|
|
马上注册，结交更多好友，享用更多功能^_^
您需要 登录 才可以下载或查看，没有账号？立即注册
x
# coding=utf-8
# import pandas as pd
# may_df = pd.read_csv('may.csv')
# june_df = pd.read_csv('june.csv')
#
# merged = pd.merge(may_df,june_df,on="states",how = 'outer',suffixes=('_ahead','behind'),indicator=True)
# # find change
# changed_rows = merged[merged['_merge']!='both']
# # find new lines
# new_rows = merged[merged['_merge']=='right_only']
# print(new_rows)
#
import pandas as pd
from tqdm import tqdm
# # 读取两张表
# df1 = pd.read_csv('may.csv')
# df2 = pd.read_csv('june.csv')
#
# # 筛选出location、project_name、building、unit、high和room相同的行
# cols = ['location', 'project_name', 'building', 'unit', 'high', 'room']
# df1_grouped = df1.groupby(cols).first().reset_index()
# df2_grouped = df2.groupby(cols).first().reset_index()
#
# # 将df1_grouped和df2_grouped合并，并比较states列的值
# df = pd.DataFrame(columns=df1.columns)
# for index, row1 in tqdm(df1_grouped.iterrows(), total=len(df1_grouped)):
# for _, row2 in df2_grouped.iterrows():
# if row1['location'] == row2['location'] and \
# row1['project_name'] == row2['project_name'] and \
# row1['building'] == row2['building'] and \
# row1['unit'] == row2['unit'] and \
# row1['high'] == row2['high'] and \
# row1['room'] == row2['room'] and \
# row1['states'] != row2['states']:
# df = df.append(row1)
#
# # 输出结果
# print(df)
import pandas as pd
from tqdm import tqdm
# 读取两张表
df1 = pd.read_excel('D:\一介书生资料库\爬虫：八爪鱼\各市县整体市场\shujuchuli\七月三亚.xlsx')
df2 = pd.read_excel('D:\一介书生资料库\爬虫：八爪鱼\各市县整体市场\shujuchuli\八月三亚.xlsx')
# 筛选出location、project_name、building、unit、high和room相同的行，并选择指定的列
cols = ['区域', '项目名称', '楼盘', '单元', '楼层', '房间', '建筑面积', '房型', '挂牌清水价', '挂牌装修价']
df1_grouped = df1.groupby(cols).first().reset_index()
df2_grouped = df2.groupby(cols).first().reset_index()
# 合并两张表，并筛选出states有变化的行
df_merged = pd.concat([df1_grouped, df2_grouped])
df_duplicates = df_merged[df_merged.duplicated(cols, keep=False)]
df_changed = df_duplicates.loc[df_duplicates['状态'] != df_duplicates['状态']]
# 输出结果
df_changed.to_excel('D:\pydata\data.xlsx', index=False)
print(df_changed)
表格标题为：区域 项目名称 楼盘 单元 楼层 房间 建筑面积 房屋用途 房型 挂牌清水价 挂牌装修价 产品类型 状态 商品房预售许可证 发证日期
提示错误：
D:\PythonProject\pythonProject\Scripts\python.exe E:\qycache\xuexi\pythonProject\房地产\process（版本2.3）.py
D:\PythonProject\pythonProject\lib\site-packages\numpy\_distributor_init.py:30: UserWarning: loaded more than 1 DLL from .libs:
D:\PythonProject\pythonProject\lib\site-packages\numpy\.libs\libopenblas.EL2C6PLE4ZYW3ECEVIV3OXXGRN2NRFM2.gfortran-win_amd64.dll
D:\PythonProject\pythonProject\lib\site-packages\numpy\.libs\libopenblas64__v0.3.21-gcc_10_3_0.dll
warnings.warn("loaded more than 1 DLL from .libs:"
Traceback (most recent call last):
File "D:\PythonProject\pythonProject\lib\site-packages\pandas\core\indexes\base.py", line 3652, in get_loc
return self._engine.get_loc(casted_key)
File "pandas\_libs\index.pyx", line 147, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\index.pyx", line 176, in pandas._libs.index.IndexEngine.get_loc
File "pandas\_libs\hashtable_class_helper.pxi", line 7080, in pandas._libs.hashtable.PyObjectHashTable.get_item
File "pandas\_libs\hashtable_class_helper.pxi", line 7088, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: '状态'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "E:\qycache\xuexi\pythonProject\房地产\process（版本2.3）.py", line 57, in <module>
df_changed = df_duplicates.loc[df_duplicates['状态'] != df_duplicates['状态']]
File "D:\PythonProject\pythonProject\lib\site-packages\pandas\core\frame.py", line 3761, in __getitem__
indexer = self.columns.get_loc(key)
File "D:\PythonProject\pythonProject\lib\site-packages\pandas\core\indexes\base.py", line 3654, in get_loc
raise KeyError(key) from err
KeyError: '状态'
进程已结束,退出代码1
|
|
( 粤ICP备18085999号-1 | 粤公网安备 44051102000585号)
狗仔卡
发表于 2023-11-3 08:31:45
置顶卡
千斤顶
显身卡
发表于 2023-11-3 08:31:53
楼主