142 lines
5.8 KiB
Python
142 lines
5.8 KiB
Python
from pathlib import Path
|
|
from typing import Union
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
|
|
# 尝试导入 Polars
|
|
try:
|
|
import polars as pl
|
|
HAS_POLARS = True
|
|
except ImportError:
|
|
HAS_POLARS = False
|
|
|
|
|
|
def read_signal_txt(path: Union[str, Path]) -> np.ndarray:
|
|
"""
|
|
Read a txt file and return the first column as a numpy array.
|
|
|
|
Args:
|
|
path (str | Path): Path to the txt file.
|
|
|
|
Returns:
|
|
np.ndarray: The first column of the txt file as a numpy array.
|
|
"""
|
|
path = Path(path)
|
|
if not path.exists():
|
|
raise FileNotFoundError(f"File not found: {path}")
|
|
|
|
if HAS_POLARS:
|
|
df = pl.read_csv(path, has_header=False, infer_schema_length=0)
|
|
return df[:, 0].to_numpy()
|
|
else:
|
|
df = pd.read_csv(path, header=None, dtype=float)
|
|
return df.iloc[:, 0].to_numpy()
|
|
|
|
|
|
def read_label_csv(path: Union[str, Path], verbose=True) -> pd.DataFrame:
|
|
"""
|
|
Read a CSV file and return it as a pandas DataFrame.
|
|
|
|
Args:
|
|
path (str | Path): Path to the CSV file.
|
|
Returns:
|
|
pd.DataFrame: The content of the CSV file as a pandas DataFrame.
|
|
"""
|
|
path = Path(path)
|
|
if not path.exists():
|
|
raise FileNotFoundError(f"File not found: {path}")
|
|
|
|
# 直接用pandas读取 包含中文 故指定编码
|
|
df = pd.read_csv(path, encoding="gbk")
|
|
if verbose:
|
|
print(f"Label file read from {path}, number of rows: {len(df)}")
|
|
|
|
# 统计打标情况
|
|
# isLabeled=1 表示已打标
|
|
# Event type 有值的为PSG导出的事件
|
|
# Event type 为nan的为手动打标的事件
|
|
# score=1 显著事件， score=2 为受干扰事件 score=3 为非显著应删除事件
|
|
# 确认后的事件在correct_EventsType
|
|
# 输出事件信息 按照总计事件、低通气、中枢性、阻塞性、混合型按行输出 格式为 总计/来自PSG/手动/删除/未标注
|
|
# Columns:
|
|
# Index Event type Stage Time Epoch Date Duration HR bef. HR extr. HR delta O2 bef. O2 min. O2 delta Body Position Validation Start End score remark correct_Start correct_End correct_EventsType isLabeled
|
|
# Event type:
|
|
# Hypopnea
|
|
# Central apnea
|
|
# Obstructive apnea
|
|
# Mixed apnea
|
|
|
|
num_labeled = np.sum(df["isLabeled"] == 1)
|
|
num_psg_events = np.sum(df["Event type"].notna())
|
|
num_manual_events = num_labeled - num_psg_events
|
|
num_deleted = np.sum(df["score"] == 3)
|
|
|
|
# 统计事件
|
|
num_total = np.sum((df["isLabeled"] == 1) & (df["score"] != 3))
|
|
num_unlabeled = num_total - num_labeled
|
|
|
|
num_psg_hyp = np.sum(df["Event type"] == "Hypopnea")
|
|
num_psg_csa = np.sum(df["Event type"] == "Central apnea")
|
|
num_psg_osa = np.sum(df["Event type"] == "Obstructive apnea")
|
|
num_psg_msa = np.sum(df["Event type"] == "Mixed apnea")
|
|
|
|
num_hyp = np.sum((df["correct_EventsType"] == "Hypopnea") & (df["score"] != 3))
|
|
num_csa = np.sum((df["correct_EventsType"] == "Central apnea") & (df["score"] != 3))
|
|
num_osa = np.sum((df["correct_EventsType"] == "Obstructive apnea") & (df["score"] != 3))
