def excel2txt():
# 对王辉的excel的表格转成txt
path = r'C:\Users\chend\Desktop\dataset\doubanbook-wanghui\doubanbook-wanghui.xlsx'
txt = pd.read_excel(path, header=0, sheet_name=None, dtype='str')
txt = list(txt.values())
user = handleUser(txt[0])
book = handleBook(txt[1])
user_book = handleUser_book(txt[2])
book_labels = handleBook_labels(txt[3])
user_book_score = handleUser_book_score(txt[4],txt[2])
print('-----------------------------------------------------------------------------')
print(user.shape,book.shape,user_book.shape,book_labels.shape,user_book_score.shape)
print('-----------------------------------------------------------------------------')
dbop.store(user, 'user')
dbop.store(book,'book')
dbop.store(book_labels,'book_labels')
dbop.store(user_book,'user_book')
dbop.store(user_book_score,'user_book_score')
booksid = []
booklabels = []
# booklabelsdf = pd.DataFrame(columns=['bookid','booklabels'])
for line in txt:
line = eval(line)
booksid.append(line['图书id'])
booklabels.append(line['图书标签'])
book_labels = pd.DataFrame(zip(booksid, booklabels),
columns=['bookid', 'booklabels'])
# 去除没有标签的图书
book_labels = delNolabelBook(book_labels)
# 对book_labels个格式进行调整
book_labels = regularTable(book_labels)
# 显示所有列与行
# pd.set_option('display.max_columns', None)
# pd.set_option('display.max_rows', None)
# 清洗标签，只保留四个一下汉字,且化繁体为简体
book_labels = cleanData(book_labels)
# print(book_labels)
return book_labels
if __name__ == '__main__':
book_labels = read_txt()
print(book_labels.shape)
dbop.store(book_labels, 'book_labels')
txt = f.readlines()
usesid = []
booksid = []
booksscore = []
for line in txt:
line = eval(line)
usesid.append(line['用户id'])
booksid.append(line['图书id'])
booksscore.append(line['图书评分'])
user_book_score = pd.DataFrame(zip(usesid, booksid, booksscore),
columns=['userid', 'booksid', 'booksscore'])
# 显示所有列与行
# pd.set_option('display.max_columns', None)
# pd.set_option('display.max_rows', None)
# 去除没有读过书的的用户，没给评分
user_book_score = delNoitemInfo(user_book_score)
# 表格结构调整
user_book_score = regularTable(user_book_score)
return user_book_score
if __name__ == "__main__":
txt_path = r'C:\Users\chend\Desktop\dataset\doubanbook-lijia1\user-score.txt'
user_book_score = read_txt()
print(user_book_score.shape)
dbop.store(user_book_score, 'user_book_score')
return user_book
def read_txt():
path = r'C:\Users\chend\Desktop\dataset\doubanbook-lijia\user-book.txt'
with open(path, encoding='utf-8-sig') as f:
txt = f.readlines()
usesid = []
booksid = []
for line in txt:
line = eval(line)
usesid.append(line['用户id'])
booksid.append(line['图书id'])
user_book = pd.DataFrame(zip(usesid, booksid),
columns=['userid', 'booksid'])
# 删除没读过书的用户
user_book = delNoReadBook(user_book)
#user_booK格式调整
user_book = regularTable(user_book)
return user_book
if __name__ == "__main__":
user_book = read_txt()
print(user_book.shape)
dbop.store(user_book, 'user_book')
# booktable.append(book)
return book
if __name__ == '__main__':
path = r'C:\Users\chend\Desktop\dataset\doubanbook-lijia\book.txt'
# 从txt文件中读入DataFrame
with open(path, encoding='utf-8') as f:
txt = f.readlines()
# print(txt)
booksid = []
booksname = []
booksauthor = []
for line in txt:
line = eval(line)
booksid.append(line['图书id'])
booksname.append(line['图书名称'])
booksauthor.append(line['图书作者'])
book = pd.DataFrame(zip(booksid, booksname, booksauthor),
columns=['bookid', 'bookname', 'bookauthor'])
# print(book)
book = addcover(book)
print(
'--------------------------------------------------------------------------------------'
)
# pd.set_option('display.max_columns', None)
# 存入数据库book表
print(book.shape)
dbop.store(book, 'book')