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:
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")
library(data.table)
library(caret)
#> Loading required package: lattice
#> Loading required package: ggplot2
library(superml)
#> Loading required package: R6
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 LandContour
#> 1: 1 60 RL 65 8450 Pave <NA> Reg Lvl
#> 2: 2 20 RL 80 9600 Pave <NA> Reg Lvl
#> 3: 3 60 RL 68 11250 Pave <NA> IR1 Lvl
#> 4: 4 70 RL 60 9550 Pave <NA> IR1 Lvl
#> 5: 5 60 RL 84 14260 Pave <NA> IR1 Lvl
#> 6: 6 50 RL 85 14115 Pave <NA> IR1 Lvl
#> Utilities LotConfig LandSlope Neighborhood Condition1 Condition2 BldgType
#> 1: AllPub Inside Gtl CollgCr Norm Norm 1Fam
#> 2: AllPub FR2 Gtl Veenker Feedr Norm 1Fam
#> 3: AllPub Inside Gtl CollgCr Norm Norm 1Fam
#> 4: AllPub Corner Gtl Crawfor Norm Norm 1Fam
#> 5: AllPub FR2 Gtl NoRidge Norm Norm 1Fam
#> 6: AllPub Inside Gtl Mitchel Norm Norm 1Fam
#> HouseStyle OverallQual OverallCond YearBuilt YearRemodAdd RoofStyle RoofMatl
#> 1: 2Story 7 5 2003 2003 Gable CompShg
#> 2: 1Story 6 8 1976 1976 Gable CompShg
#> 3: 2Story 7 5 2001 2002 Gable CompShg
#> 4: 2Story 7 5 1915 1970 Gable CompShg
#> 5: 2Story 8 5 2000 2000 Gable CompShg
#> 6: 1.5Fin 5 5 1993 1995 Gable CompShg
#> Exterior1st Exterior2nd MasVnrType MasVnrArea ExterQual ExterCond Foundation
#> 1: VinylSd VinylSd BrkFace 196 Gd TA PConc
#> 2: MetalSd MetalSd None 0 TA TA CBlock
#> 3: VinylSd VinylSd BrkFace 162 Gd TA PConc
#> 4: Wd Sdng Wd Shng None 0 TA TA BrkTil
#> 5: VinylSd VinylSd BrkFace 350 Gd TA PConc
#> 6: VinylSd VinylSd None 0 TA TA Wood
#> BsmtQual BsmtCond BsmtExposure BsmtFinType1 BsmtFinSF1 BsmtFinType2
#> 1: Gd TA No GLQ 706 Unf
#> 2: Gd TA Gd ALQ 978 Unf
#> 3: Gd TA Mn GLQ 486 Unf
#> 4: TA Gd No ALQ 216 Unf
#> 5: Gd TA Av GLQ 655 Unf
#> 6: Gd TA No GLQ 732 Unf
#> BsmtFinSF2 BsmtUnfSF TotalBsmtSF Heating HeatingQC CentralAir Electrical
#> 1: 0 150 856 GasA Ex Y SBrkr
#> 2: 0 284 1262 GasA Ex Y SBrkr
#> 3: 0 434 920 GasA Ex Y SBrkr
#> 4: 0 540 756 GasA Gd Y SBrkr
#> 5: 0 490 1145 GasA Ex Y SBrkr
#> 6: 0 64 796 GasA Ex Y SBrkr
#> 1stFlrSF 2ndFlrSF LowQualFinSF GrLivArea BsmtFullBath BsmtHalfBath FullBath
#> 1: 856 854 0 1710 1 0 2
#> 2: 1262 0 0 1262 0 1 2
#> 3: 920 866 0 1786 1 0 2
#> 4: 961 756 0 1717 1 0 1
#> 5: 1145 1053 0 2198 1 0 2
#> 6: 796 566 0 1362 1 0 1
#> HalfBath BedroomAbvGr KitchenAbvGr KitchenQual TotRmsAbvGrd Functional
#> 1: 1 3 1 Gd 8 Typ
#> 2: 0 3 1 TA 6 Typ
#> 3: 1 3 1 Gd 6 Typ
#> 4: 0 3 1 Gd 7 Typ
#> 5: 1 4 1 Gd 9 Typ
#> 6: 1 1 1 TA 5 Typ
#> Fireplaces FireplaceQu GarageType GarageYrBlt GarageFinish GarageCars
#> 1: 0 <NA> Attchd 2003 RFn 2
#> 2: 1 TA Attchd 1976 RFn 2
#> 3: 1 TA Attchd 2001 RFn 2
#> 4: 1 Gd Detchd 1998 Unf 3
