通过运行函数将多行添加到pandas数据帧

Question

我正在运行此功能5次，希望我的数据帧有5行。但是，它只保存最后一行。任何人都能看到问题吗？任何帮助表示赞赏。谢谢!!

（是的，这很粗糙，但此时我尝试了太多东西）

def Bucket(num1, num2, num3, num4, num5, num6, num7, num8, name, name_total, name_unprocessed, insideframe, counter):    
    for num1 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=a")]' %name):
        print('%s a: ' %name + num1.text)
        name_unprocessed = num1.text
    for num2 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=b")]' %name):
        print('%s b: ' %name + num2.text) 
    for num3 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=c")]' %name):
        print('%s c: '%name + num3.text) 
    for num4 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=d")]' %name):
        print('%s d: ' %name + num4.text) 
    for num5 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=e")]' %name):
        print('%s e: ' %name + num5.text)
    for num6 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=f")]' %name):
        print('%s f: ' %name + num6.text) 
    for num7 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=g")]' %name):
        print('%s g: ' %name + num7.text)
    for num8 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=Duplicate")]' %name):
        print('%s h: ' %name + num8.text)
    name_total = int(num1.text)+int(num2.text)+int(num3.text)+int(num4.text)+int(num5.text)+int(num6.text)+int(num7.text)+int(num8.text)
    print('%s Total: ' %name + str(name_total))


    DF2 = {'a': ['%s' % Time],
            'b': ['%s' % Date],
            'c': ['%s' % Day],
            'd': ['%s' % int(num1.text)],
            'e': ['%s' % int(num2.text)],
            'f': ['%s' % int(num3.text)],
            'g': ['%s' % int(num4.text)],
            'h': ['%s' % int(num5.text)],
            'i': ['%s' % int(num6.text)],
            'j': ['%s' % int(num7.text)],
            'k': ['%s' % int(num8.text)],
            'Total': ['%s' % name_total],
            'Bucket': ['%s' % name]}
    frame2 = DataFrame(DF2)

    if counter == 0:
        SMSdf = insideframe.append(frame2)
        SMS.df = DataFrame(SMSdf, columns=['Time', 'Date', 'Day', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'Total', 'Bucket'])
        SMS.df.to_excel('Sprint_Log.xlsx', 'Sheet 1', index=False)
    else:
        SMSdf = SMSdf.append(frame2)
        SMS.df = DataFrame(SMSdf, columns=['Time', 'Date', 'Day', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'Total', 'Bucket'])
        SMS.df.to_excel('Log.xlsx', 'Sheet 1', index=False)

    counter=+1

Bucket(...1)
Bucket(...2)
Bucket(...3)
Bucket(...4)
Bucket(...5)

Answer 1

每次致电

SMS.df.to_excel('Log.xlsx', 'Sheet 1', index=False)

如果已存在，则覆盖Log.xlsx。这就是为什么只保存最后一行的原因。

Per the docs，

  

如果传递现有的ExcelWriter对象，则表单将被添加到   现有的工作手册。这可用于将不同的DataFrame保存为一个   工作簿：

>>> writer = ExcelWriter('output.xlsx')
>>> df1.to_excel(writer,'Sheet1')
>>> df2.to_excel(writer,'Sheet2')
>>> writer.save()

---

因此，您应该在Bucket之外定义作者一次，将作者传递给Bucket，然后使用SMS.df.to_excel(writer, sheet, index=False)。 请注意，每次调用Bucket时，您还需要写入不同的工作表。

import pandas as pd

def Bucket(num1, num2, num3, num4, num5, num6, num7, num8, name, name_total, name_unprocessed, insideframe, counter, writer):    
    ...
    else:
        SMSdf = SMSdf.append(frame2)
        SMS.df = pd.DataFrame(SMSdf, columns=['Time', 'Date', 'Day', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'Total', 'Bucket'])
        sheet = 'Sheet {}'.format(counter)
        SMS.df.to_excel(writer, sheet, index=False)

writer = pd.ExcelWriter('output.xlsx')
for counter in range(1, 6):
    Bucket(..., counter, writer)
writer.save()

---

这是一个简单的可运行示例，它将两个数据帧保存到一个xlsx文件中，然后将其读回：

import numpy as np
import pandas as pd

df1 = pd.DataFrame(np.random.randint(10, size=(5,4)))
df2 = pd.DataFrame(np.random.randint(10, size=(3,6)))
writer = pd.ExcelWriter('/tmp/output.xlsx')
df1.to_excel(writer,'Sheet1')
df2.to_excel(writer,'Sheet2')
writer.save()

reader = pd.ExcelFile('/tmp/output.xlsx')
for sheet in reader.sheet_names:
    df = reader.parse(sheet)
    print(df)

Answer 2

这就是我如何将它保存到同一个Excel工作表中的相同数据框中。

def Bucket(num1, num2, num3, num4, num5, num6, num7, num8, name, name_total, name_unprocessed, insideframe):    
    for num1 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=a")]' %name):
        print('%s a: ' %name + num1.text)
        name_unprocessed = num1.text
    for num2 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=b")]' %name):
        print('%s b: ' %name + num2.text) 
    for num3 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=c")]' %name):
        print('%s c: '%name + num3.text) 
    for num4 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=d")]' %name):
        print('%s d: ' %name + num4.text) 
    for num5 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=e")]' %name):
    print('%s e: ' %name + num5.text)
    for num6 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=f")]' %name):
        print('%s f: ' %name + num6.text) 
    for num7 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=g")]' %name):
        print('%s g: ' %name + num7.text)
    for num8 in driver.find_elements_by_xpath('.//a [contains(@href, "%s&singleTopic=1&dashboardSort=Duplicate")]' %name):
        print('%s h: ' %name + num8.text)
    name_total = int(num1.text)+int(num2.text)+int(num3.text)+int(num4.text)+int(num5.text)+int(num6.text)+int(num7.text)+int(num8.text)
   print('%s Total: ' %name + str(name_total))


    DF2 = {'a': ['%s' % Time],
        'b': ['%s' % Date],
        'c': ['%s' % Day],
        'd': ['%s' % int(num1.text)],
        'e': ['%s' % int(num2.text)],
        'f': ['%s' % int(num3.text)],
        'g': ['%s' % int(num4.text)],
        'h': ['%s' % int(num5.text)],
        'i': ['%s' % int(num6.text)],
        'j': ['%s' % int(num7.text)],
        'k': ['%s' % int(num8.text)],
        'Total': ['%s' % name_total],
        'Bucket': ['%s' % name]}
    Bucket.frame2 = DataFrame(DF2)

Bucket(...1)
SMSdf = insideframe.append(Bucket.frame2)
Bucket(...2)
SMSdf = SMSdf.append(Bucket.frame2)
Bucket(...3)
SMSdf = SMSdf.append(Bucket.frame2)
Bucket(...4)
SMSdf = SMSdf.append(Bucket.frame2)
Bucket(...5)
SMSdf = SMSdf.append(Bucket.frame2)