import pandas as pd
# 获取所有数据,并通过ts列拼接
def get_data_dict(t1, t2, data):
df_t1 = pd.read_csv(t1, encoding='gbk')
df_t2 = pd.read_csv(t2, encoding='gbk')
df_data = pd.read_csv(data, encoding='gbk')[['ts', 'flow']]
print(df_t1)
print(df_t2)
print(df_data)
concate_data = pd.merge(df_t1, df_data, how='left', on=['ts'])
mean_data = concate_data['flow'].mean()
concate_data.loc[concate_data['flow'] == 0, 'flow'] = mean_data
concate_data.loc[concate_data['flow'].isnull(), 'flow'] = mean_data
print(concate_data)
concate_data.to_csv('../data/110005_.csv', index=False)
return concate_data
if __name__ == '__main__':
# 获取所有数据,并利用字典封装
concate_data = get_data_dict("../data/2020.1.1-2023.4.18.csv", "../data/2022.5.18-2023.4.18.csv", "../data/110005.csv")
print("concate_data:", len(concate_data))```
将两个不同的dataframe拼接
最新推荐文章于 2024-07-22 22:22:13 发布