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")
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 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] 50794.05SVM 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
#> -139243 -13025 -186 12472 158743
#>
#> Coefficients:
#> Estimate Std. Error t value Pr(>|t|)
#> (Intercept) -2.008e+06 1.260e+06 -1.593 0.111462
#> MSSubClass -3.830e+01 4.350e+01 -0.880 0.378829
#> MSZoning -1.445e+02 1.162e+03 -0.124 0.901098
#> LotFrontage 6.473e+01 2.697e+01 2.400 0.016598 *
#> LotArea 4.401e-01 1.168e-01 3.767 0.000176 ***
#> Street -3.784e+04 1.182e+04 -3.201 0.001414 **
#> LotShape 3.651e+03 1.641e+03 2.225 0.026301 *
#> LandContour 2.807e+03 1.842e+03 1.524 0.127719
#> Utilities -2.701e+04 2.727e+04 -0.991 0.322180
#> LotConfig 3.069e+02 8.777e+02 0.350 0.726639
#> LandSlope 1.813e+03 4.229e+03 0.429 0.668286
#> Neighborhood -3.361e+02 1.538e+02 -2.186 0.029074 *
#> Condition1 -1.932e+03 6.913e+02 -2.795 0.005297 **
#> Condition2 -4.259e+03 3.532e+03 -1.206 0.228200
#> BldgType -2.483e+03 1.668e+03 -1.488 0.136958
#> HouseStyle 2.632e+02 8.262e+02 0.319 0.750084
#> OverallQual 1.336e+04 1.120e+03 11.930 < 2e-16 ***
#> OverallCond 6.068e+03 9.974e+02 6.084 1.70e-09 ***
#> YearBuilt 4.657e+02 6.701e+01 6.950 6.80e-12 ***
#> YearRemodAdd 1.766e+02 6.343e+01 2.784 0.005477 **
#> RoofStyle -1.631e+02 1.564e+03 -0.104 0.916996
#> RoofMatl -9.933e+02 2.137e+03 -0.465 0.642230
#> Exterior1st -4.735e+02 5.755e+02 -0.823 0.410843
#> Exterior2nd 9.892e+02 5.221e+02 1.895 0.058425 .
#> MasVnrType 4.333e+03 1.360e+03 3.186 0.001489 **
#> MasVnrArea 1.631e+01 5.720e+00 2.852 0.004438 **
#> ExterQual 3.787e+03 1.960e+03 1.932 0.053642 .
#> ExterCond 1.081e+03 1.979e+03 0.547 0.584829
#> Foundation 3.883e+02 1.450e+03 0.268 0.788846
#> BsmtQual 7.885e+03 1.226e+03 6.429 2.03e-10 ***
#> BsmtCond -1.370e+03 1.557e+03 -0.880 0.379040
#> BsmtExposure 2.390e+03 8.087e+02 2.956 0.003198 **
#> BsmtFinType1 -2.546e+02 6.252e+02 -0.407 0.683943
#> BsmtFinSF1 5.254e+01 4.982e+00 10.544 < 2e-16 ***
#> BsmtFinType2 -9.432e+02 9.958e+02 -0.947 0.343782
#> BsmtFinSF2 4.247e+01 8.402e+00 5.055 5.16e-07 ***
#> BsmtUnfSF 3.213e+01 4.503e+00 7.136 1.90e-12 ***
#> Heating 1.569e+03 3.627e+03 0.433 0.665359
#> HeatingQC -2.590e+03 1.113e+03 -2.326 0.020214 *
#> CentralAir 4.251e+03 4.370e+03 0.973 0.330970
#> Electrical 2.337e+03 1.815e+03 1.287 0.198278
#> `1stFlrSF` 5.243e+01 5.824e+00 9.002 < 2e-16 ***
#> `2ndFlrSF` 6.578e+01 5.045e+00 13.038 < 2e-16 ***
#> LowQualFinSF 2.598e+00 1.859e+01 0.140 0.888898
#> BsmtFullBath 1.516e+03 2.452e+03 0.618 0.536538
#> BsmtHalfBath -8.169e+03 3.729e+03 -2.191 0.028694 *
#> FullBath 3.146e+03 2.583e+03 1.218 0.223441
#> HalfBath -1.372e+03 2.416e+03 -0.568 0.570139
#> BedroomAbvGr -1.173e+04 1.594e+03 -7.358 4.05e-13 ***
#> KitchenAbvGr -2.394e+04 4.839e+03 -4.948 8.89e-07 ***
#> KitchenQual 7.690e+03 1.521e+03 5.057 5.11e-07 ***
#> TotRmsAbvGrd 3.323e+03 1.160e+03 2.865 0.004266 **
#> Functional -8.284e+03 1.356e+03 -6.110 1.45e-09 ***
#> Fireplaces 8.055e+02 2.159e+03 0.373 0.709194
#> FireplaceQu 1.473e+03 1.181e+03 1.248 0.212406
#> GarageType 1.958e+03 1.083e+03 1.808 0.070876 .
#> GarageYrBlt 1.195e+00 4.366e+00 0.274 0.784395
#> GarageFinish 2.291e+03 1.200e+03 1.910 0.056460 .
#> GarageCars 4.727e+03 2.887e+03 1.637 0.101914
#> GarageArea 1.305e+01 9.440e+00 1.383 0.167042
#> GarageQual 4.180e+03 2.532e+03 1.651 0.099071 .
