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'
#> 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] 52674.66SVM 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) -5.486e+05 1.656e+06 -0.331 0.740544
#> MSSubClass -1.360e+02 4.720e+01 -2.882 0.004042 **
#> MSZoning -7.076e+02 1.559e+03 -0.454 0.650131
#> LotFrontage -8.279e+00 3.396e+01 -0.244 0.807425
#> LotArea 3.842e-01 1.306e-01 2.942 0.003336 **
#> Street -3.855e+04 2.110e+04 -1.827 0.068036 .
#> LotShape 3.608e+02 2.161e+03 0.167 0.867448
#> LandContour 2.930e+02 2.491e+03 0.118 0.906408
#> Utilities NA NA NA NA
#> LotConfig 1.795e+03 1.142e+03 1.573 0.116125
#> LandSlope 1.263e+04 5.551e+03 2.275 0.023126 *
#> Neighborhood 4.359e+02 2.021e+02 2.157 0.031293 *
#> Condition1 -2.321e+03 8.421e+02 -2.756 0.005963 **
#> Condition2 -1.268e+04 3.398e+03 -3.731 0.000202 ***
#> BldgType -1.011e+03 1.988e+03 -0.509 0.611008
#> HouseStyle -5.780e+01 1.005e+03 -0.057 0.954167
#> OverallQual 1.559e+04 1.431e+03 10.896 < 2e-16 ***
#> OverallCond 5.581e+03 1.246e+03 4.481 8.34e-06 ***
#> YearBuilt 2.883e+02 8.607e+01 3.349 0.000842 ***
#> YearRemodAdd 2.103e+02 8.303e+01 2.533 0.011459 *
#> RoofStyle 8.422e+03 2.072e+03 4.064 5.22e-05 ***
#> RoofMatl -1.841e+04 2.428e+03 -7.580 8.20e-14 ***
#> Exterior1st -1.576e+03 7.756e+02 -2.032 0.042428 *
#> Exterior2nd 1.367e+03 7.850e+02 1.741 0.081984 .
#> MasVnrType 2.880e+03 1.668e+03 1.727 0.084557 .
#> MasVnrArea 2.412e+01 7.684e+00 3.139 0.001745 **
#> ExterQual 2.231e+03 2.538e+03 0.879 0.379595
#> ExterCond 2.660e+03 2.473e+03 1.075 0.282451
#> Foundation -3.208e+03 2.024e+03 -1.585 0.113339
#> BsmtQual 5.920e+03 1.589e+03 3.725 0.000207 ***
#> BsmtCond -1.509e+03 1.553e+03 -0.972 0.331439
#> BsmtExposure 1.769e+03 9.874e+02 1.791 0.073575 .
#> BsmtFinType1 -1.013e+03 8.931e+02 -1.134 0.257015
#> BsmtFinSF1 1.539e+01 6.258e+00 2.460 0.014064 *
#> BsmtFinType2 -1.875e+03 1.284e+03 -1.461 0.144414
#> BsmtFinSF2 3.057e+01 9.952e+00 3.072 0.002188 **
#> BsmtUnfSF 6.262e+00 5.899e+00 1.062 0.288706
#> Heating 3.193e+03 4.565e+03 0.699 0.484514
#> HeatingQC -1.712e+03 1.459e+03 -1.173 0.241051
#> CentralAir 4.193e+03 5.316e+03 0.789 0.430501
#> Electrical 5.997e+02 2.170e+03 0.276 0.782285
#> `1stFlrSF` 3.910e+01 7.522e+00 5.198 2.47e-07 ***
#> `2ndFlrSF` 4.195e+01 6.082e+00 6.897 9.67e-12 ***
#> LowQualFinSF 5.715e+01 2.557e+01 2.235 0.025630 *
#> BsmtFullBath 8.067e+03 3.158e+03 2.554 0.010796 *
#> BsmtHalfBath -3.108e+03 4.522e+03 -0.687 0.492023
#> FullBath 9.045e+03 3.357e+03 2.694 0.007180 **
#> HalfBath -1.272e+03 3.140e+03 -0.405 0.685638
#> BedroomAbvGr -7.879e+03 1.995e+03 -3.949 8.43e-05 ***
#> KitchenAbvGr -1.834e+04 6.549e+03 -2.800 0.005215 **
#> KitchenQual 7.282e+03 1.876e+03 3.882 0.000111 ***
#> TotRmsAbvGrd 4.786e+03 1.489e+03 3.215 0.001347 **
#> Functional -3.162e+03 1.450e+03 -2.181 0.029447 *
#> Fireplaces 3.923e+03 2.807e+03 1.398 0.162575
#> FireplaceQu 1.337e+03 1.460e+03 0.916 0.359904
#> GarageType -7.291e+02 1.259e+03 -0.579 0.562513
#> GarageYrBlt -4.793e+00 5.297e+00 -0.905 0.365839
#> GarageFinish 1.346e+03 1.544e+03 0.872 0.383561
#> GarageCars 1.563e+04 3.417e+03 4.573 5.44e-06 ***
#> GarageArea 8.488e+00 1.137e+01 0.747 0.455473
#> GarageQual 7.339e+03 3.430e+03 2.139 0.032659 *
#> GarageCond -5.238e+03 3.224e+03 -1.625 0.104599
#> PavedDrive -4.252e+03 3.193e+03 -1.332 0.183334
#> WoodDeckSF 1.704e+01 9.774e+00 1.744 0.081515 .
