Pandas
读取文件------------------------------------------------------------------------------- df = pd.read_excel(xxxxxxxxxxxxxxxx,index_col=False) df = pd.read_csv("xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx.csv") data_power= pd.read_csv(xxxxxxxx, encoding='gbk', sep=',') # 列以','为分隔符分隔列 有中文编码可以用gbk data_r = pd.read_csv(xxxxxxxxxxxx, encoding='gbk', sep=' ') # 列以' '为分隔符 修改字段名--------------------------------------------------------------------------------- df1.rename(columns={ "Date_Time":"times", }, inplace=True) 遍历dataframe---------------------------------------------------------------------------- for index, row in df1.iterrows(): if "_" in str(df1["times"].iloc[index]): df1["times"].iloc[index] = str(df1["times"].iloc[index]).replace('_',' ') 对每一行的值进行修改 for index, row in data_airia.iterrows(): start = datetime.datetime.strptime(str(data_airia["起报时刻"].iloc[index]).split(' ')[0].replace('/','-'), "%Y-%m-%d") stop = datetime.datetime.strptime(str(data_airia["预报时刻"].iloc[index]).split(' ')[0].replace('/','-'), "%Y-%m-%d") data_airia["预报时刻"].iloc[index] = datetime.datetime.strptime(str(data_airia["预报时刻"].iloc[index]), "%Y/%m/%d %H:%M:%S").strftime("%Y-%m-%d %H:%M:%S") data_airia["forecastorder"].iloc[index] = int((stop-start).days) data_airia["起报时刻"].iloc[index] = str(data_airia["起报时刻"].iloc[index]).replace('/' ,'-') data_airia["预报时刻"].iloc[index] = str(data_airia["预报时刻"].iloc[index]).replace('/', '-') 取值-------------------------------------------------------------------------------------- df. loc[行][列] df[列].iloc[行] 删除某几列--------------------------------------------------------------------------------- new_df.drop(list(new_df)[0:1], axis=1, inplace=True) df_2 = df2_sheet.drop(columns=['实发功率', "实测辐照度"]) new_data.drop([0], axis=0, inplace=True) # 删除第一行 两个dataframe上下连接--------------------------------------------------------------------------- weather_df = pd.concat(weather_df_list, axis=0,ignore_index=True) dataframe 横向连接----------------------------------------------------------------------------- data = pd.merge(weather_df, power_df, how='left', on='date_time', sort=False) data.sort_values(by='date_time', inplace=True) dataframe写入excel--------------------------------------------------------------------------------- writer = pd.ExcelWriter(os.path.join(base_path, 'total.xlsx')) data_total.to_excel(writer, index=False) writer.save() 拷贝dataframe------------------------------------------------------------------------------------------- data_total = file_data.copy() df的列名列表---------------------------------------------------------------------------------------------- column_list = list(df.columns)