
import numpy as np
import pandas as pd
from IPython.display import display, HTML


ratings = pd.read_csv('BX-Book-Ratings.csv',sep=';')
ratings.head()


#No negative ratings
ratings[ratings['Book-Rating']<0].head()


ratings[ratings['User-ID']==69188].head()


users = pd.read_csv('BX-Users.csv',sep=';')
users.head()


books = pd.read_csv('BX-Books.csv',sep='";"')
books.head()

C:\Users\Sahil Gupta\Anaconda2\envs\gl-env\lib\site-packages\ipykernel\__main__.py:1: ParserWarning: Falling back to the 'python' engine because the 'c' engine does not support regex separators; you can avoid this warning by specifying engine='python'.
  if __name__ == '__main__':


books.columns = [col.replace("\"","") for col in books.columns]


books['ISBN'] = [val.replace("\"","") for val in books['ISBN']]


books['ISBN'].head()

0    0195153448
1    0002005018
2    0060973129
3    0374157065
4    0393045218
Name: ISBN, dtype: object


books['Image-URL-L'] = [val.replace("\"","") for val in books['Image-URL-L']]


books['Image-URL-L'].head()

0    http://images.amazon.com/images/P/0195153448.0...
1    http://images.amazon.com/images/P/0002005018.0...
2    http://images.amazon.com/images/P/0060973129.0...
3    http://images.amazon.com/images/P/0374157065.0...
4    http://images.amazon.com/images/P/0393045218.0...
Name: Image-URL-L, dtype: object


# Create a new conda environment with Python 2.7.x
#!conda create -n gl-env python=2.7 anaconda=4.0.0

# Activate the conda environment
#!activate gl-env


#!python -m pip install --upgrade pip


#!pip install --upgrade --no-cache-dir https://get.graphlab.com/GraphLab-Create/2.1/gupta376@umn.edu/4715-4040-4813-090E-5214-4B52-7359-CB73/GraphLab-Create-License.tar.gz


import graphlab


#graphlab.get_dependencies()


from sklearn.cross_validation import cross_val_score, train_test_split


## Train the model (fit the data)
train_data, test_data = train_test_split(ratings, train_size=0.95, random_state=100)


train_data.head()


sf = graphlab.SFrame(train_data)
sfTest = graphlab.SFrame(test_data)

This non-commercial license of GraphLab Create for academic use is assigned to gupta376@umn.edu and will expire on December 12, 2017.

[INFO] graphlab.cython.cy_server: GraphLab Create v2.1 started. Logging: C:\Users\SAHILG~1\AppData\Local\Temp\graphlab_server_1483465715.log.0


popularity_model = graphlab.popularity_recommender.create(sf, user_id='User-ID', item_id='ISBN', target='Book-Rating')

Recsys training: model = popularity

Preparing data set.

    Data has 1092291 observations with 102300 users and 330476 items.

    Data prepared in: 1.44484s

1092291 observations to process; with 330476 unique items.


popularity_recomm = popularity_model.recommend(users=range(1,10),k=5)
popularity_recomm.print_rows(num_rows=10)

+---------+------------+-------+------+
| User-ID |    ISBN    | score | rank |
+---------+------------+-------+------+
|    1    | 0679415327 |  10.0 |  1   |
|    1    | 0971938830 |  10.0 |  2   |
|    1    | 0486424650 |  10.0 |  3   |
|    1    | 0785270639 |  10.0 |  4   |
|    1    | 3492223303 |  10.0 |  5   |
|    2    | 0679415327 |  10.0 |  1   |
|    2    | 0971938830 |  10.0 |  2   |
|    2    | 0486424650 |  10.0 |  3   |
|    2    | 0785270639 |  10.0 |  4   |
|    2    | 3492223303 |  10.0 |  5   |
+---------+------------+-------+------+
[45 rows x 4 columns]


aggr = pd.merge(graphlab.SFrame.to_dataframe(popularity_recomm), books[['ISBN','Book-Title']], on = ['ISBN'], how='inner')


display(aggr)


popularity_model.evaluate_rmse(sfTest, target='Book-Rating')

