timeitrepeat - 通过重复来理解模式

from functools import reduce
reduce((lambda x, y: x * y), range(1, 2000))

(function) def repeat(
    stmt: _stmt = "pass",
    setup: _stmt = "pass",
    timer: _timer = ...,
    repeat: int = 5,
    number: int = 1000000,
    globals: dict[str, any] | none = none
) -> list[float]

def run_experiment(number_of_repeats, number_of_runs=1000):
    execution_time = timeit.repeat(
        "from functools import reduce; reduce((lambda x, y: x * y), range(1, 2000))",
        repeat=number_of_repeats,
        number=number_of_runs
    )
    return execution_time

repeat_values = [5, 20, 100, 500, 3000, 10000]

import timeit
import matplotlib.pyplot as plt
import json
import os
import statistics
import numpy as np

def run_experiment(number_of_repeats, number_of_runs=1000):
    execution_time = timeit.repeat(
        "from functools import reduce; reduce((lambda x, y: x * y), range(1, 2000))",
        repeat=number_of_repeats,
        number=number_of_runs
    )
    return execution_time

def save_result(result, repeats):
    filename = f'execution_time_results_{repeats}.json'
    with open(filename, 'w') as f:
        json.dump(result, f)

def load_result(repeats):
    filename = f'execution_time_results_{repeats}.json'
    if os.path.exists(filename):
        with open(filename, 'r') as f:
            return json.load(f)
    return None

def truncated_mean(data, percentile=95):
    data = np.array(data)
    lower_bound = np.percentile(data, (100 - percentile) / 2)
    upper_bound = np.percentile(data, 100 - (100 - percentile) / 2)
    return np.mean(data[(data >= lower_bound) & (data <= upper_bound)])

# List of number_of_repeats to test
repeat_values = [5, 20, 100, 500, 1000, 3000]

# Run experiments and collect results
results = []
for repeats in repeat_values:
    result = load_result(repeats)
    if result is None:
        print(f"Running experiment for {repeats} repeats...")
        try:
            result = run_experiment(repeats)
            save_result(result, repeats)
            print(f"Experiment for {repeats} repeats completed and saved.")
        except KeyboardInterrupt:
            print(f"\nExperiment for {repeats} repeats interrupted.")
            continue
    else:
        print(f"Loaded existing results for {repeats} repeats.")

    # Print time taken per repetition
    avg_time = statistics.mean(result)
    print(f"Average time per repetition for {repeats} repeats: {avg_time:.6f} seconds")

    results.append(result)

trunc_means = [truncated_mean(r) for r in results]
medians = [np.median(r) for r in results]
mins = [np.min(r) for r in results]
maxs = [np.max(r) for r in results]

# Create subplots
fig, axs = plt.subplots(2, 2, figsize=(15, 12))
fig.suptitle('Execution Time Analysis for Different Number of Repeats', fontsize=16)

metrics = [
    ('Truncated Mean (95%)', trunc_means),
    ('Median', medians),
    ('Min', mins),
    ('Max', maxs)
]

for (title, data), ax in zip(metrics, axs.flatten()):
    ax.plot(repeat_values, data, marker='o')
    ax.set_title(title)
    ax.set_xlabel('Number of Repeats')
    ax.set_ylabel('Execution Time (seconds)')
    ax.set_xscale('log')
    ax.grid(True, which="both", ls="-", alpha=0.2)

    # Set x-ticks and labels for each data point
    ax.set_xticks(repeat_values)
    ax.set_xticklabels(repeat_values)

    # Rotate x-axis labels for better readability
    ax.tick_params(axis='x', rotation=45)

plt.tight_layout()

# Save the plot to a file
plt.savefig('execution_time_analysis.png', dpi=300, bbox_inches='tight')
print("Plot saved as 'execution_time_analysis.png'")

# Create histograms for data distribution with 10 bins
fig, axs = plt.subplots(2, 3, figsize=(20, 12))
fig.suptitle('Data Distribution Histograms for Different Number of Repeats (10 bins)', fontsize=16)

for repeat, result, ax in zip(repeat_values, results, axs.flatten()):
    ax.hist(result, bins=10, edgecolor='black')
    ax.set_title(f'Repeats: {repeat}')
    ax.set_xlabel('Execution Time (seconds)')
    ax.set_ylabel('Frequency')

plt.tight_layout()

# Save the histograms to a file
plt.savefig('data_distribution_histograms_10bins.png', dpi=300, bbox_inches='tight')
print("Histograms saved as 'data_distribution_histograms_10bins.png'")

# Create histograms for 1000 and 3000 repeats with 30 bins
fig, axs = plt.subplots(1, 2, figsize=(15, 6))
fig.suptitle('Data Distribution Histograms for 1000 and 3000 Repeats (30 bins)', fontsize=16)

for repeat, result, ax in zip([1000, 3000], results[-2:], axs):
    ax.hist(result, bins=100, edgecolor='black')
    ax.set_title(f'Repeats: {repeat}')
    ax.set_xlabel('Execution Time (seconds)')
    ax.set_ylabel('Frequency')

plt.tight_layout()

# Save the detailed histograms to a file
plt.savefig('data_distribution_histograms_detailed.png', dpi=300, bbox_inches='tight')
print("Detailed histograms saved as 'data_distribution_histograms_detailed.png'")

plt.show()