Krishna Rao kkraoj

## order_time.csv

          
            order_id
            fulfillment_time_seconds

            
              0
              2.9509841658615305e-08

            
              1
              0.019505169765189057

            
              2
              7.303478954872057e-16

            
              3
              1.9101714003472088e-24

            
              4
              0.0003794473081403896

            
              5
              1.865537747211439e-33

            
              6
              0.2553208994364204

            
              7
              1.5598051802319622e-14

            
              8
              4.6173232860197476e-10

## order_value.csv

          
            order_id
            order_value_usd

            
              0
              0.7395043833099897

            
              1
              1.0355865556717134

            
              2
              0.6764152559872895

            
              3
              0.3446415677127145

            
              4
              1.1726401061050669

            
              5
              1.3904307829698468

            
              6
              0.4426054505368791

            
              7
              0.6919847590849365

            
              8
              1.2532877991500495

## cv_right.rmd
```{r first separate data into folds before choosing features}

# train the model on training set

# Leave out fold
accuracy.rates <- c()
for (itr in seq_len(folds)){
  # Note: since input features are already random, no need to shuffle the data
  # before creating folds. But ideally, examples need to be shuffled before
  # creating folds to get rid of recording/data collecting bias

## cv_wrong.rmd
```{r setup, include=FALSE}
rm(list=ls())
knitr::opts_chunk$set(echo = TRUE)
library(caret)
library(ggplot2)

```

# Cross validation Example: The wrong way and the right way
	order_id	fulfillment_time_seconds
	0	2.9509841658615305e-08
	1	0.019505169765189057
	2	7.303478954872057e-16
	3	1.9101714003472088e-24
	4	0.0003794473081403896
	5	1.865537747211439e-33
	6	0.2553208994364204
	7	1.5598051802319622e-14
	8	4.6173232860197476e-10
	order_id	order_value_usd
	0	0.7395043833099897
	1	1.0355865556717134
	2	0.6764152559872895
	3	0.3446415677127145
	4	1.1726401061050669
	5	1.3904307829698468
	6	0.4426054505368791
	7	0.6919847590849365
	8	1.2532877991500495
	```{r first separate data into folds before choosing features}

	# train the model on training set

	# Leave out fold
	accuracy.rates <- c()
	for (itr in seq_len(folds)){
	# Note: since input features are already random, no need to shuffle the data
	# before creating folds. But ideally, examples need to be shuffled before
	# creating folds to get rid of recording/data collecting bias
	```{r setup, include=FALSE}
	rm(list=ls())
	knitr::opts_chunk$set(echo = TRUE)
	library(caret)
	library(ggplot2)

	```

	# Cross validation Example: The wrong way and the right way