{'rmse_by_item': Columns:
 	ISBN	str
 	count	int
 	rmse	float
 
 Rows: 40456
 
 Data:
 +------------+-------+---------------+
 |    ISBN    | count |      rmse     |
 +------------+-------+---------------+
 | 0263737330 |   1   | 2.86717550543 |
 | 037312189X |   1   |      0.0      |
 | 0345274563 |   1   | 2.92307692308 |
 | 0333387287 |   1   | 2.86717550543 |
 | 050552239X |   1   |      0.0      |
 | 0743410602 |   1   |  2.5652173913 |
 | 0590212877 |   1   | 2.33333333333 |
 | 043957742X |   1   |      0.0      |
 | 0743417844 |   1   |      0.0      |
 | 0312929994 |   1   |     2.625     |
 +------------+-------+---------------+
 [40456 rows x 3 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.,
 'rmse_by_user': Columns:
 	User-ID	int
 	count	int
 	rmse	float
 
 Rows: 17780
 
 Data:
 +---------+-------+---------------+
 | User-ID | count |      rmse     |
 +---------+-------+---------------+
 |  237313 |   1   |      2.4      |
 |  43116  |   1   | 3.43323863636 |
 |  115341 |   1   | 5.36170212766 |
 |  69188  |   1   |      5.0      |
 |  118012 |   1   | 3.66666666667 |
 |  66750  |   1   | 1.11428571429 |
 |  97741  |   1   |      1.0      |
 |  230692 |   1   |      1.5      |
 |  135535 |   1   |     2.875     |
 |  36992  |   2   | 2.63200857442 |
 +---------+-------+---------------+
 [17780 rows x 3 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.,
 'rmse_overall': 4.073509434250113}


item_sim_model = graphlab.item_similarity_recommender.create(sf, user_id='User-ID', item_id='ISBN', target='Book-Rating')

Recsys training: model = item_similarity

Preparing data set.

    Data has 862335 observations with 89722 users and 286804 items.

    Data prepared in: 1.12007s

Training model from provided data.

Gathering per-item and per-user statistics.

+--------------------------------+------------+

| Elapsed Time (Item Statistics) | % Complete |

+--------------------------------+------------+

| 15.546ms                       | 1          |


#Make Recommendations:
item_sim_recomm = item_sim_model.recommend(users=range(1,10),k=5)
item_sim_recomm.print_rows(num_rows=10)

+---------+------------+------------------+------+
| User-ID |    ISBN    |      score       | rank |
+---------+------------+------------------+------+
|    1    | 044021145X | 0.0100413656235  |  1   |
|    1    | 0060928336 | 0.00940719604492 |  2   |
|    1    | 0440213525 | 0.00894405722618 |  3   |
|    1    | 0312195516 | 0.00889273405075 |  4   |
|    1    | 0440214041 | 0.00855695486069 |  5   |
|    2    | 044021145X | 0.0100413656235  |  1   |
|    2    | 0060928336 | 0.00940719604492 |  2   |
|    2    | 0440213525 | 0.00894405722618 |  3   |
|    2    | 0312195516 | 0.00889273405075 |  4   |
|    2    | 0440214041 | 0.00855695486069 |  5   |
+---------+------------+------------------+------+
[45 rows x 4 columns]


item_sim_recomm.show()

Canvas is updated and available in a tab in the default browser.


aggr = pd.merge(graphlab.SFrame.to_dataframe(item_sim_recomm), books[['ISBN','Book-Title']], on = ['ISBN'], how='inner')


display(aggr)


model_performance = graphlab.compare(sfTest, [popularity_model, item_sim_model])
graphlab.show_comparison(model_performance,[popularity_model, item_sim_model])

