Backend

#description : Build a book recommendation system 
#import the libraries
import numpy as np
import pandas as pd
from sklearn.metrics.pairwise import cosine_similarity
from sklearn.feature_extraction.text import CountVectorizer
#Load the data
from google.colab import files
files.upload()
#store the data
df= pd.read_csv('books1.csv', encoding='unicode_escape' , error_bad_lines=False)
#show the data
df
#create a list of columns to keep
columns=['Title','Author','Interest']
#create a function to combine the important columns/features
def combine_features(data):
  features=[]
  for i in range(0,data.shape[0]):
    features.append(data['Title'][i]+' '+data['Authors'][i]+' '+data['Interest'][i])
  return features
#create a column to store the combined features
df['combined_features']=combine_features(df)
#show the data
df
#convert the text from the new column to a matrix of word counts
cm=CountVectorizer().fit_transform(df['combined_features'])
#get the cosine similarity matrix from the count matrix
cs=cosine_similarity(cm)
#print the scores

#get the title of the book the reader likes
Title=df['Title'][1]
#show the title
Title
#find the book id of the book that user likes
Book_Id=df[df.Title==Title]['Book_Id'].values[0]
#show the book_Id
Book_Id
#create a list of tuples in the form(book_id, similarity scores)
scores=list(enumerate(cs[Book_Id]))

#sort the list of similar books in descending order
sorted_scores=sorted(scores,key=lambda x:x[1],reverse=True)
sorted_scores=sorted_scores[1:]
#show the sorted scores
sorted_scores
#create a loop to print the first 5 books from the sorted list
j=0
print('The 5 most recommended books are: \n')
for item in sorted_scores:
  Book_Title=df[df.Book_Id==item[0]] ['Title']
  print(j+1,Book_Title)
  j=j+1
  if j>=5:
    break