Generate Batch Prediction file for Auto ML

generate_test_jsonl.py

import json
from google.cloud import storage

BUCKET='apt-task-314904-us'
DELIMITER='/'
TEST_PREFIX='test1/test1/'

TEST_BASE_PATH = f'gs://{BUCKET}/{TEST_PREFIX}'


print("Starting the import file generation process")
print("Process Details")
print(f"BUCKET : {BUCKET}")

storage_client = storage.Client()

print("Fetchig list of Test objects")
test_blobs = storage_client.list_blobs(BUCKET, prefix=TEST_PREFIX, delimiter=DELIMITER)

test_file = open("test.jsonl", "w")

for blob in test_blobs:  
    full_path = f"gs://{BUCKET}/{blob.name}"
    mime_type = "image/jpeg"

    data = {
        'content': full_path,
        'mimeType': mime_type
    }

    jsonLine = json.dumps(data)
    test_file.write(jsonLine + "\n")
    
test_file.close()