%% Setting Environment
clc; clear all; close all;

%% Reading csv file
dataframe = readtable('Heart.csv');                                     % Reading the .csv file as a table
dataframe(:,1) = [];                                                    % Removing the row_names column
[n_data, n_features] = size(dataframe);                                  % Getting the size of the dataframe
fprintf('Size of the dataframe :: %d x %d\n', size(dataframe));
disp(dataframe(1:5,:));

%% Numerical Data Analysis
features = dataframe.Properties.VariableNames;                            % Extracting the header names
disp(features)
% Percentages of two categories in the target array
Target = dataframe.chd;                                                 % Extracting the target column
fprintf('Size of the target array :: %d x %d\n', size(Target));

Target_1 = sum(Target == 1);                                              % Counting number of rows with target == 1
Target_0 = sum(Target == 0);                                              % Counting number of rows with target == 0
fprintf('Percentage of 1s :: %.2f\nPercentage of 0s :: %.2f\n', Target_1/n_data, Target_0/n_data);

% Number of missing data in the data array
n_missing = sum(ismissing(dataframe));                                  % Counting missing values column wise

for i=1:n_features
fprintf('Number of missing values in %s :: %d\n', features{i}, n_missing(i));
end

%% Visual Data Analysis

dataframe.famhist = double(categorical(dataframe.famhist));             % Converting the categorical variable to numerical to plot the correlation
[R,PValue] = corrplot(dataframe, 'type', 'Pearson','tail','both');       % Plots and returns the Pearson Correlations and P values (pair-wise)

PROBLEMS 1.1. Consider the continuous-time signals displayed in Fi...