In f0nzie/petroleum.ml: Machine Learning Applications in Machine Learning

library(petro.One)


major <- c("machine learning")
minor <- c("reservoir", "production", "logging", "completion", "intervention",
           "drilling", "geology", "seismic", "petrophysics", "geophysics", 
           "economics")
lesser <- c("data", "algorithm")

prod.df <- join_keywords(major, minor, lesser, get_papers = TRUE, sleep = 4)
prod.df

library(ggplot2)
library(dplyr)

keywords <- prod.df$keywords    # get the keywords from the list

# data only
keywords %>%
    filter(Var3 == "data") %>%
    ggplot(aes(x=reorder(Var2, paper_count), y=paper_count)) +
   coord_flip()+
geom_bar(stat="identity")

# algorithm only
keywords %>%
    filter(Var3 == "algorithm") %>%
    ggplot(aes(x=reorder(Var2, paper_count), y=paper_count)) +
   coord_flip()+
    geom_bar(stat="identity")

plotting using `magrittr

library(magrittr)
library(dplyr)

keywords.1 <- prod.df %>% 
    # extract2("keywords") %>%
    `[[`("keywords") %>%
    filter(Var3 == "data")

keywords.1 %>%
    ggplot(aes(x=reorder(Var2, paper_count), y=paper_count)) +
    coord_flip()+
    geom_bar(stat="identity")

keywords.2 <- prod.df %>% 
    # extract2("keywords") %>%
    `[[`("keywords") %>%
    filter(Var3 == "algorithm")

keywords.2 %>%
    ggplot(aes(x=reorder(Var2, paper_count), y=paper_count)) +
    coord_flip()+
    geom_bar(stat="identity")

replace well construction1 by drilling

# replace `well construction`1 by `drilling`
keywords.2 <- prod.df %>% 
    # extract2("keywords") %>%
    `[[`("keywords") %>%
    filter(Var3 == "algorithm") %>%
    mutate(paper_count = ifelse(Var2 == "well construction",, paper_count))
    # mutate(Var2 = ifelse(Var2 == "well construction", "drilling", Var2))

keywords.2 %>%
    ggplot(aes(x = reorder(Var2, paper_count), y=paper_count)) +
    coord_flip()+
    geom_bar(stat="identity")

library(petro.One)


major <- c("machine learning")
discipline <- c("reservoir", "production", "logging", "completion", "intervention",
           "drilling", "geology", "seismic", "petrophysics", "geophysics", 
           "economics")
learning <- c("supervised learning", "unsupervised learning")

by.learning <- join_keywords(major, discipline, learning, get_papers = TRUE, sleep = 3)

library(petro.One)


major <- c("machine learning")
discipline <- c("reservoir", "production", "logging", "completion", "intervention",
           "drilling", "geology", "seismic", "petrophysics", "geophysics", 
           "economics")
learning <- c("supervised learning", "unsupervised learning")

tech_class <- c("clustering", "classification", "regression")

by.learning <- join_keywords(major, discipline, learning, tech_class,
                             get_papers = TRUE, sleep = 3)

by reference in papers: ML techniques

library(petro.One)


major <- c("machine learning")
minor <- c("reservoir", "production", "logging", "completion", "intervention",
           "drilling", "geology", "seismic", "petrophysics", "geophysics", 
           "economics")

ml_technique <- c("SVM", "Support Vector Machine",  "Genetic algorithm", "neural network", 
                  "fuzzy logic", "decision tree", "k-means", "boosting", 
                  "deep learning", "PCA", "principal component analysis",
                  "logistic regression", "kernel density estimation", 
                  "nearest neighbors", "reinforcement learning")

by.ml_technique <- join_keywords(major, minor, ml_technique, get_papers = TRUE, sleep = 3)
by.ml_technique

SVM = Support Vector Machine

Replace the long-SVM by SVM

var3.str.1 <- "SVM"
var3.str.2 <- "Support Vector Machine"

not.svm.only <- by.ml_technique %>%
    `[[`("keywords") %>%
    select(Var1, Var2, Var3, paper_count) %>% 
    filter(Var3 != var3.str.1 & Var3 != var3.str.2) %>% 
    as.data.frame() %>% 
    print

var3.str.1 <- "SVM"
var3.str.2 <- "Support Vector Machine"

svm.only <- by.ml_technique %>%
    `[[`("keywords") %>%
    select(Var1, Var2, Var3, paper_count) %>% 
    filter(Var3 == var3.str.1 | Var3 == var3.str.2) %>% 
    mutate(Var3 = ifelse(Var3 == var3.str.2, var3.str.1, Var3)) %>% 
    group_by(Var1, Var2, Var3) %>% 
    summarize(paper_count = sum(paper_count)) %>% 
    as.data.frame() %>% 
    print

# binding both dataframes
keywords.new <- rbind(not.svm.only, svm.only)
keywords.new

PCA

var3.str.1 <- "PCA"
var3.str.2 <- "principal component analysis"

not.pca.only <- keywords.new %>%
    select(Var1, Var2, Var3, paper_count) %>% 
    filter(Var3 != var3.str.1 & Var3 != var3.str.2) %>%
    as.data.frame() %>% 
    print

var3.str.1 <- "PCA"
var3.str.2 <- "principal component analysis"

pca.only <- keywords.new %>%
    select(Var1, Var2, Var3, paper_count) %>% 
    filter(Var3 == var3.str.1 | Var3 == var3.str.2) %>% 
    mutate(Var3 = ifelse(Var3 == var3.str.2, var3.str.1, Var3)) %>% 
    group_by(Var1, Var2, Var3) %>% 
    summarize(paper_count = sum(paper_count)) %>% 
    as.data.frame() %>% 
    print

keywords.new.2 <- rbind(not.pca.only, pca.only)
keywords.new.2

add new ML techniques

• naive bayes
• "GPR", " Gaussian Processes Regression",
• "gaussian mixture", "hidden markov"
• "deep learning", "convolutional network", "Boltzman machine",

library(petro.One)


major <- c("machine learning")
minor <- c("reservoir", "production", "logging", "completion", "intervention", "workover",
           "drilling", "geology", "seismic", "petrophysics", "geophysics", 
           "economics", "surface facilities")

ml_technique.2 <- c("SVM", "Support Vector Machine", "discriminant analysis", 
                    "logistic regression",
                    "naive bayes", "nearest neighbor",
                     "linear regression", "SVR", "Support Vector Regressor", 
                    "GPR", " Gaussian Processes Regression",
                    "decision tree", "neural network", "neural nets",  
                     "k-means", "c-means", "hierarchical", "gaussian mixture", "hidden markov",

                    "deep learning", "convolutional network", "Boltzman machine",

                   "Genetic algorithm", "fuzzy logic", "boosting", 
                  "PCA", "principal component analysis",
                  "kernel density estimation", 
                   "reinforcement learning")

by.ml_technique.2 <- join_keywords(major, minor, ml_technique.2, get_papers = TRUE, sleep = 3)
by.ml_technique.2

save(by.ml_technique.2, file = "ml_technique_2.rda")  # just in case

# load(file = "ml_technique_2.rda") 
load("R:/github-oilgains/petro.One/ml_technique_2.rda")

by.ml_technique.2$keywords

library(dplyr)

var3.str.1 <- "SVM"
var3.str.2 <- "Support Vector Machine"

not.svm.only <- by.ml_technique.2 %>%
    `[[`("keywords") %>%
    select(Var1, Var2, Var3, paper_count) %>% 
    filter(Var3 != var3.str.1 & Var3 != var3.str.2) %>% 
    as.data.frame() %>% 
    print

var3.str.1 <- "SVM"
var3.str.2 <- "Support Vector Machine"

svm.only <- by.ml_technique.2 %>%
    `[[`("keywords") %>%
    select(Var1, Var2, Var3, paper_count) %>% 
    filter(Var3 == var3.str.1 | Var3 == var3.str.2) %>% 
    mutate(Var3 = ifelse(Var3 == var3.str.2, var3.str.1, Var3)) %>% 
    group_by(Var1, Var2, Var3) %>% 
    summarize(paper_count = sum(paper_count)) %>% 
    as.data.frame() %>% 
    print

