Industry-Specific Financial Analysis

from keyneg_enterprise import KeyNeg, list_industries, __version__

# Check available industries
print(f"Version: {__version__}")
print(f"Available industries: {len(list_industries())}")

# Initialize with multiple financial industry taxonomies
kn = KeyNeg(industry=['finance', 'regulatory', 'esg'])

print(f"Keywords loaded: {len(kn.all_keywords)}")

import kagglehub
import pandas as pd
from collections import Counter

# Load the same dataset
path = kagglehub.dataset_download('yousefsaeedian/financial-q-and-a-10k')
df = pd.read_csv(f'{path}/Financial-QA-10k.csv')

# Sample same 500 contexts
sample_df = df.sample(n=500, random_state=42)
contexts = sample_df['context'].tolist()

# Analyze with Enterprise
results = kn.analyze_batch(contexts)

# Count negative contexts
negative = [r for r in results if r['sentiments']]
print(f"Contexts with negative sentiment: {len(negative)}/500")

# Aggregate keywords (Enterprise-specific!)
all_keywords = []
for r in results:
    if r['keywords']:
        all_keywords.extend([k[0] for k in r['keywords']])

keyword_counts = Counter(all_keywords)
print("\\nTop Finance-Specific Keywords Detected:")
for kw, count in keyword_counts.most_common(10):
    print(f"  {kw}: {count}")

# Analyze Goldman Sachs context
gs_context = """Our businesses may be adversely affected by conditions
in global financial markets. Capital adequacy requirements and
regulatory capital rules may limit our ability to return capital
to shareholders through dividends and share repurchases."""

result = kn.analyze(gs_context)

print("Sentiments:", [s[0] for s in result['sentiments']])
print("Keywords:", [k[0] for k in result['keywords'][:5]])
print("Categories:", result['categories'])