Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
C
CS-6604-WebArchive
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Container Registry
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
namanahuja
CS-6604-WebArchive
Commits
d60c6ddd
Commit
d60c6ddd
authored
5 years ago
by
Naman
Browse files
Options
Downloads
Patches
Plain Diff
classifiers
parent
cf194f0d
No related branches found
Branches containing commit
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
archiveTextClassifier.py
+261
-0
261 additions, 0 deletions
archiveTextClassifier.py
with
261 additions
and
0 deletions
archiveTextClassifier.py
0 → 100644
+
261
−
0
View file @
d60c6ddd
#!/usr/bin/env python
# coding: utf-8
# In[2]:
import
os
import
pandas
as
pd
from
html_similarity
import
style_similarity
,
structural_similarity
,
similarity
from
bs4
import
BeautifulSoup
,
Doctype
from
bs4.element
import
Comment
from
collections
import
Counter
from
scipy.spatial
import
distance
from
nltk.corpus
import
stopwords
from
nltk.tokenize
import
word_tokenize
from
nltk.tokenize.treebank
import
TreebankWordDetokenizer
import
string
import
spacy
from
nltk.metrics
import
edit_distance
from
nltk.metrics
import
edit_distance
from
nltk.metrics
import
interval_distance
from
nltk
import
jaccard_distance
import
textdistance
from
sklearn.model_selection
import
train_test_split
from
sklearn.preprocessing
import
StandardScaler
from
sklearn.ensemble
import
RandomForestClassifier
from
sklearn.metrics
import
accuracy_score
from
sklearn
import
svm
# In[3]:
def
tag_visible
(
element
):
if
element
.
parent
.
name
in
[
'
style
'
,
'
script
'
,
'
head
'
,
'
title
'
,
'
meta
'
,
'
[document]
'
]:
return
False
if
isinstance
(
element
,
Comment
):
return
False
return
True
# In[4]:
def
text_from_html
(
htmlPage
):
soup
=
BeautifulSoup
(
htmlPage
,
'
html.parser
'
)
texts
=
soup
.
findAll
(
text
=
True
)
visible_texts
=
filter
(
tag_visible
,
texts
)
return
u
"
"
.
join
(
t
.
strip
()
for
t
in
visible_texts
)
# In[5]:
def
split
(
word
):
return
[
char
for
char
in
word
]
# In[6]:
def
filter_text
(
text
):
stop_words
=
set
(
stopwords
.
words
(
'
english
'
))
stop_words
.
update
(
split
(
string
.
punctuation
))
nlp
=
spacy
.
load
(
'
en_core_web_sm
'
)
spacy_stopwords
=
spacy
.
lang
.
en
.
stop_words
.
STOP_WORDS
stop_words
.
update
(
spacy_stopwords
)
#stop_words.update(["\\t","\\n","\\r"])
text
=
text
.
replace
(
"
\\
n
"
,
""
)
text
=
text
.
replace
(
"
\\
r
"
,
""
)
text
=
text
.
replace
(
"
\\
t
"
,
""
)
word_tokens_text
=
word_tokenize
(
text
)
filtered_text
=
[
w
for
w
in
word_tokens_text
if
not
w
in
stop_words
]
filtered_text
=
TreebankWordDetokenizer
().
detokenize
(
filtered_text
)
return
filtered_text
# In[ ]:
# In[ ]:
# In[7]:
def
classiyRF
(
archiveData
,
newRecord
):
archiveData
.
sort
(
key
=
lambda
x
:
x
[
'
timestamp
'
],
reverse
=
False
)
basePayload
=
archiveData
[
0
][
'
payload
'
]
basePayloadText
=
text_from_html
(
basePayload
)
basePayloadFilteredText
=
filter_text
(
basePayloadText
)
lastSavedDataIndex
=
0
dataset
=
[]
print
(
str
(
len
(
archiveData
))
+
"
datapoints found
"
)
for
i
in
range
(
1
,
len
(
archiveData
)):
if
(
i
%
100
is
0
):
print
(
str
(
i
)
+
"
Records processed
"
)
hasContentChanged
=
False
overallSimilarity
=
similarity
(
basePayload
,
archiveData
[
i
][
'
payload
'
])
styleSimilarity
=
style_similarity
(
basePayload
,
archiveData
[
i
][
'
payload
'
])
structuralSimilarity
=
structural_similarity
(
basePayload
,
archiveData
[
i
][
'
payload
'
])
archiveText
=
text_from_html
(
archiveData
[
i
][
'
payload
'
])
filteredArchiveText
=
filter_text
(
archiveText
)
cosineSimilarity
=
textdistance
.
cosine
.
normalized_similarity
(
basePayloadFilteredText
,
filteredArchiveText
)
jaccardSimilarity
=
textdistance
.
jaccard
.
normalized_similarity
(
basePayloadFilteredText
,
filteredArchiveText
)
#editDistanceSimilarity = textdistance.levenshtein.normalized_similarity(basePayloadFilteredText , filteredArchiveText)
sorensenDiceSimilarity
=
textdistance
.
sorensen_dice
.
normalized_similarity
(
basePayloadFilteredText
,
filteredArchiveText
)
if
(
overallSimilarity
<
0.80
or
cosineSimilarity
<
0.95
):
hasContentChanged
=
True
lastSavedDataIndex
=
i
basePayload
=
archiveData
[
i
][
'
payload
'
]
basePayloadText
=
archiveText
basePayloadFilteredText
=
filteredArchiveText
data
=
[
overallSimilarity
,
styleSimilarity
,
structuralSimilarity
,
cosineSimilarity
,
jaccardSimilarity
,
sorensenDiceSimilarity
,
hasContentChanged
]
dataset
.
append
(
data
)
df
=
pd
.
DataFrame
(
dataset
,
columns
=
[
'
similarity
'
,
'
styleSimilarity
'
,
'
structureSimilarity
'
,
'
cosine
'
,
'
jaccard
'
,
'
sorensen
'
,
'
changed
'
])
print
(
"
Dataframe created
"
)
X
=
df
.
iloc
[:,
0
:
6
].
values
y
=
df
.
iloc
[:,
6
].
values
sc
=
StandardScaler
()
X_train
=
sc
.
fit_transform
(
X
)
overallSimilarity
=
similarity
(
basePayload
,
newRecord
[
'
payload
'
])
styleSimilarity
=
style_similarity
(
basePayload
,
newRecord
[
'
payload
'
])
structuralSimilarity
=
structural_similarity
(
basePayload
,
newRecord
[
'
payload
'
])
archiveText
=
text_from_html
(
newRecord
[
'
payload
'
])
filteredArchiveText
=
filter_text
(
archiveText
)
cosineSimilarity
=
textdistance
.
cosine
.
normalized_similarity
(
basePayloadFilteredText
,
filteredArchiveText
)
jaccardSimilarity
=
textdistance
.
jaccard
.
normalized_similarity
(
basePayloadFilteredText
,
filteredArchiveText
)
#editDistanceSimilarity = textdistance.levenshtein.normalized_similarity(basePayloadFilteredText , filteredArchiveText)
sorensenDiceSimilarity
=
textdistance
.
sorensen_dice
.
normalized_similarity
(
basePayloadFilteredText
,
filteredArchiveText
)
X_test
=
[
overallSimilarity
,
styleSimilarity
,
structuralSimilarity
,
cosineSimilarity
,
jaccardSimilarity
,
sorensenDiceSimilarity
]
print
(
"
Starting Random Forest Classification
"
)
regressor
=
RandomForestClassifier
(
n_estimators
=
20
,
random_state
=
0
)
regressor
.
fit
(
X_train
,
y
)
y_pred
=
regressor
.
predict
([
X_test
])
return
y_pred
# In[ ]:
def
classiySVM
(
archiveData
,
newRecord
):
archiveData
.
