Question

我正在使用python中的pandas读取多张excel文件。我有三个案例

某些工作表包含第1行的数据

delimited table Example: 
;;
;;
;;
Country;Company;Product
US;ABC;XYZ
US;ABD;XYY

，有些在表格之前有空行数，有些表格有摘要我知道使用skip_blank我可以摆脱顶部的空白行，但顶部空白行的数量本质上不固定可能是3或4或8

delimited table Example: 

Product summary table for East region;;
Date: 1st Sep, 2016;;
;;
Country;Company;Product
US;ABC;XYZ
US;ABD;XYY

表我试图阅读所有这些表但不确定如何 - 有没有办法弄清楚从第3行摘要结束和第4行是我的表标题和第一列标题是＆＃39;国家＆＃39;

import wx
import wx.grid as gridlib


class PanelOne(wx.Panel):
    """"""    

    def __init__(self, parent):
        """Constructor"""
        wx.Panel.__init__(self, parent=parent)
        txt = wx.TextCtrl(self)


class PanelTwo(wx.Panel):
    """"""    

    def __init__(self, parent):
        """Constructor"""
        wx.Panel.__init__(self, parent=parent)

        grid = gridlib.Grid(self)
        grid.CreateGrid(25,12)

        sizer = wx.BoxSizer(wx.VERTICAL)
        sizer.Add(grid, 0, wx.EXPAND)
        self.SetSizer(sizer)


class MyForm(wx.Frame):    

    def __init__(self):
        wx.Frame.__init__(self, None, wx.ID_ANY, 
                          "Panel Switcher Tutorial")

        self.panel_one = PanelOne(self)
        self.panel_two = PanelTwo(self)
        self.panel_two.Hide()

        self.sizer = wx.BoxSizer(wx.VERTICAL)
        self.sizer.Add(self.panel_one, 1, wx.EXPAND)
        self.sizer.Add(self.panel_two, 1, wx.EXPAND)
        self.SetSizer(self.sizer)


        menubar = wx.MenuBar()
        fileMenu = wx.Menu()
        switch_panels_menu_item = fileMenu.Append(wx.ID_ANY, 
                                                  "Switch Panels", 
                                                  "Some text")
        self.Bind(wx.EVT_MENU, self.onSwitchPanels, 
                  switch_panels_menu_item)
        menubar.Append(fileMenu, '&File')
        self.SetMenuBar(menubar)    

    def onSwitchPanels(self, event):
        """"""
        if self.panel_one.IsShown():
            self.SetTitle("Panel Two Showing")
            self.panel_one.Hide()
            self.panel_two.Show()
        else:
            self.SetTitle("Panel One Showing")
            self.panel_one.Show()
            self.panel_two.Hide()
        self.Layout()


# Run the program
if __name__ == "__main__":
    app = wx.App(False)
    frame = MyForm()
    frame.Show()
    app.MainLoop()

Answer 1

我建议使用以下算法：

阅读整个表格
考虑第一行不包含缺失值作为标题
删除标题

这段代码对我来说没问题：

import pandas as pd
for sheet in range(3):
    raw_data = pd.read_excel('blank_rows.xlsx', sheetname=sheet, header=None)
    print(raw_data)
    # looking for the header row
    for i, row in raw_data.iterrows():
        if row.notnull().all():
            data = raw_data.iloc[(i+1):].reset_index(drop=True)
            data.columns = list(raw_data.iloc[i])
            break
    # transforming columns to numeric where possible
    for c in data.columns:
        data[c] = pd.to_numeric(data[c], errors='ignore')
    print(data)

根据您的示例使用this toy data sample。来自原始数据帧

         0        1        2
0  Country  Company  Product
1       US      ABC      XYZ
2       US      ABD      XYY

         0        1        2
0      NaN      NaN      NaN
1      NaN      NaN      NaN
2      NaN      NaN      NaN
3  Country  Company  Product
4       US      ABC      XYZ
5       US      ABD      XYY

                                       0        1        2
0  Product summary table for East region      NaN      NaN
1                    Date: 1st Sep, 2016      NaN      NaN
2                                    NaN      NaN      NaN
3                                Country  Company  Product
4                                     US      ABC      XYZ
5                                     US      ABD      XYY

脚本生成相同的表

  Country Company Product
0      US     ABC     XYZ
1      US     ABD     XYY

动态跳过python pandas中的顶级空白行

1 个答案: