notebook.community

Edit and run 





In [1]:



    


source("loadData.R")

# load and clean the data
raw <- loadData()

"Raw data:"
format(head(raw,3), digits=3)

clean <- cleanData(raw)

"Cleaned data:"
format(head(clean,3), digits=3)

dataPrime <- data.frame()
wells <- unique(clean$Well.Name)

for (well_i in wells) {
    data_i <- clean[clean$Well.Name == well_i,]
    
    data_i$GR <- (data_i$GR - mean(data_i$GR, na.rm=T)) / sd(data_i$GR, na.rm=T)
    data_i$ILD_log10 <- (data_i$ILD_log10 - mean(data_i$ILD_log10, na.rm=T)) / sd(data_i$ILD_log10, na.rm=T)
    data_i$DeltaPHI <- (data_i$DeltaPHI - mean(data_i$DeltaPHI, na.rm=T)) / sd(data_i$DeltaPHI, na.rm=T)
    data_i$PHIND <- (data_i$PHIND - mean(data_i$PHIND, na.rm=T)) / sd(data_i$PHIND, na.rm=T)
    data_i$PE <- (data_i$PE - mean(data_i$PE, na.rm=T)) / sd(data_i$PE, na.rm=T)
    
    dataPrime <- rbind(dataPrime, data_i)
}

cs <- dataPrime
rm(dataPrime)

"Centered and scaled data:"
format(head(cs,3), digits=3)



    


















    






'Raw data:'









    









FaciesFormationWell.NameDepthGRILD_log10DeltaPHIPHINDPENM_MRELPOS


	
3        A1 SH    SHRIMPLIN2793     77.5     0.664     9.9     11.9     4.6      1        1.000    

	
3        A1 SH    SHRIMPLIN2794     78.3     0.661    14.2     12.6     4.1      1        0.979    

	
3        A1 SH    SHRIMPLIN2794     79.0     0.658    14.8     13.1     3.6      1        0.957    














    






'Cleaned data:'









    









FaciesFormationWell.NameDepthGRILD_log10DeltaPHIPHINDPEisMarineRELPOS


	
FSiS     A1 SH    SHRIMPLIN2793     77.5     0.664     9.9     11.9     4.6      FALSE    1.000    

	
FSiS     A1 SH    SHRIMPLIN2794     78.3     0.661    14.2     12.6     4.1      FALSE    0.979    

	
FSiS     A1 SH    SHRIMPLIN2794     79.0     0.658    14.8     13.1     3.6      FALSE    0.957    














    






'Centered and scaled data:'









    









FaciesFormationWell.NameDepthGRILD_log10DeltaPHIPHINDPEisMarineRELPOS


	
FSiS     A1 SH    SHRIMPLIN2793     0.216     0.01855 0.512    -0.0487   0.421   FALSE    1.000    

	
FSiS     A1 SH    SHRIMPLIN2794     0.237     0.00567 1.517     0.0736  -0.133   FALSE    0.979    

	
FSiS     A1 SH    SHRIMPLIN2794     0.258    -0.00721 1.657     0.1648  -0.687   FALSE    0.957    





















In [2]:



    


source("preProcData.R")

paste("# columns before forward, backward, and central difference feature-building:", ncol(cs))

lag <- lagData(cs, 30)

paste("# columns after lag feature-building:", ncol(lag))
format(head(lag,3), digits=3)



    


















    






'# columns before forward, backward, and central difference feature-building: 11'









    






'# columns after lag feature-building: 191'









    









FaciesFormationWell.NameDepthRELPOSGR_n15ILD_log10_n15DeltaPHI_n15PHIND_n15isMarine_n15...DeltaPHI_14PHIND_14isMarine_14PE_14GR_15ILD_log10_15DeltaPHI_15PHIND_15isMarine_15PE_15


	
FSiS     A1 SH    SHRIMPLIN2793     1.000     0.23435 -0.827   0.956    -0.0487  FALSE    ...      1.540    -0.0487  FALSE     0.421   0.234    -0.827   0.956    -0.0487  FALSE     0.421   

	
FSiS     A1 SH    SHRIMPLIN2794     0.979    -0.00292 -0.952   0.419     0.0736  FALSE    ...      1.307     0.0736  FALSE    -0.133   0.555    -0.604   1.540     0.0736  FALSE    -0.133   

	
FSiS     A1 SH    SHRIMPLIN2794     0.957    -0.15735 -1.038   0.255     0.1648  FALSE    ...      0.839     0.1648  FALSE    -0.687   0.376    -0.527   1.307     0.1648  FALSE    -0.687

Training functions





In [89]:



    


source("trainingFunctions.R")

buildBlendedModel <- function(train, test, p=.25, recruit_wgt=.5) {
    blendedModel <- list()

    test_wells <- unique(test$Well.Name)
    
