【导出填充率大于某值的sites】

# -*- coding: utf-8 -*-
"""
Created on Fri Aug 12 15:48:40 2022
Task:导出填充率大于75%的sites
"""
import os
import pandas as pd
import numpy as np
import shutil

path=r'D:\Fluxnet\要插补的LE_Driversqc=0'
site_name=[]
Filling_Rate=[]
for i in os.listdir(path):

    a=pd.read_csv(os.path.join(path,i))
    a.drop(['LE_F_MDS_QC'],axis=1,inplace=True)
    a.replace(-9999,np.nan,inplace=True)
    # print(a.shape[0])
    pre_num=a.shape[0]   
    # print(a.isna().sum().sort_values(ascending=True))
    a=a.interpolate()
    # print(a.isna().sum().sort_values(ascending=True))
    a=a.dropna()
    # print(a.shape[0])
    afterdrop_num=a.shape[0]
    # print(a.isna().sum().sort_values(ascending=True))
     
    #将字典内的填充率导出
    dic1=i.split('_',6)[1]
    site_name+=[dic1]
    
    dic2=afterdrop_num/pre_num
    Filling_Rate+=[dic2]
    
    dic={'site':site_name,
         'Filling_Rate':Filling_Rate}
    
    a=pd.DataFrame(dic)

path1=r'D:\Fluxnet\要训练的LE_qc=0_Driversqc=0'
outpath=r'D:\Fluxnet\填充率大于75%的可训练站点_Drivers_Before_Filled'

#统计一下填充率在%以上的站点个数
# print(len(goal_site_name))
# print(pd.value_counts(goal_site_name))

# goal=[]
goal_site_name=[j for j in a.loc[a['Filling_Rate']>=0.80]['site']]
print(len(goal_site_name))
# print( a.loc[a['Filling_Rate']>=0.75,'site'])
# print(a.loc[a['Filling_Rate']>=0.75]['site'])
for i in os.listdir(path1):  
    # print(i.split('_',6)[1] in goal_site_name)   
    if i.split('_',3)[0] in goal_site_name:
        #这块儿注意下，列表加的也得列表格式！不然字符串的形式就一个字母一个字母地都输进去了
        # goal+=[i] print(goal) print(len(goal))
        shutil.copy(os.path.join(path1,i),os.path.join(outpath,i))


############################就这四行其实#############################        
goal_site=[j for j in a.loc[a['filling_rate']>=0.80]['site']]        
for i in os.listdir(path1):
    if i.split('_',3)[0] in goal_site:
        shutil.copy(os.path.join(path,i),os.path.join(outpath,i))