Tech Industry Employee Analysis

from keyneg_enterprise import KeyNeg, list_industries, __version__

print(f"Version: {__version__}")

# Initialize with tech industry taxonomies
kn = KeyNeg(industry=['tech', 'saas', 'gig'])

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

import kagglehub
import pandas as pd

# Download Glassdoor dataset
path = kagglehub.dataset_download('davidgauthier/glassdoor-job-reviews')
df = pd.read_csv(f'{path}/glassdoor_reviews.csv')

# Filter to major tech companies
tech_companies = ['google', 'amazon', 'apple', 'microsoft', 'facebook', 'netflix']
df_tech = df[df['firm'].str.lower().isin(tech_companies)]

print(f"Total reviews: {len(df)}")
print(f"Tech company reviews: {len(df_tech)}")

from collections import Counter

# Sample 500 reviews from the "cons" column
sample_df = df_tech.sample(n=500, random_state=42)
reviews = sample_df['cons'].dropna().tolist()

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

# Count negative reviews
negative = [r for r in results if r['sentiments']]
print(f"Reviews 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 Tech-Specific Keywords Detected:")
for kw, count in keyword_counts.most_common(10):
    print(f"  {kw}: {count}")