sort
(
key
=
lambda
x
:
x
[
'
timestamp
'
],
reverse
=
False
)
basePayload
=
archiveData
[
0
][
'
payload
'
]
basePayloadText
=
text_from_html
(
basePayload
)
basePayloadFilteredText
=
filter_text
(
basePayloadText
)
lastSavedDataIndex
=
0
dataset
=
[]
print
(
str
(
len
(
archiveData
))
+
"
datapoints found
"
)
for
i
in
range
(
1
,
len
(
archiveData
)):
if
(
i
%
100
is
0
):
print
(
str
(
i
)
+
"
Records processed
"
)
hasContentChanged
=
False
overallSimilarity
=
similarity
(
basePayload
,
archiveData
[
i
][
'
payload
'
])
styleSimilarity
=
style_similarity
(
basePayload
,
archiveData
[
i
][
'
payload
'
])
structuralSimilarity
=
structural_similarity
(
basePayload
,
archiveData
[
i
][
'
payload
'
])
archiveText
=
text_from_html
(
archiveData
[
i
][
'
payload
'
])
filteredArchiveText
=
filter_text
(
archiveText
)
cosineSimilarity
=
textdistance
.
cosine
.
normalized_similarity
(
basePayloadFilteredText
,
filteredArchiveText
)
jaccardSimilarity
=
textdistance
.
jaccard
.
normalized_similarity
(
basePayloadFilteredText
,
filteredArchiveText
)
#editDistanceSimilarity = textdistance.levenshtein.normalized_similarity(basePayloadFilteredText , filteredArchiveText)
sorensenDiceSimilarity
=
textdistance
.
sorensen_dice
.
normalized_similarity
(
basePayloadFilteredText
,
filteredArchiveText
)
if
(
overallSimilarity
<
0.80
or
cosineSimilarity
<
0.95
):
hasContentChanged
=
True
lastSavedDataIndex
=
i
basePayload
=
archiveData
[
i
][
'
payload
'
]
basePayloadText
=
archiveText
basePayloadFilteredText
=
filteredArchiveText
data
=
[
overallSimilarity
,
styleSimilarity
,
structuralSimilarity
,
cosineSimilarity
,
jaccardSimilarity
,
sorensenDiceSimilarity
,
hasContentChanged
]
dataset
.
append
(
data
)
df
=
pd
.
DataFrame
(
dataset
,
columns
=
[
'
similarity
'
,
'
styleSimilarity
'
,
'
structureSimilarity
'
,
'
cosine
'
,
'
jaccard
'
,
'
sorensen
'
,
'
changed
'
])
print
(
"
Dataframe created
"
)
X
=
df
.
iloc
[:,
0
:
6
].
values
y
=
df
.
iloc
[:,
6
].
values
sc
=
StandardScaler
()
X_train
=
sc
.
fit_transform
(
X
)
overallSimilarity
=
similarity
(
basePayload
,
newRecord
[
'
payload
'
])
styleSimilarity
=
style_similarity
(
basePayload
,
newRecord
[
'
payload
'
])
structuralSimilarity
=
structural_similarity
(
basePayload
,
newRecord
[
'
payload
'
])
archiveText
=
text_from_html
(
newRecord
[
'
payload
'
])
filteredArchiveText
=
filter_text
(
archiveText
)
cosineSimilarity
=
textdistance
.
cosine
.
normalized_similarity
(
basePayloadFilteredText
,
filteredArchiveText
)
jaccardSimilarity
=
textdistance
.
jaccard
.
normalized_similarity
(
basePayloadFilteredText
,
filteredArchiveText
)
#editDistanceSimilarity = textdistance.levenshtein.normalized_similarity(basePayloadFilteredText , filteredArchiveText)
sorensenDiceSimilarity
=
textdistance
.
sorensen_dice
.
normalized_similarity
(
basePayloadFilteredText
,
filteredArchiveText
)
X_test
=
[
overallSimilarity
,
styleSimilarity
,
structuralSimilarity
,
cosineSimilarity
,
jaccardSimilarity
,
sorensenDiceSimilarity
]
print
(
"
Starting SVM Classification
"
)
regressor
=
svm
.
SVC
()
regressor
.
fit
(
X_train
,
y
)
y_pred
=
regressor
.
predict
([
X_test
])
return
y_pred
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment