load good read book dataset in neo4j

load_goodread_dataset.py

import pandas as pd
from neo4j import GraphDatabase
 
# Connect to Neo4j database
uri = "bolt://localhost:7687"
username = "neo4j"
password = "password"
driver = GraphDatabase.driver(uri, auth=(username, password))
 
def create_book_nodes(tx, book_title, publisher, author_name, language, rating):
    # Create Book node and Author node if not exists, then create relationships
    tx.run("""
   MERGE (b:Book {title: $book_title, publisher: $publisher, language: $language, rating: $rating})
   MERGE (a:Author {name: $author_name})
   MERGE (a)-[:WROTE]->(b)
   """, book_title=book_title, publisher=publisher, language=language, rating=rating, author_name=author_name)
 
def load_data_to_neo4j(csv_file_path):
    # Load the Goodreads Books dataset into a pandas DataFrame
    df = pd.read_csv(csv_file_path)
    # replace NaN values with "Not Available"
    df.fillna("Not Available", inplace=True)
 
    # Start a session with Neo4j
    with driver.session() as session:
        # Iterate over each row in the dataset and load it into Neo4j
        for index, row in df.iterrows():
            # Extract book details
            book_title = row['Name']
            author_name = row['Authors']  # Assuming 'authors' column contains the author names
            publisher = row['Publisher']
            language = row['Language']
            rating = row['Rating']
            # Create nodes and relationships in Neo4j
            session.write_transaction(create_book_nodes, book_title, publisher, author_name, language, rating)
 
    print(f"Data from {csv_file_path} has been loaded into Neo4j.")
 
# Path to the Goodreads dataset CSV file
csv_file_path = "/home/deepak/Downloads/good_reads_book_data.csv"  # Replace with your actual path to the dataset
 
# Load data into Neo4j
load_data_to_neo4j(csv_file_path)
 
# Close the connection
driver.close()