def order_count_contact(target='all'):
print('start order_count_contact() method')
df_dataSet = pd.DataFrame()
try:
df_dataSet = pd.read_csv('E:\\data\\DiDiData\\data_csv\\dataset\\'+target+'set.csv')
except FileNotFoundError:
dir_path = 'E:\\data\\DiDiData\\data_csv\\order_count_30min\\order_count_replaceTimeBand\\'
file_list = ft.listdir_nohidden(dir_path)
file_list.sort()
start = 0
end = len(file_list)
if target == 'train':
end = 17
elif target == 'test':
start = 17
for i in range(start, end):
file_path = os.path.join(dir_path, file_list[i])
df = pd.read_csv(file_path)
df.rename(columns={'half_hour': 'time'}, inplace=True)
df.set_index(keys=['start_district_id', 'dest_district_id', 'date', 'time'], inplace=True)
if i == start:
df_dataSet = df
else:
df_dataSet = pd.concat([df_dataSet, df], axis=0)
print('end order_count_contact() method')
return df_dataSet
# print(df.dtypes)
if i == 0:
df_out = df
else:
# df_out = df_out.append(df, ignore_index=True)
df_out = df_out.append(df)
print(fileDate)
# 最后一天的数据加入后
if i == len(fileList) - 1:
# if i == 1:
# df_out = df_out.unstack(0)
destPath = 'E:\\data\\DiDiData\\data_csv\\order_count_totalCity\\totalFlow_60min.csv'
df_out.to_csv(destPath)
if __name__ == "__main__":
time_Now = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
print('current time:', time_Now)
dirPath = 'E:\\data\\DiDiData\\data_csv\\order_lite\\'
fileList = ft.listdir_nohidden(dirPath)
fileList.sort()
time_interval = timedelta(minutes=60)
threshold = 0
# 调用方法获取满足时间间隔和阈值的 order_count_totalCity , 并写入 csv文件
flow_statistics_totalCity(fileList, time_interval, threshold)