You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
19 lines
641 B
19 lines
641 B
import pandas as pd
|
|
|
|
df = pd.read_csv("alpha_list.csv")
|
|
|
|
# 检查 id 列的类型
|
|
print(f"id 列类型: {df['id'].dtype}")
|
|
|
|
# 检查是否有重复
|
|
duplicates = df[df.duplicated(subset=['id'], keep=False)]
|
|
print(f"\n重复的 id 数量: {len(duplicates)}")
|
|
|
|
if len(duplicates) > 0:
|
|
print("\n重复的 id 示例:")
|
|
for aid in duplicates['id'].unique()[:5]:
|
|
rows = df[df['id'] == aid]
|
|
print(f" {aid}: 出现 {len(rows)} 次")
|
|
# 打印这些行的 fitness 看是否相同
|
|
for _, row in rows.iterrows():
|
|
print(f" fitness: {row['is'][:100] if isinstance(row['is'], str) else row['is']}...") |