SuperML R package is designed to
unify the model training process in R like Python. Generally, it’s seen
that people spend lot of time in searching for packages, figuring out
the syntax for training machine learning models in R. This behaviour is
highly apparent in users who frequently switch between R and Python.
This package provides a python´s scikit-learn interface
(fit, predict) to train models faster.
In addition to building machine learning models, there are handy functionalities to do feature engineering
This ambitious package is my ongoing effort to help the r-community build ML models easily and faster in R.
You can install latest cran version using (recommended):
You can install the developmemt version directly from github using:
For machine learning, superml is based on the existing R packages. Hence, while installing the package, we don’t install all the dependencies. However, while training any model, superml will automatically install the package if its not found. Still, if you want to install all dependencies at once, you can simply do:
This package uses existing r-packages to build machine learning model. In this tutorial, we’ll use data.table R package to do all tasks related to data manipulation.
We’ll quickly prepare the data set to be ready to served for model training.
load("../data/reg_train.rda")
# if the above doesn't work, you can try: load("reg_train.rda")
# superml::check_package("caret")
library(data.table)
library(caret)
#> Loading required package: ggplot2
#> Loading required package: lattice
library(superml)
library(Metrics)
#>
#> Attaching package: 'Metrics'
#> The following objects are masked from 'package:caret':
#>
#> precision, recall
head(reg_train)
#> Id MSSubClass MSZoning LotFrontage LotArea Street Alley LotShape
#> <int> <int> <char> <int> <int> <char> <char> <char>
#> 1: 1 60 RL 65 8450 Pave <NA> Reg
#> 2: 2 20 RL 80 9600 Pave <NA> Reg
#> 3: 3 60 RL 68 11250 Pave <NA> IR1
#> 4: 4 70 RL 60 9550 Pave <NA> IR1
#> 5: 5 60 RL 84 14260 Pave <NA> IR1
#> 6: 6 50 RL 85 14115 Pave <NA> IR1
#> LandContour Utilities LotConfig LandSlope Neighborhood Condition1 Condition2
#> <char> <char> <char> <char> <char> <char> <char>
#> 1: Lvl AllPub Inside Gtl CollgCr Norm Norm
#> 2: Lvl AllPub FR2 Gtl Veenker Feedr Norm
#> 3: Lvl AllPub Inside Gtl CollgCr Norm Norm
#> 4: Lvl AllPub Corner Gtl Crawfor Norm Norm
#> 5: Lvl AllPub FR2 Gtl NoRidge Norm Norm
#> 6: Lvl AllPub Inside Gtl Mitchel Norm Norm
#> BldgType HouseStyle OverallQual OverallCond YearBuilt YearRemodAdd RoofStyle
#> <char> <char> <int> <int> <int> <int> <char>
#> 1: 1Fam 2Story 7 5 2003 2003 Gable
