F - Intervals

本文介绍了一种算法,旨在解决如何最小化删除区间数量的问题,确保剩下的区间不会出现三个及以上的重叠情况。通过按区间右端点排序并跟踪重叠状态,实现高效求解。

Chiaki has n intervals and the i-th of them is [liri]. She wants to delete some intervals so that there does not exist three intervals ab and c such that aintersects with bb intersects with c and c intersects with a.

Chiaki is interested in the minimum number of intervals which need to be deleted.

Note that interval a intersects with interval b if there exists a real number x such that la ≤ x ≤ ra and lb ≤ x ≤ rb.

Input

There are multiple test cases. The first line of input contains an integer T, indicating the number of test cases. For each test case:

The first line contains an integer n (1 ≤ n ≤ 50000) -- the number of intervals.

Each of the following n lines contains two integers li and ri (1 ≤ li < ri ≤ 109) denoting the i-th interval. Note that for every 1 ≤ i < j ≤ nli ≠ lj or ri ≠rj.

It is guaranteed that the sum of all n does not exceed 500000.

Output

For each test case, output an integer m denoting the minimum number of deletions. Then in the next line, output m integers in increasing order denoting the index of the intervals to be deleted. If m equals to 0, you should output an empty line in the second line.

Sample Input
1
11
2 5
4 7
3 9
6 11
1 12
10 15
8 17
13 18
16 20
14 21
19 22

Sample Output
4
3 5 7 10

Hint

题意:问至少删除多少个区间才能保证剩下来的区间不会有三个及其以上的重叠。

思路:先将区间按右端点从小到大排序,记录一下重叠了两次的最右端位置right,若后面的区间的左端点小于它,则删除这个区间,若大于它,则将right更新=min(此区间的L,上一个区间的R).

#include<stdio.h>
#include<algorithm>
using namespace std;
struct node{
    int l,r,index;
}inter[50005];
bool cmp(node a,node b){
    if(a.r==b.r) return a.l<b.l;
    return a.r<b.r;
}
int sum,ans[50005];
int main(){
    int t;scanf("%d",&t);
    while(t--){
        int n;scanf("%d",&n);
        for(int i=0;i<n;i++) scanf("%d%d",&inter[i].l,&inter[i].r),inter[i].index=i+1;
        sort(inter,inter+n,cmp);
        sum=0;int right=0;node last=inter[0];
        for(int i=1;i<n;i++){
            if(inter[i].l<=right) {ans[sum++]=inter[i].index;continue;}
            if(inter[i].l<=last.r) right=last.r;
            last=inter[i];
        }
        sort(ans,ans+sum);
        printf("%d\n",sum);
        for(int i=0;i<sum-1;i++) printf("%d ",ans[i]);
        printf("%d\n",ans[sum-1]);
    }
}



