Domain market Example

Packages to load

[1]:

import ratingslib.ratings as rl
import pandas as pd
from ratingslib.datasets.filenames import FILENAME_DOMAIN_NAMES, dataset_path
from ratingslib.utils import logmsg
from ratingslib.utils.logmsg import set_logger
from ratingslib.utils.methods import print_pandas

Set precision to 4 digits

[2]:

pd.set_option('float_format', "{:.4f}".format)

Set logger to show extra information during computations

[3]:

set_logger(logmsg.EXAMPLE)

Get the filename and add columns dictionary

[4]:

filename_dn = dataset_path(FILENAME_DOMAIN_NAMES)
COLUMNS_DOMAIN_DICT = {
    'item_i': 'DomainNameI',
    'item_j': 'DomainNameJ',
    'points_i': 'TrendsI',
    'points_j': 'TrendsJ',
}

Winloss ratings

[5]:

rl.Winloss(normalization=False).rate_from_file(filename_dn,
                                                      columns_dict=COLUMNS_DOMAIN_DICT)

EXAMPLE: Winloss[normalization=False]
Rating method for filename:
c:\ratingslib\datasets\examples\domainMarketExample.csv
MATRIX:
W
[2. 0. 4. 1. 3.]

[5]:

	Item	rating	ranking
0	authorization.com	2.0000	3
1	desirous.com	0.0000	5
2	jean.com	4.0000	1
3	peaked.com	1.0000	4
4	true.com	3.0000	2

Colley ratings

[6]:

rl.Colley().rate_from_file(filename_dn,
                        columns_dict=COLUMNS_DOMAIN_DICT)

EXAMPLE: Colley
Rating method for filename:
c:\ratingslib\datasets\examples\domainMarketExample.csv
MATRIX:
C
[[ 6. -1. -1. -1. -1.]
 [-1.  6. -1. -1. -1.]
 [-1. -1.  6. -1. -1.]
 [-1. -1. -1.  6. -1.]
 [-1. -1. -1. -1.  6.]]
MATRIX:
b
[ 1. -1.  3.  0.  2.]

[6]:

	Item	rating	ranking
0	authorization.com	0.5000	3
1	desirous.com	0.2143	5
2	jean.com	0.7857	1
3	peaked.com	0.3571	4
4	true.com	0.6429	2

Massey ratings

[7]:

rl.Massey().rate_from_file(filename_dn,
                                 columns_dict=COLUMNS_DOMAIN_DICT)

EXAMPLE: Massey[data_limit=0]
Rating method for filename:
c:\ratingslib\datasets\examples\domainMarketExample.csv
MATRIX:
Massey adjusted
[[ 4. -1. -1. -1. -1.]
 [-1.  4. -1. -1. -1.]
 [-1. -1.  4. -1. -1.]
 [-1. -1. -1.  4. -1.]
 [ 1.  1.  1.  1.  1.]]
MATRIX:
d adjusted
[  26. -313.  263. -189.    0.]

[7]:

	Item	rating	ranking
0	authorization.com	5.2000	3
1	desirous.com	-62.6000	5
2	jean.com	52.6000	1
3	peaked.com	-37.8000	4
4	true.com	42.6000	2

Offesne Defense ratings

[8]:

rl.OffenseDefense().rate_from_file(filename_dn,
                                columns_dict=COLUMNS_DOMAIN_DICT)

EXAMPLE: OffenseDefense[tol=0.0001]
Rating method for filename:
c:\ratingslib\datasets\examples\domainMarketExample.csv
MATRIX:
od A
[[ 0.  1. 88.  5. 73.]
 [93.  0. 88. 80. 73.]
 [ 4.  0.  0.  0. 73.]
 [93. 20. 88.  0. 73.]
 [ 3.  0. 76.  0.  0.]]
INFO: iterations: 16 error: 7.715371838667995e-05 tol: 0.0001000
MATRIX:
Offensive vector
[105.48   7.23 900.54  32.97 703.57]
MATRIX:
Defensive vector
[0.49 3.51 0.14 3.85 0.11]

[8]:

	Item	rating	ranking
0	authorization.com	214.6477	3
1	desirous.com	2.0604	5
2	jean.com	6356.2606	1
3	peaked.com	8.5660	4
4	true.com	6235.3988	2