#> GarageCond -3.997e+03 2.491e+03 -1.604 0.108970
#> PavedDrive -3.272e+03 2.625e+03 -1.246 0.212904
#> WoodDeckSF 1.629e+01 7.618e+00 2.138 0.032734 *
#> OpenPorchSF 2.127e+01 1.437e+01 1.479 0.139374
#> EnclosedPorch 3.056e+00 1.515e+01 0.202 0.840151
#> `3SsnPorch` 1.704e+01 3.440e+01 0.495 0.620553
#> ScreenPorch 3.825e+01 1.530e+01 2.500 0.012578 *
#> PoolArea 1.092e+02 2.295e+01 4.758 2.26e-06 ***
#> Fence -1.986e+03 1.152e+03 -1.724 0.085018 .
#> MiscVal -1.095e+00 4.416e+00 -0.248 0.804163
#> MoSold -2.236e+02 3.141e+02 -0.712 0.476744
#> YrSold 3.308e+02 6.273e+02 0.527 0.598066
#> SaleType 1.091e+03 1.100e+03 0.992 0.321271
#> SaleCondition 1.645e+03 9.888e+02 1.663 0.096558 .
#> ---
#> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#>
#> (Dispersion parameter for gaussian family taken to be 648612116)
#>
#> Null deviance: 6.2335e+12 on 1023 degrees of freedom
#> Residual deviance: 6.1553e+11 on 949 degrees of freedom
#> AIC: 23757
#>
#> Number of Fisher Scoring iterations: 2
predictions <- lf$predict(df = xtest)
rmse(actual = xtest$SalePrice, predicted = predictions)
#> [1] 51530.25Lasso Regression
lf <- LMTrainer$new(family = "gaussian", alpha = 1, lambda = 1000)
lf$fit(X = xtrain, y = "SalePrice")
predictions <- lf$predict(df = xtest)
rmse(actual = xtest$SalePrice, predicted = predictions)
#> [1] 55911.69Ridge Regression
lf <- LMTrainer$new(family = "gaussian", alpha=0)
lf$fit(X = xtrain, y = "SalePrice")
predictions <- lf$predict(df = xtest)
rmse(actual = xtest$SalePrice, predicted = predictions)
#> [1] 56556.61Logistic Regression with CV
lf <- LMTrainer$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 833350284068
#> GarageCars 465479127916
#> 1stFlrSF 445606600578
#> GarageArea 396242047750
#> YearBuilt 364988991992
#> FullBath 286370539079
#> BsmtFinSF1 284612099870
#> GarageYrBlt 254491890949
#> ExterQual 223773978981
#> TotRmsAbvGrd 219141701180
#> 2ndFlrSF 189706505897
#> LotArea 169461096779
#> Fireplaces 141235914606
#> YearRemodAdd 134142408678
#> KitchenQual 132732494284
#> FireplaceQu 131673516393
#> MasVnrArea 107853599183
#> Foundation 104223221462
#> BsmtQual 99876088175
#> OpenPorchSF 83642601447
#> BsmtFinType1 78327672652
#> LotFrontage 77809357818
#> BsmtUnfSF 63322066423
#> Neighborhood 61053253580
#> WoodDeckSF 59661913778
#> HeatingQC 51360521952
#> GarageType 47242624339
#> BedroomAbvGr 41064075573
#> Exterior2nd 38308339821
#> Exterior1st 35097827861
#> MSSubClass 34774064972
#> OverallCond 33679741152
#> RoofStyle 31494089946
#> HalfBath 30374947665
#> MoSold 30024831953
#> GarageFinish 29552460141
#> HouseStyle 26939781931
#> BsmtExposure 22214362388
#> MSZoning 21832228050
#> BsmtFullBath 21242098578
#> LotShape 20582280804
#> YrSold 18993656717
#> MasVnrType 16121832830
#> LandContour 15579897406
#> LotConfig 14240812890
#> GarageQual 14017925183
#> SaleType 13991450447
#> SaleCondition 13697063876
#> GarageCond 12968703189
#> ScreenPorch 12669353846
#> CentralAir 12257009224
#> LandSlope 11752540501
#> BldgType 10826146503
#> PoolArea 9881220379
#> BsmtCond 9136680119
#> Fence 8706441341
#> ExterCond 8230230400
#> EnclosedPorch 8095663365
#> BsmtFinSF2 6653807222
#> Functional 6329620593
#> KitchenAbvGr 5895685275
#> BsmtFinType2 5833219898
#> LowQualFinSF 4879512060
#> Condition1 4860876751
#> RoofMatl 3785085428
#> PavedDrive 3709917158
#> Electrical 3491437439
#> BsmtHalfBath 3357275107
#> MiscVal 2143773519
#> 3SsnPorch 2123549514
#> Heating 1308976630
#> Street 830618588
#> Condition2 201504146
#> Utilities 54630098
rmse(actual = xtest$SalePrice, predicted = pred)
#> [1] 35475.5Xgboost
xgb <- XGBTrainer$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] 5
#>
#> $max_depth
#> [1] 2
#>
#> $accuracy_avg
#> [1] 0.006834145
#>
#> $accuracy_sd
#> [1] 0.0033791
#>
#> $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$fit(X = xtrain, y = "Survived", valid = xtest)
pred <- xgb$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] 0.7964744
#>
#> $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