0
我有一個訓練有素的分類器，有一直工作正常。Python機器學習訓練Classifer錯誤指數是越界
我試圖修改它來處理多個.csv文件使用循環，但是這已經打破它，原始代碼（這是工作正常）現在返回與.csv文件相同的錯誤它的點它以前處理沒有任何問題。
我非常困惑，看不到什麼會突然導致此錯誤出現之前，一切工作正常。原始（工作）代碼是;
# -*- coding: utf-8 -*-
import csv
import pandas
import numpy as np
import sklearn.ensemble as ske
import re
import os
import collections
import pickle
from sklearn.externals import joblib
from sklearn import model_selection, tree, linear_model, svm
# Load dataset
url = 'test_6_During_100.csv'
dataset = pandas.read_csv(url)
dataset.set_index('Name', inplace = True)
##dataset = dataset[['ProcessorAffinity','ProductVersion','Handle','Company',
## 'UserProcessorTime','Path','Product','Description',]]
# Open file to output everything to
new_url = re.sub('\.csv$', '', url)
f = open(new_url + " output report", 'w')
f.write(new_url + " output report\n")
f.write("\n")
# shape
print(dataset.shape)
print("\n")
f.write("Dataset shape " + str(dataset.shape) + "\n")
f.write("\n")
clf = joblib.load(os.path.join(
os.path.dirname(os.path.realpath(__file__)),
'classifier/classifier.pkl'))
Class_0 = []
Class_1 = []
prob = []
for index, row in dataset.iterrows():
res = clf.predict([row])
if res == 0:
if index in malware:
Class_0.append(index)
elif index in Class_1:
Class_1.append(index)
else:
print "Is ", index, " recognised?"
designation = raw_input()
if designation == "No":
Class_0.append(index)
else:
Class_1.append(index)
dataset['Type'] = 1
dataset.loc[dataset.index.str.contains('|'.join(Class_0)), 'Type'] = 0
print "\n"
results = []
results.append(collections.OrderedDict.fromkeys(dataset.index[dataset['Type'] == 0]))
print (results)
X = dataset.drop(['Type'], axis=1).values
Y = dataset['Type'].values
clf.set_params(n_estimators = len(clf.estimators_) + 40, warm_start = True)
clf.fit(X, Y)
joblib.dump(clf, 'classifier/classifier.pkl')
output = collections.Counter(Class_0)
print "Class_0; \n"
f.write ("Class_0; \n")
for key, value in output.items():
f.write(str(key) + " ; " + str(value) + "\n")
print(str(key) + " ; " + str(value))
print "\n"
f.write ("\n")
output_1 = collections.Counter(Class_1)
print "Class_1; \n"
f.write ("Class_1; \n")
for key, value in output_1.items():
f.write(str(key) + " ; " + str(value) + "\n")
print(str(key) + " ; " + str(value))
print "\n"
f.close()
我的新代碼是一樣的，但是包裹的一對夫婦嵌套循環內，以保持腳本運行，同時有文件的文件夾內的過程中，新的代碼（代碼導致錯誤）低於;
# -*- coding: utf-8 -*-
import csv
import pandas
import numpy as np
import sklearn.ensemble as ske
import re
import os
import time
import collections
import pickle
from sklearn.externals import joblib
from sklearn import model_selection, tree, linear_model, svm
# Our arrays which we'll store our process details in and then later print out data for
Class_0 = []
Class_1 = []
prob = []
results = []
# Open file to output our report too
timestr = time.strftime("%Y%m%d%H%M%S")
f = open(timestr + " output report.txt", 'w')
f.write(timestr + " output report\n")
f.write("\n")
count = len(os.listdir('.'))
while (count > 0):
# Load dataset
for filename in os.listdir('.'):
if filename.endswith('.csv') and filename.startswith("processes_"):
url = filename
dataset = pandas.read_csv(url)
dataset.set_index('Name', inplace = True)
clf = joblib.load(os.path.join(
os.path.dirname(os.path.realpath(__file__)),
'classifier/classifier.pkl'))
for index, row in dataset.iterrows():
res = clf.predict([row])
if res == 0:
if index in Class_0:
Class_0.append(index)
elif index in Class_1:
Class_1.append(index)
else:
print "Is ", index, " recognised?"
designation = raw_input()
if designation == "No":
Class_0.append(index)
else:
Class_1.append(index)
dataset['Type'] = 1
dataset.loc[dataset.index.str.contains('|'.join(Class_0)), 'Type'] = 0
print "\n"
results.append(collections.OrderedDict.fromkeys(dataset.index[dataset['Type'] == 0]))
print (results)
X = dataset.drop(['Type'], axis=1).values
Y = dataset['Type'].values
clf.set_params(n_estimators = len(clf.estimators_) + 40, warm_start = True)
clf.fit(X, Y)
joblib.dump(clf, 'classifier/classifier.pkl')
os.remove(filename)
output = collections.Counter(Class_0)
print "Class_0; \n"
f.write ("Class_0; \n")
for key, value in output.items():
f.write(str(key) + " ; " + str(value) + "\n")
print(str(key) + " ; " + str(value))
print "\n"
f.write ("\n")
output_1 = collections.Counter(Class_1)
print "Class_1; \n"
f.write ("Class_1; \n")
for key, value in output_1.items():
f.write(str(key) + " ; " + str(value) + "\n")
print(str(key) + " ; " + str(value))
print "\n"
f.close()
誤差（IndexError: index 1 is out of bounds for size 1）被引用預測線res = clf.predict([row])。據我所知，問題在於沒有足夠的「類」或數據的標籤類型（我正在尋找二元分類器）？但我一直在使用這個確切的方法（在嵌套循環之外），沒有任何問題。
https://codeshare.io/Gkpb44 - 包含我的.csv數據上面的代碼共享鏈接提到.csv文件。