#> 2: 1Fam 1Story 6 8 1976 1976 Gable
#> 3: 1Fam 2Story 7 5 2001 2002 Gable
#> 4: 1Fam 2Story 7 5 1915 1970 Gable
#> 5: 1Fam 2Story 8 5 2000 2000 Gable
#> 6: 1Fam 1.5Fin 5 5 1993 1995 Gable
#> RoofMatl Exterior1st Exterior2nd MasVnrType MasVnrArea ExterQual ExterCond
#> <char> <char> <char> <char> <int> <char> <char>
#> 1: CompShg VinylSd VinylSd BrkFace 196 Gd TA
#> 2: CompShg MetalSd MetalSd None 0 TA TA
#> 3: CompShg VinylSd VinylSd BrkFace 162 Gd TA
#> 4: CompShg Wd Sdng Wd Shng None 0 TA TA
#> 5: CompShg VinylSd VinylSd BrkFace 350 Gd TA
#> 6: CompShg VinylSd VinylSd None 0 TA TA
#> Foundation BsmtQual BsmtCond BsmtExposure BsmtFinType1 BsmtFinSF1
#> <char> <char> <char> <char> <char> <int>
#> 1: PConc Gd TA No GLQ 706
#> 2: CBlock Gd TA Gd ALQ 978
#> 3: PConc Gd TA Mn GLQ 486
#> 4: BrkTil TA Gd No ALQ 216
#> 5: PConc Gd TA Av GLQ 655
#> 6: Wood Gd TA No GLQ 732
#> BsmtFinType2 BsmtFinSF2 BsmtUnfSF TotalBsmtSF Heating HeatingQC CentralAir
#> <char> <int> <int> <int> <char> <char> <char>
#> 1: Unf 0 150 856 GasA Ex Y
#> 2: Unf 0 284 1262 GasA Ex Y
#> 3: Unf 0 434 920 GasA Ex Y
#> 4: Unf 0 540 756 GasA Gd Y
#> 5: Unf 0 490 1145 GasA Ex Y
#> 6: Unf 0 64 796 GasA Ex Y
#> Electrical 1stFlrSF 2ndFlrSF LowQualFinSF GrLivArea BsmtFullBath
#> <char> <int> <int> <int> <int> <int>
#> 1: SBrkr 856 854 0 1710 1
#> 2: SBrkr 1262 0 0 1262 0
#> 3: SBrkr 920 866 0 1786 1
#> 4: SBrkr 961 756 0 1717 1
#> 5: SBrkr 1145 1053 0 2198 1
#> 6: SBrkr 796 566 0 1362 1
#> BsmtHalfBath FullBath HalfBath BedroomAbvGr KitchenAbvGr KitchenQual
#> <int> <int> <int> <int> <int> <char>
#> 1: 0 2 1 3 1 Gd
#> 2: 1 2 0 3 1 TA
#> 3: 0 2 1 3 1 Gd
#> 4: 0 1 0 3 1 Gd
#> 5: 0 2 1 4 1 Gd
#> 6: 0 1 1 1 1 TA
#> TotRmsAbvGrd Functional Fireplaces FireplaceQu GarageType GarageYrBlt
#> <int> <char> <int> <char> <char> <int>
#> 1: 8 Typ 0 <NA> Attchd 2003
#> 2: 6 Typ 1 TA Attchd 1976
#> 3: 6 Typ 1 TA Attchd 2001
#> 4: 7 Typ 1 Gd Detchd 1998
#> 5: 9 Typ 1 TA Attchd 2000
#> 6: 5 Typ 0 <NA> Attchd 1993
#> GarageFinish GarageCars GarageArea GarageQual GarageCond PavedDrive
#> <char> <int> <int> <char> <char> <char>
#> 1: RFn 2 548 TA TA Y
#> 2: RFn 2 460 TA TA Y
#> 3: RFn 2 608 TA TA Y
#> 4: Unf 3 642 TA TA Y
#> 5: RFn 3 836 TA TA Y
#> 6: Unf 2 480 TA TA Y
#> WoodDeckSF OpenPorchSF EnclosedPorch 3SsnPorch ScreenPorch PoolArea PoolQC
#> <int> <int> <int> <int> <int> <int> <char>
#> 1: 0 61 0 0 0 0 <NA>
#> 2: 298 0 0 0 0 0 <NA>
#> 3: 0 42 0 0 0 0 <NA>
#> 4: 0 35 272 0 0 0 <NA>
#> 5: 192 84 0 0 0 0 <NA>
#> 6: 40 30 0 320 0 0 <NA>
#> Fence MiscFeature MiscVal MoSold YrSold SaleType SaleCondition SalePrice
