Last active
February 13, 2024 23:57
-
-
Save pgao/fa115eaf211aafe114909064ac79aa31 to your computer and use it in GitHub Desktop.
a script to upload the yelp reviews dataset (https://huggingface.co/datasets/yelp_review_full) to tidepool
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
import datetime | |
import pandas as pd | |
import os | |
import requests | |
from requests.adapters import HTTPAdapter | |
from requests.packages.urllib3.util.retry import Retry | |
from time import sleep | |
from uuid import uuid4 | |
################################# | |
# Set up URLs + request headers # | |
################################# | |
requests_with_retry = requests.Session() | |
requests_with_retry.mount("https://", HTTPAdapter(max_retries=Retry(total=3, backoff_factor=1, raise_on_status=False, status_forcelist=[500, 502, 503, 504]))) | |
DATA_FILEPATH = 'train-00000-of-00001.parquet' | |
# submission and validation endpoints - reference https://docs.tidepool.so/reference/ | |
API_BASE = 'https://shoreline.tidepool.so/api/v1/events' | |
# API keys are project specific - reference https://docs.tidepool.so/docs/manage-api-keys | |
headers = { | |
"X-Tidepool-Api-Key": os.environ.get('TIDEPOOL_API_KEY'), | |
"Content-Type": "application/json", | |
} | |
############################################ | |
# Load in data, batch it up, and format it # | |
############################################ | |
# A little utility to batch data, since the API takes up to 100 events per batch | |
def make_batches(all_entries, n=100): | |
return [all_entries[i : i + n] for i in range(0, len(all_entries), n)] | |
df = pd.read_parquet(DATA_FILEPATH) | |
formatted_events = [] | |
for i in range(df.shape[0]): | |
# Set all required fields from the entry | |
event = {} | |
event['text'] = df['text'][i] | |
# fake iso timestamp | |
event['timestamp'] = datetime.datetime.now().isoformat() | |
event['properties'] = { | |
'label': int(df['label'][i]) | |
} | |
# fake out required fields | |
event['id'] = str(uuid4()) | |
event['session_id'] = str(uuid4()) | |
event['user_id'] = str(uuid4()) | |
event['event_name'] = 'USER_MESSAGE' | |
formatted_events.append(event) | |
batched_events = make_batches(formatted_events) | |
###################### | |
# Make the requests! # | |
###################### | |
# Validate a single batch of data before going through the rest. | |
validate_resp = requests.post(f'{API_BASE}/validate', json=batched_events[0], headers=headers) | |
# validate_resp.raise_for_status() | |
try: | |
validate_resp.raise_for_status() | |
except requests.exceptions.HTTPError as e: | |
print(e.args[0]) | |
except requests.exceptions.RequestException as e: | |
cause = e.args[0] | |
print(str(cause.args[0])) | |
# Submit all the batches! | |
for i, batch in enumerate(batched_events): | |
track_response = requests_with_retry.post(f'{API_BASE}/track', json=batch, headers=headers) | |
if not track_response.ok: | |
print(track_response.text) | |
track_response.raise_for_status() | |
print(f"Submitted batch {i + 1} of {len(batched_events)}") | |
sleep(0.5) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment