72 KiB
72 KiB
import pandas as pd
books=pd.read_csv('books.csv')
books
isbn13 | isbn10 | title | subtitle | authors | categories | thumbnail | description | published_year | average_rating | num_pages | ratings_count | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 9780002005883 | 0002005883 | Gilead | NaN | Marilynne Robinson | Fiction | http://books.google.com/books/content?id=KQZCP... | A NOVEL THAT READERS and critics have been eag... | 2004.0 | 3.85 | 247.0 | 361.0 |
1 | 9780002261982 | 0002261987 | Spider's Web | A Novel | Charles Osborne;Agatha Christie | Detective and mystery stories | http://books.google.com/books/content?id=gA5GP... | A new 'Christie for Christmas' -- a full-lengt... | 2000.0 | 3.83 | 241.0 | 5164.0 |
2 | 9780006163831 | 0006163831 | The One Tree | NaN | Stephen R. Donaldson | American fiction | http://books.google.com/books/content?id=OmQaw... | Volume Two of Stephen Donaldson's acclaimed se... | 1982.0 | 3.97 | 479.0 | 172.0 |
3 | 9780006178736 | 0006178731 | Rage of angels | NaN | Sidney Sheldon | Fiction | http://books.google.com/books/content?id=FKo2T... | A memorable, mesmerizing heroine Jennifer -- b... | 1993.0 | 3.93 | 512.0 | 29532.0 |
4 | 9780006280897 | 0006280897 | The Four Loves | NaN | Clive Staples Lewis | Christian life | http://books.google.com/books/content?id=XhQ5X... | Lewis' work on the nature of love divides love... | 2002.0 | 4.15 | 170.0 | 33684.0 |
... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
6805 | 9788185300535 | 8185300534 | I Am that | Talks with Sri Nisargadatta Maharaj | Sri Nisargadatta Maharaj;Sudhakar S. Dikshit | Philosophy | http://books.google.com/books/content?id=Fv_JP... | This collection of the timeless teachings of o... | 1999.0 | 4.51 | 531.0 | 104.0 |
6806 | 9788185944609 | 8185944601 | Secrets Of The Heart | NaN | Khalil Gibran | Mysticism | http://books.google.com/books/content?id=XcrVp... | NaN | 1993.0 | 4.08 | 74.0 | 324.0 |
6807 | 9788445074879 | 8445074873 | Fahrenheit 451 | NaN | Ray Bradbury | Book burning | NaN | NaN | 2004.0 | 3.98 | 186.0 | 5733.0 |
6808 | 9789027712059 | 9027712050 | The Berlin Phenomenology | NaN | Georg Wilhelm Friedrich Hegel | History | http://books.google.com/books/content?id=Vy7Sk... | Since the three volume edition ofHegel's Philo... | 1981.0 | 0.00 | 210.0 | 0.0 |
6809 | 9789042003408 | 9042003405 | 'I'm Telling You Stories' | Jeanette Winterson and the Politics of Reading | Helena Grice;Tim Woods | Literary Criticism | http://books.google.com/books/content?id=2lVyR... | This is a jubilant and rewarding collection of... | 1998.0 | 3.70 | 136.0 | 10.0 |
6810 rows × 12 columns
books.describe(include='all')
isbn13 | isbn10 | title | subtitle | authors | categories | thumbnail | description | published_year | average_rating | num_pages | ratings_count | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
count | 6.810000e+03 | 6810 | 6810 | 2381 | 6738 | 6711 | 6481 | 6548 | 6804.000000 | 6767.000000 | 6767.000000 | 6.767000e+03 |
unique | NaN | 6810 | 6398 | 2009 | 3780 | 567 | 6481 | 6474 | NaN | NaN | NaN | NaN |
