DriveML: Self-Drive machine learning projects

1. Introduction

The document introduces the DriveML package and how it can help you to build effortless machine learning binary classification models in short period

DriveML is a series of functions sucha as AutoDataPrep, AutoMAR, autoMLmodel. DriveML automates some of the most difficult machine learning functions such as data exploratory analysis, data pre-processing, feature engineering, model training, model validation, model tuning and model selection.

This package automates following steps on any input dataset for machine learning classification problems

Exploratory data analysis using SmartEDA functions
- Generate automated EDA report in HTML format to understand the distributions of the data
Data cleaning
- Replacing NA, infinite values
- Removing duplicates
- Cleaning feature names
Feature engineering
- Missing at random features
- Missing variable imputation
- Outlier treatment - Oultier flag and imputation with 5th or 95th percentile value
- Date variable transformation
- Bulk interactions for numerical features
- Frequent tranformer for categorical features
- Categorical feature engineering - one hot encoding
- Feature selection using zero variance, correlation and AUC method
Model training and validation
- Automated test and validation set creations
- Hyperparameter tuing using random search
- Mutliple binary classification included like logistic regression, randomForest, xgboost, glmnet, rpart
- Model validation using AUC value
- Model plots like training and testing ROC curve, threshold plot
- Probaility scores and model objects
Ensemble modelling
- Model ensembling using nnls and nnet method
Model Explanation
- Lift plot
- Partial dependence plot
- Feature importance plot
Model report
- model output in rmarkdown html format

To summarize, DriveML package helps in getting the complete Machine learning classification model just by running the function instead of writing lengthy r code.

This package performs ML models in R using MLR package

Missing not at random features

Algorithm: Missing at random features

Select all the missing features X_i where i=1,2,…..,N.
For i=1 to N:
- Define Y_i, which will have value of 1 if X_i has a missing value, 0 if X_i is not having missing value
- Impute all X_(i+1 ) 〖to X〗_(N ) variables using imputation method
- Fit binary classifier f_m to the training data using Y_i ~ X_(i+1 ) 〖+⋯+ X〗_(N )
- Calculate AUC ∝_ivalue between actual Y_i and predicted Y ̂_i
- If ∝_i is low then the missing values in X_i are missing at random,Y_i to be dropped
- Repeat steps 1 to 4 for all the independent variables in the original dataset

3. DriveML: Machine learning classfication model

About data

This database contains 76 attributes, but all published experiments refer to using a subset of 14 of them. In particular, the Cleveland database is the only one that has been used by ML researchers to this date. The “goal” field refers to the presence of heart disease in the patient. It is integer valued from 0 (no presence) to 4.

Data Source Kaggle.

Install the package “DriveML” to get the example data set.

install.packages("DriveML")
library("DriveML")
library("SmartEDA")
## Load sample dataset from ISLR pacakge
heart = DriveML::heart

more detailed attribute information is there in DriveML help page

3.1 Data Exploration

For data exploratory analysis used SmartEDA package

Overview of the data

Understanding the dimensions of the dataset, variable names, overall missing summary and data types of each variables

# Overview of the data - Type = 1
ExpData(data=heart,type=1)

# Structure of the data - Type = 2
ExpData(data=heart,type=2)

Overview of the data

Descriptions	Obs
Sample size (Nrow)	303
No. of Variables (Ncol)	14
No. of Numeric Variables	14
No. of Factor Variables	0
No. of Text Variables	0
No. of Logical Variables	0
No. of Unique Variables	0
No. of Date Variables	0
No. of Zero variance Variables (Uniform)	0
%. of Variables having complete cases	100% (14)
%. of Variables having <50% missing cases	0% (0)
%. of Variables having >50% missing cases	0% (0)
%. of Variables having >90% missing cases	0% (0)

Structure of the data

S.no	Variable Name	Variable Type	No. of Unique values
1	age	integer	41
2	sex	integer	2
3	cp	integer	4
4	trestbps	integer	49
5	chol	integer	152
6	fbs	integer	2
7	restecg	integer	3
8	thalach	integer	91
9	exang	integer	2
10	oldpeak	numeric	40
11	slope	integer	3
12	ca	integer	5
13	thal	integer	4
14	target_var	integer	2

Summary of numerical variables

ExpNumStat(heart,by="GA",gp="target_var",Qnt=seq(0,1,0.1),MesofShape=2,Outlier=TRUE,round=2)

Distributions of Numerical variables

Box plots for all numerical variables vs categorical dependent variable - Bivariate comparision only with categories

Boxplot for all the numeric attributes by each category of target_var

plot4 <- ExpNumViz(heart,target="target_var",type=1,nlim=3,fname=NULL,Page=c(2,2),sample=8)
plot4[[1]]

Summary of categorical variables

Cross tabulation with target_var variable

Custom tables between all categorical independent variables and target_var variable target_var

ExpCTable(Carseats,Target="Urban",margin=1,clim=10,nlim=3,round=2,bin=NULL,per=F)

VARIABLE	CATEGORY	target_var:0	target_var:1	TOTAL
sex	0	24	72	96
sex	1	114	93	207
sex	TOTAL	138	165	303
fbs	0	116	142	258
fbs	1	22	23	45
fbs	TOTAL	138	165	303
restecg	0	79	68	147
restecg	1	56	96	152
restecg	2	3	1	4
restecg	TOTAL	138	165	303
exang	0	62	142	204
exang	1	76	23	99
exang	TOTAL	138	165	303
slope	0	12	9	21
slope	1	91	49	140
slope	2	35	107	142
slope	TOTAL	138	165	303
target_var	0	138	0	138
target_var	1	0	165	165
target_var	TOTAL	138	165	303

Distributions of categorical variables

Stacked bar plot with vertical or horizontal bars for all categorical variables

plot5 <- ExpCatViz(heart,target = "target_var", fname = NULL, clim=5,col=c("slateblue4","slateblue1"),margin=2,Page = c(2,1),sample=2)
plot5[[1]]

Outlier analysis using boxplot

ExpOutliers(heart, varlist = c("oldpeak","trestbps","chol"), method = "boxplot",  treatment = "mean", capping = c(0.1, 0.9))

Category	oldpeak	trestbps	chol
Lower cap : 0.1	0	110	188
Upper cap : 0.9	2.8	152	308.8
Lower bound	-2.4	90	115.75
Upper bound	4	170	369.75
Num of outliers	5	9	5
Lower outlier case
Upper outlier case	102,205,222,251,292	9,102,111,204,224,242,249,261,267	29,86,97,221,247
Mean before	1.04	131.62	246.26
Mean after	0.97	130.1	243.04
Median before	0.8	130	240
Median after	0.65	130	240

3.2 Data preparations using `autoDataprep`

dateprep <- autoDataprep(data = heart,
                             target = 'target_var',
                             missimpute = 'default',
                             auto_mar = FALSE,
                             mar_object = NULL,
                             dummyvar = TRUE,
                             char_var_limit = 15,
                             aucv = 0.002,
                             corr = 0.98,
                             outlier_flag = TRUE,
                             uid = NULL,
                             onlykeep = NULL,
                             drop = NULL)
printautoDataprep(dateprep)

## Data preparation result 
## Call:
##  autoDataprep(data = heart, target = "target_var", missimpute = "default",      auto_mar = FALSE, mar_object = NULL, dummyvar = TRUE, char_var_limit = 15,      aucv = 0.002, corr = 0.98, outlier_flag = TRUE, uid = NULL,      onlykeep = NULL, drop = NULL) 
## 
##  *** Data preparation summary *** 
## Total no. of columns available in the data set:  14 
## No. of numeric columns:                          8 
## No. of factor / character columns:               0 
## No. of date columns:                             0 
## No. of logical columns:                          0 
## No. of unique columns:                           0 
## No. of MAR columns:                              0 
## No. of dummy variables created:                  0 
## 
##  *** Variable reduction *** 
## Step 1 - Checked and removed useless variables:         6 
## Step 2 - No. of variables before fetature reduction:    22 
## Step 3 - No. of zero variance columns (Constant):       0 
## Step 4 - No. of high correlated or bijection columns:   3 
## Step 5 - No. of low AUC valued columns:                 2 
## *Final number of columns considered for ML model:       17 
## 
##  *** Data preparation highlights *** 
## Missing replaced with { 
## --> factor = imputeMode()
## --> integer = imputeMean()
## --> numeric = imputeMedian()
## --> character = imputeMode() }

