import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report

def build_turnover_model(employee_data: pd.DataFrame) -> dict:
    """
    Build and evaluate a turnover prediction model.

    Input: DataFrame with columns for features + 'left_company' (0/1).
    Output: dict with model, feature importance, and evaluation metrics.
    """
    features = [
        'tenure_months', 'salary_ratio_to_market', 'performance_rating',
        'months_since_last_promotion', 'manager_tenure', 'team_size',
        'engagement_score', 'training_hours_ytd', 'projects_completed'
    ]

    X = employee_data[features]
    y = employee_data['left_company']

    X_train, X_test, y_train, y_test = train_test_split(
        X, y, test_size=0.2, random_state=42, stratify=y
    )

    model = RandomForestClassifier(n_estimators=100, random_state=42)
    model.fit(X_train, y_train)

    y_pred = model.predict(X_test)
    report = classification_report(y_test, y_pred, output_dict=True)

    importance = (
        pd.DataFrame({'feature': features, 'importance': model.feature_importances_})
        .sort_values('importance', ascending=False)
    )

    return {'model': model, 'importance': importance, 'evaluation': report}


def score_flight_risk(model, current_employees: pd.DataFrame) -> pd.DataFrame:
    """
    Score current employees for flight risk.

    Returns DataFrame with employee_id, flight_risk_score (0-1), and risk_level.
    """
    probabilities = model.predict_proba(current_employees[model.feature_names_in_])[:, 1]

    risk_levels = pd.cut(
        probabilities,
        bins=[0, 0.25, 0.50, 0.75, 1.0],
        labels=['Low', 'Medium', 'High', 'Critical']
    )

    return pd.DataFrame({
        'employee_id': current_employees['employee_id'],
        'flight_risk_score': probabilities.round(3),
        'risk_level': risk_levels
    }).sort_values('flight_risk_score', ascending=False)

QUESTION
  Sales voluntary turnover is 22% vs 12% company average. Why?

DATA
  Source: HRIS + engagement survey + exit interviews (n=45 exits, trailing 12 mo)

ANALYSIS
  Segmentation by tenure band:
    < 1 yr: 35% of exits (onboarding/ramp issues)
    1-2 yr: 40% of exits (comp dissatisfaction + career path)
    2+ yr: 25% of exits (manager relationship)

  Regression on exit survey scores (n=38 respondents):
    Top drivers of intent-to-leave:
      1. "I am paid fairly" (beta = -0.42, p < 0.01)
      2. "I see a career path here" (beta = -0.31, p < 0.01)
      3. "My manager supports my development" (beta = -0.28, p < 0.05)

  Compensation benchmark:
    Sales IC3 compa-ratio: 0.88 (12% below midpoint)
    Sales IC2 compa-ratio: 0.91 (9% below midpoint)
    Rest of company average: 0.98

FINDINGS
  1. Sales comp is significantly below market, especially at IC2-IC3
  2. No defined career ladder for Sales ICs beyond IC3
  3. New hires (< 1 yr) leaving due to unrealistic ramp expectations

RECOMMENDATIONS
  1. Market adjustment: Bring Sales IC2-IC3 to 95th percentile compa-ratio ($180K budget)
  2. Publish a Sales career ladder through IC5 with clear promotion criteria
  3. Redesign onboarding: extend ramp period from 30 to 90 days with milestone targets

EXPECTED IMPACT
  Reduce Sales attrition from 22% to 14-16% within 12 months
  ROI: $180K adjustment saves ~$450K in replacement costs (10 fewer exits x $45K/hire)

import pandas as pd
import statsmodels.api as sm

def analyze_pay_equity(employee_data: pd.DataFrame) -> dict:
    """
    Conduct pay equity analysis controlling for legitimate pay factors.

    Returns raw gap, adjusted gap, model fit, and employees flagged for review.
    """
    # Raw gap
    avg_by_gender = employee_data.groupby('gender')['salary'].mean()
    raw_gap = (avg_by_gender['Female'] - avg_by_gender['Male']) / avg_by_gender['Male']

    # Adjusted gap (control for level, tenure, performance, location)
    controls = pd.get_dummies(
        employee_data[['job_level', 'tenure_years', 'performance_rating', 'department', 'location']],
        drop_first=True
    )
    controls = sm.add_constant(controls)
    controls['is_female'] = (employee_data['gender'] == 'Female').astype(int)

    model = sm.OLS(employee_data['salary'], controls).fit()
    adjusted_gap = model.params['is_female']

    # Flag outliers (residual > 2 std dev)
    employee_data['predicted'] = model.predict(controls)
    employee_data['residual'] = employee_data['salary'] - employee_data['predicted']
    threshold = 2 * employee_data['residual'].std()
    flagged = employee_data[abs(employee_data['residual']) > threshold]

    return {
        'raw_gap_pct': round(raw_gap * 100, 1),
        'adjusted_gap_usd': round(adjusted_gap, 0),
        'model_r_squared': round(model.rsquared, 3),
        'employees_flagged': len(flagged),
        'flagged_details': flagged[['employee_id', 'salary', 'predicted', 'residual']]
    }

# Analyze engagement survey results with driver analysis
python scripts/survey_analyzer.py --file survey_results.csv
python scripts/survey_analyzer.py --file survey_results.csv --prior prior_survey.csv --json

# Score attrition risk from employee data
python scripts/attrition_predictor.py --file employees.csv
python scripts/attrition_predictor.py --file employees.csv --threshold 0.7 --json

# Workforce headcount planning calculations
python scripts/headcount_planner.py --file workforce.csv --growth 0.15 --attrition 0.12
python scripts/headcount_planner.py --file workforce.csv --growth 0.15 --attrition 0.12 --json