The original dataset is downloaded from https://www.kaggle.com/datasets/sid321axn/malicious-urls-dataset which consists of a huge dataset of 651,191 URLs, out of which 428103 benign or safe URLs, 96457 defacement URLs, 94111 phishing URLs, and 32520 malware URLs. The dataset only made up of URL and target class. We further process that data that did the following checks:
+
+
number of redirections
+
show the redirect chain
+
show hsts headers a website use
+
check for SSL stripping
+
check for host name embedding (deceptive url)
+
whether javascript present in url
+
whether have shortening service
+
whether url uses have ip address
+
check for tracking mechanism
+
check of URL encoding
+
check for executables
+
+
+
+
+
+
+
+
In [ ]:
+
+
+
importpandasaspd
+importnumpyasnp
+importseabornassns
+importmatplotlib.pyplotasplt
+
+fromgoogle.colabimportdrive
+drive.mount('/content/drive')
+
+# Ensure that all rows are displayed
+pd.set_option('display.max_rows',None)
+
+# Ensure that all columns are displayed
+pd.set_option('display.max_columns',None)
+
+# Load the data
+path='/content/drive/MyDrive/Colab Notebooks/url_db_cleaned.csv'
+
+data=pd.read_csv(path)
+
+data.head()
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Mounted at /content/drive
+
+
+
+
+
+
+
+
+
+
+
<ipython-input-2-2f803395ba41>:18: DtypeWarning: Columns (11) have mixed types. Specify dtype option on import or set low_memory=False.
+ data = pd.read_csv(path)
+
+
+
+
+
+
+
Out[ ]:
+
+
+
+
+
+
+
+
+
+
+
+
+
domain
+
subdomain
+
top_level_domain
+
query
+
fragment
+
redirect
+
path
+
redirect_chain
+
hsts_header
+
ssl_stripping
+
hostname_embedding
+
javascript_check
+
shortening_service
+
has_ip_address
+
tracking_descriptions
+
url_encoding
+
has_executable
+
qr_code_type_id
+
contents
+
qr_code_id
+
created_at
+
result_category
+
+
+
+
+
0
+
famouswhy
+
people
+
com
+
{}
+
NaN
+
0
+
/marguerite_churchill/
+
{https://people.famouswhy.com/marguerite_churc...
+
{"No HSTS Header detected"}
+
{false}
+
0
+
NaN
+
NaN
+
NaN
+
{}
+
NaN
+
NaN
+
9
+
https://people.famouswhy.com/marguerite_church...
+
403ffba7-f30e-438b-af75-4f4aaa999377
+
2024-08-10 09:54:43.798 +0800
+
benign
+
+
+
1
+
charlotteobserver
+
events
+
com
+
{}
+
NaN
+
0
+
/statesville-nc/events/jazz%2Bconcerts
+
{}
+
{}
+
{}
+
0
+
NaN
+
NaN
+
NaN
+
{}
+
Yes
+
NaN
+
9
+
https://events.charlotteobserver.com/statesvil...
+
9e5c7974-82aa-40b7-94a0-4fa7d49c1d79
+
2024-08-10 09:54:59.363 +0800
+
benign
+
+
+
2
+
wikia
+
icehockey
+
com
+
{}
+
NaN
+
1
+
/wiki/Cory_Pecker
+
{https://icehockey.wikia.com/wiki/Cory_Pecker,...
+
{"No HSTS Header detected","No HSTS Header det...
+
{false,false}
+
0
+
NaN
+
NaN
+
NaN
+
{}
+
NaN
+
NaN
+
9
+
https://icehockey.wikia.com/wiki/Cory_Pecker
+
e8b37ba0-ffbb-4e1f-b77a-5617472ddfe9
+
2024-08-10 09:55:10.845 +0800
+
benign
+
+
+
3
+
vimeo
+
NaN
+
com
+
{}
+
NaN
+
0
+
/9425680
+
{https://vimeo.com/9425680}
+
{"No HSTS Header detected"}
+
{false}
+
0
+
NaN
+
NaN
+
NaN
+
{}
+
NaN
+
NaN
+
9
+
https://vimeo.com/9425680
+
8e9c40e1-2a77-4da0-ac25-8384827c2b68
+
2024-08-10 09:55:11.564 +0800
+
benign
+
+
+
4
+
pensiiilfov
+
www
+
ro
+
{view=article, id=77, Itemid=184, option=com_c...
+
NaN
+
0
+
/index.php
+
{http://www.pensiiilfov.ro/index.php?option=co...
+
{"Not an HTTPS connection"}
+
{false}
+
0
+
NaN
+
NaN
+
NaN
+
{}
+
NaN
+
NaN
+
1
+
http://www.pensiiilfov.ro/index.php?option=com...
+
65cec661-0c54-42d4-9f80-e0486e8a7cfc
+
2024-08-10 09:55:11.512 +0800
+
defacement
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Data Cleaning
+
+
+
+
+
+
+
In [ ]:
+
+
+
# Drop the 'qr_code_id' and 'created_at' columns
+data=data.drop(columns=['qr_code_id','created_at'])
+
+# Replace all NaN and None values with 0
+data=data.fillna(0)
+
+# Replace the string "{}" with 0
+data=data.replace("{}",0)
+
+# Rename the 'qr_code_id' column to 'tls'
+data=data.rename(columns={'qr_code_type_id':'tls'})
+
+# Rename the 'qr_code_id' column to 'tls'
+data=data.rename(columns={'result_category':'target'})
+
+# Change the value in 'tls' column: 0 when value is 1, 1 when value is 9
+data['tls']=data['tls'].replace({1:0,9:1})
+
+# Display the first few rows to verify
+data.head(20)
+
+
+
+
+
+
+
+
+
+
+
+
+
Out[ ]:
+
+
+
+
+
+
+
+
+
+
+
+
+
domain
+
subdomain
+
top_level_domain
+
query
+
fragment
+
redirect
+
path
+
redirect_chain
+
hsts_header
+
ssl_stripping
+
hostname_embedding
+
javascript_check
+
shortening_service
+
has_ip_address
+
tracking_descriptions
+
url_encoding
+
has_executable
+
tls
+
contents
+
target
+
+
+
+
+
0
+
famouswhy
+
people
+
com
+
0
+
0
+
0
+
/marguerite_churchill/
+
{https://people.famouswhy.com/marguerite_churc...
