###
###
###  Heart - Preliminary Analysis
###                               ver 0.0.4
###
####################################################


#-------------------------------------------------
###--- 0. Preliminary
library(tidyverse)
Heart <- read_csv("https://nmimoto.github.io/datasets/heart.csv")
Heart

class(Heart)               # it's already tibble
print(Heart, n=100)        # if you want to see more rows
print(Heart, width=1000)   # if you want to see more cols
names(Heart)


#  #0  "X1"         index
#  #1  "Age"        age in years
#  #2  "Sex"        (Qualitative) sex (1 = male; 0 = female)
#  #3  "ChestPain"  (Qualitative) chest pain type
#                      -- Value 1: typical angina
#                      -- Value 2: atypical angina
#                      -- Value 3: non-anginal pain
#                      -- Value 4: asymptomatic
#  #4  "RestBP"     resting blood pressure (in mm Hg on admission to the hospital)
#  #5  "Chol"       serum cholestoral in mg/dl
#  #6  "Fbs"        (Qualitative) fasting blood sugar > 120 mg/dl (1 = true; 0 = false)
#  #7  "RestECG"    (Qualitative) resting electrocardiographic results
#                       -- Value 0: normal
#                       -- Value 1: having ST-T wave abnormality (T wave inversions and/or ST elevation or depression of > 0.05 mV)
#                       -- Value 2: showing probable or definite left ventricular hypertrophy by Estes' criteria
#  #8  "MaxHR"      maximum heart rate achieved
#  #9  "ExAng"      (Qualitative) exercise induced angina (1 = yes; 0 = no)
#  #10 "Oldpeak"    oldpeak = ST depression induced by exercise relative to rest
#  #11 "Slope"      the slope of the peak exercise ST segment
#  #12 "Ca"         number of major vessels (0-3) colored by flourosopy
#  #13 "Thal"       (Qualitative) Thalium stress test
#                     3 = normal; 6 = fixed defect; 7 = reversable defect
#  #14 "AHD"        (Qualitative)(Response) Yes/No based on an angiographic test
#                       diagnosis of heart disease (angiographic disease status)
#                       -- Value 0: < 50% diameter narrowing
#                       -- Value 1: > 50% diameter narrowing
#                       (in any major vessel: attributes 59 through 68 are vessels)


#- table of the respoonse variable
table(Heart$AHD)

###
### column "AHD" is the respoinse variable.
###

print(Heart2, width=1000)

# Rename medv column as resp.
Heart2 <- Heart %>%
    select(-"index") %>%             # remove col named "index"
    rename(resp=AHD) %>%             # rename the column
    relocate(resp)                   # move "resp" to 1st column

print(Heart2, width=1000)

Heart2 <- Heart2 %>%
    mutate(resp     = as.factor(resp),        # Turn these columns to <factor> instead of <double>
           Sex      = as.factor(Sex),
           ChestPain= as.factor(ChestPain),
           Fbs      = as.factor(Fbs),
           RestECG  = as.factor(RestECG),
           ExAng    = as.factor(ExAng),
           Thal     = as.factor(Thal))

print(Heart2, width=1000)

table(Heart2$resp)    # note that first level is "No"



#-------------------------------------------------
###--- 1. Routine Exploratory Analysis (class of resp should be <fct>)
Orig <- Heart2
resp.col.name <- "resp"

  #- Check for N/A in data. Remove if there's any.
  summary(Orig)
  dim(Orig)
  sum(is.na(Orig))
  # If there is na in the data, run below
  dim(Orig)
  Orig <- Orig %>% na.omit()
  dim(Orig)


  ##----------
  ##- Correlation Check

  # Pick columns that are numeric
  library(corrplot)    # install.packages("corrplot")
    Orig_num <- Orig %>% select_if(is.numeric)
    cor(Orig_num)
    corrplot::corrplot(cor(Orig_num))
    corrplot::corrplot(cor(Orig_num), method="number")


  ##----------
  ##- Visualization

  # pairs(Orig) equivalent
  library(GGally)      # install.packages("GGally")
    GGally::ggpairs(Orig[, c(2:7,   1)], aes(color=resp, alpha=1))
    GGally::ggpairs(Orig[, c(8:14,  1)], aes(color=resp, alpha=1))


  ###----------
  ###- Chi-sq test of association for each column

  # Pick columns that has more than 1 unique value
  list_cols <- Orig %>% summarise_all(function(x) length(unique(x))) %>%
        gather() %>% filter(value>1) %>% pull(key)

  # Apply chisq.test to those columns
  ChiSq.pval <- Orig %>% select(list_cols) %>%
        summarise_all(funs(chisq.test(., Orig$resp)$p.value))

  ChiSq.pval <- Orig %>% summarise_all(funs(chisq.test(., Orig$resp)$p.value))
  ChiSq.pval
  barplot(t(t(as.matrix(ChiSq.pval))), las=2, cex.names=1,
          main="p-values from Chi-sq test of association")
  abline(h=.05, col='red')

  which(ChiSq.pval < .05)             # Col num of variables w <.05 p-value
  list_cols[which(ChiSq.pval < .05)]  # Top list of 'important' variables

  which(ChiSq.pval > .6)              # Col num of variables w >.6 p-value
  list_cols[which(ChiSq.pval > .6)]   # Top list of 'unimportatnt' variables

### End of Routine Exploratory Analysis.


# which(ChiSq.pval < .05)             # Col num of variables w <.05 p-value
# [1]  1  3  4  8 10 11 12 13 14
# Top list of 'important' variables
# [1] "resp"      "Sex"       "ChestPain" "RestECG"   "ExAng"     "Oldpeak"
# [7] "Slope"     "Ca"        "Thal"

# which(ChiSq.pval > .6)              # Col num of variables w >.6 p-value
# [1] 7
# list_cols[which(ChiSq.pval > .6)]   # Top list of 'unimportatnt' variables
# [1] "Fbs"