#> 5: 1 TA Attchd 2000 RFn 3
#> 6: 0 <NA> Attchd 1993 Unf 2
#> GarageArea GarageQual GarageCond PavedDrive WoodDeckSF OpenPorchSF
#> 1: 548 TA TA Y 0 61
#> 2: 460 TA TA Y 298 0
#> 3: 608 TA TA Y 0 42
#> 4: 642 TA TA Y 0 35
#> 5: 836 TA TA Y 192 84
#> 6: 480 TA TA Y 40 30
#> EnclosedPorch 3SsnPorch ScreenPorch PoolArea PoolQC Fence MiscFeature
#> 1: 0 0 0 0 <NA> <NA> <NA>
#> 2: 0 0 0 0 <NA> <NA> <NA>
#> 3: 0 0 0 0 <NA> <NA> <NA>
#> 4: 272 0 0 0 <NA> <NA> <NA>
#> 5: 0 0 0 0 <NA> <NA> <NA>
#> 6: 0 320 0 0 <NA> MnPrv Shed
#> MiscVal MoSold YrSold SaleType SaleCondition SalePrice
#> 1: 0 2 2008 WD Normal 208500
#> 2: 0 5 2007 WD Normal 181500
#> 3: 0 9 2008 WD Normal 223500
#> 4: 0 2 2006 WD Abnorml 140000
#> 5: 0 12 2008 WD Normal 250000
#> 6: 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] 47177.52SVM 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)
#>
#> Deviance Residuals:
#> Min 1Q Median 3Q Max
#> -339890 -15323 -1318 12807 250963
#>
#> Coefficients:
#> Estimate Std. Error t value Pr(>|t|)
#> (Intercept) -1.195e+06 1.638e+06 -0.729 0.465962
#> MSSubClass -2.242e+02 6.628e+01 -3.382 0.000749 ***
#> MSZoning 1.092e+03 1.540e+03 0.709 0.478447
#> LotFrontage -4.871e+01 3.475e+01 -1.402 0.161268
#> LotArea 4.661e-01 1.298e-01 3.591 0.000346 ***
#> Street -3.448e+04 1.740e+04 -1.981 0.047849 *
#> LotShape 4.938e+02 2.187e+03 0.226 0.821389
#> LandContour -7.851e+02 2.197e+03 -0.357 0.720844
#> Utilities -6.306e+04 3.504e+04 -1.800 0.072220 .
#> LotConfig 5.514e+02 1.429e+03 0.386 0.699782
#> LandSlope 5.230e+03 5.165e+03 1.013 0.311535
#> Neighborhood -5.642e+01 1.876e+02 -0.301 0.763710
#> Condition1 -2.654e+03 9.116e+02 -2.911 0.003681 **
#> Condition2 -1.060e+04 3.385e+03 -3.133 0.001783 **
#> BldgType 2.757e+03 2.818e+03 0.978 0.328252
#> HouseStyle 1.497e+02 9.619e+02 0.156 0.876401
#> OverallQual 1.377e+04 1.442e+03 9.547 < 2e-16 ***
#> OverallCond 5.256e+03 1.279e+03 4.109 4.31e-05 ***
#> YearBuilt 3.357e+02 8.213e+01 4.088 4.72e-05 ***
#> YearRemodAdd 1.312e+02 8.670e+01 1.513 0.130639
#> RoofStyle 4.687e+03 2.225e+03 2.106 0.035423 *
#> RoofMatl -1.515e+04 3.200e+03 -4.735 2.53e-06 ***
#> Exterior1st 7.662e+01 5.791e+02 0.132 0.894780
#> Exterior2nd 1.645e+02 6.367e+02 0.258 0.796203
#> MasVnrType 2.443e+03 1.736e+03 1.407 0.159808
#> MasVnrArea 3.306e+01 7.277e+00 4.543 6.25e-06 ***
#> ExterQual 1.017e+03 2.427e+03 0.419 0.675372
#> ExterCond 3.279e+03 2.450e+03 1.338 0.181078
#> Foundation -3.947e+03 1.548e+03 -2.550 0.010929 *
#> BsmtQual 6.917e+03 1.580e+03 4.378 1.33e-05 ***
#> BsmtCond -6.143e+03 2.023e+03 -3.037 0.002457 **
#> BsmtExposure 4.922e+03 1.048e+03 4.697 3.03e-06 ***
#> BsmtFinType1 -1.187e+03 7.239e+02 -1.639 0.101545
#> BsmtFinSF1 3.679e+00 6.208e+00 0.593 0.553574