PROGRESS: Evaluate model M0

recommendations finished on 1000/47880 queries. users per second: 287.309

recommendations finished on 2000/47880 queries. users per second: 284.384

recommendations finished on 3000/47880 queries. users per second: 286.821

recommendations finished on 4000/47880 queries. users per second: 286.685

recommendations finished on 5000/47880 queries. users per second: 287.046

recommendations finished on 6000/47880 queries. users per second: 287.064

recommendations finished on 7000/47880 queries. users per second: 287.079

recommendations finished on 8000/47880 queries. users per second: 287.537

recommendations finished on 9000/47880 queries. users per second: 287.533


popularity_recomm.show()

Canvas is accessible via web browser at the URL: http://localhost:54099/index.html
Opening Canvas in default web browser.


matrix_factor_model = graphlab.factorization_recommender.create(sf, user_id='User-ID', item_id='ISBN', target='Book-Rating', 
                                                                regularization=1e-6, max_iterations=500)

Recsys training: model = factorization_recommender

Preparing data set.

    Data has 1092291 observations with 102300 users and 330476 items.

    Data prepared in: 1.43589s

Training factorization_recommender for recommendations.

+--------------------------------+--------------------------------------------------+----------+

| Parameter                      | Description                                      | Value    |

+--------------------------------+--------------------------------------------------+----------+

| num_factors                    | Factor Dimension                                 | 8        |

| regularization                 | L2 Regularization on Factors                     | 1e-006   |


#Make Recommendations:
matrix_factor_recomm = matrix_factor_model.recommend(users=[69188],k=5)
matrix_factor_recomm.print_rows(num_rows=5)

+---------+------------+---------------+------+
| User-ID |    ISBN    |     score     | rank |
+---------+------------+---------------+------+
|  69188  | 0671734563 | 31.7740267971 |  1   |
|  69188  | 0394800389 | 31.5581492641 |  2   |
|  69188  | 0553057758 | 28.8189067104 |  3   |
|  69188  | 0152047379 | 28.4868544796 |  4   |
|  69188  | 0380799502 |  28.193433688 |  5   |
+---------+------------+---------------+------+
[5 rows x 4 columns]


matrix_factor_model.evaluate_rmse(sfTest, target='Book-Rating')

{'rmse_by_item': Columns:
 	ISBN	str
 	count	int
 	rmse	float
 
 Rows: 40456
 
 Data:
 +------------+-------+----------------+
 |    ISBN    | count |      rmse      |
 +------------+-------+----------------+
 | 0263737330 |   1   | 0.133969233303 |
 | 037312189X |   1   | 0.256416325525 |
 | 0345274563 |   1   | 4.99950559524  |
 | 0333387287 |   1   | 0.834043906002 |
 | 050552239X |   1   | 0.700068726272 |
 | 0743410602 |   1   | 0.906036569805 |
 | 0590212877 |   1   | 1.04643426922  |
 | 043957742X |   1   | 0.384221271544 |
 | 0743417844 |   1   | 4.03500670853  |
 | 0312929994 |   1   | 7.76407335785  |
 +------------+-------+----------------+
 [40456 rows x 3 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.,
 'rmse_by_user': Columns:
 	User-ID	int
 	count	int
 	rmse	float
 
 Rows: 17780
 
 Data:
 +---------+-------+----------------+
 | User-ID | count |      rmse      |
 +---------+-------+----------------+
 |  237313 |   1   | 2.23872773436  |
 |  43116  |   1   | 0.585648565621 |
 |  115341 |   1   |  6.0998668513  |
 |  69188  |   1   | 1.13800565985  |
 |  118012 |   1   | 3.63738138887  |
 |  66750  |   1   | 2.53537179616  |
 |  97741  |   1   | 2.83883710119  |
 |  230692 |   1   |  1.108466939   |
 |  135535 |   1   | 9.15111968753  |
 |  36992  |   2   | 12.6012445133  |
 +---------+-------+----------------+
 [17780 rows x 3 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.,
 'rmse_overall': 4.254394701094985}


rank_factor_model = graphlab.ranking_factorization_recommender.create(sf, user_id='User-ID', item_id='ISBN', target='Book-Rating', 
                                                                max_iterations=50)

Recsys training: model = ranking_factorization_recommender

Preparing data set.