top | NaN | 0786282258 | The Lord of the Rings | A Novel | Agatha Christie | Fiction | http://books.google.com/books/content?id=6dVAW... | This is a reproduction of the original artefac... | NaN | NaN | NaN | NaN |
freq | NaN | 1 | 11 | 226 | 37 | 2588 | 1 | 6 | NaN | NaN | NaN | NaN |
mean | 9.780677e+12 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 1998.630364 | 3.933284 | 348.181026 | 2.106910e+04 |
std | 6.068911e+08 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 10.484257 | 0.331352 | 242.376783 | 1.376207e+05 |
min | 9.780002e+12 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 1853.000000 | 0.000000 | 0.000000 | 0.000000e+00 |
25% | 9.780330e+12 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 1996.000000 | 3.770000 | 208.000000 | 1.590000e+02 |
50% | 9.780553e+12 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 2002.000000 | 3.960000 | 304.000000 | 1.018000e+03 |
75% | 9.780810e+12 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 2005.000000 | 4.130000 | 420.000000 | 5.992500e+03 |
max | 9.789042e+12 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 2019.000000 | 5.000000 | 3342.000000 | 5.629932e+06 |
books.isnull().sum()
isbn13 0 isbn10 0 title 0 subtitle 4429 authors 72 categories 99 thumbnail 329 description 262 published_year 6 average_rating 43 num_pages 43 ratings_count 43 dtype: int64
books.drop('thumbnail', inplace=True, axis=1)
books.drop('subtitle', inplace=True, axis=1)
books.drop('description', inplace=True, axis=1)
books.drop('isbn13', inplace=True, axis=1)
books.drop('isbn10', inplace=True, axis=1)
books.isnull().sum()
title 0 authors 72 categories 99 published_year 6 average_rating 43 num_pages 43 ratings_count 43 dtype: int64
books.dropna(inplace=True)
books
title | authors | categories | published_year | average_rating | num_pages | ratings_count | |
---|---|---|---|---|---|---|---|
0 | Gilead | Marilynne Robinson | Fiction | 2004.0 | 3.85 | 247.0 | 361.0 |
1 | Spider's Web | Charles Osborne;Agatha Christie | Detective and mystery stories | 2000.0 | 3.83 | 241.0 | 5164.0 |
2 | The One Tree | Stephen R. Donaldson | American fiction | 1982.0 | 3.97 | 479.0 | 172.0 |
3 | Rage of angels | Sidney Sheldon | Fiction | 1993.0 | 3.93 | 512.0 | 29532.0 |
4 | The Four Loves | Clive Staples Lewis | Christian life | 2002.0 | 4.15 | 170.0 | 33684.0 |
... | ... | ... | ... | ... | ... | ... | ... |
6805 | I Am that | Sri Nisargadatta Maharaj;Sudhakar S. Dikshit | Philosophy | 1999.0 | 4.51 | 531.0 | 104.0 |
6806 | Secrets Of The Heart | Khalil Gibran | Mysticism | 1993.0 | 4.08 | 74.0 | 324.0 |
6807 | Fahrenheit 451 | Ray Bradbury | Book burning | 2004.0 | 3.98 | 186.0 | 5733.0 |
6808 | The Berlin Phenomenology | Georg Wilhelm Friedrich Hegel | History | 1981.0 | 0.00 | 210.0 | 0.0 |
6809 | 'I'm Telling You Stories' | Helena Grice;Tim Woods | Literary Criticism | 1998.0 | 3.70 | 136.0 | 10.0 |
6599 rows × 7 columns
books.describe(include='all')
title | authors | categories | published_year | average_rating | num_pages | ratings_count | |