#> BsmtFinType2 -3.781e+02 1.264e+03 -0.299 0.764917
#> BsmtFinSF2 8.339e+00 1.095e+01 0.761 0.446649
#> BsmtUnfSF 1.463e+00 5.833e+00 0.251 0.801986
#> Heating -1.677e+03 3.957e+03 -0.424 0.671797
#> HeatingQC -1.338e+03 1.484e+03 -0.902 0.367528
#> CentralAir 6.649e+03 5.696e+03 1.167 0.243434
#> Electrical 7.839e+01 2.282e+03 0.034 0.972597
#> `1stFlrSF` 5.272e+01 7.348e+00 7.175 1.46e-12 ***
#> `2ndFlrSF` 5.011e+01 6.185e+00 8.103 1.65e-15 ***
#> LowQualFinSF 4.548e+01 2.161e+01 2.104 0.035630 *
#> BsmtFullBath 1.067e+04 3.127e+03 3.413 0.000670 ***
#> BsmtHalfBath 4.019e+03 4.636e+03 0.867 0.386155
#> FullBath 8.986e+03 3.344e+03 2.687 0.007335 **
#> HalfBath 9.154e+02 3.151e+03 0.291 0.771453
#> BedroomAbvGr -5.486e+03 2.011e+03 -2.728 0.006491 **
#> KitchenAbvGr -2.481e+04 5.959e+03 -4.164 3.42e-05 ***
#> KitchenQual 7.359e+03 1.867e+03 3.942 8.68e-05 ***
#> TotRmsAbvGrd 4.127e+03 1.430e+03 2.886 0.003995 **
#> Functional -5.056e+03 1.692e+03 -2.988 0.002876 **
#> Fireplaces -3.645e+03 2.747e+03 -1.327 0.184893
#> FireplaceQu 5.295e+03 1.461e+03 3.623 0.000306 ***
#> GarageType -1.595e+03 1.290e+03 -1.237 0.216431
#> GarageYrBlt -6.246e+00 4.742e+00 -1.317 0.188070
#> GarageFinish 1.039e+03 1.530e+03 0.679 0.497258
#> GarageCars 1.247e+04 3.390e+03 3.677 0.000249 ***
#> GarageArea 8.377e+00 1.114e+01 0.752 0.452356
#> GarageQual 5.224e+03 2.257e+03 2.315 0.020829 *
#> GarageCond -1.755e+03 2.877e+03 -0.610 0.542112
#> PavedDrive -2.110e+03 3.438e+03 -0.614 0.539589
#> WoodDeckSF 2.171e+01 9.324e+00 2.328 0.020118 *
#> OpenPorchSF -1.085e+01 1.681e+01 -0.645 0.518909
#> EnclosedPorch 1.356e+01 1.956e+01 0.693 0.488349
#> `3SsnPorch` 4.777e+01 3.952e+01 1.209 0.227103
#> ScreenPorch 8.152e+01 1.886e+01 4.323 1.70e-05 ***
#> PoolArea -1.398e+02 3.339e+01 -4.187 3.10e-05 ***
#> Fence -7.729e+02 1.124e+03 -0.688 0.491915
#> MiscVal 5.601e-01 1.990e+00 0.281 0.778420
#> MoSold -1.505e+02 3.995e+02 -0.377 0.706492
#> YrSold 1.151e+02 8.142e+02 0.141 0.887568
#> SaleType 2.828e+03 1.357e+03 2.084 0.037447 *
#> SaleCondition 1.312e+03 1.301e+03 1.008 0.313565
#> ---
#> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#>
#> (Dispersion parameter for gaussian family taken to be 1062927255)
#>
#> Null deviance: 6.6562e+12 on 1023 degrees of freedom
#> Residual deviance: 1.0087e+12 on 949 degrees of freedom
#> AIC: 24263
#>
#> Number of Fisher Scoring iterations: 2
predictions <- lf$predict(df = xtest)
rmse(actual = xtest$SalePrice, predicted = predictions)
#> [1] 34112.1Lasso Regression
lf <- LMTrainer$new(family = "gaussian", alpha = 1, lambda = 1000)
lf$fit(X = xtrain, y = "SalePrice")
predictions <- lf$predict(df = xtest)
rmse(actual = xtest$SalePrice, predicted = predictions)