    Data has 1092291 observations with 102300 users and 330476 items.

    Data prepared in: 1.45786s

Training ranking_factorization_recommender for recommendations.

+--------------------------------+--------------------------------------------------+----------+

| Parameter                      | Description                                      | Value    |

+--------------------------------+--------------------------------------------------+----------+

| num_factors                    | Factor Dimension                                 | 32       |

| regularization                 | L2 Regularization on Factors                     | 1e-009   |


#Make Recommendations:
rank_factor_recomm = rank_factor_model.recommend(users=[69188],k=5)
rank_factor_recomm.print_rows(num_rows=5)

+---------+------------+---------------+------+
| User-ID |    ISBN    |     score     | rank |
+---------+------------+---------------+------+
|  69188  | 0811825558 | 14.8589946487 |  1   |
|  69188  | 0345315715 | 14.6149875381 |  2   |
|  69188  | 0553380958 | 14.2803146103 |  3   |
|  69188  | 0060976241 | 13.6427222946 |  4   |
|  69188  | 0812550706 | 13.5892755249 |  5   |
+---------+------------+---------------+------+
[5 rows x 4 columns]


rank_factor_model.evaluate_rmse(sfTest, target='Book-Rating')

{'rmse_by_item': Columns:
 	ISBN	str
 	count	int
 	rmse	float
 
 Rows: 40456
 
 Data:
 +------------+-------+---------------+
 |    ISBN    | count |      rmse     |
 +------------+-------+---------------+
 | 0263737330 |   1   | 5.34130151484 |
 | 037312189X |   1   | 4.46604509565 |
 | 0345274563 |   1   |  1.4633745617 |
 | 0333387287 |   1   | 5.31082303736 |
 | 050552239X |   1   | 4.30599315378 |
 | 0743410602 |   1   | 1.65934709001 |
 | 0590212877 |   1   | 3.46737320635 |
 | 043957742X |   1   | 3.38589246485 |
 | 0743417844 |   1   | 8.80384717795 |
 | 0312929994 |   1   | 2.51979693857 |
 +------------+-------+---------------+
 [40456 rows x 3 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.,
 'rmse_by_user': Columns:
 	User-ID	int
 	count	int
 	rmse	float
 
 Rows: 17780
 
 Data:
 +---------+-------+----------------+
 | User-ID | count |      rmse      |
 +---------+-------+----------------+
 |  237313 |   1   | 1.49798698637  |
 |  43116  |   1   | 2.84383349207  |
 |  115341 |   1   | 5.26586948249  |
 |  69188  |   1   | 3.36552937242  |
 |  118012 |   1   | 5.01669451508  |
 |  66750  |   1   | 3.62250982311  |
 |  97741  |   1   | 2.89033086512  |
 |  230692 |   1   | 0.797411755591 |
 |  135535 |   1   | 2.65705485728  |
 |  36992  |   2   | 3.30571380721  |
 +---------+-------+----------------+
 [17780 rows x 3 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.,
 'rmse_overall': 7.080758290955872}


books[['ISBN','Book-Title','Book-Author','Year-Of-Publication','Publisher']].head()


items_data = books[['ISBN','Book-Title','Book-Author','Year-Of-Publication','Publisher']]
items_data.to_csv('items_data.csv', sep="|",index=False)

items_sf = graphlab.SFrame.read_csv('items_data.csv', sep="|")

Unable to parse line "078946697X|"DK Readers: Creating the X-Men, How It All Began (Level 4: Proficient Readers)\"""|Michael Teitelbaum|2000|DK Publishing Inc"

Unable to parse line "2070426769|"Peuple du ciel, suivi de 'Les Bergers\"""|Jean-Marie Gustave Le ClÃ?Â©zio|2003|Gallimard"

Unable to parse line "0789466953|"DK Readers: Creating the X-Men, How Comic Books Come to Life (Level 4: Proficient Readers)\"""|James Buckley|2000|DK Publishing Inc"

3 lines failed to parse correctly

Finished parsing file C:\Users\Sahil Gupta\Google Drive\Winter Project\items_data.csv

Parsing completed. Parsed 100 lines in 0.746783 secs.

