In [1]:

    

import graphlab


    

In [2]:

    

people = graphlab.SFrame('people_wiki.gl/')


    

    




[INFO] This non-commercial license of GraphLab Create is assigned to zhanglh13@fudan.edu.cnand will expire on September 21, 2016. For commercial licensing options, visit https://dato.com/buy/.

[INFO] Start server at: ipc:///tmp/graphlab_server-18880 - Server binary: c:\home\courses\machine learning - uw\dato\lib\site-packages\graphlab\unity_server.exe - Server log: C:\Users\linghao\AppData\Local\Temp\graphlab_server_1443775729.log.0
[INFO] GraphLab Server Version: 1.6

In [3]:

    

people['word_count'] = graphlab.text_analytics.count_words(people['text'])


    

In [6]:

    

elton = people[people['name'] == 'Elton John']


    

In [8]:

    

elton['word_count'] = graphlab.text_analytics.count_words(elton['text'])


    

In [12]:

    

elton_word_count_table = elton[['word_count']].stack('word_count', new_column_name=['word', 'count'])


    

In [14]:

    

elton_word_count_table.sort('count', ascending=False)


    

    
Out[14]:





    

        
word
        
count
    
    

        
the
        
27
    
    

        
in
        
18
    
    

        
and
        
15
    
    

        
of
        
13
    
    

        
a
        
10
    
    

        
has
        
9
    
    

        
he
        
7
    
    

        
john
        
7
    
    

        
on
        
6
    
    

        
since
        
5
    

[255 rows x 2 columns]
Note: Only the head of the SFrame is printed.
You can use print_rows(num_rows=m, num_columns=n) to print more rows and columns.

In [16]:

    

tfidf = graphlab.text_analytics.tf_idf(people['word_count'])


    

In [17]:

    

people['tfidf'] = tfidf['docs']


    

In [19]:

    

elton2 = people[people['name'] == 'Elton John']


    

In [22]:

    

elton_tfidf_talbe = elton2[['tfidf']].stack('tfidf', new_column_name=['word', 'tfidf'])


    

In [23]:

    

elton_tfidf_talbe.sort('tfidf', ascending=False)


    

    
Out[23]:





    

        
word
        
tfidf
    
    

        
furnish
        
18.38947184
    
    

        
elton
        
17.48232027
    
    

        
billboard
        
17.3036809575
    
    

        
john
        
13.9393127924
    
    

        
songwriters
        
11.250406447
    
    

        
overallelton
        
10.9864953892
    
    

        
tonightcandle
        
10.9864953892
    
    

        
19702000
        
10.2933482087
    
    

        
fivedecade
        
10.2933482087
    
    

        
aids
        
10.262846934
    

[255 rows x 2 columns]
Note: Only the head of the SFrame is printed.
You can use print_rows(num_rows=m, num_columns=n) to print more rows and columns.

In [26]:

    

paul = people[people['name'] == 'Paul McCartney']


    

In [25]:

    

victoria = people[people['name'] == 'Victoria Beckham']


    

In [30]:

    

graphlab.distances.cosine(elton2['tfidf'][0], paul['tfidf'][0])


    

    
Out[30]:





0.8250310029221779

In [31]:

    

graphlab.distances.cosine(elton2['tfidf'][0], victoria['tfidf'][0])


    

    
Out[31]:





0.9567006376655429

In [39]:

    

word_count_knn_model = graphlab.nearest_neighbors.create(people, features=['word_count'], distance='cosine', label='name')


    

    




PROGRESS: Starting brute force nearest neighbors model training.

In [41]:

    

tfidf_knn_model = graphlab.nearest_neighbors.create(people, features=['tfidf'], distance='cosine', label='name')


    

    




PROGRESS: Starting brute force nearest neighbors model training.

In [42]:

    

word_count_knn_model.query(elton2)


    

    




PROGRESS: Starting pairwise querying.
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 0            | 1       | 0.00169288  | 6.001ms      |
PROGRESS: | Done         |         | 100         | 304.018ms    |
PROGRESS: +--------------+---------+-------------+--------------+






    
Out[42]:





    

        
query_label
        
reference_label
        
distance
        
rank
    
    

        
0
        
Elton John
        
2.22044604925e-16
        
1
    
    

        
0
        
Cliff Richard
        
0.16142415259
        
2
    
    

        
0
        
Sandro Petrone
        
0.16822542751
        
3
    
    

        
0
        
Rod Stewart
        
0.168327165587
        
4
    
    

        
0
        
Malachi O'Doherty
        
0.177315545979
        
5
    

[5 rows x 4 columns]

In [44]:

    

tfidf_knn_model.query(elton2)


    

    




PROGRESS: Starting pairwise querying.
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 0            | 1       | 0.00169288  | 12.001ms     |
PROGRESS: | Done         |         | 100         | 315.018ms    |
PROGRESS: +--------------+---------+-------------+--------------+






    
Out[44]:





    

        
query_label
        
reference_label
        
distance
        
rank
    
    

        
0
        
Elton John
        
-2.22044604925e-16
        
1
    
    

        
0
        
Rod Stewart
        
0.717219667893
        
2
    
    

        
0
        
George Michael
        
0.747600998969
        
3
    
    

        
0
        
Sting (musician)
        
0.747671954431
        
4
    
    

        
0
        
Phil Collins
        
0.75119324879
        
5
    

[5 rows x 4 columns]

In [45]:

    

word_count_knn_model.query(victoria)


    

    




PROGRESS: Starting pairwise querying.
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 0            | 1       | 0.00169288  | 6ms          |
PROGRESS: | Done         |         | 100         | 300.017ms    |
PROGRESS: +--------------+---------+-------------+--------------+






    
Out[45]:





    

        
query_label
        
reference_label
        
distance
        
rank
    
    

        
0
        
Victoria Beckham
        
-2.22044604925e-16
        
1
    
    

        
0
        
Mary Fitzgerald (artist)
        
0.207307036115
        
2
    
    

        
0
        
Adrienne Corri
        
0.214509782788
        
3
    
    

        
0
        
Beverly Jane Fry
        
0.217466468741
        
4
    
    

        
0
        
Raman Mundair
        
0.217695474992
        
5
    

[5 rows x 4 columns]

In [46]:

    

tfidf_knn_model.query(victoria)


    

    




PROGRESS: Starting pairwise querying.
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 0            | 1       | 0.00169288  | 10.001ms     |
PROGRESS: | Done         |         | 100         | 340.02ms     |
PROGRESS: +--------------+---------+-------------+--------------+






    
Out[46]:





    

        
query_label
        
reference_label
        
distance
        
rank
    
    

        
0
        
Victoria Beckham
        
1.11022302463e-16
        
1
    
    

        
0
        
David Beckham
        
0.548169610263
        
2
    
    

        
0
        
Stephen Dow Beckham
        
0.784986706828
        
3
    
    

        
0
        
Mel B
        
0.809585523409
        
4
    
    

        
0
        
Caroline Rush
        
0.819826422919
        
5
    

[5 rows x 4 columns]