+
{"No HSTS Header detected"}
+
{false}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://people.famouswhy.com/marguerite_church...
+
benign
+
+
+
1
+
charlotteobserver
+
events
+
com
+
0
+
0
+
0
+
/statesville-nc/events/jazz%2Bconcerts
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
Yes
+
0
+
1
+
https://events.charlotteobserver.com/statesvil...
+
benign
+
+
+
2
+
wikia
+
icehockey
+
com
+
0
+
0
+
1
+
/wiki/Cory_Pecker
+
{https://icehockey.wikia.com/wiki/Cory_Pecker,...
+
{"No HSTS Header detected","No HSTS Header det...
+
{false,false}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://icehockey.wikia.com/wiki/Cory_Pecker
+
benign
+
+
+
3
+
vimeo
+
0
+
com
+
0
+
0
+
0
+
/9425680
+
{https://vimeo.com/9425680}
+
{"No HSTS Header detected"}
+
{false}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://vimeo.com/9425680
+
benign
+
+
+
4
+
pensiiilfov
+
www
+
ro
+
{view=article, id=77, Itemid=184, option=com_c...
+
0
+
0
+
/index.php
+
{http://www.pensiiilfov.ro/index.php?option=co...
+
{"Not an HTTPS connection"}
+
{false}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
http://www.pensiiilfov.ro/index.php?option=com...
+
defacement
+
+
+
5
+
npr
+
0
+
org
+
0
+
0
+
0
+
/artists/134598784/seasick-steve
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://npr.org/artists/134598784/seasick-steve
+
benign
+
+
+
6
+
rottentomatoes
+
0
+
com
+
0
+
0
+
2
+
/celebrity/virna_lisi/
+
{https://rottentomatoes.com/celebrity/virna_li...
+
{"HSTS Header: max-age=31536000 ; includeSubDo...
+
{false,false,false}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://rottentomatoes.com/celebrity/virna_lisi/
+
benign
+
+
+
7
+
majorleagueumpires
+
0
+
com
+
0
+
0
+
0
+
/
+
{https://majorleagueumpires.com/}
+
{"No HSTS Header detected"}
+
{false}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://majorleagueumpires.com/
+
benign
+
+
+
8
+
ebay
+
0
+
com
+
{_nkw=wil%2Bwheaton}
+
0
+
1
+
/sch/i.html
+
{https://ebay.com/sch/i.html?_nkw=wil+wheaton,...
+
{"HSTS Header: max-age=31536000","HSTS Header:...
+
{false,false}
+
0
+
0
+
0
+
0
+
0
+
Yes
+
0
+
1
+
https://ebay.com/sch/i.html?_nkw=wil+wheaton
+
benign
+
+
+
9
+
spokeo
+
0
+
com
+
0
+
0
+
2
+
/Susan%2BMeldrum
+
{https://spokeo.com/Susan+Meldrum,https://www....
+
{"No HSTS Header detected","HSTS Header: max-a...
+
{false,false,false}
+
0
+
0
+
0
+
0
+
0
+
Yes
+
0
+
1
+
https://spokeo.com/Susan+Meldrum
+
benign
+
+
+
10
+
sharetv
+
0
+
org
+
0
+
0
+
2
+
/person/noah_beery_jr
+
{https://sharetv.org/person/noah_beery_jr,http...
+
{"No HSTS Header detected","No HSTS Header det...
+
{false,false,false}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://sharetv.org/person/noah_beery_jr
+
benign
+
+
+
11
+
123people
+
0
+
com
+
0
+
0
+
0
+
/s/jesse%2Baaron
+
{https://123people.com/s/jesse+aaron}
+
{"No HSTS Header detected"}
+
{false}
+
0
+
0
+
0
+
0
+
0
+
Yes
+
0
+
1
+
https://123people.com/s/jesse+aaron
+
benign
+
+
+
12
+
123people
+
0
+
ca
+
0
+
0
+
1
+
/s/kevin%2Bbrown
+
{https://123people.ca/s/kevin+brown,https://ww...
+
{"No HSTS Header detected","No HSTS Header det...
+
{false,false}
+
0
+
0
+
0
+
0
+
0
+
Yes
+
0
+
1
+
https://123people.ca/s/kevin+brown
+
benign
+
+
+
13
+
zimtelegraph
+
0
+
com
+
{p=6151}
+
0
+
1
+
/
+
{https://zimtelegraph.com/?p=6151,https://www....
+
{"No HSTS Header detected","No HSTS Header det...
+
{false,false}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://zimtelegraph.com/?p=6151
+
benign
+
+
+
14
+
manta
+
0
+
com
+
0
+
0
+
2
+
/c/mtk113h/john-wornall-house-museum
+
{https://manta.com/c/mtk113h/john-wornall-hous...
+
{"No HSTS Header detected","Not an HTTPS conne...
+
{true,false,false}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://manta.com/c/mtk113h/john-wornall-house...