------------------------------------------------------
Inferred types from first 100 line(s) of file as 
column_type_hints=[str,str,str,long,str]
If parsing fails due to incorrect types, you can correct
the inferred type list above and pass it to read_csv in
the column_type_hints argument
------------------------------------------------------

Unable to parse line "078946697X|"DK Readers: Creating the X-Men, How It All Began (Level 4: Proficient Readers)\"""|Michael Teitelbaum|2000|DK Publishing Inc"

Unable to parse line "2070426769|"Peuple du ciel, suivi de 'Les Bergers\"""|Jean-Marie Gustave Le ClÃ?Â©zio|2003|Gallimard"

Unable to parse line "0789466953|"DK Readers: Creating the X-Men, How Comic Books Come to Life (Level 4: Proficient Readers)\"""|James Buckley|2000|DK Publishing Inc"


items_sf.head(2)


content_based_model = graphlab.item_content_recommender.create(items_sf, observation_data=graphlab.SFrame(ratings), 
                                                               user_id='User-ID', item_id='ISBN', target='Book-Rating')

WARNING: The ItemContentRecommender model is still in beta.
WARNING: This feature transformer is still in beta, and some interpretation rules may change in the future.
('Applying transform:\n', Class             : AutoVectorizer

Model Fields
------------
Features          : ['Book-Title', 'Book-Author', 'Year-Of-Publication', 'Publisher']
Excluded Features : ['ISBN']

Column               Type  Interpretation  Transforms                         Output Type
-------------------  ----  --------------  ---------------------------------  -----------
Book-Title           str   short_text      3-Character NGram Counts -> TFIDF  dict       
Book-Author          str   categorical     None                               str        
Year-Of-Publication  int   numerical       None                               int        
Publisher            str   categorical     None                               str        

)

Recsys training: model = item_content_recommender

Defaulting to brute force instead of ball tree because there are multiple distance components.

Starting brute force nearest neighbors model training.

Starting pairwise querying.

+--------------+---------+-------------+--------------+

| Query points | # Pairs | % Complete. | Elapsed Time |

+--------------+---------+-------------+--------------+

| 0            | 67844   |             | 198.834ms    |

| 17           | 4681236 | 0.00635649  | 1.24s        |

	User-ID	ISBN	Book-Rating
0	276725	034545104X	0
1	276726	0155061224	5
2	276727	0446520802	0
3	276729	052165615X	3
4	276729	0521795028	6

	User-ID	ISBN	Book-Rating
289554	69188	0060911239	0
289555	69188	0060929499	8
289556	69188	0060969989	8
289557	69188	014027684X	9
289558	69188	014029628X	9

	User-ID	Location	Age
0	1	nyc, new york, usa	NaN
1	2	stockton, california, usa	18.0
2	3	moscow, yukon territory, russia	NaN
3	4	porto, v.n.gaia, portugal	17.0
4	5	farnborough, hants, united kingdom	NaN

	"ISBN	Book-Title	Book-Author	Year-Of-Publication	Publisher	Image-URL-S	Image-URL-M	Image-URL-L"
0	"0195153448	Classical Mythology	Mark P. O. Morford	2002	Oxford University Press	http://images.amazon.com/images/P/0195153448.0...	http://images.amazon.com/images/P/0195153448.0...	http://images.amazon.com/images/P/0195153448.0...
1	"0002005018	Clara Callan	Richard Bruce Wright	2001	HarperFlamingo Canada	http://images.amazon.com/images/P/0002005018.0...	http://images.amazon.com/images/P/0002005018.0...	http://images.amazon.com/images/P/0002005018.0...
2	"0060973129	Decision in Normandy	Carlo D'Este	1991	HarperPerennial	http://images.amazon.com/images/P/0060973129.0...	http://images.amazon.com/images/P/0060973129.0...	http://images.amazon.com/images/P/0060973129.0...
3	"0374157065	Flu: The Story of the Great Influenza Pandemic...	Gina Bari Kolata	1999	Farrar Straus Giroux	http://images.amazon.com/images/P/0374157065.0...	http://images.amazon.com/images/P/0374157065.0...	http://images.amazon.com/images/P/0374157065.0...
4	"0393045218	The Mummies of Urumchi	E. J. W. Barber	1999	W. W. Norton & Company	http://images.amazon.com/images/P/0393045218.0...	http://images.amazon.com/images/P/0393045218.0...	http://images.amazon.com/images/P/0393045218.0...

