process_data.py

import re

def parse_dataset_file(filepath):
    data = {}

    round_index = None

    with open(filepath, "r", encoding="utf-8") as f:
        for line in f:
            line = line.strip()
            if not line:
                continue

            # -------- Round index --------
            if line.startswith("Round_index"):
                round_index = int(line.split()[-1])
                data[round_index] = {
                    "anchors": {},
                    "cluster": None
                }

            # -------- Anchor line --------
            elif line.startswith("Anchor"):
                # Anchor 1: Ddoa=0.13 tof_delta=-2.26 rssi=-63.31 Kurt=17.69, RMS=52.73, energy=-3.03 dB
                anchor_match = re.match(r"Anchor\s+(\d+):", line)
                anchor_id = int(anchor_match.group(1))

                features = {}

                features["Ddoa"] = float(re.search(r"Ddoa=([-.\d]+)", line).group(1))
                features["tof_delta"] = float(re.search(r"tof_delta=([-.\d]+)", line).group(1))
                features["rssi"] = float(re.search(r"rssi=([-.\d]+)", line).group(1))
                features["kurt"] = float(re.search(r"Kurt=([-.\d]+)", line).group(1))
                features["rms"] = float(re.search(r"RMS=([-.\d]+)", line).group(1))
                features["energy_db"] = float(re.search(r"energy=([-.\d]+)", line).group(1))

                data[round_index]["anchors"][anchor_id] = features

            # -------- Cluster line --------
            elif line.startswith("Unfiltered Cluster"):
                m_id = re.search(r"ID=(\d+)", line)
                m_x  = re.search(r"X=([-.\d]+)", line)
                m_y  = re.search(r"Y=([-.\d]+)", line)
            
                # 防御式编程（关键）
                if not (m_id and m_x and m_y):
                    # 可以选择 continue 或打印调试
                    # print("Skip malformed cluster line:", line)
                    continue
            
                cluster_id = int(m_id.group(1))
                x = float(m_x.group(1))
                y = float(m_y.group(1))
            
                data[round_index]["cluster"] = {
                    "id": cluster_id,
                    "x": x,
                    "y": y
                }


    return data

# data = parse_dataset_file("dataset/chest_4HZ.txt")

# # 访问示例
# round_2771 = data[2771]
# anchor_3 = data[2771]["anchors"][3]

# print(anchor_3["tof_delta"])
# print(round_2771["cluster"]["x"])