import pandas as pd
mm = ["ABC,50m,DEF,45ji", "ABC,50m,ABC,45ji,ABC,", "CDE,50m,BGT,45ji,SCD,"]
nn = ["ABC", "DEF", "CDE", "SCD", "BGT"]
dl = []
for m in mm:
for n in nn:
if n in m:
dl.append((m, n))
dd = pd.DataFrame(dl)
dd.columns = ["字符", "种类"]
print(dd)
dt = dd.groupby("字符")["种类"].apply(lambda x: x.str.cat(sep=",")).reset_index()
dt["元素个数"] = dt.种类.str.contains(",")
# print(dt)
# print(dt.loc[dt.元素个数 == True])
# 计算逗号出现的次数+1
comma_count = dt["种类"].str.count(',') + 1
dt["元素个数"] = comma_count
print(dt)
python 文本打标签
最新推荐文章于 2024-07-19 23:36:34 发布