#> <char> <char> <int> <int> <int> <char> <char> <int>
#> 1: <NA> <NA> 0 2 2008 WD Normal 208500
#> 2: <NA> <NA> 0 5 2007 WD Normal 181500
#> 3: <NA> <NA> 0 9 2008 WD Normal 223500
#> 4: <NA> <NA> 0 2 2006 WD Abnorml 140000
#> 5: <NA> <NA> 0 12 2008 WD Normal 250000
#> 6: MnPrv Shed 700 10 2009 WD Normal 143000
split <- createDataPartition(y = reg_train$SalePrice, p = 0.7)
xtrain <- reg_train[split$Resample1]
xtest <- reg_train[!split$Resample1]# remove features with 90% or more missing values
# we will also remove the Id column because it doesn't contain
# any useful information
na_cols <- colSums(is.na(xtrain)) / nrow(xtrain)
na_cols <- names(na_cols[which(na_cols > 0.9)])
xtrain[, c(na_cols, "Id") := NULL]
xtest[, c(na_cols, "Id") := NULL]
# encode categorical variables
cat_cols <- names(xtrain)[sapply(xtrain, is.character)]
for(c in cat_cols){
lbl <- LabelEncoder$new()
lbl$fit(c(xtrain[[c]], xtest[[c]]))
xtrain[[c]] <- lbl$transform(xtrain[[c]])
xtest[[c]] <- lbl$transform(xtest[[c]])
}
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
#> The data contains NA values. Imputing NA with 'NA'
# removing noise column
noise <- c('GrLivArea','TotalBsmtSF')
xtrain[, c(noise) := NULL]
xtest[, c(noise) := NULL]
# fill missing value with -1
xtrain[is.na(xtrain)] <- -1
xtest[is.na(xtest)] <- -1KNN Regression
knn <- KNNTrainer$new(k = 2,prob = T,type = 'reg')
knn$fit(train = xtrain, test = xtest, y = 'SalePrice')
probs <- knn$predict(type = 'prob')
labels <- knn$predict(type='raw')
rmse(actual = xtest$SalePrice, predicted=labels)
#> [1] 46861.85SVM Regression
svm <- SVMTrainer$new()
svm$fit(xtrain, 'SalePrice')
pred <- svm$predict(xtest)
rmse(actual = xtest$SalePrice, predicted = pred)Simple Regresison
lf <- LMTrainer$new(family="gaussian")
lf$fit(X = xtrain, y = "SalePrice")
summary(lf$model)
#>
#> Call:
#> stats::glm(formula = f, family = self$family, data = X, weights = self$weights)
#>
#> Coefficients: (1 not defined because of singularities)
#> Estimate Std. Error t value Pr(>|t|)
#> (Intercept) -9.803e+05 1.331e+06 -0.737 0.461603
#> MSSubClass -1.162e+02 4.481e+01 -2.594 0.009638 **
#> MSZoning -7.596e+02 1.237e+03 -0.614 0.539376
#> LotFrontage 7.689e+01 2.755e+01 2.790 0.005369 **
#> LotArea 5.475e-01 1.085e-01 5.047 5.38e-07 ***
#> Street -5.022e+04 1.433e+04 -3.506 0.000477 ***
#> LotShape -1.546e+03 1.656e+03 -0.933 0.351002
#> LandContour 8.270e+02 1.790e+03 0.462 0.644146
#> Utilities NA NA NA NA
#> LotConfig 3.058e+02 1.020e+03 0.300 0.764467
#> LandSlope -3.559e+03 4.461e+03 -0.798 0.425149
#> Neighborhood -2.853e+02 1.729e+02 -1.650 0.099225 .