train_data <- dateprep$master_data

3.3 Machine learning models using `autoMLmodel`

Automated training, tuning and validation of machine learning models. This function includes following binary classification techniques

Logistic regression - logreg
- Regularised regression - glmnet
- Extreme gradient boosting - xgboost
- Random forest - randomForest
- Random forest - ranger
- Decision tree - rpart

mymodel <- autoMLmodel( train = heart,
                        test = NULL,
                        target = 'target_var',
                        testSplit = 0.2,
                        tuneIters = 10,
                        tuneType = "random",
                        models = "all",
                        varImp = 10,
                        liftGroup = 50,
                        maxObs = 4000,
                        uid = NULL,
                        htmlreport = FALSE,
                        seed = 1991)

3.3 Model output

Model performance

Model	Fitting time	Scoring time	Train AUC	Test AUC	Accuracy	Precision	Recall	F1_score
glmnet	2.558 secs	0.008 secs	0.928	0.908	0.820	0.824	0.848	0.836
logreg	2.513 secs	0.004 secs	0.929	0.906	0.820	0.824	0.848	0.836
randomForest	2.785 secs	0.012 secs	1.000	0.877	0.754	0.765	0.788	0.776
ranger	2.981 secs	0.044 secs	0.999	0.900	0.803	0.784	0.879	0.829
xgboost	2.938 secs	0.004 secs	0.996	0.907	0.820	0.806	0.879	0.841
rpart	2.559 secs	0.004 secs	0.927	0.814	0.738	0.730	0.818	0.771

Randomforest model ROC curve and variable importance

Training data set ROC

TrainROC <- mymodel$trainedModels$randomForest$modelPlots$TrainROC
TrainROC

Test data set ROC

TestROC <- mymodel$trainedModels$randomForest$modelPlots$TestROC
TestROC

Variable importance

VarImp <- mymodel$trainedModels$randomForest$modelPlots$VarImp
VarImp

## [[1]]

Threshold

Threshold <- mymodel$trainedModels$randomForest$modelPlots$Threshold
Threshold

DriveML: Self-Drive machine learning projects

Automated machine learning classification model functions

Dayananda Ubrangala, Sayan Putatunda, Kiran R, Ravi Prasad Kondapalli

2020-05-29

1. Introduction

Missing not at random features

2. Functionalities of DriveML

3. DriveML: Machine learning classfication model

About data

3.1 Data Exploration

Overview of the data

Summary of numerical variables

Distributions of Numerical variables

Summary of categorical variables

Distributions of categorical variables

Outlier analysis using boxplot

3.2 Data preparations using `autoDataprep`

3.3 Machine learning models using `autoMLmodel`

3.3 Model output

DriveML: Self-Drive machine learning projects

Automated machine learning classification model functions

Dayananda Ubrangala, Sayan Putatunda, Kiran R, Ravi Prasad Kondapalli

2020-05-29

1. Introduction

Missing not at random features

2. Functionalities of DriveML

3. DriveML: Machine learning classfication model

About data

3.1 Data Exploration

Overview of the data

Summary of numerical variables

Distributions of Numerical variables

Summary of categorical variables

Distributions of categorical variables

Outlier analysis using boxplot

3.2 Data preparations using autoDataprep

3.3 Machine learning models using autoMLmodel

3.3 Model output

3.2 Data preparations using `autoDataprep`

3.3 Machine learning models using `autoMLmodel`