Crystallite_size_distr_calculations

import math
import statistics

units = {}

# Known constants
BIN_MIN_NM = 0.0
units["BIN_MIN_NM"] = "nm"

BIN_MAX_NM = 25.0
units["BIN_MAX_NM"] = "nm"

BIN_WIDTH_NM = 0.25
units["BIN_WIDTH_NM"] = "nm"

OUTPUT_FILE = "crystallite_size_distribution.txt"
units["OUTPUT_FILE"] = "text filename"

# Files to analyze
INPUT_FILE_1 = "file_1.txt"

# Calculations
num_bins = int(round((BIN_MAX_NM - BIN_MIN_NM) / BIN_WIDTH_NM))
units["num_bins"] = "count"

length_values = []
bin_counts = [0] * num_bins

with open(INPUT_FILE_1, "r", encoding="utf-8") as f:
    lines = f.readlines()

# Skip the first line (weird header)
lines = lines[1:]

for line in lines:
    stripped = line.strip()

    # Skip empty or comment lines
    if not stripped or stripped.startswith("#"):
        continue

    parts = stripped.split("\t")

    # Skip malformed rows
    if len(parts) < 1:
        continue

    cleaned_parts = [p.strip() for p in parts]

    # Length values are in the last column
    length_text = cleaned_parts[-1]

    # Skip missing values
    if length_text == "" or length_text.lower() == "nan":
        continue

    try:
        length_nm = float(length_text)
        units["length_nm"] = "nm"
    except ValueError:
        continue

    # Keep only values inside the requested histogram range
    if BIN_MIN_NM <= length_nm < BIN_MAX_NM:
        length_values.append(length_nm)
        bin_index = int((length_nm - BIN_MIN_NM) / BIN_WIDTH_NM)
        if 0 <= bin_index < num_bins:
            bin_counts[bin_index] += 1

observation_count = len(length_values)
units["observation_count"] = "count"

if observation_count == 0:
    raise ValueError("No valid Length observations were found in the file within the requested range.")

average_crystallite_size = statistics.mean(length_values)
units["average_crystallite_size"] = "nm"

if observation_count > 1:
    standard_deviation = statistics.stdev(length_values)
else:
    standard_deviation = 0.0
units["standard_deviation"] = "nm"

total_counts_in_bins = sum(bin_counts)
units["total_counts_in_bins"] = "count"

with open(OUTPUT_FILE, "w", encoding="utf-8") as out_file:
    out_file.write("Summary\n")
    out_file.write(f"Average_crystallite_size_nm\t{average_crystallite_size:.6f}\n")
    out_file.write(f"Standard_deviation_nm\t{standard_deviation:.6f}\n")
    out_file.write(f"Total_observations\t{observation_count}\n")
    out_file.write("\n")
    out_file.write("Bin_start_nm\tBin_end_nm\tBin_center_nm\tCount\tFrequency\n")

    for idx in range(num_bins):
        bin_start_nm = BIN_MIN_NM + idx * BIN_WIDTH_NM
        units["bin_start_nm"] = "nm"

        bin_end_nm = bin_start_nm + BIN_WIDTH_NM
        units["bin_end_nm"] = "nm"

        bin_center_nm = (bin_start_nm + bin_end_nm) / 2.0
        units["bin_center_nm"] = "nm"

        count_in_bin = bin_counts[idx]
        units["count_in_bin"] = "count"

        frequency = count_in_bin / observation_count
        units["frequency"] = "fraction"

        out_file.write(
            f"{bin_start_nm:.2f}\t{bin_end_nm:.2f}\t{bin_center_nm:.2f}\t{count_in_bin}\t{frequency:.6f}\n"
        )

# Outputs
print(f"Processed file: {INPUT_FILE_1}")
print(f"Output written to: {OUTPUT_FILE}")
print(f"Average crystallite size: {average_crystallite_size:.6f} nm")
print(f"Standard deviation: {standard_deviation:.6f} nm")
print(f"Total observations: {observation_count}")

print("=== Variable Summary ===")
for k, v in units.items():
    try:
        if not isinstance(eval(k), (list, dict, set)):
            print(f"  {k} = {eval(k)} [{v}]")
    except:
        pass