+
benign
+
+
+
15
+
youtube
+
0
+
com
+
{v=TlqWAJFUols}
+
0
+
1
+
/watch
+
{https://youtube.com/watch?v=TlqWAJFUols,https...
+
{"HSTS Header: max-age=31536000; includeSubDom...
+
{false,false}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://youtube.com/watch?v=TlqWAJFUols
+
benign
+
+
+
16
+
torcache
+
0
+
net
+
{title=%5Bkickass.to%5Dunbroken.2014.1080p.brr...
+
0
+
0
+
/torrent/DEAC407A10AE056525A93EFA957BD252715DE...
+
{http://torcache.net/torrent/DEAC407A10AE05652...
+
{"Not an HTTPS connection"}
+
{false}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
http://torcache.net/torrent/DEAC407A10AE056525...
+
benign
+
+
+
17
+
google
+
0
+
com
+
0
+
0
+
1
+
/
+
{https://google.com/,https://www.google.com/}
+
{"No HSTS Header detected","No HSTS Header det...
+
{false,false}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://google.com/
+
benign
+
+
+
18
+
tvfanatic
+
0
+
com
+
0
+
0
+
2
+
/2009/05/merik-tadros-previews-ncis-showdown-s...
+
{https://tvfanatic.com/2009/05/merik-tadros-pr...
+
{"No HSTS Header detected","No HSTS Header det...
+
{false,false,false}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://tvfanatic.com/2009/05/merik-tadros-pre...
+
benign
+
+
+
19
+
filmreference
+
0
+
com
+
0
+
0
+
0
+
/film/46/Janis-Paige.html
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://filmreference.com/film/46/Janis-Paige....
+
benign
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
In [ ]:
+
+
+
# List of columns to modify to 1
+columns_to_modify=['hostname_embedding','javascript_check','shortening_service',
+ 'has_ip_address','url_encoding','has_executable',
+ 'tracking_descriptions']
+
+# Update the values: set to 1 if not already 0
+forcolumnincolumns_to_modify:
+ data[column]=data[column].apply(lambdax:1ifx!=0else0)
+
+# Convert 'ssl_stripping' column: set to 1 if the value is "true", else set to 0
+data['ssl_stripping']=data['ssl_stripping'].apply(lambdax:1if"true"instr(x).lower()else0)
+
+
+# Display the first few rows to verify changes
+data.head(20)
+
+
+
+
+
+
+
+
+
+
+
+
+
Out[ ]:
+
+
+
+
+
+
+
+
+
+
+
+
+
domain
+
subdomain
+
top_level_domain
+
query
+
fragment
+
redirect
+
path
+
redirect_chain
+
hsts_header
+
ssl_stripping
+
hostname_embedding
+
javascript_check
+
shortening_service
+
has_ip_address
+
tracking_descriptions
+
url_encoding
+
has_executable
+
tls
+
contents
+
target
+
+
+
+
+
0
+
famouswhy
+
people
+
com
+
0
+
0
+
0
+
/marguerite_churchill/
+
{https://people.famouswhy.com/marguerite_churc...
+
{"No HSTS Header detected"}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://people.famouswhy.com/marguerite_church...
+
benign
+
+
+
1
+
charlotteobserver
+
events
+
com
+
0
+
0
+
0
+
/statesville-nc/events/jazz%2Bconcerts
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
0
+
1
+
https://events.charlotteobserver.com/statesvil...
+
benign
+
+
+
2
+
wikia
+
icehockey
+
com
+
0
+
0
+
1
+
/wiki/Cory_Pecker
+
{https://icehockey.wikia.com/wiki/Cory_Pecker,...
+
{"No HSTS Header detected","No HSTS Header det...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://icehockey.wikia.com/wiki/Cory_Pecker
+
benign
+
+
+
3
+
vimeo
+
0
+
com
+
0
+
0
+
0
+
/9425680
+
{https://vimeo.com/9425680}
+
{"No HSTS Header detected"}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://vimeo.com/9425680
+
benign
+
+
+
4
+
pensiiilfov
+
www
+
ro
+
{view=article, id=77, Itemid=184, option=com_c...
+
0
+
0
+
/index.php
+
{http://www.pensiiilfov.ro/index.php?option=co...
+
{"Not an HTTPS connection"}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
http://www.pensiiilfov.ro/index.php?option=com...
+
defacement
+
+
+
5
+
npr
+
0
+
org
+
0
+
0
+
0
+
/artists/134598784/seasick-steve
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://npr.org/artists/134598784/seasick-steve
+
benign
+
+
+
6
+
rottentomatoes
+
0
+
com
+
0
+
0
+
2
+
/celebrity/virna_lisi/
+
{https://rottentomatoes.com/celebrity/virna_li...
+
{"HSTS Header: max-age=31536000 ; includeSubDo...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://rottentomatoes.com/celebrity/virna_lisi/
+
benign
+
+
+
7
+
majorleagueumpires
+
0
+
com
+
0
+
0
+
0
+
/
+
{https://majorleagueumpires.com/}
+
{"No HSTS Header detected"}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://majorleagueumpires.com/
+
benign
+
+
+
8
+
ebay
+
0
+
com
+
{_nkw=wil%2Bwheaton}
+
0
+
1
+
/sch/i.html
+
{https://ebay.com/sch/i.html?_nkw=wil+wheaton,...
+
{"HSTS Header: max-age=31536000","HSTS Header:...
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
0
+
1
+
https://ebay.com/sch/i.html?_nkw=wil+wheaton
+
benign
+
+
+
9
+
spokeo
+
0
+
com
+
0
+
0
+
2
+
/Susan%2BMeldrum
+
{https://spokeo.com/Susan+Meldrum,https://www....
+
{"No HSTS Header detected","HSTS Header: max-a...
