recommendation loading data

load_data.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

from pyspark.sql import SparkSession
spark = SparkSession.builder.appName('rec').getOrCreate()

books_rating_path = "book_recommendation/book_recommendation/BX-Book-Ratings.csv"
books_path = "book_recommendation/book_recommendation/BX-Books.csv"
books_user_path = "book_recommendation/book_recommendation/BX-Users.csv"

books = spark.read.format("csv") \
    .option("inferSchema","true") \
    .option("header","true") \
    .option("mode","DROPMALFORMED") \
    .option("delimiter", ";") \
    .load(books_path)

users = spark.read.format("csv") \
    .option("inferSchema","true") \
    .option("header","true") \
    .option("mode","DROPMALFORMED") \
    .option("delimiter", ";") \
    .load(books_user_path)

ratings = spark.read.format("csv") \
    .option("inferSchema","true") \
    .option("header","true") \
    .option("mode","DROPMALFORMED") \
    .option("delimiter", ";") \
    .load(books_rating_path)