completed SQL queries

AI_ASSIST.md

@@ -8,14 +8,22 @@ Document one session where you used an LLM to help with a query or a design deci
 
 TODO: What were you trying to solve? Paste the relevant SQL or schema fragment.
 
+CREATE OR REPLACE VIEW vw_dim_zones AS
+SELECT
+    location_id,
+    zone
+    borough
+FROM nyc_taxi.raw_zones;
 ## The prompt
 
 TODO: What did you ask the AI? Include the context you provided.
-
+why this query was giving me a syntax error in PostgreSQL?
 ## The response
 
 TODO: What did it suggest? Did it work first try?
 
+AI pointed out that i forgot a comma after zone .
 ## Reflection
 
 TODO: Did you understand *why* the suggestion worked, or did you accept it blindly?
+I understood why the error happened and i added comma .

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 represents one taxi trip.
+- **Primary key:** There is no primary key . 
+- **Foreign keys:** pickup_location_id and dropoff_location_id and both link to vw_dim_zones.location_id
+- **Measures:** fare_amount , trip_distance , tip_amount ,total_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 row represents one taxi zone
+- **Primary key:** location_id
+- **Foreign keys:** None
+- **Measures:** None. descriptive attributes only .

schema_setup.sql

@@ -5,7 +5,9 @@
 -- TODO: complete the SELECT (location_id, zone, borough).
 CREATE OR REPLACE VIEW vw_dim_zones AS
 SELECT
-    -- TODO
+    location_id,
+    zone,
+    borough
 FROM nyc_taxi.raw_zones;
 
 -- Fact: one row per taxi trip.
@@ -15,12 +17,25 @@ FROM nyc_taxi.raw_zones;
 -- TODO: complete the SELECT and the WHERE.
 CREATE OR REPLACE VIEW vw_fact_trips AS
 SELECT
-    -- TODO
+    vendor_id,
+    pickup_datetime::TIMESTAMP AS pickup_datetime,
+    dropoff_datetime,
+    pickup_location_id,
+    dropoff_location_id,
+    passenger_count,
+    trip_distance,
+    fare_amount,
+    tip_amount,
+    total_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 vw_fact_trips f
+JOIN 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
+    vendor_id,
+    pickup_datetime,
+    dropoff_datetime,
+    COUNT(*) AS duplicate_count
+FROM nyc_taxi.raw_trips
+GROUP BY
+    vendor_id,
+    pickup_datetime,
+    dropoff_datetime
+HAVING COUNT(*) > 1;
 
 -- 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(*) FILTER (WHERE pickup_location_id IS NULL) AS null_pickup_location_id,
+    COUNT(*) FILTER (WHERE dropoff_location_id IS NULL) AS null_dropoff_location_id
+FROM nyc_taxi.raw_trips;
 
 -- 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(fare_amount) AS minimum_fare,
+    MAX(fare_amount) AS maximum_fare,
+    COUNT(*) FILTER (WHERE fare_amount < 0) AS negative_fare_count
+FROM nyc_taxi.raw_trips;
 
 -- 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 DISTINCT
+    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

@@ -5,18 +5,89 @@
 -- 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_trips
+FROM vw_fact_trips;
+SELECT
+    d.borough,
+    COUNT(*) AS trip_count
+FROM vw_fact_trips f
+JOIN vw_dim_zones d
+    ON f.pickup_location_id = d.location_id
+GROUP BY d.borough
+ORDER BY trip_count DESC;
+SELECT
+    pickup_location_id,
+    dropoff_location_id,
+    COUNT(*) AS trip_count
+FROM vw_fact_trips
+GROUP BY
+    pickup_location_id,
+    dropoff_location_id
+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
+    d.zone,
+    SUM(f.fare_amount) AS total_revenue
+FROM vw_fact_trips f
+JOIN vw_dim_zones d
+    ON f.pickup_location_id = d.location_id
+GROUP BY d.zone
+ORDER BY total_revenue DESC
+LIMIT 1;
+SELECT
+    d.zone,
+    DATE(f.pickup_datetime) AS trip_date,
+    SUM(f.fare_amount) AS total_revenue
+FROM vw_fact_trips f
+JOIN vw_dim_zones d
+    ON f.pickup_location_id = d.location_id
+GROUP BY
+    d.zone,
+    DATE(f.pickup_datetime)
+ORDER BY total_revenue DESC
+LIMIT 1;
 
 
 -- 3. Geospatial: total number of trips and average trip_distance for each borough.
 -- TODO
+SELECT
+    d.borough,
+    COUNT(*) AS total_trips,
+    AVG(f.trip_distance) AS average_trip_distance
+FROM vw_fact_trips f
+JOIN vw_dim_zones d
+    ON f.pickup_location_id = d.location_id
+GROUP BY d.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(pickup_datetime, 'Day') AS day_of_week,
+    SUM(tip_amount) AS total_tips
+FROM vw_fact_trips
+GROUP BY day_of_week
+ORDER BY total_tips DESC
+LIMIT 1;
+
+SELECT
+    EXTRACT(HOUR FROM pickup_datetime) AS hour_of_day,
+    AVG(tip_amount) AS average_tip
+FROM vw_fact_trips
+GROUP BY hour_of_day
+ORDER BY average_tip DESC
+LIMIT 1;
+
+SELECT *
+FROM vw_fact_trips
+LIMIT 1;
+