#> Condition1 -2.418e+03 6.602e+02 -3.662 0.000264 ***
#> Condition2 -1.689e+03 2.679e+03 -0.630 0.528576
#> BldgType -4.932e+02 1.735e+03 -0.284 0.776221
#> HouseStyle -2.151e+02 8.004e+02 -0.269 0.788214
#> OverallQual 9.515e+03 1.191e+03 7.987 3.97e-15 ***
#> OverallCond 7.189e+03 1.057e+03 6.802 1.83e-11 ***
#> YearBuilt 3.760e+02 7.050e+01 5.334 1.20e-07 ***
#> YearRemodAdd 2.135e+02 6.546e+01 3.261 0.001149 **
#> RoofStyle 1.407e+03 1.731e+03 0.812 0.416742
#> RoofMatl -1.901e+03 1.880e+03 -1.011 0.312338
#> Exterior1st -6.420e+02 4.562e+02 -1.407 0.159636
#> Exterior2nd 5.089e+02 4.973e+02 1.023 0.306441
#> MasVnrType -3.328e+03 1.439e+03 -2.313 0.020940 *
#> MasVnrArea 3.145e+01 6.345e+00 4.957 8.49e-07 ***
#> ExterQual 1.012e+04 2.000e+03 5.062 4.97e-07 ***
#> ExterCond -1.199e+03 1.971e+03 -0.608 0.543012
#> Foundation -1.608e+03 9.433e+02 -1.704 0.088646 .
#> BsmtQual 2.772e+03 1.253e+03 2.212 0.027187 *
#> BsmtCond -5.408e+02 2.127e+03 -0.254 0.799413
#> BsmtExposure 5.993e+03 8.397e+02 7.137 1.89e-12 ***
#> BsmtFinType1 -1.608e+02 5.700e+02 -0.282 0.777950
#> BsmtFinSF1 4.891e+01 4.896e+00 9.988 < 2e-16 ***
#> BsmtFinType2 -2.123e+02 8.811e+02 -0.241 0.809663
#> BsmtFinSF2 3.328e+01 8.103e+00 4.107 4.35e-05 ***
#> BsmtUnfSF 2.726e+01 4.541e+00 6.004 2.74e-09 ***
#> Heating -4.176e+03 2.951e+03 -1.415 0.157345
#> HeatingQC -7.145e+02 1.276e+03 -0.560 0.575542
#> CentralAir 3.896e+03 4.590e+03 0.849 0.396194
#> Electrical 2.125e+03 1.852e+03 1.148 0.251357
#> `1stFlrSF` 6.030e+01 5.896e+00 10.226 < 2e-16 ***
#> `2ndFlrSF` 7.234e+01 5.232e+00 13.827 < 2e-16 ***
#> LowQualFinSF 2.232e+01 1.827e+01 1.222 0.222123
#> BsmtFullBath 1.890e+03 2.511e+03 0.753 0.451827
#> BsmtHalfBath -4.010e+03 3.905e+03 -1.027 0.304781
#> FullBath 3.612e+02 2.704e+03 0.134 0.893777
#> HalfBath -1.713e+03 2.535e+03 -0.676 0.499402
#> BedroomAbvGr -1.039e+04 1.702e+03 -6.106 1.49e-09 ***
#> KitchenAbvGr -2.465e+04 5.175e+03 -4.762 2.21e-06 ***
#> KitchenQual 1.173e+04 1.383e+03 8.485 < 2e-16 ***
#> TotRmsAbvGrd 2.919e+03 1.198e+03 2.437 0.014991 *
#> Functional -4.968e+03 1.301e+03 -3.818 0.000143 ***
#> Fireplaces 2.859e+03 1.840e+03 1.554 0.120592
#> FireplaceQu 3.904e+00 9.929e+02 0.004 0.996863
#> GarageType -7.973e+02 1.152e+03 -0.692 0.488991
#> GarageYrBlt -2.514e+00 5.069e+00 -0.496 0.620042
#> GarageFinish -1.025e+03 1.478e+03 -0.694 0.488020
#> GarageCars 5.084e+03 2.935e+03 1.732 0.083544 .
#> GarageArea 1.449e+01 9.405e+00 1.541 0.123650
#> GarageQual 7.368e+03 2.931e+03 2.514 0.012112 *
#> GarageCond -4.444e+03 2.569e+03 -1.730 0.083970 .
