importing mysql data getting errors.

[fiercetartan]

I am getting this errors when trying to import text from a mysql file. The errors I am getting range from

sample error:

Traceback (most recent call last): File "C:\PycharmProjects\fakevrealnews\outputtestwithseperatelines2.py", line 62, in self.body_model = os.path.join(*self.body_model) NameError: name 'os' is not defined

with open(self.body_model, "r", encoding="utf-8") as f:
OSError: [Errno 22] Invalid argument: 'JPMorgan Chase & Co., is building up its Canadian

The code below reflects the latest code attempt which is outlined below:

Here is the code:

import spacy
import json
import mysql.connector
from getpass import getpass
from mysql.connector import connect, Error
import os


class SpacyOperations:
    def __init__(self, body_model, country_file, category_model, segment_model):
        self.body_model = body_model
        self.country_file = country_file
        self.category_model = category_model
        self.segment_model = segment_model
        self.nlp_category = spacy.load(category_model) #
        self.nlp_segment = spacy.load(segment_model)
        self.nlp_country = spacy.load(country_file)

    def calculate_max_category(self):
        # Load the text from a file
        with open(self.body_model, "r", encoding="utf-8") as f:
            text = f.read()

        # Split the text into lines
        #lines = text.split("\n")

        # Process each line with Spacy
        results = []
        for line in lines:
            doc_category = self.nlp_category(line)
            doc_segment = self.nlp_segment(line)
            doc_country = self.nlp_country(line)

            # Get the category with the highest value
            max_category = max(doc_category.cats, key=doc_category.cats.get)
            max_segment = max(doc_segment.cats, key=doc_segment.cats.get)
            max_country = max(doc_country.cats, key=doc_country.cats.get)

            # Create a dictionary with all the elements and their values
            result = {
                "category": max_category,
                "country": max_country,
                "segment": max_segment,
                "body": line
            }

            results.append(result)

        return results
try:
    db_conn = mysql.connector.connect(
      user = 'my fake name',
      password = 'tricky',
      host = '127.0.0.1',
      port=3306,
      database = 'newz'
    )

    connector = db_conn.cursor()
    mysql = "SELECT story FROM tnewz WHERE author = 'Christine Dobby'"
    connector.execute(mysql)
    body_model = connector.fetchall()[0]
    body_model = ''.join(body_model)


    # Extract the first element of each tuple
    # body_model = result()
except Error as e:
    print("Error while connecting to MySQL", e)


country_file = "C:/PycharmProjects/fakevrealnews/countryid/textcat_model/model-best"
category_model = "C:/PycharmProjects/fakevrealnews/textcat_model/model-best"
segment_model = "C:/PycharmProjects/fakevrealnews/re_gov_ins/textcat_model/model-best"


spacy_operations = SpacyOperations(body_model, country_file, category_model, segment_model)
results = spacy_operations.calculate_max_category()

# Save the results to a JSON file
with open('d45669.json', 'w', encoding="utf-8") as f:
    json.dump(results, f, ensure_ascii=False, indent=4)


    # close the cursor and database connection
    connector.close()
    db_conn.close()

[fiercetartan]

it seems that the community are stumped on this issue too. Perhaps I will just save it as a .json file?