Mohamad Bader AA

AI_ASSIST.md

@@ -5,17 +5,30 @@ Document one session where you used an LLM to help with a query or a design deci
 > ⚠️ Never paste real customer data or PII into an LLM. The NYC taxi dataset used here is public, so sample rows are safe to share.
 
 ## The problem
+didnt know how to get the day of the week or the hour for verification
+## The prompt
 
-TODO: What were you trying to solve? Paste the relevant SQL or schema fragment.
+how do i get day of the week from timestamp date in postgresql 
+## The response
 
-## The prompt
+In PostgreSQL, you can easily get the day of the week from a timestamp using either EXTRACT() / DATE_PART() or TO_CHAR().The best method depends on whether you want the result as a number (e.g., 0-6 or 1-7) or as a text name (e.g., "Monday").Here is how to do both.1. Get the Day of the Week as a NumberYou can use EXTRACT(DOW FROM timestamp) or EXTRACT(ISODOW FROM timestamp). Pay close attention to how they count the days:Standard Day of Week (DOW)Range: 0 (Sunday) to 6 (Saturday).SQLSELECT EXTRACT(DOW FROM TIMESTAMP '2026-07-01'); 
+-- Returns 3 (Since July 1, 2026 is a Wednesday)
+ISO 8601 Day of Week (ISODOW)Range: 1 (Monday) to 7 (Sunday). This is highly recommended if your weeks strictly start on Monday.SQLSELECT EXTRACT(ISODOW FROM TIMESTAMP '2026-07-01'); 
+-- Returns 3 (Wednesday)
+💡 Note: You can also use DATE_PART('dow', timestamp) which achieves the exact same result as EXTRACT.2. Get the Day of the Week as text (Name)If you need the actual name of the day, use the TO_CHAR() function with the appropriate template pattern.Full Day Name (Day)SQLSELECT TO_CHAR(TIMESTAMP '2026-07-01', 'Day'); 
+-- Returns 'Wednesday ' (padded with spaces)
+
+SELECT TO_CHAR(TIMESTAMP '2026-07-01', 'FMDay'); 
+-- Returns 'Wednesday' (FM removes trailing whitespace padding)
+Abbreviated Day Name (Dy)SQLSELECT TO_CHAR(TIMESTAMP '2026-07-01', 'FMDy'); 
+-- Returns 'Wed'
+Quick Reference TableFunction / PatternResult for a WednesdayFormat TypeRange/NotesEXTRACT(DOW FROM ...)3Numeric0 (Sun) - 6 (Sat)EXTRACT(ISODOW FROM ...)3Numeric1 (Mon) - 7 (Sun)TO_CHAR(..., 'FMDay')"Wednesday"TextFull name, capitalizedTO_CHAR(..., 'fmday')"wednesday"TextFull name, lowercaseTO_CHAR(..., 'FMDy')"Wed"Text3-letter abbreviation
 
-TODO: What did you ask the AI? Include the context you provided.
 
-## The response
 
-TODO: What did it suggest? Did it work first try?
 
+it didnt work first try since i used extract first then to_char (t.pickup_datetime, 'D') which gave me only the index of the day so i switched to (t.pickup_datetime, 'Day') which showed the day name
+also did the same with the hour
 ## Reflection
 
-TODO: Did you understand *why* the suggestion worked, or did you accept it blindly?
+i did understand why and learned few more things to keep in mind considering timestamps and datetime and the use of Day/'HH12 AM'

data_dictionary.md

@@ -4,14 +4,14 @@ Document both views. State the grain in one sentence, identify the keys, and lis
 
 ## vw_fact_trips
 
-- **Grain:** TODO (one sentence, e.g. "One row per ...")
-- **Primary key:** TODO
-- **Foreign keys:** TODO
-- **Measures:** TODO (columns you would SUM or AVG)
+- **Grain:** (one row per taxi trip)
+- **Primary key:** (none)
+- **Foreign keys:** (pickup_location_id, dropoff_location_id) both linking to vw_dim_zones.location_id
+- **Measures:** (fare_amount, trip_distance, tip_amount, passenger_count)
 