# binding both dataframes
keywords.new <- rbind(not.svm.only, svm.only)
keywords.new

var3.str.1 <- "PCA"
var3.str.2 <- "principal component analysis"

not.pca.only <- keywords.new %>%
    select(Var1, Var2, Var3, paper_count) %>% 
    filter(Var3 != var3.str.1 & Var3 != var3.str.2) %>%
    as.data.frame() %>% 
    print


pca.only <- keywords.new %>%
    select(Var1, Var2, Var3, paper_count) %>% 
    filter(Var3 == var3.str.1 | Var3 == var3.str.2) %>% 
    mutate(Var3 = ifelse(Var3 == var3.str.2, var3.str.1, Var3)) %>% 
    group_by(Var1, Var2, Var3) %>% 
    summarize(paper_count = sum(paper_count)) %>% 
    as.data.frame() %>% 
    print

keywords.new.2 <- rbind(not.pca.only, pca.only)
keywords.new.2

var3.str.1 <- "neural network"
var3.str.2 <- "neural nets"

not.nnet.only <- keywords.new.2 %>%
    select(Var1, Var2, Var3, paper_count) %>% 
    filter(Var3 != var3.str.1 & Var3 != var3.str.2) %>%
    as.data.frame() %>% 
    print


nnet.only <- keywords.new.2 %>%
    select(Var1, Var2, Var3, paper_count) %>% 
    filter(Var3 == var3.str.1 | Var3 == var3.str.2) %>% 
    mutate(Var3 = ifelse(Var3 == var3.str.2, var3.str.1, Var3)) %>% 
    group_by(Var1, Var2, Var3) %>% 
    summarize(paper_count = sum(paper_count)) %>% 
    as.data.frame() %>% 
    print

keywords.new.3 <- rbind(not.nnet.only, nnet.only)
keywords.new.3

library(petro.One)


major <- c("machine learning")
minor <- c("reservoir", "production", "logging", "completion", "intervention", "workover",
           "drilling", "geology", "seismic", "petrophysics", "geophysics", 
           "economics", "surface facilities")

ml_technique.3 <- c("SVR", "Support Vector Regression", 
                    "GPR", " Gaussian Process Regression"
                  )

by.ml_technique.3 <- join_keywords(major, minor, ml_technique.3, get_papers = TRUE, sleep = 3)
by.ml_technique.3

# save(by.ml_technique.2, file = "ml_technique_2.rda")  # just in case

ML techniques organized by supervised and unspervised

library(petro.One)


major <- c("machine learning")
minor <- c("reservoir", "production", "surface facilities", "metering",
           "logging", 
           "completion", "intervention", "workover", "drilling", 
           "geology", "petrophysics", "geophysics", "seismic",
           "economics")

ml_technique.4 <- c("boosting", 
                    "discriminant analysis", 
                    "kernel approximation",
                    "genetic algorithm",
                    "SVM", "Support Vector Machine", 
                    "nearest neighbor", "k-nearest neighbor",
                    "deep learning", 
                    "convolutional network", "convolutional neural",
                    "kernel density estimation",
                    "naive bayes", 
                    "logistic regression",
                    "neural network", "neural nets", 
                    "decision tree",
                    "Gradient Boosting Tree",
                    "linear regression", 
                    "random forest",
                    "GPR", " Gaussian Process Regression",

                    "PCA", "principal component analysis",
                    "SVD", "Singular Value Decomposition",
                    "c-means", "fuzzy c-means",
                     "k-means",  
                    "gaussian mixture", "gaussian mixture model",

                    "reinforcement learning",
                    "hierarchical", "hierarchical clustering",

                    "fuzzy logic", 
                    "hidden markov",

                    "SVR", "Support Vector Regression"
                   )

by.ml_technique.4 <- join_keywords(major, minor, ml_technique.4, get_papers = TRUE, sleep = 3)
by.ml_technique.4

save(by.ml_technique.4, file = "ml_technique_4.rda")  # just in case

write.csv(by.ml_technique.4, file = "ml_technique_4.csv")  # just in case

ml.keywords.4 <- by.ml_technique.4$keywords
ml.papers.4 <- by.ml_technique.4$papers

f0nzie/petroleum.ml documentation built on May 12, 2019, 6:22 p.m.