import os import numpy as np import matplotlib.pyplot as plt import re from matplotlib.ticker import MaxNLocator from scipy.stats import linregress # 解决中文显示问题 plt.rcParams['font.sans-serif'] = ['SimHei', 'Microsoft YaHei', 'WenQuanYi Micro Hei'] plt.rcParams['axes.unicode_minus'] = False def natural_sort_key(s): """自然排序算法:确保文件名按数字顺序排列""" return [int(text) if text.isdigit() else text.lower() for text in re.split(r'(\d+)', s)] def normalize_data(data): """归一化数据到[0,1]范围""" min_val = min(data) max_val = max(data) if max_val == min_val: # 避免除以零 return [0.5] * len(data) # 所有值相同,返回0.5 return [(x - min_val) / (max_val - min_val) for x in data] def find_stable_intervals(counts, method='std', min_window=300, max_window=2000, threshold=0.5, merge_gap=300, min_length=500): """ 改进版稳定区间检测:支持三种不同指标 :param counts: 预测框数量列表(已归一化) :param method: 检测方法 ('std', 'cv', 'slope') :param min_window: 最小窗口尺寸 :param max_window: 最大窗口尺寸 :param threshold: 阈值(基于整体统计量) :param merge_gap: 相邻区间合并的最大间隔 :param min_length: 最小有效区间长度 :return: 优化后的稳定区间列表 """ n = len(counts) if n == 0: return [] # 计算整体统计量(基于归一化数据) total_mean = np.mean(counts) total_std = np.std(counts) # 1. 自适应窗口机制 window_size = min(max_window, max(min_window, n // 10)) step_size = max(1, window_size // 2) # 50%重叠滑动 # 2. 初始检测稳定区间 base_intervals = [] for i in range(0, n - window_size + 1, step_size): window = counts[i:i + window_size] if len(window) < 2: # 至少需要2个点计算 continue # 根据不同方法计算稳定性指标 if method == 'std': # 标准差方法 std_dev = np.std(window) if std_dev < total_std * threshold: base_intervals.append((i, i + window_size - 1)) elif method == 'cv': # 变异系数方法 mean_val = np.mean(window) if mean_val > 0: # 避免除以0 cv = np.std(window) / mean_val if cv >= threshold: base_intervals.append((i, i + window_size - 1)) elif method == 'slope': # 趋势斜率方法 x = np.arange(len(window)) slope, _, _, _, _ = linregress(x, window) if abs(slope) < threshold * total_std / window_size: base_intervals.append((i, i + window_size - 1)) # 如果没有检测到任何区间,直接返回 if not base_intervals: return [] # 极值点检测 min_val = min(counts) max_val = max(counts) min_indices = [i for i, x in enumerate(counts) if x == min_val] max_indices = [i for i, x in enumerate(counts) if x == max_val] # 3. 合并相邻平稳段 base_intervals.sort(key=lambda x: x[0]) # 确保按起始索引排序 merged_intervals = [] current_start, current_end = base_intervals[0] for start, end in base_intervals[1:]: if start - current_end <= merge_gap: # 间隔小于合并阈值 current_end = max(current_end, end) # 扩展当前区间 else: merged_intervals.append((current_start, current_end)) current_start, current_end = start, end merged_intervals.append((current_start, current_end)) # 4. 过滤短时伪平稳段 final_intervals = [ (start, end) for start, end in merged_intervals if (end - start + 1) >= min_length # 区间长度包含两端点 ] return final_intervals def plot_box_count_trend(file_list, box_counts, stable_intervals, output_path, title_suffix="", method_name="标准差"): """ 绘制预测框数量变化趋势图并标记稳定区间 :param file_list: 文件名列表 :param box_counts: 原始预测框数量列表 :param stable_intervals: 稳定区间列表 :param output_path: 输出图片路径 :param title_suffix: 标题后缀 :param method_name: 检测方法名称 """ plt.figure(figsize=(20, 10)) # 绘制整体趋势(原始数据) plt.plot(file_list, box_counts, 'b-', linewidth=1.5, label='预测框数量') # 标记稳定区间 - 确保区间显示 for i, (start, end) in enumerate(stable_intervals): interval_files = file_list[start:end + 1] interval_counts = box_counts[start:end + 1] if not interval_counts: # 确保区间有效 continue # 计算区间统计量 avg_count = np.mean(interval_counts) min_count = np.min(interval_counts) max_count = np.max(interval_counts) std_dev = np.std(interval_counts) # 绘制稳定区间 - 增加透明度使区间更明显 plt.fill_between(interval_files, min_count, max_count, color='green', alpha=0.3, # 增加透明度使区间更明显 zorder=0, # 确保填充在数据线下方 label=f'稳定区间{i + 1}' if i == 0 else "") # 添加区间标注 - 确保标注位置正确 mid_idx = start + (end - start) // 2 if mid_idx < len(file_list): # 确保索引有效 plt.annotate(f"区间{i + 1}: {start + 1}-{end + 1}\n均值: {avg_count:.1f}±{std_dev:.1f}", (file_list[mid_idx], avg_count), xytext=(0, 20), textcoords='offset points', ha='center', fontsize=10, bbox=dict(boxstyle="round,pad=0.3", fc="yellow", alpha=0.7), zorder=10) # 确保标注在最上层 # 设置图表属性 plt.title(f'预测框数量变化趋势及稳定区间分析 - {method_name}{title_suffix}', fontsize=18) plt.xlabel('图像文件名', fontsize=14) plt.ylabel('预测框数量', fontsize=14) plt.xticks(rotation=90, fontsize=7) plt.grid(True, linestyle='--', alpha=0.6) plt.legend(loc='upper right') # 限制X轴刻度数量 plt.gca().xaxis.set_major_locator(MaxNLocator(20)) plt.tight_layout() plt.savefig(output_path, dpi=150, bbox_inches='tight') plt.close() def plot_combined_intervals(file_list, box_counts, intervals_std, intervals_cv, intervals_slope, output_path): """ 绘制三种方法检测结果的合并图 :param file_list: 文件名列表 :param box_counts: 原始预测框数量列表 :param intervals_std: 标准差方法检测的区间 :param intervals_cv: 变异系数方法检测的区间 :param intervals_slope: 趋势斜率方法检测的区间 :param output_path: 输出图片路径 """ plt.figure(figsize=(20, 10)) # 绘制整体趋势(原始数据) plt.plot(file_list, box_counts, 'b-', linewidth=1.5, label='预测框数量') # 为每种方法定义不同的颜色和标签 method_colors = { '标准差': ('green', '标准差区间'), '变异系数': ('blue', '变异系数区间'), '趋势斜率': ('orange', '趋势斜率区间') } # 绘制标准差方法的区间 - 确保区间显示 for i, (start, end) in enumerate(intervals_std): interval_files = file_list[start:end + 1] min_count = min(box_counts[start:end + 1]) max_count = max(box_counts[start:end + 1]) plt.fill_between(interval_files, min_count, max_count, color=method_colors['标准差'][0], alpha=0.3, zorder=0, # 确保填充在数据线下方 label=method_colors['标准差'][1] if i == 0 else "") # 绘制变异系数方法的区间 - 确保区间显示 for i, (start, end) in enumerate(intervals_cv): interval_files = file_list[start:end + 1] min_count = min(box_counts[start:end + 1]) max_count = max(box_counts[start:end + 1]) plt.fill_between(interval_files, min_count, max_count, color=method_colors['变异系数'][0], alpha=0.3, zorder=0, # 确保填充在数据线下方 label=method_colors['变异系数'][1] if i == 0 else "") # 绘制趋势斜率方法的区间 - 确保区间显示 for i, (start, end) in enumerate(intervals_slope): interval_files = file_list[start:end + 1] min_count = min(box_counts[start:end + 1]) max_count = max(box_counts[start:end + 1]) plt.fill_between(interval_files, min_count, max_count, color=method_colors['趋势斜率'][0], alpha=0.3, zorder=0, # 确保填充在数据线下方 label=method_colors['趋势斜率'][1] if i == 0 else "") # 设置图表属性 plt.title('预测框数量变化趋势及稳定区间分析 - 三种方法合并', fontsize=18) plt.xlabel('图像文件名', fontsize=14) plt.ylabel('预测框数量', fontsize=14) plt.xticks(rotation=90, fontsize=7) plt.grid(True, linestyle='--', alpha=0.6) plt.legend(loc='upper right') # 限制X轴刻度数量 plt.gca().xaxis.set_major_locator(MaxNLocator(20)) plt.tight_layout() plt.savefig(output_path, dpi=150, bbox_inches='tight') plt.close() # 配置路径 label_dir = "F:/0701-label" # 替换为您的标签文件夹路径 output_dir = "F:/0710-stable" # 输出目录 os.makedirs(output_dir, exist_ok=True) # 获取文件列表并按自然顺序排序 file_list = [f for f in os.listdir(label_dir) if f.endswith(".txt")] file_list.sort(key=natural_sort_key) # 提取文件名(不含扩展名) file_names = [os.path.splitext(f)[0] for f in file_list] # 统计每个文件的预测框数量 box_counts = [] for file in file_list: file_path = os.path.join(label_dir, file) count = 0 with open(file_path, 'r') as f: for line in f: if line.strip(): # 非空行 count += 1 box_counts.append(count) # 归一化预测框数量(仅用于区间检测) normalized_counts = normalize_data(box_counts) # 计算整体统计数据 total_mean = np.mean(box_counts) total_std = np.std(box_counts) # 使用三种不同方法找出稳定区间(基于归一化数据) intervals_std = find_stable_intervals( normalized_counts, method='std', min_window=300, max_window=2000, threshold=0.9, # 标准差阈值 merge_gap=300, min_length=300 ) intervals_cv = find_stable_intervals( normalized_counts, method='cv', min_window=300, max_window=2000, threshold=0.9, # 变异系数阈值 merge_gap=300, min_length=300 ) intervals_slope = find_stable_intervals( normalized_counts, method='slope', min_window=300, max_window=2000, threshold=0.2, # 趋势斜率阈值 merge_gap=300, min_length=300 ) # 生成三种方法的结果图片 output_std = os.path.join(output_dir, "box_count_stable_intervals_std.png") output_cv = os.path.join(output_dir, "box_count_stable_intervals_cv.png") output_slope = os.path.join(output_dir, "box_count_stable_intervals_slope.png") output_combined = os.path.join(output_dir, "box_count_stable_intervals_combined.png") # 绘制图表(不显示归一化曲线) plot_box_count_trend(file_names, box_counts, intervals_std, output_std, title_suffix="", method_name="标准差方法") plot_box_count_trend(file_names, box_counts, intervals_cv, output_cv, title_suffix="", method_name="变异系数方法") plot_box_count_trend(file_names, box_counts, intervals_slope, output_slope, title_suffix="", method_name="趋势斜率方法") # 生成合并图 plot_combined_intervals(file_names, box_counts, intervals_std, intervals_cv, intervals_slope, output_combined) # 输出详细结果 print(f"分析完成! 共处理 {len(file_list)} 个文件") print(f"整体平均框数: {total_mean:.2f} ± {total_std:.2f}") def print_interval_info(intervals, method_name): print(f"\n{method_name}发现 {len(intervals)} 个稳定区间:") for i, (start, end) in enumerate(intervals): interval_counts = box_counts[start:end + 1] interval_normalized = normalized_counts[start:end + 1] avg_count = np.mean(interval_counts) std_dev = np.std(interval_counts) cv = std_dev / avg_count if avg_count > 0 else 0 # 计算趋势斜率(基于原始数据) x = np.arange(len(interval_counts)) slope, _, _, _, _ = linregress(x, interval_counts) print(f"区间{i + 1}:") print(f" - 文件范围: {start + 1}-{end + 1} (共{end - start + 1}个文件)") print(f" - 平均框数: {avg_count:.2f} ± {std_dev:.2f}") print(f" - 变异系数: {cv:.4f}") print(f" - 趋势斜率: {slope:.6f}") print(f" - 最小值: {min(interval_counts)}, 最大值: {max(interval_counts)}") print_interval_info(intervals_std, "标准差方法") print_interval_info(intervals_cv, "变异系数方法") print_interval_info(intervals_slope, "趋势斜率方法") # 合并所有检测到的区间 all_intervals = intervals_std + intervals_cv + intervals_slope def merge_intervals(intervals, merge_gap=300, min_length=500): """合并重叠或接近的区间""" if not intervals: return [] # 按起始索引排序 intervals.sort(key=lambda x: x[0]) merged = [] current_start, current_end = intervals[0] for start, end in intervals[1:]: if start - current_end <= merge_gap: # 间隔小于合并阈值 current_end = max(current_end, end) # 扩展当前区间 else: merged.append((current_start, current_end)) current_start, current_end = start, end merged.append((current_start, current_end)) # 过滤短区间 final_merged = [ (start, end) for start, end in merged if (end - start + 1) >= min_length ] return final_merged # 合并所有检测到的区间 merged_intervals = merge_intervals(all_intervals, merge_gap=300, min_length=500) # 保存区间信息到文本文件 def save_interval_report(intervals, method_name, file_path): with open(file_path, 'a') as f: f.write(f"\n{method_name}稳定区间分析报告\n") f.write(f"稳定区间数: {len(intervals)}\n") for i, (start, end) in enumerate(intervals): interval_counts = box_counts[start:end + 1] interval_normalized = normalized_counts[start:end + 1] avg_count = np.mean(interval_counts) std_dev = np.std(interval_counts) cv = std_dev / avg_count if avg_count > 0 else 0 # 计算趋势斜率 x = np.arange(len(interval_counts)) slope, _, _, _, _ = linregress(x, interval_counts) f.write(f"\n区间 {i + 1}:\n") f.write(f" 起始文件索引: {start + 1} ({file_names[start]})\n") f.write(f" 结束文件索引: {end + 1} ({file_names[end]})\n") f.write(f" 文件数量: {end - start + 1}\n") f.write(f" 平均预测框数: {avg_count:.2f} ± {std_dev:.2f}\n") f.write(f" 变异系数: {cv:.4f}\n") f.write(f" 趋势斜率: {slope:.6f}\n") f.write(f" 最小值: {min(interval_counts)}, 最大值: {max(interval_counts)}\n") f.write("=" * 80 + "\n") # 创建报告文件 interval_info_path = os.path.join(output_dir, "stable_intervals_report.txt") with open(interval_info_path, 'w') as f: f.write(f"稳定区间综合分析报告\n") f.write(f"总文件数: {len(file_list)}\n") f.write(f"整体平均框数: {total_mean:.2f} ± {total_std:.2f}\n") f.write(f"归一化范围: {min(box_counts)}-{max(box_counts)}\n") # 保存三种方法的区间报告 save_interval_report(intervals_std, "标准差方法", interval_info_path) save_interval_report(intervals_cv, "变异系数方法", interval_info_path) save_interval_report(intervals_slope, "趋势斜率方法", interval_info_path) # 保存合并后的区间报告 with open(interval_info_path, 'a') as f: f.write("\n\n=== 合并区间分析报告 ===\n") f.write("此部分展示三种方法检测到的所有稳定区间合并后的结果\n") f.write(f"合并后稳定区间数: {len(merged_intervals)}\n") for i, (start, end) in enumerate(merged_intervals): interval_counts = box_counts[start:end + 1] avg_count = np.mean(interval_counts) std_dev = np.std(interval_counts) cv = std_dev / avg_count if avg_count > 0 else 0 # 计算趋势斜率 x = np.arange(len(interval_counts)) slope, _, _, _, _ = linregress(x, interval_counts) # 检测此区间被哪些方法覆盖 covered_by = [] if any(start >= s and end <= e for s, e in intervals_std): covered_by.append("标准差") if any(start >= s and end <= e for s, e in intervals_cv): covered_by.append("变异系数") if any(start >= s and end <= e for s, e in intervals_slope): covered_by.append("趋势斜率") f.write(f"\n合并区间 {i + 1}:\n") f.write(f" 起始文件索引: {start + 1} ({file_names[start]})\n") f.write(f" 结束文件索引: {end + 1} ({file_names[end]})\n") f.write(f" 文件数量: {end - start + 1}\n") f.write(f" 平均预测框数: {avg_count:.2f} ± {std_dev:.2f}\n") f.write(f" 最小值: {min(interval_counts)}, 最大值: {max(interval_counts)}\n") f.write(f" 覆盖方法: {', '.join(covered_by) if covered_by else '无'}\n") # 添加合并区间统计 total_covered_files = sum(end - start + 1 for start, end in merged_intervals) coverage_percentage = (total_covered_files / len(file_list)) * 100 f.write("\n合并区间统计:\n") f.write(f" 总覆盖文件数: {total_covered_files}/{len(file_list)} ({coverage_percentage:.2f}%)\n") f.write(f" 平均区间长度: {np.mean([end - start + 1 for start, end in merged_intervals]):.1f} 文件\n") f.write(f" 最长区间: {max([end - start + 1 for start, end in merged_intervals])} 文件\n") f.write(f" 最短区间: {min([end - start + 1 for start, end in merged_intervals])} 文件\n") print_interval_info(merged_intervals, "合并区间") print(f"\n结果图片已保存至: {output_dir}") print(f"详细区间报告已保存至: {interval_info_path}") 把这个代码改成合并相邻平稳段之前的图,过滤短时伪平稳段之前的图也绘制出来
最新发布
07-25
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值