library(readr)
heart <- read_csv(
  "../data/heart.csv",
  col_types = cols(
    age = col_double(),
    sex = col_factor(levels = c("0", "1")),
    cp = col_factor(levels = c("0", "1", "2", "3")),
    trestbps = col_double(),
    chol = col_double(),
    fbs = col_factor(levels = c("0", "1")),
    restecg = col_factor(levels = c("0", "1", "2")),
    thalach = col_double(),
    exang = col_factor(levels = c("0", "1")),
    oldpeak = col_double(),
    slope = col_factor(levels = c("0", "1", "2")),
    ca = col_double(),
    thal = col_factor(levels = c("0", "1", "2", "3")),
    target = col_factor(levels = c("neg", "pos"))
  )
)

#View(heart)

### STEP 3a. Pre#View the Loaded Datasets, Identify the Data Types  ----
# Dimensions refer to the number of observations (rows) and the number of
# attributes/variables/features (columns).
#Understanding data types is key for effective analysis.It helps choose suitable visualizations and algorithms,  
#and highlights the need for conversions between categorical and numerical data when necessary.


dim(heart)

sapply(heart, class)

# It is more sensible to count categorical variables (factors or dimensions)
# than numeric variables, e.g., counting the number of male and female
# participants instead of counting the frequency of each participant’s height.

heart_freq <- heart$target
cbind(frequency = table(heart_freq),
      percentage = prop.table(table(heart_freq)) * 100)

# We, therefore, must manually create a function that can calculate the mode.

heart_target_mode <- names(table(heart$target))[
  which(table(heart$target) == max(table(heart$target)))
]
print(heart_target_mode)

summary(heart)

# calculate the standard deviation of only columns that are numeric, thus
# leaving out the columns termed as “factors” (categorical) or those that have
# a string data type.

sapply(heart[, -c(2, 3, 6, 7, 9, 11, 13, 14)], sd)

#or
sapply(heart[, c(1, 4, 5, 8, 10, 12)], sd)

# The Kurtosis informs you of how often outliers occur in the results.
# There are different formulas for calculating kurtosis.
# Specifying “type = 2” allows us to use the 2nd formula which is the same
# kurtosis formula used in SPSS and SAS.

# In “type = 2” (used in SPSS and SAS):
# 1.    Kurtosis < 3 implies a low number of outliers
# 2.    Kurtosis = 3 implies a medium number of outliers
# 3.    Kurtosis > 3 implies a high number of outliers

if (!is.element("e1071", installed.packages()[, 1])) {
  install.packages("e1071", dependencies = TRUE)
}
require("e1071")

sapply(heart[, -c(2, 3, 6, 7, 9, 11, 13, 14)],  kurtosis, type = 2)

# The skewness informs you of the asymmetry of the distribution of results.
# Using “type = 2” can be interpreted as:

# 1.    Skewness between -0.4 and 0.4 (inclusive) implies that there is no skew
# in the distribution of results; the distribution of results is symmetrical;
# it is a normal distribution.
# 2.    Skewness above 0.4 implies a positive skew; a right-skewed distribution.
# 3.    Skewness below -0.4 implies a negative skew; a left-skewed distribution.

sapply(heart[, -c(2, 3, 6, 7, 9, 11, 13, 14)],  skewness, type = 2)

# Note that the covariance and the correlation are computed for numeric values
# only, not categorical values.

heart_cov <- cov(heart[, -c(2, 3, 6, 7, 9, 11, 13, 14)])
#View(heart_cov)

heart_cor <- cor(heart[, -c(2, 3, 6, 7, 9, 11, 13, 14)])
#View(heart_cor)

# One-Way ANOVA can be used to test the effect of the 3 types of fertilizer on
# crop yield whereas,
# Two-Way ANOVA can be used to test the effect of the 3 types of fertilizer and
# the 2 types of planting density on crop yield.
heart_one_way_anova <- aov(trestbps ~ age, data = heart)
summary(heart_one_way_anova)

#The ANOVA rejects the null hypothesis,The ANOVA indicates a significant difference in resting blood pressure among age groups 
#(F(1, 1023) = 81.16, p < 2e-16), highlighting age as a key factor 
#in determining blood pressure. 
#This aligns with cardiovascular knowledge, correlating increased age with a higher risk of cardiovascular disease.

heart_two_way_anova <- aov(trestbps ~ exang + ca, # nolint
                                           data = heart)
summary(heart_two_way_anova)

#both variables, exercise-induced angina and the number of major vessels, are associated with statistically significant differences in 
#resting blood pressure.

# Histograms help in determining whether an attribute has a Gaussian
# distribution. They can also be used to identify the presence of outliers.


#for (i in c(1, 4, 5)) {
 # hist(heart[, i], main = names(heart)[i])
#}


#hist(heart[, 8], main = names(heart)[8])
#hist(heart[, 10], main = names(heart)[10])
#hist(heart[, 12], main = names(heart)[12])

# Box and whisker plots are useful in understanding the distribution of data.

par(mfrow = c(1, 3))
for (i in c(1, 4, 5)) {
  boxplot(heart[, i], main = names(heart)[i])
}

boxplot(heart[, 8], main = names(heart)[8])
boxplot(heart[, 10], main = names(heart)[10])
boxplot(heart[, 12], main = names(heart)[12])

# Categorical attributes (factors) can also be visualized. This is done using a
# bar chart to give an idea of the proportion of instances that belong to each
# category.

barplot(table(heart[, 2]), main = names(heart)[2])

barplot(table(heart[, 3]), main = names(heart)[3])

barplot(table(heart[, 6]), main = names(heart)[6])

barplot(table(heart[, 7]), main = names(heart)[7])

barplot(table(heart[, 9]), main = names(heart)[9])

barplot(table(heart[, 11]), main = names(heart)[11])

barplot(table(heart[, 13]), main = names(heart)[13])

barplot(table(heart[, 14]), main = names(heart)[14])

# Execute the following to create a map to identify the missing data in each
# dataset:
if (!is.element("Amelia", installed.packages()[, 1])) {
  install.packages("Amelia", dependencies = TRUE)
}
require("Amelia")

#comment
missmap(heart, col = c("red", "grey"), legend = TRUE)

# Correlation plots can be used to get an idea of which attributes change
# together. The function “corrplot()” found in the package “corrplot” is
# required to perform this. The larger the dot in the correlation plot, the
# larger the correlation. Blue represents a positive correlation whereas red
# represents a negative correlation.

if (!is.element("corrplot", installed.packages()[, 1])) {
  install.packages("corrplot", dependencies = TRUE)
}
require("corrplot")

corrplot(cor(heart[, -c(2, 3, 6, 7, 9, 11, 13, 14)]), method = "circle")



#heart <- heart[, -which(names(heart) == "target_numeric")]

# Alternatively, the 'ggcorrplot::ggcorrplot()' function can be used to plot a
# more visually appealing plot.
# The code below shows how to install a package in R:
if (!is.element("ggcorrplot", installed.packages()[, 1])) {
  install.packages("ggcorrplot", dependencies = TRUE)
}
require("ggcorrplot")

ggcorrplot(cor(heart[, -c(2, 3, 6, 7, 9, 11, 13, 14)]))

pairs(heart)

# Alternatively, the ggcorrplot package can be used to make the plots more
# appealing:
ggplot(heart,
       aes(x = age, y = sex, shape = target, color = target)) +
  geom_point() +
  geom_smooth(method = lm)

renv::snapshot()