Gfyuki

IndexError: Too many indices for array

 # returns a dictionary of n-grams frequency for any list

 def ngrams_freq(listname, n):

 counts = dict()

 # make n-grams as string iteratively

 grams = [' '.join(listname[i:i+n]) for i in range(len(listname)-n)]

 for gram in grams:

      if gram not in counts:

          counts[gram] = 1

      else:

          counts[gram] += 1

   return counts



# returns the values of features for any list

def feature_freq(listname,n):

   counts = dict()

   # make n-grams as string iteratively

   grams = [' '.join(listname[i:i+n]) for i in range(len(listname)-n)]

   for gram in grams:

        counts[gram] = 0

   for gram in grams:

      if gram in features:

            counts[gram] += 1

   return counts



# values of n for finding n-grams

n_values = [3]



# Base address for attack data files

add = "ADFA-LD/ADFA-LD/Attack_Data_Master/"



# initializing dictionary for n-grams from all files

traindict = {}



print(" Training data from Normal")

Normal_list = 

in_address = "ADFA-LD/ADFA-LD/Training_Data_Master/"

k = 1

read_files = glob.glob(in_address+"/*.txt")

for f in read_files:

   with open(f, "r") as infile:

        globals()['Normal%s_list_array' % str(k)] = infile.read().split()

        Normal_list.extend(globals()['Normal%s_list_array' % str(k)])

        k += 1





   #print(Normal_list)

# number of lists for distinct files

Normal_list_size = k-1

# combined list of all files

listname = Normal_list



# finding n-grams and extracting top 30%

for n in n_values:

     dictname = ngrams_freq(listname,n)



 # Creating feature list

 features = 

 #features.append('Label')

 for k,v in dictname.items():

    features.append(k)





 #print (features)  #this contains sequences only



 # Writing training data to file, this file contains sequences of 3-grams



 with open('train1.csv','w') as csvfile:

    # writing features as header 

    writer = csv.DictWriter(csvfile, fieldnames = features, 

   extrasaction='ignore')

    writer.writeheader();



 features_a = np.asarray(features)

 X, y = features_a[:, 0], features_a[:, 1]

IndexError: Too many indices for array

 # returns a dictionary of n-grams frequency for any list

 def ngrams_freq(listname, n):

 counts = dict()

 # make n-grams as string iteratively

 grams = [' '.join(listname[i:i+n]) for i in range(len(listname)-n)]

 for gram in grams:

      if gram not in counts:

          counts[gram] = 1

      else:

          counts[gram] += 1

   return counts



# returns the values of features for any list

def feature_freq(listname,n):

   counts = dict()

   # make n-grams as string iteratively

   grams = [' '.join(listname[i:i+n]) for i in range(len(listname)-n)]

   for gram in grams:

        counts[gram] = 0

   for gram in grams:

      if gram in features:

            counts[gram] += 1

   return counts



# values of n for finding n-grams

n_values = [3]



# Base address for attack data files

add = "ADFA-LD/ADFA-LD/Attack_Data_Master/"



# initializing dictionary for n-grams from all files

traindict = {}



print(" Training data from Normal")

Normal_list = 

in_address = "ADFA-LD/ADFA-LD/Training_Data_Master/"

k = 1

read_files = glob.glob(in_address+"/*.txt")

for f in read_files:

   with open(f, "r") as infile:

        globals()['Normal%s_list_array' % str(k)] = infile.read().split()

        Normal_list.extend(globals()['Normal%s_list_array' % str(k)])

        k += 1





   #print(Normal_list)

# number of lists for distinct files

Normal_list_size = k-1

# combined list of all files

listname = Normal_list



# finding n-grams and extracting top 30%

for n in n_values:

     dictname = ngrams_freq(listname,n)



 # Creating feature list

 features = 

 #features.append('Label')

 for k,v in dictname.items():

    features.append(k)





 #print (features)  #this contains sequences only



 # Writing training data to file, this file contains sequences of 3-grams



 with open('train1.csv','w') as csvfile:

    # writing features as header 

    writer = csv.DictWriter(csvfile, fieldnames = features, 

   extrasaction='ignore')

    writer.writeheader();



 features_a = np.asarray(features)

 X, y = features_a[:, 0], features_a[:, 1]