	User-ID	ISBN	Book-Rating
238955	55492	0373484143	0
368161	88499	076790592X	9
124453	28591	0451411307	0
1006318	241666	0060198125	0
687490	167471	1861263317	0

	User-ID	ISBN	score	rank	Book-Title
0	1	0679415327	10.0	1	A Place of My Own: The Education of an Amateur...
1	2	0679415327	10.0	1	A Place of My Own: The Education of an Amateur...
2	3	0679415327	10.0	1	A Place of My Own: The Education of an Amateur...
3	4	0679415327	10.0	1	A Place of My Own: The Education of an Amateur...
4	5	0679415327	10.0	1	A Place of My Own: The Education of an Amateur...
5	6	0679415327	10.0	1	A Place of My Own: The Education of an Amateur...
6	7	0679415327	10.0	1	A Place of My Own: The Education of an Amateur...
7	8	0679415327	10.0	1	A Place of My Own: The Education of an Amateur...
8	9	0679415327	10.0	1	A Place of My Own: The Education of an Amateur...
9	1	0971938830	10.0	2	The Authentic Annals of the Early Hebrews
10	2	0971938830	10.0	2	The Authentic Annals of the Early Hebrews
11	3	0971938830	10.0	2	The Authentic Annals of the Early Hebrews
12	4	0971938830	10.0	2	The Authentic Annals of the Early Hebrews
13	5	0971938830	10.0	2	The Authentic Annals of the Early Hebrews
14	6	0971938830	10.0	2	The Authentic Annals of the Early Hebrews
15	7	0971938830	10.0	2	The Authentic Annals of the Early Hebrews
16	8	0971938830	10.0	2	The Authentic Annals of the Early Hebrews
17	9	0971938830	10.0	2	The Authentic Annals of the Early Hebrews
18	1	0486424650	10.0	3	The Communist Manifesto and Other Revolutionar...
19	2	0486424650	10.0	3	The Communist Manifesto and Other Revolutionar...
20	3	0486424650	10.0	3	The Communist Manifesto and Other Revolutionar...
21	4	0486424650	10.0	3	The Communist Manifesto and Other Revolutionar...
22	5	0486424650	10.0	3	The Communist Manifesto and Other Revolutionar...
23	6	0486424650	10.0	3	The Communist Manifesto and Other Revolutionar...
24	7	0486424650	10.0	3	The Communist Manifesto and Other Revolutionar...
25	8	0486424650	10.0	3	The Communist Manifesto and Other Revolutionar...
26	9	0486424650	10.0	3	The Communist Manifesto and Other Revolutionar...
27	1	0785270639	10.0	4	Living Simply In God's Abundance Strength And ...
28	2	0785270639	10.0	4	Living Simply In God's Abundance Strength And ...
29	3	0785270639	10.0	4	Living Simply In God's Abundance Strength And ...
30	4	0785270639	10.0	4	Living Simply In God's Abundance Strength And ...
31	5	0785270639	10.0	4	Living Simply In God's Abundance Strength And ...
32	6	0785270639	10.0	4	Living Simply In God's Abundance Strength And ...
33	7	0785270639	10.0	4	Living Simply In God's Abundance Strength And ...
34	8	0785270639	10.0	4	Living Simply In God's Abundance Strength And ...
35	9	0785270639	10.0	4	Living Simply In God's Abundance Strength And ...