---|---|---|---|---|---|---|---|
count | 6599 | 6599 | 6599 | 6599.000000 | 6599.000000 | 6599.000000 | 6.599000e+03 |
unique | 6216 | 3728 | 563 | NaN | NaN | NaN | NaN |
top | The Lord of the Rings | Agatha Christie | Fiction | NaN | NaN | NaN | NaN |
freq | 9 | 37 | 2561 | NaN | NaN | NaN | NaN |
mean | NaN | NaN | NaN | 1998.750417 | 3.931367 | 348.296863 | 2.143083e+04 |
std | NaN | NaN | NaN | 10.168465 | 0.331173 | 239.199411 | 1.392929e+05 |
min | NaN | NaN | NaN | 1876.000000 | 0.000000 | 0.000000 | 0.000000e+00 |
25% | NaN | NaN | NaN | 1997.000000 | 3.770000 | 208.000000 | 1.630000e+02 |
50% | NaN | NaN | NaN | 2002.000000 | 3.950000 | 304.000000 | 1.032000e+03 |
75% | NaN | NaN | NaN | 2005.000000 | 4.130000 | 420.000000 | 6.105500e+03 |
max | NaN | NaN | NaN | 2019.000000 | 5.000000 | 3342.000000 | 5.629932e+06 |
books["categories"].value_counts()
Fiction 2561 Juvenile Fiction 524 Biography & Autobiography 398 History 261 Literary Criticism 165 ... Child analysis 1 Illinois 1 Erinyes (Greek mythology) 1 Exorcism 1 People with social disabilities 1 Name: categories, Length: 563, dtype: int64
books["published_year"].value_counts()
2006.0 877 2005.0 681 2004.0 605 2003.0 569 2002.0 470 ... 1928.0 1 1904.0 1 1938.0 1 1936.0 1 1947.0 1 Name: published_year, Length: 91, dtype: int64
books["authors"].value_counts()
Agatha Christie 37 Stephen King 36 William Shakespeare 29 John Ronald Reuel Tolkien 25 Sandra Brown 23 .. Aeg 1 Pauline Reage 1 Tim Flannery 1 Saint Augustine (of Hippo) 1 Michael S. Reynolds 1 Name: authors, Length: 3728, dtype: int64
books["average_rating"].value_counts()
4.00 125 3.93 110 3.95 109 3.99 108 3.96 104 ... 4.64 1 4.68 1 4.72 1 2.44 1 4.78 1 Name: average_rating, Length: 200, dtype: int64
import sklearn
from sklearn.model_selection import train_test_split
books_train, books_test = sklearn.model_selection.train_test_split(books, test_size=0.2, random_state=1)
books_train, books_val = sklearn.model_selection.train_test_split(books_train, test_size=0.5, random_state=1)
books_train
title | authors | categories | published_year | average_rating | num_pages | ratings_count | |
---|---|---|---|---|---|---|---|
915 | The Autobiography of Alice B. Toklas | Gertrude Stein | Biography & Autobiography | 2001.0 | 3.59 | 272.0 | 233.0 |
4493 | Never Far from Nowhere | Andrea Levy | Blacks | 1996.0 | 3.68 | 282.0 | 601.0 |
1983 | Year's Happy Ending | Betty Neels | Fiction | 2001.0 | 3.95 | 216.0 | 128.0 |
2196 | Wrinkles in Time | George Smoot;Keay Davidson | Science | 1994.0 | 3.99 | 360.0 | 985.0 |
4011 | Dispatches | Michael Herr | History | 1991.0 | 4.23 | 260.0 | 12590.0 |
... | ... | ... | ... | ... | ... | ... | ... |
2841 | Magic Bites | Ilona Andrews | Fiction | 2007.0 | 4.07 | 260.0 | 82231.0 |
1713 | High Five | Janet Evanovich | Bail bond agents | 2000.0 | 4.18 | 336.0 | 99172.0 |
3469 | A Brief History of Time | Stephen Hawking | Science | 1998.0 | 4.16 | 212.0 | 214520.0 |
1657 | The Magus | John Fowles | Fiction | 2001.0 | 4.05 | 656.0 | 36909.0 |
