使用Python从数据集中填充单词合并字段

Question

我试图在一个页面("guest_1“、.、"guest_10")中填充一个包含10个合并字段的单词模板，其中包含数据集中的一列。模板可以在这里找到：https://file.io/GVO4hyOwBCiv

我能够使用docx-mailmerge包(请参阅下面的代码# This Works会话)用常量数据填充单词模板，但通过循环数据集(参见下面的# This does not work)来复制结果，没有成功。

我首先需要创建dict类型的对象(在下面的代码中，我将它们称为guests_page_1和guests_page_2)。这些dict对象中的每一个都应该有最多10个项(例如{'guest_1': 'Name 1', 'guest_2': 'Name 1'})。因此，数据集(在下面的示例中，guests)应该被分割成多个对象(每个对象最多可以创建10个项)，然后使用merge_templates函数将填充的模板复制到多个页面上(取决于数据集的大小)。

下面的示例总结如下:我需要将guests (包含18个名称)数据集拆分为两个类型为dict (guests_page_1和guests_page_2)的对象。guests_page_1应该包含前10个名称，guests_page_2应该包含其余8个名称。然后，我需要将guests_page_1和guests_page_2添加到merge_templates函数中。

# Requirements: python -m pip install docx-mailmerge

# Import packages
from natsort import natsorted
import os

from mailmerge import MailMerge
import pandas as pd


# Set working directory to user's 'Downloads' folder
os.chdir(os.path.join(os.path.expanduser('~'), 'Downloads'))

# Import template
document = MailMerge('Template.docx')

# Get set of Merge Fields
document_guest_fields = document.get_merge_fields()

# Sort Merge Fields
document_guest_fields = natsorted(document_guest_fields)



## This works

guests_page_1 = {}
guests_page_2 = {}

for i in document_guest_fields:
    guests_page_1[i] = 'Name 1'

for i in document_guest_fields:
    guests_page_2[i] = 'Name 2'

document.merge_templates([guests_page_1, guests_page_2], separator='continuous_section')
document.write('Template-Output.docx')

document.close()



## This does not work

# Create dummy dataset with 18 names
guests = [
    ['Tom'],
    ['Jones'],
    ['Krystal'],
    ['Albert'],
    ['Paloma'],
    ['Shania'],
    ['Max'],
    ['Steve'],
    ['Paul'],
    ['Patrick'],
    ['Lucia'],
    ['Rachel'],
    ['Ray'],
    ['Jessica'],
    ['Julianna'],
    ['Lucille'],
    ['Leandro'],
    ['Vincent'],
    ]

guests = pd.DataFrame(guests, columns = ['name'])


guests_page_1 = {}

for index, row in guests.iterrows():
    for i in document_guest_fields:
        guests_page_1[i] = row['name']

document.merge_templates([guests_page_1], separator='continuous_section')
document.write('Template-Output.docx')

document.close()

有人知道如何解决这个问题吗？提前谢谢。

Answer 1

我找到了解决办法：

# Import packages
from natsort import natsorted
import os

from mailmerge import MailMerge
import pandas as pd

# Split dataframe into chunks of up to 10 rows - adapted from: https://stackoverflow.com/a/28882020/9195104
def split_dataframe(df, chunk_size=10000):

    chunks = list()
    num_chunks = len(df) // chunk_size+1

    for i in range(num_chunks):
        chunks.append(df[i*chunk_size:(i+1)*chunk_size])

    for i in range(len(chunks)):
        chunks[i].index = pd.RangeIndex(start=1, stop=len(chunks[i])+1, step=1)
        chunks[i].reset_index(inplace=True, level=0)
        chunks[i] = chunks[i].rename(columns={'index': 'merge_field'})
        chunks[i]['merge_field'] = chunks[i]['merge_field'].astype(str)
        chunks[i]['merge_field'] = chunks[i]['merge_field'].str.replace(r'^(.*)$', r'guest_\1', regex=True)

    return chunks



# Set working directory to user's 'Downloads' folder
os.chdir(os.path.join(os.path.expanduser('~'), 'Downloads'))

# Import template
document = MailMerge('Template.docx')

# Get set of Merge Fields
document_guest_fields = document.get_merge_fields()

# Sort Merge Fields
document_guest_fields = natsorted(document_guest_fields)

# Create dummy dataset with 18 names
guests = [
    ['Tom'],
    ['Jones'],
    ['Krystal'],
    ['Albert'],
    ['Paloma'],
    ['Shania'],
    ['Max'],
    ['Steve'],
    ['Paul'],
    ['Patrick'],
    ['Lucia'],
    ['Rachel'],
    ['Ray'],
    ['Jessica'],
    ['Julianna'],
    ['Lucille'],
    ['Leandro'],
    ['Vincent'],
    ]

guests = pd.DataFrame(guests, columns = ['name'])

# Split guests dataframe
guests = split_dataframe(guests, chunk_size=10)

# Create guests dictionary object
guests_list = {}

for i in range(len(guests)):
    guests_list[i] = dict(zip(guests[i]['merge_field'], guests[i]['name']))

# Fill Word Template file
document.merge_templates(list(guests_list.values()), separator='continuous_section')
document.write('Template-Output.docx')
document.close()