python读写多个csv文件汇总

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
#将多个文件统计并重新添加表头
import pandas as pd
import os
import glob
import codecs
import pandas as pd
import os
import glob
import codecs
import csv
from collections import Counter
import re
#path = r"F://良好数据的csv文件"
path = r"F://zhengwangwork//data//良好数据的压缩包//udat自主化识别结果//udat-csv"
csv_files = glob.glob(os.path.join(path, "*.csv"))
file_name=[]
data=[]
dd=[]
keys = ['1000','19','90','1','2','4','7','3','6','5','11','12','13','20','30','31','32','40','300','301','200','201']
for f in csv_files:
path=f.split("\")[-1]
file_name.append(path)
#lines = open(f).readlines()
#for writer_obj in lines:
#
re.sub('s','',lines)
with open(f,encoding='utf-8') as csv_file:
writer_obj = csv.DictReader(csv_file)
for row in writer_obj:
data.append(row['severity'].replace(" ",""))#去掉字符串中的空格，当然也可以去#掉其它的符号
from collections import Counter
res = Counter(data)#res 为字典
data=[]#counter存在计数累加的bug，故此清零
dd.append(res)
print(res)
#print(dd)
#print(data)
name2=[file_name]
test=pd.DataFrame(columns=keys,index=name2,data=dd)
test['axis_1']=test.loc[:,['4','1000','19','90','5','6','7','11','12','13','20','31','32','10','300','301','200','201']].apply(lambda x:x.sum(),axis=1)
test['axis_2']=test.loc[:,['1','2','3']].apply(lambda x:x.sum(),axis=1)#统计并求和
#print(test)
#test.to_csv("C:/Users/hxy/source/repos/读取多个csv文件统计到一个里面/读取多个csv文件统计到一个里面/1.csv",encoding="gbk")
test.to_csv("F:/zhengwangwork/data/良好数据的压缩包/udat自主化识别结果/1.csv",encoding="gbk")