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
0
+
1
+
https://spokeo.com/Susan+Meldrum
+
benign
+
+
+
10
+
sharetv
+
0
+
org
+
0
+
0
+
2
+
/person/noah_beery_jr
+
{https://sharetv.org/person/noah_beery_jr,http...
+
{"No HSTS Header detected","No HSTS Header det...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://sharetv.org/person/noah_beery_jr
+
benign
+
+
+
11
+
123people
+
0
+
com
+
0
+
0
+
0
+
/s/jesse%2Baaron
+
{https://123people.com/s/jesse+aaron}
+
{"No HSTS Header detected"}
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
0
+
1
+
https://123people.com/s/jesse+aaron
+
benign
+
+
+
12
+
123people
+
0
+
ca
+
0
+
0
+
1
+
/s/kevin%2Bbrown
+
{https://123people.ca/s/kevin+brown,https://ww...
+
{"No HSTS Header detected","No HSTS Header det...
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
0
+
1
+
https://123people.ca/s/kevin+brown
+
benign
+
+
+
13
+
zimtelegraph
+
0
+
com
+
{p=6151}
+
0
+
1
+
/
+
{https://zimtelegraph.com/?p=6151,https://www....
+
{"No HSTS Header detected","No HSTS Header det...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://zimtelegraph.com/?p=6151
+
benign
+
+
+
14
+
manta
+
0
+
com
+
0
+
0
+
2
+
/c/mtk113h/john-wornall-house-museum
+
{https://manta.com/c/mtk113h/john-wornall-hous...
+
{"No HSTS Header detected","Not an HTTPS conne...
+
1
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://manta.com/c/mtk113h/john-wornall-house...
+
benign
+
+
+
15
+
youtube
+
0
+
com
+
{v=TlqWAJFUols}
+
0
+
1
+
/watch
+
{https://youtube.com/watch?v=TlqWAJFUols,https...
+
{"HSTS Header: max-age=31536000; includeSubDom...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://youtube.com/watch?v=TlqWAJFUols
+
benign
+
+
+
16
+
torcache
+
0
+
net
+
{title=%5Bkickass.to%5Dunbroken.2014.1080p.brr...
+
0
+
0
+
/torrent/DEAC407A10AE056525A93EFA957BD252715DE...
+
{http://torcache.net/torrent/DEAC407A10AE05652...
+
{"Not an HTTPS connection"}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
http://torcache.net/torrent/DEAC407A10AE056525...
+
benign
+
+
+
17
+
google
+
0
+
com
+
0
+
0
+
1
+
/
+
{https://google.com/,https://www.google.com/}
+
{"No HSTS Header detected","No HSTS Header det...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://google.com/
+
benign
+
+
+
18
+
tvfanatic
+
0
+
com
+
0
+
0
+
2
+
/2009/05/merik-tadros-previews-ncis-showdown-s...
+
{https://tvfanatic.com/2009/05/merik-tadros-pr...
+
{"No HSTS Header detected","No HSTS Header det...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://tvfanatic.com/2009/05/merik-tadros-pre...
+
benign
+
+
+
19
+
filmreference
+
0
+
com
+
0
+
0
+
0
+
/film/46/Janis-Paige.html
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://filmreference.com/film/46/Janis-Paige....
+
benign
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
In [ ]:
+
+
+
importre
+
+defprocess_hsts_header(value):
+ # If the value is already 0, return 0
+ ifvalue==0:
+ return0
+
+ # Check if the value starts with '{' and ends with '}', indicating it's an array-like format
+ ifisinstance(value,str)andvalue.startswith("{")andvalue.endswith("}"):
+ # Remove the curly braces and split the string by commas
+ items=re.findall(r'\"(.*?)\"',value)
+
+ # Check the first item in the parsed list
+ ifitemsand'no'initems[0].lower():
+ return0
+ else:
+ return1
+ else:
+ # If it's not in the expected format, return 0
+ return0
+
+# Apply the function to the 'hsts_header' column
+data['hsts_header']=data['hsts_header'].apply(process_hsts_header)
+
+# Display the first few rows to verify the changes
+data.head(20)
+
+
+
+
+
+
+
+
+
+
+
+
+
Out[ ]:
+
+
+
+
+
+
+
+
+
+
+
+
+
domain
+
subdomain
+
top_level_domain
+
query
+
fragment
+
redirect
+
path
+
redirect_chain
+
hsts_header
+
ssl_stripping
+
hostname_embedding
+
javascript_check
+
shortening_service
+
has_ip_address
+
tracking_descriptions
+
url_encoding
+
has_executable
+
tls
+
contents
+
target
+
+
+
+
+
0
+
famouswhy
+
people
+
com
+
0
+
0
+
0
+
/marguerite_churchill/
+
{https://people.famouswhy.com/marguerite_churc...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://people.famouswhy.com/marguerite_church...
+
benign
+
+
+
1
+
charlotteobserver
+
events
+
com
+
0
+
0
+
0
+
/statesville-nc/events/jazz%2Bconcerts
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
0
+
1
+
https://events.charlotteobserver.com/statesvil...
+
benign
+
+
+
2
+
wikia
+
icehockey
+
com
+
0
+
0
+
1
+
/wiki/Cory_Pecker
+
{https://icehockey.wikia.com/wiki/Cory_Pecker,...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://icehockey.wikia.com/wiki/Cory_Pecker
+
benign
+
+
+
3
+
vimeo
+
0
+
com
+
0
+
0
+
0
+
/9425680
+
{https://vimeo.com/9425680}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://vimeo.com/9425680
+
benign
+
+
+
4
+
pensiiilfov
+
www
+
ro
+
{view=article, id=77, Itemid=184, option=com_c...
