Spaces:
Sleeping
Sleeping
File size: 1,639 Bytes
dbaa71b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
from obsei.analyzer.classification_analyzer import (
ClassificationAnalyzerConfig,
ZeroShotClassificationAnalyzer,
)
from obsei.source.google_news_source import GoogleNewsConfig, GoogleNewsSource
# Only fetch title and highlight
source_config_without_full_text = GoogleNewsConfig(
query="ai",
max_results=150,
after_date='2023-12-01',
before_date='2023-12-31',
)
# Fetch full news article
source_config_with_full_text = GoogleNewsConfig(
query="ai",
max_results=5,
fetch_article=True,
lookup_period="1d",
# proxy="http://127.0.0.1:8080"
)
source = GoogleNewsSource()
analyzer_config = ClassificationAnalyzerConfig(
labels=["buy", "sell", "going up", "going down"],
)
text_analyzer = ZeroShotClassificationAnalyzer(
model_name_or_path="typeform/mobilebert-uncased-mnli", device="auto"
)
news_articles_without_full_text = source.lookup(source_config_without_full_text)
news_articles_with_full_text = source.lookup(source_config_with_full_text)
analyzer_responses_without_full_text = text_analyzer.analyze_input(
source_response_list=news_articles_without_full_text,
analyzer_config=analyzer_config,
)
analyzer_responses_with_full_text = text_analyzer.analyze_input(
source_response_list=news_articles_with_full_text, analyzer_config=analyzer_config
)
for article in news_articles_without_full_text:
print(article.__dict__)
for response in analyzer_responses_without_full_text:
print(response.__dict__)
for article in news_articles_with_full_text:
print(article.__dict__)
for response in analyzer_responses_with_full_text:
print(response.__dict__)
|