 ## vw_dim_zones
 
-- **Grain:** TODO
-- **Primary key:** TODO
-- **Foreign keys:** TODO (or "none")
-- **Measures:** TODO (or "none, descriptive attributes only")
+- **Grain:** (one zone per row)
+- **Primary key:** (location_id)
+- **Foreign keys:** (none)
+- **Measures:** (none, "descriptive attributes only")

schema_setup.sql

@@ -3,24 +3,35 @@
 
 -- Dimension: one row per location_id. Treat location_id as the primary key.
 -- TODO: complete the SELECT (location_id, zone, borough).
-CREATE OR REPLACE VIEW vw_dim_zones AS
+CREATE OR REPLACE VIEW dev_bader.vw_dim_zones AS
 SELECT
-    -- TODO
-FROM nyc_taxi.raw_zones;
+    z.location_id,
+    z.zone,
+    z.borough
+FROM nyc_taxi.raw_zones z;
 
 -- Fact: one row per taxi trip.
 --   - Exclude rows where fare_amount is less than 0.
 --   - Cast pickup_datetime to TIMESTAMP.
 --   - Keep the location IDs so the view can join to vw_dim_zones.
 -- TODO: complete the SELECT and the WHERE.
-CREATE OR REPLACE VIEW vw_fact_trips AS
+CREATE OR REPLACE VIEW dev_bader.vw_fact_trips AS
 SELECT
-    -- TODO
+    vendor_id,
+    pickup_datetime::timestamp AS pickup_datetime,
+    dropoff_datetime,
+    passenger_count,
+    pickup_location_id,
+    dropoff_location_id,
+    trip_distance,
+    fare_amount,
+    tip_amount,
+    payment_type
 FROM nyc_taxi.raw_trips
--- TODO: WHERE fare_amount >= 0
-;
+WHERE fare_amount >= 0;
 
 -- Join-readiness test (run after creating the views; it must run without error
 -- and return a count close to the vw_fact_trips row count):
 -- SELECT COUNT(*) FROM vw_fact_trips f
 -- JOIN vw_dim_zones d ON f.pickup_location_id = d.location_id;
+SELECT COUNT(*) FROM dev_bader.vw_fact_trips f JOIN dev_bader.vw_dim_zones d ON f.pickup_location_id = d.location_id;

validation_queries.sql

@@ -5,16 +5,40 @@
 
 -- 1. Duplicate check: are there rows with the same vendor_id, pickup_datetime, dropoff_datetime?
 -- TODO: GROUP BY the three columns and keep only groups with HAVING COUNT(*) > 1.
+SELECT
+    t.vendor_id,
+    t.pickup_datetime,
+    t.dropoff_datetime,
+    COUNT(*) AS duplicate_count
+FROM nyc_taxi.raw_trips t
+GROUP BY t.vendor_id, t.pickup_datetime, t.dropoff_datetime
+HAVING COUNT(*) > 1
+ORDER BY duplicate_count DESC;
 
 
 -- 2. Null integrity: how many rows have a NULL pickup_location_id or dropoff_location_id?
 -- TODO: count the NULLs (COUNT(*) FILTER (WHERE ... IS NULL) is handy for several columns at once).
-
+SELECT
+    COUNT(*) AS total_rows,
+    COUNT(*) FILTER (WHERE t.pickup_location_id IS NULL)  AS null_pickup,
+    COUNT(*) FILTER (WHERE t.dropoff_location_id IS NULL) AS null_dropoff
+FROM nyc_taxi.raw_trips t;
 
 -- 3. Range validation: what are the min and max fare_amount? Are there negative values?
 -- TODO: SELECT MIN(fare_amount), MAX(fare_amount), and a count of rows where fare_amount < 0.
+SELECT
+    MIN(t.fare_amount) AS min_fare,
+    MAX(t.fare_amount) AS max_fare,
+    COUNT(*) FILTER (WHERE t.fare_amount < 0) AS negative_fares
+FROM nyc_taxi.raw_trips t;
 
