Jovian
Sign In
Learn practical skills, build real-world projects, and advance your career
import pandas as pd
import numpy as np
from scipy.sparse import csr_matrix
import sklearn
from sklearn.decomposition import TruncatedSVD

book = pd.read_csv('BX-Books.csv', sep=';', error_bad_lines=False, encoding="latin-1")
book.columns = ['ISBN', 'bookTitle', 'bookAuthor', 'yearOfPublication', 'publisher', 'imageUrlS', 'imageUrlM', 'imageUrlL']
user = pd.read_csv('BX-Users.csv', sep=';', error_bad_lines=False, encoding="latin-1")
user.columns = ['userID', 'Location', 'Age']
rating = pd.read_csv('BX-Book-Ratings.csv', sep=';', error_bad_lines=False, encoding="latin-1")
rating.columns = ['userID', 'ISBN', 'bookRating']
b'Skipping line 6452: expected 8 fields, saw 9\nSkipping line 43667: expected 8 fields, saw 10\nSkipping line 51751: expected 8 fields, saw 9\n' b'Skipping line 92038: expected 8 fields, saw 9\nSkipping line 104319: expected 8 fields, saw 9\nSkipping line 121768: expected 8 fields, saw 9\n' b'Skipping line 144058: expected 8 fields, saw 9\nSkipping line 150789: expected 8 fields, saw 9\nSkipping line 157128: expected 8 fields, saw 9\nSkipping line 180189: expected 8 fields, saw 9\nSkipping line 185738: expected 8 fields, saw 9\n' b'Skipping line 209388: expected 8 fields, saw 9\nSkipping line 220626: expected 8 fields, saw 9\nSkipping line 227933: expected 8 fields, saw 11\nSkipping line 228957: expected 8 fields, saw 10\nSkipping line 245933: expected 8 fields, saw 9\nSkipping line 251296: expected 8 fields, saw 9\nSkipping line 259941: expected 8 fields, saw 9\nSkipping line 261529: expected 8 fields, saw 9\n' C:\Users\Susan\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py:2717: DtypeWarning: Columns (3) have mixed types. Specify dtype option on import or set low_memory=False. interactivity=interactivity, compiler=compiler, result=result) 
rating.head()
user.head()
book.head()
combine_book_rating = pd.merge(rating, book, on='ISBN')
columns = ['yearOfPublication', 'publisher', 'bookAuthor', 'imageUrlS', 'imageUrlM', 'imageUrlL']
combine_book_rating = combine_book_rating.drop(columns, axis=1)
combine_book_rating.head()