Hard Data Analytics Interview Questions

SELECT DISTINCT customer_id FROM orders WHERE month = 'Jan' EXCEPT SELECT customer_id FROM orders WHERE month = 'Feb';

-- create an inactive relationship Sales[ShipDate] -> 'Date'[Date] in the model Sales by Ship Date = CALCULATE( [Total Sales], USERELATIONSHIP(Sales[ShipDate], 'Date'[Date]) ) -- the measure uses the inactive relationship only inside this CALCULATE -- the alternative is a second role-playing date table

import pandas as pd import statsmodels.formula.api as smf df = pd.read_csv('marketing.csv') model = smf.ols('sales ~ ad_spend', data=df).fit() print(model.summary()) # coefficients, p-values, R-squared # predicted sales for a spend of 50,000 print(model.predict(pd.DataFrame({'ad_spend': [50000]})))

WITH ranked AS ( SELECT category, product, SUM(amount) AS revenue, DENSE_RANK() OVER ( PARTITION BY category ORDER BY SUM(amount) DESC ) AS rnk FROM sales GROUP BY category, product ) SELECT category, product, revenue FROM ranked WHERE rnk <= 3 ORDER BY category, rnk;

WITH d AS ( SELECT DISTINCT user_id, CAST(login_time AS DATE) AS dt FROM logins ), g AS ( SELECT user_id, dt, dt - CAST(ROW_NUMBER() OVER (PARTITION BY user_id ORDER BY dt) AS INT) AS grp FROM d ) SELECT DISTINCT user_id FROM g GROUP BY user_id, grp HAVING COUNT(*) >= 3; -- gaps and islands: consecutive dates share the same grp value

WITH active AS ( SELECT DISTINCT customer_id, DATE_TRUNC('month', order_date) AS month FROM orders ) SELECT a.month, COUNT(*) AS active_customers, COUNT(*) - COUNT(n.customer_id) AS churned_next_month, ROUND(100.0 * (COUNT(*) - COUNT(n.customer_id)) / COUNT(*), 1) AS churn_pct FROM active a LEFT JOIN active n ON n.customer_id = a.customer_id AND n.month = a.month + INTERVAL '1 month' GROUP BY a.month ORDER BY a.month;

-- dim_customer has valid_from, valid_to (NULL for current row) SELECT o.order_id, o.order_date, c.customer_id, c.city FROM fact_orders o JOIN dim_customer c ON c.customer_id = o.customer_id AND o.order_date >= c.valid_from AND o.order_date < COALESCE(c.valid_to, DATE '9999-12-31');

MERGE INTO dim_product t USING stg_product s ON t.product_id = s.product_id WHEN MATCHED AND (t.name <> s.name OR t.category <> s.category) THEN UPDATE SET name = s.name, category = s.category, updated_at = CURRENT_TIMESTAMP WHEN NOT MATCHED THEN INSERT (product_id, name, category, updated_at) VALUES (s.product_id, s.name, s.category, CURRENT_TIMESTAMP);

New Customers = VAR PeriodStart = MIN ( 'Date'[Date] ) VAR CurrentCustomers = VALUES ( Sales[CustomerID] ) VAR PastCustomers = CALCULATETABLE ( VALUES ( Sales[CustomerID] ), 'Date'[Date] < PeriodStart, REMOVEFILTERS ( 'Date' ) ) RETURN COUNTROWS ( EXCEPT ( CurrentCustomers, PastCustomers ) )

import pandas as pd # df columns: store_type ('pilot' or 'control'), period ('pre' or 'post'), sales avg = df.pivot_table(index='store_type', columns='period', values='sales', aggfunc='mean') pilot_change = avg.loc['pilot', 'post'] - avg.loc['pilot', 'pre'] control_change = avg.loc['control', 'post'] - avg.loc['control', 'pre'] did = pilot_change - control_change print(f'Estimated pilot effect per store: {did:.1f}')

import numpy as np rng = np.random.default_rng(42) control = df.loc[df.variant == 'A', 'revenue'].to_numpy() treat = df.loc[df.variant == 'B', 'revenue'].to_numpy() diffs = [] for _ in range(5000): c = rng.choice(control, size=len(control), replace=True) t = rng.choice(treat, size=len(treat), replace=True) diffs.append(t.mean() - c.mean()) low, high = np.percentile(diffs, [2.5, 97.5]) print(f'95% CI for difference: {low:.2f} to {high:.2f}')

WITH dau AS ( SELECT CAST(event_ts AS DATE) AS day, COUNT(DISTINCT user_id) AS dau FROM events GROUP BY CAST(event_ts AS DATE) ) SELECT d.day, d.dau, (SELECT COUNT(DISTINCT e.user_id) FROM events e WHERE CAST(e.event_ts AS DATE) BETWEEN d.day - INTERVAL '29 days' AND d.day) AS mau, ROUND(100.0 * d.dau / (SELECT COUNT(DISTINCT e.user_id) FROM events e WHERE CAST(e.event_ts AS DATE) BETWEEN d.day - INTERVAL '29 days' AND d.day), 1) AS stickiness_pct FROM dau d ORDER BY d.day;

WITH ordered AS ( SELECT user_id, event_ts, LAG(event_ts) OVER (PARTITION BY user_id ORDER BY event_ts) AS prev_ts FROM page_events ), flagged AS ( SELECT *, CASE WHEN prev_ts IS NULL OR event_ts - prev_ts > INTERVAL '30 minutes' THEN 1 ELSE 0 END AS new_session FROM ordered ) SELECT user_id, event_ts, SUM(new_session) OVER (PARTITION BY user_id ORDER BY event_ts) AS session_no FROM flagged;