import numpy as np
import matplotlib.pyplot as plt
import os
import sys

'''
    CSCI 1470.2 Spring 2026 HW #5
'''
def compute_and_plot_histogram(filename):
    if not os.path.exists(filename):
        print(f"Error: The file '{filename}' was not found.")
        print(f"Please ensure '{filename} is in the same directory as this script.")
        return
        
    data = None
    try:
        # Read float 64 data from the input data file.
        data = np.loadtxt(filename, dtype=np.float64)        
        # Flatten the array in case the data is read as a 2D array
    except ValueError as e:
        print(f"Error reading file: {e}")
        print("Ensure the file only contains integers or floating point numbers, and standard delimiters (spaces/commas).")
    except Exception as e:
        print(f"An unexpected error occurred: {e}")   
    
    flat_data = data.flatten()
    data_size = flat_data.size
    
    #   The numbe of bins is the number of data points // 4, up to 20 bins.
    number_of_bins = min(data_size // 4, 20)
    # Compute the histogram using numpy.
    # numpy.histogram returns two arrays: 
    #   [1] 'counts': the number of items in each bin
    #   [2] 'bin_edges':  the bin edges. There is one more bin_edge than there are counts' values. 
    counts, bin_edges = np.histogram(data, bins=number_of_bins)

    print('-' * 55)    
    print(f'-- Histogram of Data from {filename}.')
    print(f'-- [range: left-inclusive, except the last]: frequency')
    print('-' * 55)
    for i in range(len(counts)):
        print(f"bin {i+1} => [{bin_edges[i]},{bin_edges[i+1]}]: {counts[i]}")
    
    # Plot the histogram using matplotlib
    plt.figure(figsize=(10, 6))
    
    # matplolib.pyplot.hist can do the calculation and plotting in one step.

    plt.hist(flat_data, bins=number_of_bins, color='g', rwidth=0.8)
    
    plt.title(f'Histogram of Data from {filename}')
    plt.xlabel('Value')
    plt.ylabel('Frequency')
    plt.grid(axis='y', alpha=0.75)
    
    # 5. Display the plot
    plt.show()

if __name__ == "__main__":
    data_file_name = input("Please input the name of your file: ")
    compute_and_plot_histogram(data_file_name)