|
|
num_msa = np.sum((df["correct_EventsType"] == "Mixed apnea") & (df["score"] != 3))
|
|
|
|
num_manual_hyp = np.sum((df["Event type"].isna()) & (df["correct_EventsType"] == "Hypopnea"))
|
|
num_manual_csa = np.sum((df["Event type"].isna()) & (df["correct_EventsType"] == "Central apnea"))
|
|
num_manual_osa = np.sum((df["Event type"].isna()) & (df["correct_EventsType"] == "Obstructive apnea"))
|
|
num_manual_msa = np.sum((df["Event type"].isna()) & (df["correct_EventsType"] == "Mixed apnea"))
|
|
|
|
num_deleted_hyp = np.sum((df["score"] == 3) & (df["correct_EventsType"] == "Hypopnea"))
|
|
num_deleted_csa = np.sum((df["score"] == 3) & (df["correct_EventsType"] == "Central apnea"))
|
|
num_deleted_osa = np.sum((df["score"] == 3) & (df["correct_EventsType"] == "Obstructive apnea"))
|
|
num_deleted_msa = np.sum((df["score"] == 3) & (df["correct_EventsType"] == "Mixed apnea"))
|
|
|
|
num_unlabeled_hyp = np.sum((df["isLabeled"] == 0) & (df["correct_EventsType"] == "Hypopnea"))
|
|
num_unlabeled_csa = np.sum((df["isLabeled"] == 0) & (df["correct_EventsType"] == "Central apnea"))
|
|
num_unlabeled_osa = np.sum((df["isLabeled"] == 0) & (df["correct_EventsType"] == "Obstructive apnea"))
|
|
num_unlabeled_msa = np.sum((df["isLabeled"] == 0) & (df["correct_EventsType"] == "Mixed apnea"))
|
|
|
|
|
|
|
|
if verbose:
|
|
print("Event Statistics:")
|
|
# 格式化输出 总计/来自PSG/手动/删除/未标注 指定宽度
|
|
print("Type Total / PSG / Manual / Deleted / Unlabeled")
|
|
print(f"Hypopnea: {num_hyp:4d} / {num_psg_hyp:4d} / {num_manual_hyp:4d} / {num_deleted_hyp:4d} / {num_unlabeled_hyp:4d}")
|
|
print(f"Central apnea: {num_csa:4d} / {num_psg_csa:4d} / {num_manual_csa:4d} / {num_deleted_csa:4d} / {num_unlabeled_csa:4d}")
|
|
print(f"Obstructive ap: {num_osa:4d} / {num_psg_osa:4d} / {num_manual_osa:4d} / {num_deleted_osa:4d} / {num_unlabeled_osa:4d}")
|
|
print(f"Mixed apnea: {num_msa:4d} / {num_psg_msa:4d} / {num_manual_msa:4d} / {num_deleted_msa:4d} / {num_unlabeled_msa:4d}")
|
|
print(f"Total events: {num_total:4d} / {num_psg_events:4d} / {num_manual_events:4d} / {num_deleted:4d} / {num_unlabeled:4d}")
|
|
|
|
|
|
|
|
|
|
df["Start"] = df["Start"].astype(int)
|
|
df["End"] = df["End"].astype(int)
|
|
return df
|
|
|
|
|
|
def read_disable_excel(path: Union[str, Path]) -> pd.DataFrame:
|
|
"""
|
|
Read an Excel file and return it as a pandas DataFrame.
|
|
|
|
Args:
|
|
path (str | Path): Path to the Excel file.
|
|
Returns:
|
|
pd.DataFrame: The content of the Excel file as a pandas DataFrame.
|
|
"""
|
|
path = Path(path)
|
|
if not path.exists():
|
|
raise FileNotFoundError(f"File not found: {path}")
|
|
|
|
# 直接用pandas读取
|
|
df = pd.read_excel(path)
|
|
df["id"] = df["id"].astype(int)
|
|
df["start"] = df["start"].astype(int)
|
|
df["end"] = df["end"].astype(int)
|
|
return df |