+
0
+
0
+
/index.php
+
{http://www.pensiiilfov.ro/index.php?option=co...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
http://www.pensiiilfov.ro/index.php?option=com...
+
defacement
+
+
+
5
+
npr
+
0
+
org
+
0
+
0
+
0
+
/artists/134598784/seasick-steve
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://npr.org/artists/134598784/seasick-steve
+
benign
+
+
+
6
+
rottentomatoes
+
0
+
com
+
0
+
0
+
2
+
/celebrity/virna_lisi/
+
{https://rottentomatoes.com/celebrity/virna_li...
+
1
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://rottentomatoes.com/celebrity/virna_lisi/
+
benign
+
+
+
7
+
majorleagueumpires
+
0
+
com
+
0
+
0
+
0
+
/
+
{https://majorleagueumpires.com/}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://majorleagueumpires.com/
+
benign
+
+
+
8
+
ebay
+
0
+
com
+
{_nkw=wil%2Bwheaton}
+
0
+
1
+
/sch/i.html
+
{https://ebay.com/sch/i.html?_nkw=wil+wheaton,...
+
1
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
0
+
1
+
https://ebay.com/sch/i.html?_nkw=wil+wheaton
+
benign
+
+
+
9
+
spokeo
+
0
+
com
+
0
+
0
+
2
+
/Susan%2BMeldrum
+
{https://spokeo.com/Susan+Meldrum,https://www....
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
0
+
1
+
https://spokeo.com/Susan+Meldrum
+
benign
+
+
+
10
+
sharetv
+
0
+
org
+
0
+
0
+
2
+
/person/noah_beery_jr
+
{https://sharetv.org/person/noah_beery_jr,http...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://sharetv.org/person/noah_beery_jr
+
benign
+
+
+
11
+
123people
+
0
+
com
+
0
+
0
+
0
+
/s/jesse%2Baaron
+
{https://123people.com/s/jesse+aaron}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
0
+
1
+
https://123people.com/s/jesse+aaron
+
benign
+
+
+
12
+
123people
+
0
+
ca
+
0
+
0
+
1
+
/s/kevin%2Bbrown
+
{https://123people.ca/s/kevin+brown,https://ww...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
0
+
1
+
https://123people.ca/s/kevin+brown
+
benign
+
+
+
13
+
zimtelegraph
+
0
+
com
+
{p=6151}
+
0
+
1
+
/
+
{https://zimtelegraph.com/?p=6151,https://www....
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://zimtelegraph.com/?p=6151
+
benign
+
+
+
14
+
manta
+
0
+
com
+
0
+
0
+
2
+
/c/mtk113h/john-wornall-house-museum
+
{https://manta.com/c/mtk113h/john-wornall-hous...
+
0
+
1
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://manta.com/c/mtk113h/john-wornall-house...
+
benign
+
+
+
15
+
youtube
+
0
+
com
+
{v=TlqWAJFUols}
+
0
+
1
+
/watch
+
{https://youtube.com/watch?v=TlqWAJFUols,https...
+
1
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://youtube.com/watch?v=TlqWAJFUols
+
benign
+
+
+
16
+
torcache
+
0
+
net
+
{title=%5Bkickass.to%5Dunbroken.2014.1080p.brr...
+
0
+
0
+
/torrent/DEAC407A10AE056525A93EFA957BD252715DE...
+
{http://torcache.net/torrent/DEAC407A10AE05652...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
http://torcache.net/torrent/DEAC407A10AE056525...
+
benign
+
+
+
17
+
google
+
0
+
com
+
0
+
0
+
1
+
/
+
{https://google.com/,https://www.google.com/}
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://google.com/
+
benign
+
+
+
18
+
tvfanatic
+
0
+
com
+
0
+
0
+
2
+
/2009/05/merik-tadros-previews-ncis-showdown-s...
+
{https://tvfanatic.com/2009/05/merik-tadros-pr...
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://tvfanatic.com/2009/05/merik-tadros-pre...
+
benign
+
+
+
19
+
filmreference
+
0
+
com
+
0
+
0
+
0
+
/film/46/Janis-Paige.html
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
https://filmreference.com/film/46/Janis-Paige....