#> [1] 40095.21Ridge Regression
lf <- LMTrainer$new(family = "gaussian", alpha=0)
lf$fit(X = xtrain, y = "SalePrice")
predictions <- lf$predict(df = xtest)
rmse(actual = xtest$SalePrice, predicted = predictions)
#> [1] 39663.39Logistic Regression with CV
lf <- LMTrainer$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 876335663148
#> 1stFlrSF 496824285769
#> GarageCars 496428723445
#> GarageArea 375950891452
#> YearBuilt 372595809715
#> FullBath 334535870077
#> GarageYrBlt 271502481223
#> 2ndFlrSF 238506672041
#> TotRmsAbvGrd 234508183975
#> BsmtFinSF1 231560790441
#> ExterQual 229571841020
#> MasVnrArea 188253292094
#> LotArea 187929069935
#> YearRemodAdd 178232672872
#> FireplaceQu 147653809502
#> KitchenQual 141720155457
#> Fireplaces 141232109658
#> BsmtQual 116273512210
#> Foundation 98363852614
#> OpenPorchSF 87715869624
#> LotFrontage 85282098599
#> BsmtUnfSF 77180208968
#> BsmtFinType1 73008736307
#> Neighborhood 69394532266
#> WoodDeckSF 60691270268
#> HeatingQC 56498062396
#> BedroomAbvGr 55035448679
#> MoSold 43046764506
#> GarageType 42130030414
#> Exterior2nd 41065067463
#> MSSubClass 39169061611
#> BsmtExposure 38887073076
#> OverallCond 37349932072
#> Exterior1st 32908955958
#> HouseStyle 30700922286
#> HalfBath 29944784145
#> LotShape 25612111728
#> BsmtFullBath 23577174837
#> RoofStyle 22592851206
#> GarageFinish 21792129589
#> YrSold 21745080963
#> MSZoning 18527787130
#> LandContour 17362367795
#> BsmtHalfBath 15640597540
#> SaleType 13879412169
#> SaleCondition 13859845514
#> ScreenPorch 13214213782
#> LotConfig 13009691424
#> BldgType 12984733852
#> MasVnrType 12927751811
#> Condition1 12860107386
#> CentralAir 12443210183
#> RoofMatl 12301992390
#> GarageQual 11828494238
#> EnclosedPorch 10704554730
#> BsmtCond 10699731310
#> LandSlope 10683526316
#> KitchenAbvGr 10306427352
#> GarageCond 9216481926
#> BsmtFinSF2 8581199639
#> ExterCond 7926070704
#> Functional 6060073754
#> BsmtFinType2 6004231202
#> PavedDrive 5306595470
#> Fence 5134494920
#> Electrical 5071077592
#> LowQualFinSF 4776684987
#> Condition2 3624570125
#> Heating 3039478135
#> MiscVal 2706596509
#> 3SsnPorch 2160379168
#> PoolArea 2054262842
#> Street 462732232
#> Utilities 35919859
rmse(actual = xtest$SalePrice, predicted = pred)
#> [1] 28487.59Xgboost
xgb <- XGBTrainer$new(objective = "reg:linear"
, n_estimators = 500
, eval_metric = "rmse"
, maximize = F
, learning_rate = 0.1
,max_depth = 6)
xgb$fit(X = xtrain, y = "SalePrice", valid = xtest)
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-rmse:180008.062500 val-rmse:176587.687500
#> Multiple eval metrics are present. Will use val_rmse for early stopping.
#> Will train until val_rmse hasn't improved in 50 rounds.
