selva86

# Code used in R Programming Course.
# Import Data
url <- "http://rstatistics.net/wp-content/uploads/2015/09/ozone.csv"
inputData <- read.csv(url)

# Replace outliers as missing values.
replace_outlier_with_missing <- function(x, na.rm = TRUE, ...) {
  qnt <- quantile(x, probs=c(.25, .75), na.rm = na.rm, ...)  # get %iles
  H <- 1.5 * IQR(x, na.rm = na.rm)  # outlier limit threshold
  y <- x

selva86

.libPaths()

url <- "http://rstatistics.net/wp-content/uploads/2015/09/ozone.csv"
inputData <- read.csv(url)

# Replace outliers as missing values.
replace_outlier_with_missing <- function(x, na.rm = TRUE, ...) {
  qnt <- quantile(x, probs=c(.25, .75), na.rm = na.rm, ...)  # get %iles
  H <- 1.5 * IQR(x, na.rm = na.rm)  # outlier limit threshold
  y <- x

selva86

# How to fill area under the line in base graphics
  library(xts)
  library(data.table)
  library(lubridate)
  set.seed(100)
  date_seq <- seq.POSIXt(from=ymd("2016-01-01", tz="UTC"), length=100, by = "day")
  y <- round(runif(100), 2)
  df <- data.table(date=date_seq, y)
  head(df)
  

selva86

# How to write multi-level ifelse()
set.seed(100)
abc <- sample(letters[1:5], 1000, replace = T)
df <- data.frame(v1=abc, v2="blank", stringsAsFactors = F)
head(df)

system.time({
  df$v2 <- ifelse(df$v1 == "a", "apple", 
                  ifelse(df$v1 == "b", "ball",
                         ifelse(df$v1 == "c", "cat",

selva86

## Solutions for Final Test of Learn R By Intensive Practice
Q1. 
```{r}
#1
sqrt (729)

#2
1203 %% 22

#3

selva86

# prep training and test datasets
set.seed(100)
trainRows <- createDataPartition(prostate$lpsa, p=.75, list=FALSE)
trainData <- prostate[trainRows, ]
testData  <- prostate[-trainRows, ]

# prepare X and Y matrices separately
train_x <- as.matrix(trainData[, colnames(trainData) %ni% c("lpsa", "train")])
train_y <- as.matrix(trainData[, "lpsa"])
test_x <- as.matrix(testData[, colnames(trainData) %ni% c("lpsa", "train")])

selva86

library(InformationValue)
library(ggplot2)
# 1. Import dataset
trainData <- read.csv('https://raw.githubusercontent.com/selva86/datasets/master/breastcancer_training.csv')
testData <- read.csv('https://raw.githubusercontent.com/selva86/datasets/master/breastcancer_test.csv')

# 2. Build Logistic Model
logitmod <- glm(Class ~ Cl.thickness + Cell.size + Cell.shape, family = "binomial", data=trainData)

# 3. Predict on testData

selva86

library(InformationValue)
library(ggplot2)
ks_plot <- function (actuals, predictedScores) {
    rank <- 0:10
    ks_table_out <- InformationValue:::ks_table(actuals = actuals, predictedScores = predictedScores)
    perc_positive <- c(0, ks_table_out$cum_perc_responders) * 100
    perc_negative <- c(0, ks_table_out$cum_perc_non_responders) * 100
    random_prediction <- seq(0, 100, 10)
    df <- data.frame(rank, random_prediction, perc_positive, perc_negative)
    df_stack <- stack(df, c(random_prediction, perc_positive, perc_negative))

selva86

# Pre-create a 'pizza_tc_score' vector with missing values 
set.seed(100)
pizza_tc_score <- round(runif (1000,3,10))
pizza_tc_score [c(100,204,709,816,938)] = NA

selva86

# Mini Challenge Inputs
vans  <- c(3,4,5,2,4,4,5)
boxes <- c(30,44,50,18,36,36,40)