Code Improved performance.py

def read_csv(filepath):
    """Reads CSV data from file and returns header and all data as rows of lists."""
    with open(filepath, 'r', encoding='utf-8-sig') as f:  # Handles UTF-8 BOM
        header = f.readline().strip().split(',')
        all_data = []
        for line in f:
            row = line.strip().split(',')
            if len(row) == len(header):  # Only include rows with correct length
                all_data.append(row)
    return header, all_data

def read_column(filepath, column_name):
    """Reads a single column from CSV file by column name."""
    header, all_data = read_csv(filepath)
    if column_name not in header:
        raise ValueError(f"{column_name} not found in header {header}")
    col_idx = header.index(column_name)
    return [row[col_idx] for row in all_data]

def build_data_dict(header, all_data):
    """Creates a dictionary mapping column names to lists of cleaned data."""
    data_dict = {col: [] for col in header}
    for col_idx, col_name in enumerate(header):
        for row in all_data:
            val = row[col_idx]
            try:
                if '.' in val:
                    val = float(val)
                else:
                    val = int(val)
            except ValueError:
                pass  # Keep as string if conversion fails
            data_dict[col_name].append(val)
    return data_dict

def kendall_tau(x, y):
    """Calculates Kendall Tau coefficient for two equal-length lists."""
    if len(x) != len(y):
        raise ValueError("Lists must be the same length")
    n = len(x)
    concordant = discordant = 0
    for i in range(n):
        for j in range(i+1, n):
            a, b = x[i] - x[j], y[i] - y[j]
            prod = a * b
            if prod > 0:
                concordant += 1
            elif prod < 0:
                discordant += 1
    if concordant + discordant == 0:
        return 0
    return (concordant - discordant) / (concordant + discordant)

def all_kendall_tau(data_dict):
    """Returns list of (col1, col2, tau) for all column pairs."""
    cols = list(data_dict.keys())
    coefs = []
    for i in range(len(cols)):
        for j in range(i+1, len(cols)):
            col1, col2 = cols[i], cols[j]
            try:
                tau = kendall_tau(data_dict[col1], data_dict[col2])
            except Exception as e:
                tau = None
            coefs.append((col1, col2, tau))
    return coefs

def print_kendall_table(coefs, columns, border='*'):
    """Prints a square correlation matrix for selected columns."""
    # Build lookup for fast access
    coef_dict = {}
    for c1, c2, tau in coefs:
        coef_dict[(c1, c2)] = tau
        coef_dict[(c2, c1)] = tau
    # Determine cell width
    cellw = max(max(len(col) for col in columns), 7) + 2
    # Print header
    hdr = border + ''.join([border + col.center(cellw) for col in columns]) + border
    sep = border * len(hdr)
    print(sep)
    print(' ' * (cellw + 1) + hdr)
    print(sep)
    for row_col in columns:
        row = [row_col.center(cellw)]
        for col in columns:
            if row_col == col:
                cell = '-'.center(cellw)
            else:
                tau = coef_dict.get((row_col, col))
                cell = f"{tau:.4f}".center(cellw) if tau is not None else "N/A".center(cellw)
            row.append(cell)
        print(border + ''.join([border + cell for cell in row]) + border)
    print(sep)

def main():
    csv_path = "C:/Users/aldom/Msc Data Science/Modules/Module 3 - Programming for Data Science/Assessment/Assessment resources/part_1.csv"
    header, all_data = read_csv(csv_path)
    print("Header:", header)
    print("First row:", all_data[0])
    # Build data dict
    data_dict = build_data_dict(header, all_data)
    # Example: print first 10 values of 'depression'
    col = 'depression'
    if col in data_dict:
        print(f"First 10 values of '{col}': {data_dict[col][:10]}")
    # Compute Kendall Tau for each pair
    coefs = all_kendall_tau(data_dict)
    # Print first 10 coefficients
    print("\nFirst 10 Kendall Tau coefficients:")
    for c1, c2, tau in coefs[:10]:
        print(f"{c1:>12} vs {c2:>12}: {tau:.3f}")
    # Print correlation matrix
    print("\nKendall Tau Correlation Matrix:")
    print_kendall_table(coefs, header)
    # Optional: interactive column selection
    # Uncomment below to allow user to select column
    # print("\nAvailable columns:", header)
    # colname = input("Enter column name to print first 10 values: ")
    # if colname in data_dict:
    #     print(f"First 10 of {colname}: {data_dict[colname][:10]}")
    # else:
    #     print(f"{colname} not found in columns.")

def test_sample():
    assert 1 + 1 == 2

if __name__ == "__main__":
    main()