#> PavedDrive -1.943e+03 2.708e+03 -0.717 0.473314
#> WoodDeckSF 1.210e+01 7.513e+00 1.611 0.107553
#> OpenPorchSF 1.572e+01 1.416e+01 1.110 0.267341
#> EnclosedPorch -6.549e+00 1.530e+01 -0.428 0.668665
#> `3SsnPorch` 1.480e+01 3.150e+01 0.470 0.638645
#> ScreenPorch 4.097e+01 1.558e+01 2.629 0.008700 **
#> PoolArea 8.162e+01 2.230e+01 3.659 0.000267 ***
#> Fence -1.981e+03 1.202e+03 -1.648 0.099735 .
#> MiscVal -9.256e+00 4.827e+00 -1.917 0.055474 .
#> MoSold -2.638e+02 3.185e+02 -0.828 0.407654
#> YrSold -1.153e+02 6.597e+02 -0.175 0.861285
#> SaleType 1.397e+03 1.008e+03 1.387 0.165866
#> SaleCondition 6.168e+03 1.561e+03 3.953 8.31e-05 ***
#> ---
#> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#>
#> (Dispersion parameter for gaussian family taken to be 700265710)
#>
#> Null deviance: 7.1596e+12 on 1023 degrees of freedom
#> Residual deviance: 6.6525e+11 on 950 degrees of freedom
#> AIC: 23835
#>
#> Number of Fisher Scoring iterations: 2
predictions <- lf$predict(df = xtest)
#> Warning in predict.lm(object, newdata, se.fit, scale = 1, type = if (type == :
#> prediction from rank-deficient fit; attr(*, "non-estim") has doubtful cases
rmse(actual = xtest$SalePrice, predicted = predictions)
#> [1] 50727.11Lasso Regression
lf <- LMTrainer$new(family = "gaussian", alpha = 1, lambda = 1000)
lf$fit(X = xtrain, y = "SalePrice")
predictions <- lf$predict(df = xtest)
rmse(actual = xtest$SalePrice, predicted = predictions)
#> [1] 55306.37Ridge Regression
lf <- LMTrainer$new(family = "gaussian", alpha=0)
lf$fit(X = xtrain, y = "SalePrice")
predictions <- lf$predict(df = xtest)
rmse(actual = xtest$SalePrice, predicted = predictions)
#> [1] 56136.12Logistic Regression with CV
lf <- LMTrainer$new(family = "gaussian")
lf$cv_model(X = xtrain, y = 'SalePrice', nfolds = 5, parallel = FALSE)
predictions <- lf$cv_predict(df = xtest)
coefs <- lf$get_importance()
rmse(actual = xtest$SalePrice, predicted = predictions)Random Forest
rf <- RFTrainer$new(n_estimators = 500,classification = 0)
rf$fit(X = xtrain, y = "SalePrice")
pred <- rf$predict(df = xtest)
rf$get_importance()
#> tmp.order.tmp..decreasing...TRUE..
