Scribd
Upload
9 views

source code book recommender system

minor report source code

Uploaded by

bhanu chopra
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
9 views

source code book recommender system

minor report source code

Uploaded by

bhanu chopra
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

import pandas as pd

import numpy as np
from collections import Counter
import ast
from google.colab import data_table
from google.colab import drive

data_table.enable_dataframe_formatter()

drive.mount("/content/drive", force_remount=True)

b = ’/content/drive/My Drive/csvfiles/genredata.csv’
books = pd.read_csv(b)

books.head(1)

books.info()

books.shape

books.columns

books.drop(’Unnamed: 0’,axis=1,inplace=True)

books.isna().sum()

books.isnull().sum()

no_desc = "Description not available"


books.fillna(no_desc,inplace=True)

books.duplicated().sum()

books.Num_Ratings.dtype

books[’Num_Ratings’] = books[’Num_Ratings’].str.replace(’,’,’’).astype(int)

Selecting and filtering books

popular_books = popular_books.sort_values(’Avg_Rating’,ascending=False).head(100)

popular_books = popular_books.drop_duplicates(’Book’)[[’Book’,’Author’,’Description’,’Avg_Rating’,’Num_
Ratings’,’URL’]]

popular_books = popular_books.head(50)

popular_books

Genre-Based Book Recommendation

def recommend():
books = pd.read_csv(b)
user_input = input("\nEnter genres (comma-separated): ")
user_genres = [genre.strip().capitalize() for genre in user_input.split(’,’)]

books[’Num_Ratings’] = books[’Num_Ratings’].str.replace(’,’, ’’).astype(int)

filtered_books = books[books[’Genres’].apply(lambda x: all(genre in x for genre in user_genres))]

top_num_ratings = filtered_books[filtered_books[’Num_Ratings’] >= 900000]

top_100 = top_num_ratings.sort_values(’Avg_Rating’, ascending=False).head(100)

top_no_duplicates = top_100.drop_duplicates(’Book’)[[’Book’, ’Author’, ’Description’, ’Avg_Rating’, ’Nu


m_Ratings’, ’URL’]]

top_no_duplicates = top_no_duplicates.head(5)

top_output = top_no_duplicates[[’Book’, ’Author’, ’Description’, ’URL’]]

display(top_output)

recommend()

You might also like