#> OpenPorchSF -1.414e+01 1.802e+01 -0.785 0.432826
#> EnclosedPorch 4.803e+00 1.948e+01 0.247 0.805347
#> `3SsnPorch` 7.974e+00 3.647e+01 0.219 0.826982
#> ScreenPorch 6.544e+01 2.123e+01 3.083 0.002111 **
#> PoolArea -1.758e+01 3.043e+01 -0.578 0.563478
#> Fence 4.319e+02 1.125e+03 0.384 0.701225
#> MiscVal -2.495e+00 5.995e+00 -0.416 0.677312
#> MoSold 6.121e+02 3.984e+02 1.536 0.124842
#> YrSold -2.525e+02 8.244e+02 -0.306 0.759416
#> SaleType 1.019e+03 1.415e+03 0.720 0.471766
#> SaleCondition 8.790e+02 1.217e+03 0.722 0.470255
#> ---
#> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#>
#> (Dispersion parameter for gaussian family taken to be 1086309123)
#>
#> Null deviance: 6.4759e+12 on 1023 degrees of freedom
#> Residual deviance: 1.0320e+12 on 950 degrees of freedom
#> AIC: 24285
#>
#> 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$SalePrice, predicted = predictions)
#> [1] 33375.24Lasso Regression
lf <- LMTrainer$new(family = "gaussian", alpha = 1, lambda = 1000)
lf$fit(X = xtrain, y = "SalePrice")
predictions <- lf$predict(df = xtest)
rmse(actual = xtest$SalePrice, predicted = predictions)
#> [1] 35522.21Ridge Regression
lf <- LMTrainer$new(family = "gaussian", alpha=0)
lf$fit(X = xtrain, y = "SalePrice")
predictions <- lf$predict(df = xtest)
rmse(actual = xtest$SalePrice, predicted = predictions)
#> [1] 35118.7Logistic Regression with CV
lf <- LMTrainer$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 816959503658
#> GarageCars 571717508925
#> 1stFlrSF 469367381990
#> GarageArea 445922917529
#> YearBuilt 342163815714
#> FullBath 316981816196
#> BsmtFinSF1 255059368726
#> GarageYrBlt 243599463415
#> 2ndFlrSF 203892322124
#> YearRemodAdd 198671884108
#> LotArea 197113272548
#> TotRmsAbvGrd 192367330655
#> ExterQual 183675162001
#> Fireplaces 160934480650
#> FireplaceQu 148797038168
#> MasVnrArea 129453678815
#> KitchenQual 123990803555
#> BsmtQual 95924778953
#> LotFrontage 92597206498
#> Foundation 92559260297
#> OpenPorchSF 85632300108
#> BsmtUnfSF 72063231741
#> Neighborhood 65602498836
#> BsmtFinType1 63953232873
#> GarageType 56125338549
#> WoodDeckSF 52676838921
#> HeatingQC 50763780026
#> RoofStyle 44200876029
#> Exterior2nd 43939699667
#> MSSubClass 40963503695
#> BedroomAbvGr 40169455554
#> OverallCond 39604323420
#> MoSold 34190622568
#> Exterior1st 32575303760
#> HalfBath 29155240386
#> GarageFinish 28474428804
#> HouseStyle 27769717633
#> YrSold 23370873022
#> BsmtExposure 21852320000
#> MSZoning 21088775087
#> BsmtFullBath 20013350815
#> LotShape 19625799517
#> SaleCondition 18223181907
#> LandContour 18127292957
#> MasVnrType 16942311792
#> LotConfig 16068957242
#> PoolArea 16030816482
#> CentralAir 15963614236
#> BldgType 15522084717
#> Fence 15505801266
#> LandSlope 14776238934
#> SaleType 14186579783
#> ScreenPorch 12630303876
#> KitchenAbvGr 12329863184
#> GarageQual 11958632655
#> Condition1 10999464638
#> GarageCond 9535564724
#> BsmtFinSF2 9405131122
#> BsmtFinType2 8362177456
#> ExterCond 8148532801
#> EnclosedPorch 7194603190
#> Functional 5642406404
#> PavedDrive 5230900213
#> BsmtCond 5163463799
#> RoofMatl 4602926615
#> Condition2 4124654044
#> Electrical 3654720182
#> BsmtHalfBath 3044744953
#> 3SsnPorch 2309453749
#> LowQualFinSF 2282940192
#> Heating 2099308232
#> MiscVal 1271168965
#> Street 503909992
#> Utilities 0
rmse(actual = xtest$SalePrice, predicted = pred)
#> [1] 29057.99Xgboost
xgb <- XGBTrainer$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] 0.00684267
#>
#> $accuracy_sd
#> [1] 0.004485156
#>
#> $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