IndexError: Too many indices for array

 # returns a dictionary of n-grams frequency for any list

 def ngrams_freq(listname, n):

 counts = dict()

 # make n-grams as string iteratively

 grams = [' '.join(listname[i:i+n]) for i in range(len(listname)-n)]

 for gram in grams:

      if gram not in counts:

          counts[gram] = 1

      else:

          counts[gram] += 1

   return counts



# returns the values of features for any list

def feature_freq(listname,n):

   counts = dict()

   # make n-grams as string iteratively

   grams = [' '.join(listname[i:i+n]) for i in range(len(listname)-n)]

   for gram in grams:

        counts[gram] = 0

   for gram in grams:

      if gram in features:

            counts[gram] += 1

   return counts



# values of n for finding n-grams

n_values = [3]



# Base address for attack data files

add = "ADFA-LD/ADFA-LD/Attack_Data_Master/"



# initializing dictionary for n-grams from all files

traindict = {}



print(" Training data from Normal")

Normal_list = 

in_address = "ADFA-LD/ADFA-LD/Training_Data_Master/"

k = 1

read_files = glob.glob(in_address+"/*.txt")

for f in read_files:

   with open(f, "r") as infile:

        globals()['Normal%s_list_array' % str(k)] = infile.read().split()

        Normal_list.extend(globals()['Normal%s_list_array' % str(k)])

        k += 1





   #print(Normal_list)

# number of lists for distinct files

Normal_list_size = k-1

# combined list of all files

listname = Normal_list



# finding n-grams and extracting top 30%

for n in n_values:

     dictname = ngrams_freq(listname,n)



 # Creating feature list

 features = 

 #features.append('Label')

 for k,v in dictname.items():

    features.append(k)





 #print (features)  #this contains sequences only



 # Writing training data to file, this file contains sequences of 3-grams



 with open('train1.csv','w') as csvfile:

    # writing features as header 

    writer = csv.DictWriter(csvfile, fieldnames = features, 

   extrasaction='ignore')

    writer.writeheader();



 features_a = np.asarray(features)

 X, y = features_a[:, 0], features_a[:, 1]

IndexError: Too many indices for array

 # returns a dictionary of n-grams frequency for any list

 def ngrams_freq(listname, n):

 counts = dict()

 # make n-grams as string iteratively

 grams = [' '.join(listname[i:i+n]) for i in range(len(listname)-n)]

 for gram in grams:

      if gram not in counts:

          counts[gram] = 1

      else:

          counts[gram] += 1

   return counts



# returns the values of features for any list

def feature_freq(listname,n):

   counts = dict()

   # make n-grams as string iteratively

   grams = [' '.join(listname[i:i+n]) for i in range(len(listname)-n)]

   for gram in grams:

        counts[gram] = 0

   for gram in grams:

      if gram in features:

            counts[gram] += 1

   return counts



# values of n for finding n-grams

n_values = [3]



# Base address for attack data files

add = "ADFA-LD/ADFA-LD/Attack_Data_Master/"



# initializing dictionary for n-grams from all files

traindict = {}



print(" Training data from Normal")

Normal_list = 

in_address = "ADFA-LD/ADFA-LD/Training_Data_Master/"

k = 1

read_files = glob.glob(in_address+"/*.txt")

for f in read_files:

   with open(f, "r") as infile:

        globals()['Normal%s_list_array' % str(k)] = infile.read().split()

        Normal_list.extend(globals()['Normal%s_list_array' % str(k)])

        k += 1





   #print(Normal_list)

# number of lists for distinct files

Normal_list_size = k-1

# combined list of all files

listname = Normal_list



# finding n-grams and extracting top 30%

for n in n_values:

     dictname = ngrams_freq(listname,n)



 # Creating feature list

 features = 

 #features.append('Label')

 for k,v in dictname.items():

    features.append(k)





 #print (features)  #this contains sequences only



 # Writing training data to file, this file contains sequences of 3-grams



 with open('train1.csv','w') as csvfile:

    # writing features as header 

    writer = csv.DictWriter(csvfile, fieldnames = features, 

   extrasaction='ignore')

    writer.writeheader();



 features_a = np.asarray(features)

 X, y = features_a[:, 0], features_a[:, 1]

Your Answer

StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");

StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "557"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});

function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});


}
});