#> OverallQual 908484694653
#> GarageCars 547567392469
#> 1stFlrSF 489764442491
#> GarageArea 481000546170
#> ExterQual 477104170705
#> YearBuilt 371038709543
#> BsmtFinSF1 340597056492
#> FullBath 303287368592
#> GarageYrBlt 292617742191
#> 2ndFlrSF 272923836090
#> TotRmsAbvGrd 240077565621
#> LotArea 219518965182
#> YearRemodAdd 179045361183
#> Fireplaces 155786517652
#> KitchenQual 154406026146
#> MasVnrArea 146892841302
#> BsmtQual 143508692645
#> FireplaceQu 114763286444
#> LotFrontage 97128728545
#> OpenPorchSF 93859417090
#> Neighborhood 77888636697
#> BsmtUnfSF 69192856824
#> WoodDeckSF 62987211669
#> GarageFinish 57216739851
#> BsmtExposure 53099539167
#> BedroomAbvGr 48828540451
#> GarageType 44795887238
#> MoSold 40294262110
#> RoofStyle 36695887964
#> Exterior2nd 34853516867
#> MSSubClass 34088166842
#> OverallCond 33461789883
#> HouseStyle 31054279131
#> MasVnrType 30258946528
#> HeatingQC 28825259357
#> Exterior1st 28402667316
#> HalfBath 26550565923
#> BsmtFinType1 24900660996
#> Foundation 23531134076
#> SaleCondition 22564742496
#> BsmtFullBath 21570893359
#> YrSold 21123778917
#> ScreenPorch 18670240606
#> GarageCond 18360764024
#> MSZoning 17940361365
#> LotShape 17201485087
#> LandContour 15954040699
#> GarageQual 15292927043
#> LandSlope 14626568360
#> LotConfig 14125623673
#> EnclosedPorch 13274858663
#> BsmtCond 12741238364
#> CentralAir 12490111225
#> PoolArea 12196562239
#> RoofMatl 11277404072
#> Fence 11236546727
#> BsmtHalfBath 11012044716
#> BldgType 10895089687
#> BsmtFinSF2 9580171052
#> SaleType 9573230882
#> ExterCond 9401498637
#> PavedDrive 7409085898
#> BsmtFinType2 6854882176
#> Functional 6667538404
#> Condition1 6167731532
#> KitchenAbvGr 5050205847
#> LowQualFinSF 4492805884
#> Electrical 2868657385
#> Heating 2214232162
#> MiscVal 2043128944
#> 3SsnPorch 1511071145
#> Street 819143544
#> Condition2 630608694
#> Utilities 0
rmse(actual = xtest$SalePrice, predicted = pred)
#> [1] 31809.2Xgboost
xgb <- XGBTrainer$new(objective = "reg:linear"
, n_estimators = 500
, eval_metric = "rmse"
, maximize = F
, learning_rate = 0.1
,max_depth = 6)
xgb$fit(X = xtrain, y = "SalePrice", valid = xtest)
pred <- xgb$predict(xtest)
rmse(actual = xtest$SalePrice, predicted = pred)Grid Search
xgb <- XGBTrainer$new(objective = "reg:linear")
gst <- GridSearchCV$new(trainer = xgb,
parameters = list(n_estimators = c(10,50), max_depth = c(5,2)),
n_folds = 3,
scoring = c('accuracy','auc'))
gst$fit(xtrain, "SalePrice")
gst$best_iteration()Random Search
rf <- RFTrainer$new()
rst <- RandomSearchCV$new(trainer = rf,
parameters = list(n_estimators = c(5,10),
max_depth = c(5,2)),
n_folds = 3,
scoring = c('accuracy','auc'),
n_iter = 3)
rst$fit(xtrain, "SalePrice")
#> [1] "In total, 3 models will be trained"
rst$best_iteration()
#> $n_estimators
#> [1] 10
#>
#> $max_depth
#> [1] 2
#>
#> $accuracy_avg
#> [1] 0.007805912
#>
#> $accuracy_sd
#> [1] 0.004469349
#>
#> $auc_avg
#> [1] NaN
#>
#> $auc_sd
#> [1] NAHere, we will solve a simple binary classification problem (predict people who survived on titanic ship). The idea here is to demonstrate how to use this package to solve classification problems.