+
benign
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
In [ ]:
+
+
+
# List of columns to convert to number of characters
+columns_to_convert=['domain','top_level_domain','subdomain','query',
+ 'fragment','path','redirect_chain','contents']
+
+# Apply len() function to each of the specified columns to get the number of characters
+forcolumnincolumns_to_convert:
+ data[column]=data[column].apply(lambdax:len(str(x))ifpd.notnull(x)else0)
+
+# Map the target class to numerical values
+target_mapping={
+ 'benign':0,
+ 'defacement':1,
+ 'malware':2,
+ 'phishing':3
+}
+
+data['target']=data['target'].replace(target_mapping)
+
+# Display the first few rows to verify the changes
+data.head()
+
+
+
+
+
+
+
+
+
+
+
+
+
Out[ ]:
+
+
+
+
+
+
+
+
+
+
+
+
+
domain
+
subdomain
+
top_level_domain
+
query
+
fragment
+
redirect
+
path
+
redirect_chain
+
hsts_header
+
ssl_stripping
+
hostname_embedding
+
javascript_check
+
shortening_service
+
has_ip_address
+
tracking_descriptions
+
url_encoding
+
has_executable
+
tls
+
contents
+
target
+
+
+
+
+
0
+
9
+
6
+
3
+
1
+
1
+
0
+
22
+
52
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
50
+
0
+
+
+
1
+
17
+
6
+
3
+
1
+
1
+
0
+
38
+
1
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
0
+
1
+
72
+
0
+
+
+
2
+
5
+
9
+
3
+
1
+
1
+
1
+
17
+
92
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
44
+
0
+
+
+
3
+
5
+
1
+
3
+
1
+
1
+
0
+
8
+
27
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
1
+
25
+
0
+
+
+
4
+
11
+
3
+
2
+
53
+
1
+
0
+
10
+
86
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
0
+
84
+
1
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
In [ ]:
+
+
+
# Copy the data to avoid modifying the original DataFrame
+data_encoded=data.copy()
+
+# Encode categorical variables with integer encoding
+forcolumnindata_encoded.select_dtypes(include=['object','category']).columns:
+ data_encoded[column]=data_encoded[column].astype('category').cat.codes
+
+# Calculate the correlation matrix
+correlation_matrix=data_encoded.corr(method='pearson')
+
+# Sort correlations in descending order
+sorted_correlations=correlation_matrix.unstack().sort_values(ascending=False,key=abs)
+
+# Remove duplicate correlations and self-correlations
+sorted_correlations=sorted_correlations[(sorted_correlations<1)&
+ (sorted_correlations>-1)].drop_duplicates()
+
+# Create a heatmap of the correlation matrix
+plt.figure(figsize=(12,10))
+sns.heatmap(correlation_matrix,cmap='coolwarm',center=0,annot=True,fmt=".2f")
+plt.title('Correlation Heatmap')
+plt.show()
+
+# Display sorted correlations with background gradient (optional)
+styled_correlations=correlation_matrix.style.background_gradient(cmap='coolwarm')
+styled_correlations
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Out[ ]:
+
+
+
+
+
+
+
+
+
+
domain
+
subdomain
+
top_level_domain
+
query
+
fragment
+
redirect
+
path
+
redirect_chain
+
hsts_header
+
ssl_stripping
+
hostname_embedding
+
javascript_check
+
shortening_service
+
has_ip_address
+
tracking_descriptions
+
url_encoding
+
has_executable
+
tls
+
contents
+
target
+
+
+
+
+
domain
+
1.000000
+
-0.149618
+
0.070517
+
0.025251
+
-0.001999
+
-0.091271
+
-0.103002
+
-0.032532
+
-0.132035
+
-0.020964
+
-0.016897
+
0.000905
+
-0.016502
+
0.109330
+
-0.020126
+
-0.054941
+
-0.051782
+
-0.057589
+
0.034923
+
-0.004340
+
+
+
subdomain
+
-0.149618
+
1.000000
+
-0.109429
+
0.033378
+
0.004213
+
-0.074009
+
-0.008929
+
-0.025925
+
-0.069056
+
-0.031019
+
0.489992
+
-0.000740
+
0.080844
+
-0.042574
+
0.002598
+
-0.046689
+
0.023112
+
0.001871
+
0.276423
+
0.058300
+
+
+
top_level_domain
+
0.070517
+
-0.109429
+
1.000000
+
-0.116257
+
-0.001123
+
0.029653
+
0.060649
+
0.007279
+
0.156154
+
0.045547
+
0.029927
+
0.001463
+
0.075501
+
-0.474097
+
-0.007049
+
0.075147
+
-0.076408
+
0.350973
+
-0.069449
+
-0.183335
+
+
+
query
+
0.025251
+
0.033378
+
-0.116257
+
1.000000
+
0.000368
+
0.019897
+
-0.125852
+
0.102771
+
-0.079392
+
-0.037063
+
0.031424
+
0.003336
+
-0.016585
+
-0.042096
+
0.063684
+
0.148184
+
-0.033489
+
-0.265888
+
0.673632
+
0.018143
+
+
+
fragment
+
-0.001999
+
0.004213
+
-0.001123
+
0.000368
+
1.000000
+
-0.002871
+
0.002008
+
0.002674
+
-0.003584
+
-0.001408
+
0.004069
+
-0.000034
+
0.009304
+
0.001973
+
-0.000554
+
0.001837
+
-0.001020
+
0.000983
+
0.030370
+
0.014667
+
+
+
redirect
+
-0.091271
+
-0.074009
+
0.029653
+
0.019897
+
-0.002871
+
1.000000
+
0.110208
+
0.493915
+
0.124105
+
0.312038
+
-0.048606