	User-ID	ISBN	score	rank	Book-Title
0	1	044021145X	0.010041	1	The Firm
1	2	044021145X	0.010041	1	The Firm
2	3	044021145X	0.010041	1	The Firm
3	4	044021145X	0.010041	1	The Firm
4	5	044021145X	0.010041	1	The Firm
5	6	044021145X	0.010041	1	The Firm
6	7	044021145X	0.010041	1	The Firm
7	1	0060928336	0.009407	2	Divine Secrets of the Ya-Ya Sisterhood: A Novel
8	2	0060928336	0.009407	2	Divine Secrets of the Ya-Ya Sisterhood: A Novel
9	3	0060928336	0.009407	2	Divine Secrets of the Ya-Ya Sisterhood: A Novel
10	4	0060928336	0.009407	2	Divine Secrets of the Ya-Ya Sisterhood: A Novel
11	5	0060928336	0.009407	2	Divine Secrets of the Ya-Ya Sisterhood: A Novel
12	6	0060928336	0.009407	2	Divine Secrets of the Ya-Ya Sisterhood: A Novel
13	7	0060928336	0.009407	2	Divine Secrets of the Ya-Ya Sisterhood: A Novel
14	1	0440213525	0.008944	3	The Client
15	2	0440213525	0.008944	3	The Client
16	3	0440213525	0.008944	3	The Client
17	4	0440213525	0.008944	3	The Client
18	5	0440213525	0.008944	3	The Client
19	6	0440213525	0.008944	3	The Client
20	7	0440213525	0.008944	3	The Client
21	1	0312195516	0.008893	4	The Red Tent (Bestselling Backlist)
22	2	0312195516	0.008893	4	The Red Tent (Bestselling Backlist)
23	3	0312195516	0.008893	4	The Red Tent (Bestselling Backlist)
24	4	0312195516	0.008893	4	The Red Tent (Bestselling Backlist)
25	5	0312195516	0.008893	4	The Red Tent (Bestselling Backlist)
26	6	0312195516	0.008893	4	The Red Tent (Bestselling Backlist)
27	7	0312195516	0.008893	4	The Red Tent (Bestselling Backlist)
28	1	0440214041	0.008557	5	The Pelican Brief
29	2	0440214041	0.008557	5	The Pelican Brief
30	3	0440214041	0.008557	5	The Pelican Brief
31	4	0440214041	0.008557	5	The Pelican Brief
32	5	0440214041	0.008557	5	The Pelican Brief
33	6	0440214041	0.008557	5	The Pelican Brief
34	7	0440214041	0.008557	5	The Pelican Brief
35	8	1861470592	0.035714	1	The Small Garden Handbook
36	8	0671890778	0.035714	2	Hold It! You're Exercizing Wrong : Your Prescr...
37	8	0817012370	0.035714	3	How to Recover from Grief
38	8	0553252275	0.035714	4	Reflections on Life After Life
39	8	078686043X	0.035714	5	The Beardstown Ladies' Common-Sense Investment...
40	9	0385312202	0.017857	1	Leaving Cold Sassy: The Unfinished Sequel to C...
41	9	0553278355	0.014286	2	The Bell Jar
42	9	0316899984	0.013201	3	River, Cross My Heart
43	9	0060175982	0.012821	4	Mars and Venus Starting Over: A Practical Guid...
44	9	0312950853	0.012821	5	The Nanny Murder Trial (St. Martin's True Crim...

	ISBN	Book-Title	Book-Author	Year-Of-Publication	Publisher
0	0195153448	Classical Mythology	Mark P. O. Morford	2002	Oxford University Press
1	0002005018	Clara Callan	Richard Bruce Wright	2001	HarperFlamingo Canada
2	0060973129	Decision in Normandy	Carlo D'Este	1991	HarperPerennial
3	0374157065	Flu: The Story of the Great Influenza Pandemic...	Gina Bari Kolata	1999	Farrar Straus Giroux
4	0393045218	The Mummies of Urumchi	E. J. W. Barber	1999	W. W. Norton & Company