Data Preparation
# load class
load('../data/cla_train.rda')
# if the above doesn't work, you can try: load("cla_train.rda")
head(cla_train)
#> PassengerId Survived Pclass
#> <int> <int> <int>
#> 1: 1 0 3
#> 2: 2 1 1
#> 3: 3 1 3
#> 4: 4 1 1
#> 5: 5 0 3
#> 6: 6 0 3
#> Name Sex Age SibSp Parch
#> <char> <char> <num> <int> <int>
#> 1: Braund, Mr. Owen Harris male 22 1 0
#> 2: Cumings, Mrs. John Bradley (Florence Briggs Thayer) female 38 1 0
#> 3: Heikkinen, Miss. Laina female 26 0 0
#> 4: Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35 1 0
#> 5: Allen, Mr. William Henry male 35 0 0
#> 6: Moran, Mr. James male NA 0 0
#> Ticket Fare Cabin Embarked
#> <char> <num> <char> <char>
#> 1: A/5 21171 7.2500 S
#> 2: PC 17599 71.2833 C85 C
#> 3: STON/O2. 3101282 7.9250 S
#> 4: 113803 53.1000 C123 S
#> 5: 373450 8.0500 S
#> 6: 330877 8.4583 Q
# split the data
split <- createDataPartition(y = cla_train$Survived,p = 0.7)
xtrain <- cla_train[split$Resample1]
xtest <- cla_train[!split$Resample1]
# encode categorical variables - shorter way
for(c in c('Embarked','Sex','Cabin')) {
lbl <- LabelEncoder$new()
lbl$fit(c(xtrain[[c]], xtest[[c]]))
xtrain[[c]] <- lbl$transform(xtrain[[c]])
xtest[[c]] <- lbl$transform(xtest[[c]])
}
#> The data contains blank values. Imputing them with 'NA'
#> The data contains blank values. Imputing them with 'NA'
#> The data contains blank values. Imputing them with 'NA'
#> The data contains blank values. Imputing them with 'NA'
#> The data contains blank values. Imputing them with 'NA'
# impute missing values
xtrain[, Age := replace(Age, is.na(Age), median(Age, na.rm = T))]
xtest[, Age := replace(Age, is.na(Age), median(Age, na.rm = T))]
# drop these features
to_drop <- c('PassengerId','Ticket','Name')
xtrain <- xtrain[,-c(to_drop), with=F]
xtest <- xtest[,-c(to_drop), with=F]Now, our data is ready to be served for model training. Let’s do it.
KNN Classification
knn <- KNNTrainer$new(k = 2,prob = T,type = 'class')
knn$fit(train = xtrain, test = xtest, y = 'Survived')
probs <- knn$predict(type = 'prob')
labels <- knn$predict(type = 'raw')
auc(actual = xtest$Survived, predicted = labels)
#> [1] 0.6385027Naive Bayes Classification
nb <- NBTrainer$new()
nb$fit(xtrain, 'Survived')
pred <- nb$predict(xtest)
#> Warning: predict.naive_bayes(): more features in the newdata are provided as
#> there are probability tables in the object. Calculation is performed based on
#> features to be found in the tables.
auc(actual = xtest$Survived, predicted = pred)
#> [1] 0.7771836SVM Classification
#predicts labels
svm <- SVMTrainer$new()
svm$fit(xtrain, 'Survived')
pred <- svm$predict(xtest)
auc(actual = xtest$Survived, predicted=pred)Logistic Regression
lf <- LMTrainer$new(family = "binomial")
lf$fit(X = xtrain, y = "Survived")
summary(lf$model)
#>
#> Call:
#> stats::glm(formula = f, family = self$family, data = X, weights = self$weights)
#>
#> Coefficients:
#> Estimate Std. Error z value Pr(>|z|)
#> (Intercept) 1.830070 0.616894 2.967 0.00301 **
#> Pclass -0.980785 0.192493 -5.095 3.48e-07 ***
#> Sex 2.508241 0.230374 10.888 < 2e-16 ***
#> Age -0.041034 0.009309 -4.408 1.04e-05 ***
#> SibSp -0.235520 0.117715 -2.001 0.04542 *
#> Parch -0.098742 0.137791 -0.717 0.47361
#> Fare 0.001281 0.002842 0.451 0.65230
#> Cabin 0.008408 0.004786 1.757 0.07899 .
