# using pandas cut method to convert fields into discrete intervals
books_metadata_selected['num_pages'].replace(np.nan, -1, inplace=True)
books_metadata_selected['num_pages'] = pd.to_numeric(books_metadata_selected['num_pages'])
books_metadata_selected['num_pages'] = pd.cut(books_metadata_selected['num_pages'], bins=25)
# rounding ratings to neares .5 score
books_metadata_selected['average_rating'] = books_metadata_selected['average_rating'].apply(lambda x: round(x*2)/2)
# using pandas qcut method to convert fields into quantile-based discrete intervals
books_metadata_selected['ratings_count'] = pd.qcut(books_metadata_selected['ratings_count'], 25)
# replacing missing values to year 2100
books_metadata_selected['publication_year'].replace(np.nan, 2100, inplace=True)
# replacing missing values to 'unknown'
books_metadata_selected['language_code'].replace(np.nan, 'unknown', inplace=True)
# convert is_ebook column into 1/0 where true=1 and false=0
books_metadata_selected['is_ebook'] = books_metadata_selected.is_ebook.map(
    lambda x: 1.0*(x == 'true'))
profile = pandas_profiling.ProfileReport(books_metadata_selected[['average_rating', 'is_ebook', 'num_pages', 
                                                        'publication_year', 'ratings_count']])
profile.to_file('./results/profiler_books_metadata_2.html')