Data Scientist

import numpy as np, pandas as pd

def engineer_numerical(df: pd.DataFrame, col: str) -> pd.DataFrame:
    return pd.DataFrame({
        f'{col}_log':     np.log1p(df[col]),
        f'{col}_sqrt':    np.sqrt(df[col].clip(lower=0)),
        f'{col}_squared': df[col] ** 2,
        f'{col}_binned':  pd.cut(df[col], bins=5, labels=False),
    })

def engineer_time(df: pd.DataFrame, col: str) -> pd.DataFrame:
    dt = pd.to_datetime(df[col])
    return pd.DataFrame({
        f'{col}_hour':      dt.dt.hour,
        f'{col}_dayofweek': dt.dt.dayofweek,
        f'{col}_month':     dt.dt.month,
        f'{col}_is_weekend': dt.dt.dayofweek.isin([5, 6]).astype(int),
        f'{col}_hour_sin':  np.sin(2 * np.pi * dt.dt.hour / 24),
        f'{col}_hour_cos':  np.cos(2 * np.pi * dt.dt.hour / 24),
    })

from sklearn.ensemble import RandomForestClassifier

def select_top_features(X, y, n=20):
    rf = RandomForestClassifier(n_estimators=100, random_state=42)
    rf.fit(X, y)
    importance = pd.Series(rf.feature_importances_, index=X.columns)
    return importance.nlargest(n).index.tolist()

from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score

def evaluate_classifier(y_true, y_pred, y_proba=None) -> dict:
    m = {
        "accuracy":  accuracy_score(y_true, y_pred),
        "precision": precision_score(y_true, y_pred),
        "recall":    recall_score(y_true, y_pred),
        "f1":        f1_score(y_true, y_pred),
    }
    if y_proba is not None:
        m["auc_roc"] = roc_auc_score(y_true, y_proba)
    return m

from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
import numpy as np

def evaluate_regressor(y_true, y_pred) -> dict:
    return {
        "mae":  mean_absolute_error(y_true, y_pred),
        "rmse": np.sqrt(mean_squared_error(y_true, y_pred)),
        "r2":   r2_score(y_true, y_pred),
    }

from scipy import stats
import numpy as np

def required_sample_size(baseline_rate: float, mde: float, alpha: float = 0.05, power: float = 0.8) -> int:
    """Return required N per variant. mde is relative (e.g., 0.10 = 10% lift)."""
    effect = baseline_rate * mde
    z_a = stats.norm.ppf(1 - alpha / 2)
    z_b = stats.norm.ppf(power)
    p = baseline_rate
    return int(np.ceil(2 * p * (1 - p) * (z_a + z_b) ** 2 / effect ** 2))

# Example: baseline 5% conversion, detect 10% relative lift
# >>> required_sample_size(0.05, 0.10)  -> ~62,214 per variant

def analyze_ab(control: np.ndarray, treatment: np.ndarray, alpha: float = 0.05) -> dict:
    """Analyze A/B test with proportions z-test."""
    n_c, n_t = len(control), len(treatment)
    p_c, p_t = control.mean(), treatment.mean()
    p_pool = (control.sum() + treatment.sum()) / (n_c + n_t)
    se = np.sqrt(p_pool * (1 - p_pool) * (1/n_c + 1/n_t))
    z = (p_t - p_c) / se
    p_val = 2 * (1 - stats.norm.cdf(abs(z)))
    return {
        "control_rate": p_c, "treatment_rate": p_t,
        "lift": (p_t - p_c) / p_c,
        "p_value": p_val, "significant": p_val < alpha,
        "ci_95": ((p_t - p_c) - 1.96 * se, (p_t - p_c) + 1.96 * se),
    }

# Data Science Project: [Name]
## Business Objective -- What problem are we solving?
## Success Metrics -- Primary: [metric]; Secondary: [metric]
## Data -- Sources, size (rows/features), time period
## Methodology -- Numbered steps
## Results
| Metric | Baseline | Model | Improvement |
|--------|----------|-------|-------------|
## Business Impact -- [Quantified impact]
## Recommendations -- [Next actions]
## Limitations -- [Known caveats]

python scripts/experiment_tracker.py log --name "xgb_v2" --params '{"lr":0.1,"depth":6}' --metrics '{"f1":0.87,"auc":0.92}'
python scripts/experiment_tracker.py list --sort-by f1 --top 5
python scripts/experiment_tracker.py compare --ids 1 3 5 --json
python scripts/hypothesis_tester.py ttest --file data.csv --col-a group_a --col-b group_b
python scripts/hypothesis_tester.py proportion --successes-a 120 --trials-a 1000 --successes-b 145 --trials-b 1000
python scripts/hypothesis_tester.py chi-square --file contingency.csv --json
python scripts/feature_selector.py --file dataset.csv --target churn --top 10
python scripts/feature_selector.py --file dataset.csv --target revenue --method correlation --json