#> Embarked 0.248088 0.166616 1.489 0.13649
#> ---
#> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#>
#> (Dispersion parameter for binomial family taken to be 1)
#>
#> Null deviance: 831.52 on 623 degrees of freedom
#> Residual deviance: 564.76 on 615 degrees of freedom
#> AIC: 582.76
#>
#> Number of Fisher Scoring iterations: 5
predictions <- lf$predict(df = xtest)
auc(actual = xtest$Survived, predicted = predictions)
#> [1] 0.8832145Lasso Logistic Regression
lf <- LMTrainer$new(family="binomial", alpha=1)
lf$cv_model(X = xtrain, y = "Survived", nfolds = 5, parallel = FALSE)
pred <- lf$cv_predict(df = xtest)
auc(actual = xtest$Survived, predicted = pred)Ridge Logistic Regression
lf <- LMTrainer$new(family="binomial", alpha=0)
lf$cv_model(X = xtrain, y = "Survived", nfolds = 5, parallel = FALSE)
pred <- lf$cv_predict(df = xtest)
auc(actual = xtest$Survived, predicted = pred)Random Forest
rf <- RFTrainer$new(n_estimators = 500,classification = 1, max_features = 3)
rf$fit(X = xtrain, y = "Survived")
pred <- rf$predict(df = xtest)
rf$get_importance()
#> tmp.order.tmp..decreasing...TRUE..
#> Sex 69.10742
#> Fare 57.96084
#> Age 48.50156
#> Pclass 23.91175
#> Cabin 21.19329
#> SibSp 12.58503
#> Parch 10.55128
#> Embarked 10.07059
auc(actual = xtest$Survived, predicted = pred)
#> [1] 0.7988414Xgboost
xgb <- XGBTrainer$new(objective = "binary:logistic"
, n_estimators = 500
, eval_metric = "auc"
, maximize = T
, learning_rate = 0.1
,max_depth = 6)
xgb$fit(X = xtrain, y = "Survived", valid = xtest)
pred <- xgb$predict(xtest)
auc(actual = xtest$Survived, predicted = pred)Grid Search
xgb <- XGBTrainer$new(objective="binary:logistic")
gst <-GridSearchCV$new(trainer = xgb,
parameters = list(n_estimators = c(10,50),
max_depth = c(5,2)),
n_folds = 3,
scoring = c('accuracy','auc'))
gst$fit(xtrain, "Survived")
gst$best_iteration()Random Search
rf <- RFTrainer$new()
rst <- RandomSearchCV$new(trainer = rf,
parameters = list(n_estimators = c(10,50), max_depth = c(5,2)),
n_folds = 3,
scoring = c('accuracy','auc'),
n_iter = 3)
rst$fit(xtrain, "Survived")
#> [1] "In total, 3 models will be trained"
rst$best_iteration()
#> $n_estimators
#> [1] 50
#>
#> $max_depth
#> [1] 5
#>
#> $accuracy_avg
#> [1] 0.8028846
#>
#> $accuracy_sd
#> [1] 0.01733438
#>
#> $auc_avg
#> [1] 0.7804264
#>
#> $auc_sd
#> [1] 0.02631447Let’s create some new feature based on target variable using target encoding and test a model.
# add target encoding features
xtrain[, feat_01 := smoothMean(train_df = xtrain,
test_df = xtest,
colname = "Embarked",
target = "Survived")$train[[2]]]
xtest[, feat_01 := smoothMean(train_df = xtrain,
test_df = xtest,
colname = "Embarked",
target = "Survived")$test[[2]]]
# train a random forest
# Random Forest
rf <- RFTrainer$new(n_estimators = 500,classification = 1, max_features = 4)
rf$fit(X = xtrain, y = "Survived")
pred <- rf$predict(df = xtest)
rf$get_importance()
#> tmp.order.tmp..decreasing...TRUE..
#> Sex 71.417138
#> Fare 61.039958
#> Age 51.787990
#> Pclass 24.257112
#> Cabin 21.549374
#> SibSp 12.374317
#> Parch 10.392826
#> feat_01 6.490151
#> Embarked 6.270997
auc(actual = xtest$Survived, predicted = pred)
#> [1] 0.7988414