    # build a blended model for each well in the test data
    for (well_i in test_wells) {
        test_i <- test[test$Well.Name == well_i,]
        test_iso <- max(test$Depth) - min(test$Depth)
        
        # if test well has no PE log - remove PE features from training data
        if (sum(is.na(test_i$PE_0)) > 0) {
            train_i <- subset(train, select=-c(PE_n15, PE_n14, PE_n13, PE_n12, PE_n11, PE_n10, PE_n9, PE_n8, PE_n7, PE_n6, PE_n5,
                                      PE_n4, PE_n3, PE_n2, PE_n1, PE_0, PE_1, PE_2, PE_3, PE_4, PE_5, PE_6, PE_7, PE_8,
                                      PE_9, PE_10, PE_11, PE_12, PE_13, PE_14, PE_15))
        } else {
            train_i <- train
        }
        
        # train and weight models
        blendedModel[[well_i]][["fits"]] <- trainBlendedModel(train_i)
        blendedModel[[well_i]][["weights"]] <- weightBlendedModel(train_i, test_iso, p, recruit_wgt)
    }
    
    blendedModel
}

Evaluation functions





In [90]:



    


source("evaluationFunctions.R")

predictBlendedModel <- function(test, 
                                blendedModel, 
                                classes=c("SS", "CSiS", "FSiS", "SiSh", "MS", "WS", "D", "PS", "BS")
                               ) {
    
    testPrime <- data.frame()
    
    test_wells <- unique(test$Well.Name)
    
    for (well_i in test_wells) {
        test_i <- test[test$Well.Name == well_i,]
        votes <- tallyVotes(test_i, blendedModel[[well_i]], classes)
        test_i$Predicted <- electClass(test_i, votes)
        
        testPrime <- rbind(testPrime, test_i)
    }
    
    testPrime
}

Tuning blending parameters





In [ ]:



    


source("accuracyMetrics.R")
options(warn=-1)

t0 <- Sys.time()

train <- lag[lag$Well.Name != "SHRIMPLIN" & lag$Well.Name != "CHURCHMAN BIBLE",]
test <- lag[lag$Well.Name == "SHRIMPLIN" | lag$Well.Name == "CHURCHMAN BIBLE",]

ps <- c(.5)
rws <- c(.5)

for (p in ps) {
    for (rw in rws) {
        blendedModel <- buildBlendedModel(train, test, p, rw)
        testPrime <- predictBlendedModel(test, blendedModel)
        f1 <- myF1Metric(testPrime$Predicted, testPrime$Facies)
        
        print(paste("inv dist parameter p:", p, ", recruit weight:", rw, ", f1-score", round(f1,4)))
        print("-------------")
    }
}

tn <- Sys.time()
print(tn-t0)



    


















    






Loading required package: randomForest
randomForest 4.6-12
Type rfNews() to see new features/changes/bug fixes.

Attaching package: 'randomForest'

The following object is masked from 'package:ggplot2':

    margin

Cross-validation





In [20]:



    


source("accuracyMetrics.R")

t0 <- Sys.time()

f1 <- NULL

wells <- unique(lag$Well.Name)
wells <- wells[!wells %in% "Recruit F9"]

for (i in 1:(length(wells)-1)) {
    for (j in (i+1):length(wells)) {
        trainIndex <- lag$Well.Name != wells[i] & lag$Well.Name != wells[j]
        train <- lag[trainIndex,]
        test <- lag[!trainIndex,]

        blendedModel <- buildBlendedModel(train, test)
        testPrime <- predictBlendedModel(test, blendedModel)
        
        f1_i <- myF1Metric(testPrime$Predicted, testPrime$Facies)
        f1 <- c(f1, f1_i)
        
        print(paste("Test well 1:", wells[i], ", Test well 2:", wells[j], ", f1-score:", f1_i))
        print("-------------")
    }
}

print(paste("Minimum F1:", min(f1)))
print(paste("Average F1:", mean(f1)))
print(paste("Maximum F1:", max(f1)))

tn <- Sys.time()
print(tn-t0)



    


















    