#>
#> [51] train-rmse:8518.276367 val-rmse:29630.851562
#> [101] train-rmse:5049.125977 val-rmse:28340.820312
#> [151] train-rmse:3199.518799 val-rmse:28220.812500
#> [201] train-rmse:2296.443359 val-rmse:28185.636719
#> Stopping. Best iteration:
#> [173] train-rmse:2727.999512 val-rmse:28174.412109
pred <- xgb$predict(xtest)
rmse(actual = xtest$SalePrice, predicted = pred)
#> [1] 28174.42Grid Search
xgb <- XGBTrainer$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")
#> [1] "entering grid search"
#> [1] "In total, 4 models will be trained"
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-rmse:143770.906250
#> Will train until train_rmse hasn't improved in 50 rounds.
#>
#> [10] train-rmse:16830.447266
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-rmse:143539.765625
#> Will train until train_rmse hasn't improved in 50 rounds.
#>
#> [10] train-rmse:15880.406250
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-rmse:141585.953125
#> Will train until train_rmse hasn't improved in 50 rounds.
#>
#> [10] train-rmse:15536.412109
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-rmse:143770.906250
#> Will train until train_rmse hasn't improved in 50 rounds.
#>
#> [50] train-rmse:3607.689697
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-rmse:143539.765625
#> Will train until train_rmse hasn't improved in 50 rounds.
#>
#> [50] train-rmse:3777.051514
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-rmse:141585.953125
#> Will train until train_rmse hasn't improved in 50 rounds.
#>
#> [50] train-rmse:3666.455811
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-rmse:144819.453125
#> Will train until train_rmse hasn't improved in 50 rounds.
#>
#> [10] train-rmse:32198.896484
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-rmse:144439.859375
#> Will train until train_rmse hasn't improved in 50 rounds.
#>
#> [10] train-rmse:31735.691406
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-rmse:142559.171875
#> Will train until train_rmse hasn't improved in 50 rounds.
#>
#> [10] train-rmse:30720.810547
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-rmse:144819.453125
#> Will train until train_rmse hasn't improved in 50 rounds.
#>
#> [50] train-rmse:18957.185547
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-rmse:144439.859375
#> Will train until train_rmse hasn't improved in 50 rounds.
#>
#> [50] train-rmse:17248.701172
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-rmse:142559.171875
#> Will train until train_rmse hasn't improved in 50 rounds.
#>
#> [50] train-rmse:16948.439453
gst$best_iteration()
#> $n_estimators
#> [1] 10
#>
#> $max_depth
#> [1] 5
#>
#> $accuracy_avg
#> [1] 0
#>
#> $accuracy_sd
#> [1] 0
#>
#> $auc_avg
#> [1] NaN
#>
#> $auc_sd
#> [1] NARandom Search
rf <- RFTrainer$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] 5
#>
#> $max_depth
#> [1] 2
#>
#> $accuracy_avg
#> [1] 0.009760997
#>
#> $accuracy_sd
#> [1] 0.001646201
#>
#> $auc_avg
#> [1] NaN
#>
#> $auc_sd
#> [1] NAHere, we will solve a simple binary classification problem (predict people who survived on titanic ship). The idea here is to demonstrate how to use this package to solve classification problems.
Data Preparation
# load class
load('../data/cla_train.rda')
# if the above doesn't work, you can try: load("cla_train.rda")
head(cla_train)
#> PassengerId Survived Pclass
#> 1: 1 0 3
#> 2: 2 1 1
#> 3: 3 1 3
#> 4: 4 1 1
#> 5: 5 0 3
#> 6: 6 0 3
#> Name Sex Age SibSp Parch
#> 1: Braund, Mr. Owen Harris male 22 1 0
#> 2: Cumings, Mrs. John Bradley (Florence Briggs Thayer) female 38 1 0
#> 3: Heikkinen, Miss. Laina female 26 0 0
#> 4: Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35 1 0
#> 5: Allen, Mr. William Henry male 35 0 0
#> 6: Moran, Mr. James male NA 0 0
#> Ticket Fare Cabin Embarked
#> 1: A/5 21171 7.2500 S
#> 2: PC 17599 71.2833 C85 C
#> 3: STON/O2. 3101282 7.9250 S
#> 4: 113803 53.1000 C123 S
#> 5: 373450 8.0500 S
#> 6: 330877 8.4583 Q
# split the data
split <- createDataPartition(y = cla_train$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)
#>
#> Deviance Residuals:
#> Min 1Q Median 3Q Max
#> -2.6102 -0.6018 -0.4367 0.7038 2.4493
#>
#> 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 67.80128
#> Fare 57.97193
#> Age 48.37045
#> Pclass 24.64915
#> Cabin 21.45972
#> SibSp 13.51637
#> Parch 10.45743
#> Embarked 10.23844
auc(actual = xtest$Survived, predicted = pred)
#> [1] 0.7976827Xgboost
xgb <- XGBTrainer$new(objective = "binary:logistic"
, n_estimators = 500
, eval_metric = "auc"
, maximize = T
, learning_rate = 0.1
,max_depth = 6)
xgb$fit(X = xtrain, y = "Survived", valid = xtest)
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-auc:0.886258 val-auc:0.879085
#> Multiple eval metrics are present. Will use val_auc for early stopping.
