Question

我正在尝试用LibSVM学习一些机器学习。我有一些Excel CSV格式的“testingset.csv”文件的测试数据，但我必须将此数据集转换为能够在LibSVM中工作。我有以下代码但似乎无法转换它：

import sys
import csv
from collections import defaultdict

def construct_line( label, line ):
    new_line = []
    if float( label ) == 0.0:
        label = "0"
    new_line.append( label )

    for i, item in enumerate( line ):
        if item == '' or float( item ) == 0.0:
            continue
        new_item = "%s:%s" % ( i + 1, item )
        new_line.append( new_item )
    new_line = " ".join( new_line )
    new_line += "\n"
    return new_line

# ---

input_file = sys.argv[1]
output_file = sys.argv[2]

try:
    label_index = int( sys.argv[3] )
except IndexError:
    label_index = 0

try:
    skip_headers = sys.argv[4]
except IndexError:
    skip_headers = 0

i = open( input_file, 'rb' )
o = open( output_file, 'wb' )

reader = csv.reader( i )

if skip_headers:
    headers = reader.next()

for line in reader:
    if label_index == -1:
        label = '1'
    else:
        label = line.pop( label_index )

    new_line = construct_line( label, line )
    o.write( new_line )

Answer 1

我认为代码是多余的 svm输入文件的格式是

l 1:x 2:y 3:z 4:...
l 1:x 2:y 3:z 4:...

其中l是标签

我认为您可以将输入文件准备为由\ t分隔的txt文件（将文件保存为带有excel的txt）

    A   B   C   D
1   l   x   y   z
2   l   x   y   z
...

而不是使用代码

import sys
f=[i.split() for i in open(sys.argv[1]).readlines()
open(sys.argv[1]+'_4libsvm','w').writelines([i[0]+" "+" ".join(pstr(k+1)+":"+j for k,j in enumerate(i[1:])])+"\n" for i in f])

然后执行 python pythonfile.py input1.txt input2.txt ... 它会转换所有的inputfile

CSV到LIBSVM转换器

1 个答案: