python--datafame操作

目录

导入相关包

新建df格式表格

df条件筛选

df合并

df相关属性

df单元格选取

df新增列

---

导入相关包

import pandas as pd
from pandas.core.frame import DataFrame
from openpyxl import load_workbook

新建df格式表格

#新建空数据表格，准备合并
df_all = DataFrame(columns = ["标签类型","标签"])

df条件筛选

#多条件筛选，| 表示或，&表示且，例如df_all.loc[ (df_all["标签类型"] == "8大消费群体") & 
 #(df_all["标签"] == "精致妈妈"),["标签类型","标签","覆盖人数占比-抖音"]]   
 df = df.loc[
    (df["标签类型"] == "8大消费群体") | 
    (df["标签类型"] == "城市级别")| 
    (df["标签类型"] == "预测年龄段") | 
    (df["标签类型"] == "预测性别"),
    ["标签类型","标签","覆盖人数占比-抖音"]]

df_all = df_all[df_all["tagValueName"] != "未知"]

df合并

#df左右合并how参数inner内连接、outer外连接、left左连、right右连，on连接条件
df_all = pd.merge(df_all,df,how = "outer",on = ["标签类型","标签"])
#上下合并
pd.concat([df_all,df],axis = 0)

df相关属性

#行列
size = df.shape

df单元格选取

df.iat[i,j]

df新增列

#新增列（位置，列名，列值
df.insert(0,"类型",i) ）

df取top值

#排序取top15,前两列
df = df.sort_values(by = "次数", ascending = False).iloc[0:20,0:2]