#> Will train until val_auc hasn't improved in 50 rounds.
#>
#> [51] train-auc:0.972938 val-auc:0.866370
#> Stopping. Best iteration:
#> [1] train-auc:0.886258 val-auc:0.879085
pred <- xgb$predict(xtest)
auc(actual = xtest$Survived, predicted = pred)
#> [1] 0.879085Grid Search
xgb <- XGBTrainer$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")
#> [1] "entering grid search"
#> [1] "In total, 4 models will be trained"
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-error:0.144231
#> Will train until train_error hasn't improved in 50 rounds.
#>
#> [10] train-error:0.108173
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-error:0.134615
#> Will train until train_error hasn't improved in 50 rounds.
#>
#> [10] train-error:0.112981
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-error:0.115385
#> Will train until train_error hasn't improved in 50 rounds.
#>
#> [10] train-error:0.084135
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-error:0.144231
#> Will train until train_error hasn't improved in 50 rounds.
#>
#> [50] train-error:0.045673
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-error:0.134615
#> Will train until train_error hasn't improved in 50 rounds.
#>
#> [50] train-error:0.045673
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-error:0.115385
#> Will train until train_error hasn't improved in 50 rounds.
#>
#> [50] train-error:0.038462
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-error:0.211538
#> Will train until train_error hasn't improved in 50 rounds.
#>
#> [10] train-error:0.158654
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-error:0.201923
#> Will train until train_error hasn't improved in 50 rounds.
#>
#> [10] train-error:0.168269
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-error:0.206731
#> Will train until train_error hasn't improved in 50 rounds.
#>
#> [10] train-error:0.141827
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-error:0.211538
#> Will train until train_error hasn't improved in 50 rounds.
#>
#> [50] train-error:0.127404
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-error:0.201923
#> Will train until train_error hasn't improved in 50 rounds.
#>
#> [50] train-error:0.132212
#> converting the data into xgboost format..
#> starting with training...
#> [1] train-error:0.206731
#> Will train until train_error hasn't improved in 50 rounds.
#>
#> [50] train-error:0.108173
gst$best_iteration()
#> $n_estimators
#> [1] 10
#>
#> $max_depth
#> [1] 5
#>
#> $accuracy_avg
#> [1] 0
#>
#> $accuracy_sd
#> [1] 0
#>
#> $auc_avg
#> [1] 0.8619512
#>
#> $auc_sd
#> [1] 0.02280628Random Search
rf <- RFTrainer$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] 0.7964744
#>
#> $accuracy_sd
#> [1] 0.03090914
#>
#> $auc_avg
#> [1] 0.7729436
#>
#> $auc_sd
#> [1] 0.04283084Let’s create some new feature based on target variable using target encoding and test a model.
# add target encoding features
xtrain[, feat_01 := smoothMean(train_df = xtrain,
test_df = xtest,
colname = "Embarked",
target = "Survived")$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$get_importance()
#> tmp.order.tmp..decreasing...TRUE..
#> Sex 69.787235
#> Fare 60.832089
#> Age 52.982604
#> Pclass 24.419818
#> Cabin 21.419274
#> SibSp 13.112177
#> Parch 10.175269
#> feat_01 6.675399
#> Embarked 6.450819
auc(actual = xtest$Survived, predicted = pred)
#> [1] 0.8018717