 
 -- 4. Relationship check: which pickup_location_id values in nyc_taxi.raw_trips do NOT exist in nyc_taxi.raw_zones?
 -- TODO: LEFT JOIN nyc_taxi.raw_zones ... WHERE z.location_id IS NULL  (or NOT EXISTS).
 -- Do NOT use NOT IN: a single NULL in the subquery hides every orphan.
+SELECT
+    t.pickup_location_id
+FROM nyc_taxi.raw_trips t
+LEFT JOIN nyc_taxi.raw_zones z ON t.pickup_location_id = z.location_id
+WHERE z.location_id IS NULL
+ORDER BY t.pickup_location_id;

verification_results.sql

@@ -4,19 +4,75 @@
 
 -- 1. Volume: how many total rows in vw_fact_trips? How many rows per borough?
 --    What is the most common pickup/dropoff location combination?
--- TODO
+SELECT COUNT(*) AS total_rows
+FROM dev_bader.vw_fact_trips t;
+
+
+SELECT z.borough, COUNT(*) AS borough_count
+FROM dev_bader.vw_fact_trips t
+JOIN dev_bader.vw_dim_zones z ON t.pickup_location_id = z.location_id
+GROUP BY z.borough
+ORDER BY borough_count DESC;
+
+SELECT 
+    z1.zone AS pickup_zone,
+    z2.zone AS dropoff_zone,
+    COUNT(*) AS trip_count
+FROM dev_bader.vw_fact_trips t
+JOIN dev_bader.vw_dim_zones z1 ON t.pickup_location_id = z1.location_id
+JOIN dev_bader.vw_dim_zones z2 ON t.dropoff_location_id = z2.location_id
+GROUP BY z1.zone, z2.zone
+ORDER BY trip_count DESC
+LIMIT 1;
 -- (Take a screenshot of the per-borough counts and save it as assets/borough_count.png.)
 
 
 -- 2. Revenue: which pickup zone (name, not ID) generated the highest total fare_amount?
 --    Which pickup zone collected the highest total fare_amount on any single day?
--- TODO
+SELECT 
+    z.zone AS pickup_zone,
+    SUM(f.fare_amount) AS total_fare
+FROM dev_bader.vw_fact_trips t
+JOIN dev_bader.vw_dim_zones z ON t.pickup_location_id = z.location_id
+GROUP BY z.zone
+ORDER BY total_fare DESC
+LIMIT 1;
 
 
+SELECT 
+    z.zone AS pickup_zone,
+    t.pickup_datetime::date AS trip_date,
+    SUM(t.fare_amount) AS total_fare
+FROM dev_bader.vw_fact_trips t
+JOIN dev_bader.vw_dim_zones z ON t.pickup_location_id = z.location_id
+GROUP BY z.zone, t.pickup_datetime::date
+ORDER BY total_fare DESC
+LIMIT 1;
 -- 3. Geospatial: total number of trips and average trip_distance for each borough.
--- TODO
+SELECT 
+    z.borough,
+    COUNT(*) AS total_trips,
+    AVG(t.trip_distance) AS avg_trip_distance
+FROM dev_bader.vw_fact_trips t
+JOIN dev_bader.vw_dim_zones z ON t.pickup_location_id = z.location_id
+GROUP BY z.borough
+ORDER BY total_trips DESC;
 
 
 -- 4. Time patterns: which day of the week had the highest total tip_amount?
 --    What hour of the day has the highest average tip?
--- TODO
+SELECT 
+    TO_CHAR(t.pickup_datetime, 'Day') AS day_of_week,
+    SUM(t.tip_amount) AS total_tip
+FROM dev_bader.vw_fact_trips t
+GROUP BY day_of_week
+ORDER BY total_tip DESC
+LIMIT 1;
+
+SELECT 
+    TO_CHAR(t.pickup_datetime, 'HH12 AM') AS pickup_hour,
+    AVG(t.tip_amount) AS avg_tip
+FROM dev_bader.vw_fact_trips t
+GROUP BY pickup_hour
+ORDER BY avg_tip DESC
+LIMIT 1;