Python-科学计算-pandas-09-df列字符串操作2

import pandas as pd

dict_1 = {"file_name": ["P10-CD1.txt", "P252-12EF.pdf", "P369-96BD.txt",
                        "P4-G852F.pdf", "P5-H225D.txt", "P657-36LF.pdf"],
          "order_id": [1, 2, 3, 4, 5, 6]}

df_1 = pd.DataFrame(dict_1, columns=["file_name", "order_id"])
print("初始DF：\n", df_1)

print("\n")
df_2 = df_1["file_name"].str.split("-", expand=True)
df_2.columns = ["文件名", "其它"]
print("获取新的文件名：\n", df_2)

print("\n")
df_3 = df_1["file_name"].str.split(".", expand=True)
df_3.columns = ["其它", "文件类型"]
print("获取文件类型：\n", df_3)

print("\n")
se_1 = df_2["文件名"] + "." + df_3["文件类型"]
print("新的文件名：\n", se_1)
print(type(se_1))

print("\n")
df_1["new_file_name"] = se_1
print("加入新的文件名：\n", df_1)
print(type(df_1))