[1] "Test well 1: SHRIMPLIN , Test well 2: ALEXANDER D , f1-score: 0.644444444444444"
[1] "-------------"
[1] "Test well 1: SHRIMPLIN , Test well 2: SHANKLE , f1-score: 0.616783216783217"
[1] "-------------"
[1] "Test well 1: SHRIMPLIN , Test well 2: LUKE G U , f1-score: 0.603351955307263"
[1] "-------------"
[1] "Test well 1: SHRIMPLIN , Test well 2: KIMZEY A , f1-score: 0.678474114441417"
[1] "-------------"
[1] "Test well 1: SHRIMPLIN , Test well 2: CROSS H CATTLE , f1-score: 0.674715909090909"
[1] "-------------"
[1] "Test well 1: SHRIMPLIN , Test well 2: NOLAN , f1-score: 0.573226544622426"
[1] "-------------"
[1] "Test well 1: SHRIMPLIN , Test well 2: NEWBY , f1-score: 0.520763187429854"
[1] "-------------"
[1] "Test well 1: SHRIMPLIN , Test well 2: CHURCHMAN BIBLE , f1-score: 0.63001485884101"
[1] "-------------"
[1] "Test well 1: ALEXANDER D , Test well 2: SHANKLE , f1-score: 0.625"
[1] "-------------"
[1] "Test well 1: ALEXANDER D , Test well 2: LUKE G U , f1-score: 0.653498871331828"
[1] "-------------"
[1] "Test well 1: ALEXANDER D , Test well 2: KIMZEY A , f1-score: 0.56447963800905"
[1] "-------------"
[1] "Test well 1: ALEXANDER D , Test well 2: CROSS H CATTLE , f1-score: 0.646666666666667"
[1] "-------------"
[1] "Test well 1: ALEXANDER D , Test well 2: NOLAN , f1-score: 0.579908675799087"
[1] "-------------"
[1] "Test well 1: ALEXANDER D , Test well 2: NEWBY , f1-score: 0.57558790593505"
[1] "-------------"
[1] "Test well 1: ALEXANDER D , Test well 2: CHURCHMAN BIBLE , f1-score: 0.599201065246338"
[1] "-------------"
[1] "Test well 1: SHANKLE , Test well 2: LUKE G U , f1-score: 0.605504587155963"
[1] "-------------"
[1] "Test well 1: SHANKLE , Test well 2: KIMZEY A , f1-score: 0.638680659670165"
[1] "-------------"
[1] "Test well 1: SHANKLE , Test well 2: CROSS H CATTLE , f1-score: 0.627300613496933"
[1] "-------------"
[1] "Test well 1: SHANKLE , Test well 2: NOLAN , f1-score: 0.646808510638298"
[1] "-------------"
[1] "Test well 1: SHANKLE , Test well 2: NEWBY , f1-score: 0.540939597315436"
[1] "-------------"
[1] "Test well 1: SHANKLE , Test well 2: CHURCHMAN BIBLE , f1-score: 0.579207920792079"
[1] "-------------"
[1] "Test well 1: LUKE G U , Test well 2: KIMZEY A , f1-score: 0.650190114068441"
[1] "-------------"
[1] "Test well 1: LUKE G U , Test well 2: CROSS H CATTLE , f1-score: 0.648337595907928"
[1] "-------------"
[1] "Test well 1: LUKE G U , Test well 2: NOLAN , f1-score: 0.626146788990826"
[1] "-------------"
[1] "Test well 1: LUKE G U , Test well 2: NEWBY , f1-score: 0.546472564389698"
[1] "-------------"
[1] "Test well 1: LUKE G U , Test well 2: CHURCHMAN BIBLE , f1-score: 0.617198335644938"
[1] "-------------"
[1] "Test well 1: KIMZEY A , Test well 2: CROSS H CATTLE , f1-score: 0.6289592760181"
[1] "-------------"
[1] "Test well 1: KIMZEY A , Test well 2: NOLAN , f1-score: 0.632152588555858"
[1] "-------------"
[1] "Test well 1: KIMZEY A , Test well 2: NEWBY , f1-score: 0.539181286549708"
[1] "-------------"
[1] "Test well 1: KIMZEY A , Test well 2: CHURCHMAN BIBLE , f1-score: 0.6256"
[1] "-------------"
[1] "Test well 1: CROSS H CATTLE , Test well 2: NOLAN , f1-score: 0.61119293078056"
[1] "-------------"
[1] "Test well 1: CROSS H CATTLE , Test well 2: NEWBY , f1-score: 0.610570236439499"
[1] "-------------"
[1] "Test well 1: CROSS H CATTLE , Test well 2: CHURCHMAN BIBLE , f1-score: 0.575277337559429"
[1] "-------------"
[1] "Test well 1: NOLAN , Test well 2: NEWBY , f1-score: 0.563463819691578"
[1] "-------------"
[1] "Test well 1: NOLAN , Test well 2: CHURCHMAN BIBLE , f1-score: 0.635514018691589"
[1] "-------------"
[1] "Test well 1: NEWBY , Test well 2: CHURCHMAN BIBLE , f1-score: 0.543055555555556"
[1] "-------------"
[1] "Minimum F1: 0.520763187429854"
[1] "Average F1: 0.607718649773921"
[1] "Maximum F1: 0.678474114441417"
Time difference of 8.727254 mins

Content source: esa-as/2016-ml-contest

Similar notebooks:

notebook.community | gallery | about