+
-0.001758
+
-0.019225
+
-0.072290
+
-0.003036
+
0.025532
+
-0.050106
+
-0.034452
+
0.062467
+
-0.125495
+
+
+
path
+
-0.103002
+
-0.008929
+
0.060649
+
-0.125852
+
0.002008
+
0.110208
+
1.000000
+
0.132329
+
-0.034376
+
0.035940
+
0.003492
+
-0.001263
+
0.009201
+
-0.071098
+
-0.010602
+
0.244904
+
-0.002244
+
-0.146011
+
0.561191
+
-0.149450
+
+
+
redirect_chain
+
-0.032532
+
-0.025925
+
0.007279
+
0.102771
+
0.002674
+
0.493915
+
0.132329
+
1.000000
+
0.052521
+
0.079979
+
-0.024769
+
-0.000991
+
0.002580
+
-0.038346
+
0.005351
+
0.057792
+
-0.023774
+
-0.050487
+
0.157086
+
-0.065771
+
+
+
hsts_header
+
-0.132035
+
-0.069056
+
0.156154
+
-0.079392
+
-0.003584
+
0.124105
+
-0.034376
+
0.052521
+
1.000000
+
-0.033615
+
-0.041312
+
-0.001456
+
-0.048528
+
-0.061468
+
-0.020496
+
-0.028736
+
-0.042739
+
0.298860
+
-0.113300
+
-0.157230
+
+
+
ssl_stripping
+
-0.020964
+
-0.031019
+
0.045547
+
-0.037063
+
-0.001408
+
0.312038
+
0.035940
+
0.079979
+
-0.033615
+
1.000000
+
-0.015376
+
-0.000543
+
-0.016078
+
-0.023061
+
0.000566
+
-0.009352
+
-0.016072
+
0.065977
+
-0.012553
+
-0.035747
+
+
+
hostname_embedding
+
-0.016897
+
0.489992
+
0.029927
+
0.031424
+
0.004069
+
-0.048606
+
0.003492
+
-0.024769
+
-0.041312
+
-0.015376
+
1.000000
+
-0.000308
+
0.025159
+
-0.011978
+
0.064650
+
-0.021480
+
-0.007927
+
0.015209
+
0.157565
+
-0.006299
+
+
+
javascript_check
+
0.000905
+
-0.000740
+
0.001463
+
0.003336
+
-0.000034
+
-0.001758
+
-0.001263
+
-0.000991
+
-0.001456
+
-0.000543
+
-0.000308
+
1.000000
+
0.003082
+
-0.000462
+
-0.000174
+
-0.000794
+
-0.000320
+
0.001206
+
0.001699
+
-0.002031
+
+
+
shortening_service
+
-0.016502
+
0.080844
+
0.075501
+
-0.016585
+
0.009304
+
-0.019225
+
0.009201
+
0.002580
+
-0.048528
+
-0.016078
+
0.025159
+
0.003082
+
1.000000
+
-0.035354
+
0.012540
+
-0.009572
+
-0.018367
+
0.046652
+
0.021110
+
-0.018505
+
+
+
has_ip_address
+
0.109330
+
-0.042574
+
-0.474097
+
-0.042096
+
0.001973
+
-0.072290
+
-0.071098
+
-0.038346
+
-0.061468
+
-0.023061
+
-0.011978
+
-0.000462
+
-0.035354
+
1.000000
+
-0.006584
+
-0.027852
+
0.032882
+
-0.202050
+
-0.093624
+
0.175486
+
+
+
tracking_descriptions
+
-0.020126
+
0.002598
+
-0.007049
+
0.063684
+
-0.000554
+
-0.003036
+
-0.010602
+
0.005351
+
-0.020496
+
0.000566
+
0.064650
+
-0.000174
+
0.012540
+
-0.006584
+
1.000000
+
0.014311
+
-0.005150
+
-0.019448
+
0.039709
+
-0.021144
+
+
+
url_encoding
+
-0.054941
+
-0.046689
+
0.075147
+
0.148184
+
0.001837
+
0.025532
+
0.244904
+
0.057792
+
-0.028736
+
-0.009352
+
-0.021480
+
-0.000794
+
-0.009572
+
-0.027852
+
0.014311
+
1.000000
+
-0.020636
+
-0.052264
+
0.181566
+
-0.056759
+
+
+
has_executable
+
-0.051782
+
0.023112
+
-0.076408
+
-0.033489
+
-0.001020
+
-0.050106
+
-0.002244
+
-0.023774
+
-0.042739
+
-0.016072
+
-0.007927
+
-0.000320
+
-0.018367
+
0.032882
+
-0.005150
+
-0.020636
+
1.000000
+
0.025109
+
-0.026814
+
0.121012
+
+
+
tls
+
-0.057589
+
0.001871
+
0.350973
+
-0.265888
+
0.000983
+
-0.034452
+
-0.146011
+
-0.050487
+
0.298860
+
0.065977
+
0.015209
+
0.001206
+
0.046652
+
-0.202050
+
-0.019448
+
-0.052264
+
0.025109
+
1.000000
+
-0.293321
+
-0.217785
+
+
+
contents
+
0.034923
+
0.276423
+
-0.069449
+
0.673632
+
0.030370
+
0.062467
+
0.561191
+
0.157086
+
-0.113300
+
-0.012553
+
0.157565
+
0.001699
+
0.021110
+
-0.093624
+
0.039709
+
0.181566
+
-0.026814
+
-0.293321
+
1.000000
+
-0.086009
+
+
+
target
+
-0.004340
+
0.058300
+
-0.183335
+
0.018143
+
0.014667
+
-0.125495
+
-0.149450
+
-0.065771
+
-0.157230
+
-0.035747
+
-0.006299
+
-0.002031
+
-0.018505
+
0.175486
+
-0.021144
+
-0.056759
+
0.121012
+
-0.217785
+
-0.086009
+
1.000000
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
In [ ]:
+
+
+
# Copy the data to avoid modifying the original DataFrame
+data_encoded=data.copy()
+
+# Encode categorical variables with integer encoding
+forcolumnindata_encoded.select_dtypes(include=['object','category']).columns:
+ data_encoded[column]=data_encoded[column].astype('category').cat.codes
+
+# Calculate the correlation matrix
+correlation_matrix=data_encoded.corr(method='pearson')
+
+# Extract correlations with the target class
+target_correlations=correlation_matrix['target'].drop('target').sort_values(ascending=False,key=abs)
+
+# Display correlations with the target class
+print("Correlations with the target class in descending order:")
+print(target_correlations)
+
Use stratified sampling to select 80% data for training and 20% for testing.
+
+
+
+
+
+
+
In [ ]:
+
+
+
fromsklearn.model_selectionimportStratifiedShuffleSplit
+
+# Define the stratified shuffle split
+stratified_split=StratifiedShuffleSplit(n_splits=1,test_size=0.25,random_state=42)
+
+# Separate the features and target
+X=data.drop(columns=['target'])
+y=data['target']
+
+# Perform the split
+fortrain_index,test_indexinstratified_split.split(X,y):
+ X_train,X_test=X.iloc[train_index],X.iloc[test_index]
+ y_train,y_test=y.iloc[train_index],y.iloc[test_index]
+
+# Combine X and y for training and testing sets
+train_data=X_train.copy()
+train_data['target']=y_train
+
+test_data=X_test.copy()
+test_data['target']=y_test
+
+# Display the number of samples in each set to verify
+print(f"Training set size: {len(train_data)}")
+print(f"Testing set size: {len(test_data)}")
+
+# Display the first few rows of the training set
+train_data.head()
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Training set size: 485667
+Testing set size: 161889
+
# Verify the split
+print("Training set size:",len(train_data))
+print(train_data['target'].value_counts())
+
+print("Testing set size:",len(test_data))
+print(test_data['target'].value_counts())
+
frommathimporte
+fromsklearn.ensembleimportRandomForestClassifier
+fromsklearn.preprocessingimportMinMaxScaler
+fromsklearn.model_selectionimportGridSearchCV
+fromsklearn.metricsimportclassification_report,accuracy_score
+fromsklearn.pipelineimportPipeline
+
+# Step 1: Create a pipeline with MinMaxScaler and RandomForestClassifier
+pipeline=Pipeline([
+ ('scaler',MinMaxScaler()),# Scaling with MinMaxScaler
+ ('rf',RandomForestClassifier(random_state=42))# Random Forest classifier
+])
+
+# Step 2: Define the parameter grid for GridSearchCV
+param_grid={
+ 'rf__n_estimators':[100],
+ 'rf__max_depth':[15]
+}
+
+# Step 3: Initialize GridSearchCV with the pipeline and parameter grid
+grid_search=GridSearchCV(pipeline,param_grid,cv=5,n_jobs=-1,verbose=2,scoring='accuracy')
+
+# Step 4: Fit GridSearchCV to the training data
+grid_search.fit(X_train,y_train)
+
+# Step 5: Print the best parameters found by GridSearchCV
+print("Best parameters found: ",grid_search.best_params_)
+
+# Step 6: Evaluate the model with the best parameters on the test set
+best_model=grid_search.best_estimator_
+y_pred=best_model.predict(X_test)
+
+# Evaluate Model
+evaluate_model(y_test,y_pred)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Fitting 5 folds for each of 1 candidates, totalling 5 fits
+Best parameters found: {'rf__max_depth': 15, 'rf__n_estimators': 100}
+Accuracy on test set: 0.903415303078035
+
fromsklearn.naive_bayesimportMultinomialNB
+
+# Step 1: Create a pipeline with MinMaxScaler and MultinomialNB
+pipeline=Pipeline([
+ ('scaler',MinMaxScaler()),# Scaling with MinMaxScaler
+ ('nb',MultinomialNB())# Naive Bayes classifier
+])
+
+# Step 2: Define the parameter grid for GridSearchCV
+# Naive Bayes doesn't have as many parameters as RandomForest, so the grid is smaller
+param_grid={
+ 'nb__alpha':[0.1,1.0,10.0]# Smoothing parameter
+}
+
+# Step 3: Initialize GridSearchCV with the pipeline and parameter grid
+grid_search=GridSearchCV(pipeline,param_grid,cv=5,n_jobs=-1,verbose=2,scoring='accuracy')
+
+# Step 4: Fit GridSearchCV to the training data
+grid_search.fit(X_train,y_train)
+
+# Step 5: Print the best parameters found by GridSearchCV
+print("Best parameters found: ",grid_search.best_params_)
+
+# Step 6: Evaluate the model with the best parameters on the test set
+best_model=grid_search.best_estimator_
+y_pred=best_model.predict(X_test)
+
+# Evaluate Model
+evaluate_model(y_test,y_pred)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Fitting 5 folds for each of 3 candidates, totalling 15 fits
+Best parameters found: {'nb__alpha': 0.1}
+Accuracy on test set: 0.6897503845227285
+
fromxgboostimportXGBClassifier
+fromsklearn.metricsimportclassification_report,accuracy_score
+
+# Initialize the model
+model=XGBClassifier(objective='multi:softmax',num_class=4,random_state=42)
+
+# Fit the model to the training data
+model.fit(X_train,y_train)
+
+# Predict on the test set
+y_pred=model.predict(X_test)
+
+# Evaluate the model
+evaluate_model(y_test,y_pred)
+
fromsklearn.model_selectionimportRandomizedSearchCV
+
+param_distributions={
+ 'n_estimators':[100,200],
+ 'max_depth':[6,10],
+ 'learning_rate':[0.1,0.2]
+}
+
+randomized_search=RandomizedSearchCV(
+ model,param_distributions,n_iter=8,scoring='accuracy',cv=5,verbose=1,random_state=42,n_jobs=-1
+)
+
+randomized_search.fit(X_train,y_train)
+
+# Best parameters found
+print("Best parameters found: ",randomized_search.best_params_)
+
+# Evaluate the best model
+best_model=randomized_search.best_estimator_
+y_pred=best_model.predict(X_test)
+evaluate_model(y_test,y_pred)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Fitting 5 folds for each of 8 candidates, totalling 40 fits
+
+
+
+
+
+
+
+
+
+
+
/usr/local/lib/python3.10/dist-packages/joblib/externals/loky/process_executor.py:752: UserWarning: A worker stopped while some jobs were given to the executor. This can be caused by a too short worker timeout or by a memory leak.
+ warnings.warn(
+
+
+
+
+
+
+
+
+
+
+
Best parameters found: {'n_estimators': 200, 'max_depth': 10, 'learning_rate': 0.2}
+Accuracy on test set: 0.9327749260295635
+
+
+
+
+
+
+