Refining Python code for repeated use (Xlsx To Txt file and to WordCloud ) - python-3.x

Question

I've been self-learning Python for the past Month( 0 coding experience python is my first coding language) and have finally written my first work related usable code , i am trying to refine this code for repeated use , as it converts a comment based xlx data to txt 'string type' file and finally a wordcloud; you can find below the workable code:
how the code works:
step1. xlsx file = 4 column excel worksheet
step2. python extracts all column 'B'
step3. converts it into 'Str' Format , removes spaces & converts into txt file
step4. wordcloud removes words using stopWords,
Step5. generates wordcloud according to the format
I would Like to refine it in a way :
Changing File Directory Through a simple step instead of multiple copy and pasting of directory name ( skip manual changing of all file directories )
txt file's name creation is based on xlsx file's name ( so i don't have to key in manually every time)
if anyone has a better way of refining please do let me know , i am very new to this so if you need any other information to clarify any info , lemme know
Any help would be greatly appreciated, Thank you all in advance
import openpyxl as xl
import wordcloud
from wordcloud import WordCloud,STOPWORDS
from matplotlib.pyplot import imread
import jieba
import pandas as pd
# opening the source excel file ( repeated steps needed for every different document)
filename = "C:\\Users\\shakesmilk\\Desktop\\staub\\staub天猫商品评论.xlsx"
wb1 = xl.load_workbook(filename)
ws1 = wb1.worksheets[0]
# opening the destination excel file ( repeated steps needed for every different document)
filename1 = "C:\\Users\\shakesmilk\\Desktop\\staub\\staub天猫商品评论.xlsx"
wb2 = xl.load_workbook(filename1)
wb2.create_sheet('Sheet2')
ws2 = wb2.worksheets[1]
# calculate total number of rows and
# columns in source excel file
mr = ws1.max_row
mc = ws1.max_column
minr= ws2.min_row
# # copying the cell values from source
# # excel file to destination excel file
for i in range(1, mr + 1):
for j in range(0, mc + 1):
# reading cell value from source excel file
c = ws1.cell(row=i+1, column=2)
# writing the read value to destination excel file
ws2.cell(row=i+1, column=2).value = c.value
# # #deleting first empty row/ column
ws2.delete_cols(1)
#saving the destination excel file
wb2.save(str(filename1))
# #converting sheet 2 with pandas to txt file
df = pd.read_excel(filename,sheet_name=1)
with open("C:\\Users\\shakesmilk\\Desktop\\staub\\file.txt", mode='w',encoding='utf-8') as outfile:
df.to_string(outfile,header = None ,index = None)
#open read & remove spaces from txt file
commentfiletxt= "C:\\Users\\shakesmilk\\Desktop\\staub\\file.txt"
with open(commentfiletxt, 'r' , encoding='utf-8') as f:
lines = f.readlines()
# # remove spaces
lines = [line.replace(' ', '') for line in lines]
# # finally, write lines in the file
with open(commentfiletxt,'w', encoding='utf-8') as f :
f.writelines(lines)
# txt file generated > next to create wordcloud
#wordcloud start
#remove words from wordcloud
stopwords= set(STOPWORDS)
stopwords.update(['此用户没有填写评论', 'hellip','zwj','其他特色','还没用','非常喜欢','产品功能','没有用'])
mask = imread('moon.jpg')
with open(commentfiletxt, 'r',encoding='utf-8') as file:
text = file.read()
words = jieba.lcut(text) # 精确分词
newtxt = ' '.join(words) # 空格拼接
wd = wordcloud.WordCloud(stopwords=stopwords,\
font_path="MSYH.TTC",\
background_color="white", \
width=800, \
height=300, \
max_words=500, \
max_font_size=200, \
mask = mask, \
).generate(text)
# save picture
txt = open(commentfiletxt, mode='r', encoding='utf-8')
# save picture
wd.to_file('staub2.png')

Answer 1

i continued reading "Learning Python 5th Edition" and apparently functions are a good way to make codes reusable ; guess no one is interested in noob codes, but i'm sure there are a lot of beginners out there trying to refine their codes so i'm answering my question as i progress through the book , hopefully this helps out those in need. p.s currently reading about classes , im guesssing i could transform this code further but for now for those in need , this is my 'def' example:
import openpyxl as xl
import wordcloud
from wordcloud import WordCloud,STOPWORDS
from matplotlib.pyplot import imread
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import numpy as np
import jieba
import pandas as pd
def open_excel(filename):
global wb1,ws1,filenametxt
wb1 =xl.load_workbook(filename)
ws1 = wb1.worksheets[0]
filenametxt = filename
print('Loading WorkBook Completed')
def create_sheet(filename1):
global wb2,ws2
wb2 = xl.load_workbook(filename1)
wb2.create_sheet('Sheet2')
ws2 = wb2.worksheets[1]
print('Sheet 2 Created')
mr = ws1.max_row
mc = ws1.max_column
minr = ws2.min_row
for i in range(1, mr + 1):
for j in range(0, mc + 1):
# reading cell value from source excel file
c = ws1.cell(row=i + 1, column=2)
ws2.cell(row=i + 1, column=2).value = c.value
wb2.save(filename1)
print("Data Extracted To 'Column B'" )
ws2.delete_cols(1)
print('Empty Space in Column 1 Deleted')
wb2.save(filename1)
def create_txtf(tfile):
global df
df = pd.read_excel(filenametxt, sheet_name=1)
with open(tfile, mode='w', encoding='utf-8') as outfile:
df.to_string(outfile, header=None, index=None)
print('txt file created as file.txt')
def convert_remove(tfile1):
#open read & remove spaces from txt file
global commentfiletxt
commentfiletxt = tfile1
with open(commentfiletxt, 'r', encoding='utf-8') as f:
lines = f.readlines()
# # remove spaces
lines = [line.replace(' ', '') for line in lines]
print('Empty Spaces ' ' are removed' )
# # finally, write lines in the file
with open(commentfiletxt, 'w', encoding='utf-8') as f:
f.writelines(lines)
print('Data is written correctly without spaces')
return(tfile1)
def wordcloudpic(picname,maskpathn):
stopwords = set(STOPWORDS)
stopwords.update(['此用户没有填写评论', 'hellip','zwj','其他特色','还没用','非常喜欢','产品功能','没有用','东西收到了','S','sode','c','s左右','u','middot','u','theta','rdquo','ldquo','ec','ok','好评','不错','很好','满意','好用','老板大气','好',\
'nbsp'])
mask = imread(maskpathn)
mask = mask.astype(np.uint8)
with open(commentfiletxt, 'r',encoding='utf-8') as file:
text = file.read()
words = jieba.lcut(text) # 精确分词
newtxt = ' '.join(words) # 空格拼接
wd = wordcloud.WordCloud(stopwords=stopwords,\
font_path="MSYH.TTC",\
background_color="white", \
width=800, \
height=300, \
max_words=500, \
max_font_size=200, \
mask = mask, \
).generate(text)
txt = open(commentfiletxt, mode='r', encoding='utf-8')
# save picture
wd.to_file(picname)
if __name__ == "__main__":
open_excel("C:\\Users\\shakesmilk\\Desktop\\testtest\\test天猫商品评.xlsx")
create_sheet("C:\\Users\\shakesmilk\\Desktop\\testtest\\test天猫商品评.xlsx")
create_txtf("C:\\Users\\shakesmilk\\Desktop\\testtest\\file.txt")
convert_remove("C:\\Users\\shakesmilk\\Desktop\\testtest\\file.txt")
wordcloudpic('test.png','bubble.jpg')