Refactor event statistics calculations and improve output formatting
This commit is contained in:
parent
d2ed6787d4
commit
180d872cd7
@ -7,6 +7,7 @@ import pandas as pd
|
||||
# 尝试导入 Polars
|
||||
try:
|
||||
import polars as pl
|
||||
|
||||
HAS_POLARS = True
|
||||
except ImportError:
|
||||
HAS_POLARS = False
|
||||
@ -67,14 +68,15 @@ def read_label_csv(path: Union[str, Path], verbose=True) -> pd.DataFrame:
|
||||
# Obstructive apnea
|
||||
# Mixed apnea
|
||||
|
||||
num_labeled = np.sum(df["isLabeled"] == 1)
|
||||
num_total = np.sum((df["isLabeled"] == 1) & (df["score"] != 3))
|
||||
|
||||
num_psg_events = np.sum(df["Event type"].notna())
|
||||
num_manual_events = num_labeled - num_psg_events
|
||||
num_manual_events = np.sum(df["Event type"].isna())
|
||||
|
||||
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_unlabeled = np.sum(df["isLabeled"] == -1)
|
||||
|
||||
num_psg_hyp = np.sum(df["Event type"] == "Hypopnea")
|
||||
num_psg_csa = np.sum(df["Event type"] == "Central apnea")
|
||||
@ -82,9 +84,9 @@ def read_label_csv(path: Union[str, Path], verbose=True) -> pd.DataFrame:
|
||||
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_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"))
|
||||
@ -96,25 +98,52 @@ def read_label_csv(path: Union[str, Path], verbose=True) -> pd.DataFrame:
|
||||
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"))
|
||||
num_unlabeled_hyp = np.sum((df["isLabeled"] == -1) & (df["Event type"] == "Hypopnea"))
|
||||
num_unlabeled_csa = np.sum((df["isLabeled"] == -1) & (df["Event type"] == "Central apnea"))
|
||||
num_unlabeled_osa = np.sum((df["isLabeled"] == -1) & (df["Event type"] == "Obstructive apnea"))
|
||||
num_unlabeled_msa = np.sum((df["isLabeled"] == -1) & (df["Event type"] == "Mixed apnea"))
|
||||
|
||||
num_hyp_1_score = np.sum((df["correct_EventsType"] == "Hypopnea") & (df["score"] == 1))
|
||||
num_csa_1_score = np.sum((df["correct_EventsType"] == "Central apnea") & (df["score"] == 1))
|
||||
num_osa_1_score = np.sum((df["correct_EventsType"] == "Obstructive apnea") & (df["score"] == 1))
|
||||
num_msa_1_score = np.sum((df["correct_EventsType"] == "Mixed apnea") & (df["score"] == 1))
|
||||
|
||||
num_hyp_2_score = np.sum((df["correct_EventsType"] == "Hypopnea") & (df["score"] == 2))
|
||||
num_csa_2_score = np.sum((df["correct_EventsType"] == "Central apnea") & (df["score"] == 2))
|
||||
num_osa_2_score = np.sum((df["correct_EventsType"] == "Obstructive apnea") & (df["score"] == 2))
|
||||
num_msa_2_score = np.sum((df["correct_EventsType"] == "Mixed apnea") & (df["score"] == 2))
|
||||
|
||||
num_hyp_3_score = np.sum((df["correct_EventsType"] == "Hypopnea") & (df["score"] == 3))
|
||||
num_csa_3_score = np.sum((df["correct_EventsType"] == "Central apnea") & (df["score"] == 3))
|
||||
num_osa_3_score = np.sum((df["correct_EventsType"] == "Obstructive apnea") & (df["score"] == 3))
|
||||
num_msa_3_score = np.sum((df["correct_EventsType"] == "Mixed apnea") & (df["score"] == 3))
|
||||
|
||||
num_1_score = np.sum(df["score"] == 1)
|
||||
num_2_score = np.sum(df["score"] == 2)
|
||||
num_3_score = np.sum(df["score"] == 3)
|
||||
|
||||
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}")
|
||||
|
||||
|
||||
print(f"Type {'Total':^8s} / {'From PSG':^8s} / {'Manual':^8s} / {'Deleted':^8s} / {'Unlabeled':^8s}")
|
||||
print(
|
||||
f"Hyp: {num_hyp:^8d} / {num_psg_hyp:^8d} / {num_manual_hyp:^8d} / {num_deleted_hyp:^8d} / {num_unlabeled_hyp:^8d}")
|
||||
print(
|
||||
f"CSA: {num_csa:^8d} / {num_psg_csa:^8d} / {num_manual_csa:^8d} / {num_deleted_csa:^8d} / {num_unlabeled_csa:^8d}")
|
||||
print(
|
||||
f"OSA: {num_osa:^8d} / {num_psg_osa:^8d} / {num_manual_osa:^8d} / {num_deleted_osa:^8d} / {num_unlabeled_osa:^8d}")
|
||||
print(
|
||||
f"MSA: {num_msa:^8d} / {num_psg_msa:^8d} / {num_manual_msa:^8d} / {num_deleted_msa:^8d} / {num_unlabeled_msa:^8d}")
|
||||
print(
|
||||
f"All: {num_total:^8d} / {num_psg_events:^8d} / {num_manual_events:^8d} / {num_deleted:^8d} / {num_unlabeled:^8d}")
|
||||
|
||||
print("Score Statistics (only for non-deleted events and manual created events):")
|
||||
print(f"Type {'Total':^8s} / {'Score 1':^8s} / {'Score 2':^8s} / {'Score 3':^8s}")
|
||||
print(f"Hyp: {num_hyp:^8d} / {num_hyp_1_score:^8d} / {num_hyp_2_score:^8d} / {num_hyp_3_score:^8d}")
|
||||
print(f"CSA: {num_csa:^8d} / {num_csa_1_score:^8d} / {num_csa_2_score:^8d} / {num_csa_3_score:^8d}")
|
||||
print(f"OSA: {num_osa:^8d} / {num_osa_1_score:^8d} / {num_osa_2_score:^8d} / {num_osa_3_score:^8d}")
|
||||
print(f"MSA: {num_msa:^8d} / {num_msa_1_score:^8d} / {num_msa_2_score:^8d} / {num_msa_3_score:^8d}")
|
||||
print(f"All: {num_total:^8d} / {num_1_score:^8d} / {num_2_score:^8d} / {num_3_score:^8d}")
|
||||
|
||||
df["Start"] = df["Start"].astype(int)
|
||||
df["End"] = df["End"].astype(int)
|
||||
@ -139,4 +168,4 @@ def read_disable_excel(path: Union[str, Path]) -> pd.DataFrame:
|
||||
df["id"] = df["id"].astype(int)
|
||||
df["start"] = df["start"].astype(int)
|
||||
df["end"] = df["end"].astype(int)
|
||||
return df
|
||||
return df
|
||||
|
||||
Loading…
Reference in New Issue
Block a user