Data Analyst

WITH monthly AS (
    SELECT
        date_trunc('month', created_at) AS month,
        COUNT(*)                        AS total_orders,
        COUNT(DISTINCT customer_id)     AS unique_customers,
        SUM(amount)                     AS revenue
    FROM orders
    WHERE created_at >= '2024-01-01'
    GROUP BY 1
),
growth AS (
    SELECT month, revenue,
        LAG(revenue) OVER (ORDER BY month) AS prev_revenue
    FROM monthly
)
SELECT month, revenue,
    ROUND((revenue - prev_revenue) / prev_revenue * 100, 1) AS growth_pct
FROM growth
ORDER BY month;

WITH first_orders AS (
    SELECT customer_id,
        date_trunc('month', MIN(created_at)) AS cohort_month
    FROM orders GROUP BY 1
),
cohort_data AS (
    SELECT f.cohort_month,
        date_trunc('month', o.created_at) AS order_month,
        COUNT(DISTINCT o.customer_id)     AS customers
    FROM orders o
    JOIN first_orders f ON o.customer_id = f.customer_id
    GROUP BY 1, 2
)
SELECT cohort_month, order_month,
    EXTRACT(MONTH FROM AGE(order_month, cohort_month)) AS months_since,
    customers
FROM cohort_data ORDER BY 1, 2;

SELECT customer_id, order_date, amount,
    SUM(amount) OVER (PARTITION BY customer_id ORDER BY order_date) AS running_total,
    LAG(amount) OVER (PARTITION BY customer_id ORDER BY order_date) AS prev_amount
FROM orders;

+------------------------------------------------------------+
| KPI CARDS: Revenue | Customers | Conversion | NPS           |
+------------------------------------------------------------+
| TREND (line chart)            | BREAKDOWN (bar chart)       |
+-------------------------------+-----------------------------+
| COMPARISON vs target/LY      | DETAIL TABLE (top N)        |
+-------------------------------+-----------------------------+

from scipy import stats
import numpy as np

def compare_groups(a: np.ndarray, b: np.ndarray, alpha: float = 0.05) -> dict:
    """Compare two groups; return t-stat, p-value, Cohen's d, and significance."""
    stat, p = stats.ttest_ind(a, b)
    d = (a.mean() - b.mean()) / np.sqrt((a.std()**2 + b.std()**2) / 2)
    return {"t_statistic": stat, "p_value": p, "cohens_d": d, "significant": p < alpha}

def test_independence(table, alpha=0.05):
    chi2, p, dof, _ = stats.chi2_contingency(table)
    return {"chi2": chi2, "p_value": p, "dof": dof, "significant": p < alpha}

## [Headline: action-oriented finding]

**What:** One-sentence description of the observation.
**So What:** Why this matters to the business (revenue, retention, cost).
**Now What:** Recommended action with expected impact.
**Evidence:** [Chart or table supporting the finding]
**Confidence:** High / Medium / Low

# Analysis: [Topic]
## Business Question -- What are we trying to answer?
## Hypothesis -- What do we expect to find?
## Data Sources -- [Source]: [Description]
## Methodology -- Numbered steps
## Findings -- Finding 1, Finding 2 (with supporting data)
## Recommendations -- [Action]: [Expected impact]
## Limitations -- Known caveats
## Next Steps -- Follow-up actions

python scripts/query_optimizer.py --file query.sql
python scripts/query_optimizer.py --sql "SELECT * FROM orders" --json
python scripts/data_profiler.py --file sales.csv
python scripts/data_profiler.py --file data.json --top 10 --json
python scripts/report_generator.py --file sales.csv --title "Monthly Sales Report"
python scripts/report_generator.py --file data.csv --group-by region --format markdown --json