analyst"
## [5] "math professor"
## [6] "mathematician"
## [7] "quantitative analyst"
## [8] "financial quant analyst"
## [9] "worker on a mathematical theory of knowledge"
## [10] "quantitative analyst"
## [11] "quantitative analyst"
## [12] "quantitative analyst"
## [13] "quantitative analyst"
## [14] "r&d mathematician"
## [15] "quant analyst"
## [16] "quantitative strategist"
## [17] "mathematics professor"
## [18] "math professor"
## [19] "quant"
## [20] "mathematics educator"
## [21] "math teacher"
## [22] "quantitative analyst"
## [23] "quants"
## [24] "quantitative risk analyst"
## [25] "quant"
## [26] "quantitative analyst"
## [27] "sr. quantitative analyst"
## [28] "mathematician"So, that clearly shows that the other job title selected in the survey falls mainly under below 7 categories:
Data Related jobs (like data engineer, data analytics, etc.)
Software related jobs
Executive or Top leadership positions in any organization / Institution (like ceo, cfo, head of engineering, etc.)
Teaching / Education
Student
Finance related job profiles
Quantitative or Maths related job profiles