3986 | The Complete Monty Python's Flying Circus | Graham Chapman;Monty Python (Comedy troupe);Te... | Humor | 1989.0 | 4.44 | 384.0 | 1191.0 |
2639 rows × 7 columns
books_train.describe(include='all')
title | authors | categories | published_year | average_rating | num_pages | ratings_count | |
---|---|---|---|---|---|---|---|
count | 2639 | 2639 | 2639 | 2639.000000 | 2639.000000 | 2639.000000 | 2.639000e+03 |
unique | 2547 | 1827 | 286 | NaN | NaN | NaN | NaN |
top | One Hundred Years of Solitude | Stephen King | Fiction | NaN | NaN | NaN | NaN |
freq | 4 | 18 | 1027 | NaN | NaN | NaN | NaN |
mean | NaN | NaN | NaN | 1999.032967 | 3.929807 | 349.534672 | 2.363199e+04 |
std | NaN | NaN | NaN | 9.865320 | 0.358919 | 244.871090 | 1.452470e+05 |
min | NaN | NaN | NaN | 1876.000000 | 0.000000 | 0.000000 | 0.000000e+00 |
25% | NaN | NaN | NaN | 1997.000000 | 3.770000 | 208.000000 | 1.745000e+02 |
50% | NaN | NaN | NaN | 2002.000000 | 3.950000 | 304.000000 | 1.066000e+03 |
75% | NaN | NaN | NaN | 2005.000000 | 4.130000 | 429.000000 | 6.084500e+03 |
max | NaN | NaN | NaN | 2019.000000 | 5.000000 | 3020.000000 | 4.367341e+06 |
books_test.describe(include='all')
title | authors | categories | published_year | average_rating | num_pages | ratings_count | |
---|---|---|---|---|---|---|---|
count | 1320 | 1320 | 1320 | 1320.000000 | 1320.000000 | 1320.000000 | 1.320000e+03 |
unique | 1303 | 1064 | 185 | NaN | NaN | NaN | NaN |
top | 20,000 Leagues Under the Sea | Stephen King | Fiction | NaN | NaN | NaN | NaN |
freq | 3 | 7 | 540 | NaN | NaN | NaN | NaN |
mean | NaN | NaN | NaN | 1998.590909 | 3.925470 | 339.346970 | 1.588767e+04 |
std | NaN | NaN | NaN | 10.119569 | 0.299805 | 219.560964 | 7.877064e+04 |
min | NaN | NaN | NaN | 1942.000000 | 2.330000 | 0.000000 | 0.000000e+00 |
25% | NaN | NaN | NaN | 1996.000000 | 3.750000 | 208.000000 | 1.510000e+02 |
50% | NaN | NaN | NaN | 2002.000000 | 3.950000 | 304.000000 | 1.068000e+03 |
75% | NaN | NaN | NaN | 2005.000000 | 4.130000 | 401.000000 | 6.360000e+03 |
max | NaN | NaN | NaN | 2017.000000 | 5.000000 | 3342.000000 | 2.115562e+06 |
books_val.describe(include='all')
title | authors | categories | published_year | average_rating | num_pages | ratings_count | |
---|---|---|---|---|---|---|---|
count | 2640 | 2640 | 2640 | 2640.000000 | 2640.000000 | 2640.000000 | 2.640000e+03 |
unique | 2562 | 1850 | 313 | NaN | NaN | NaN | NaN |
top | Three Complete Novels | Agatha Christie | Fiction | NaN | NaN | NaN | NaN |
freq | 6 | 14 | 994 | NaN | NaN | NaN | NaN |
mean | NaN | NaN | NaN | 1998.547727 | 3.935875 | 351.534470 | 2.200209e+04 |
std | NaN | NaN | NaN | 10.483752 | 0.316971 | 242.829463 | 1.558830e+05 |
min | NaN | NaN | NaN | 1901.000000 | 0.000000 | 4.000000 | 0.000000e+00 |
25% | NaN | NaN | NaN | 1996.000000 | 3.770000 | 208.000000 | 1.557500e+02 |
50% | NaN | NaN | NaN | 2002.000000 | 3.950000 | 309.500000 | 9.555000e+02 |
75% | NaN | NaN | NaN | 2005.000000 | 4.130000 | 430.250000 | 5.980750e+03 |
max | NaN | NaN | NaN | 2019.000000 | 5.000000 | 2965.000000 | 5.629932e+06 |