DataTalksClub · Derrick-Ryan-Giggs · Feb 11, 2026 · Feb 11, 2026 · Feb 11, 2026 · Feb 11, 2026
diff --git a/04-analytics-engineering/taxi_rides_ny/.gitignore b/04-analytics-engineering/taxi_rides_ny/.gitignore
@@ -3,7 +3,7 @@
 target/
 dbt_packages/
 logs/
-profiles.yml
+profiles.yml 
 .user.yml
 
 # Data files for DuckDB
@@ -90,3 +90,4 @@ google-*.json
 .env.local
 .env.*.local
 *.env
+dbt_internal_packages/
diff --git a/04-analytics-engineering/taxi_rides_ny/models/staging/sources.yml b/04-analytics-engineering/taxi_rides_ny/models/staging/sources.yml
@@ -3,7 +3,7 @@ sources:
     description: Raw taxi trip data from NYC TLC
     database: |
       {%- if target.type == 'bigquery' -%}
-        {{ env_var('GCP_PROJECT_ID', 'please-add-your-gcp-project-id-here') }}
+        {{ env_var('GCP_PROJECT_ID', 'dtc-de-course-484520') }}
       {%- else -%}
         taxi_rides_ny
       {%- endif -%}
@@ -13,16 +13,12 @@ sources:
       {%- else -%}
         prod
       {%- endif -%}
-    freshness:
-      warn_after: {count: 24, period: hour}
-      error_after: {count: 48, period: hour}
     tables:
       - name: green_tripdata
         description: Raw green taxi trip records
-        loaded_at_field: lpep_pickup_datetime
         columns:
           - name: vendorid
-            description: "Taxi technology provider (1 = Creative Mobile Technologies, 2 = VeriFone Inc.) - Note: Raw data may contain nulls, filtered in staging"
+            description: "Taxi technology provider"
           - name: lpep_pickup_datetime
             description: Date and time when the meter was engaged
           - name: lpep_dropoff_datetime
@@ -36,36 +32,35 @@ sources:
           - name: dolocationid
             description: TLC Taxi Zone where the meter was disengaged
           - name: ratecodeid
-            description: Rate code (1=Standard, 2=JFK, 3=Newark, 4=Nassau/Westchester, 5=Negotiated, 6=Group)
+            description: Rate code
           - name: store_and_fwd_flag
             description: Trip record held in vehicle memory (Y/N)
           - name: payment_type
-            description: Payment method (1=Credit card, 2=Cash, 3=No charge, 4=Dispute, 5=Unknown, 6=Voided)
+            description: Payment method
           - name: fare_amount
             description: Time and distance fare
           - name: extra
             description: Miscellaneous extras and surcharges
           - name: mta_tax
             description: MTA tax
           - name: tip_amount
-            description: Tip amount (credit card only)
+            description: Tip amount
           - name: tolls_amount
             description: Total tolls paid
           - name: improvement_surcharge
             description: Improvement surcharge
           - name: total_amount
             description: Total amount charged
           - name: trip_type
-            description: Trip type (1=Street-hail, 2=Dispatch)
+            description: Trip type
           - name: ehail_fee
             description: E-hail fee
 
       - name: yellow_tripdata
         description: Raw yellow taxi trip records
-        loaded_at_field: tpep_pickup_datetime
         columns:
           - name: vendorid
-            description: "Taxi technology provider (1 = Creative Mobile Technologies, 2 = VeriFone Inc.) - Note: Raw data may contain nulls, filtered in staging"
+            description: "Taxi technology provider"
           - name: tpep_pickup_datetime
             description: Date and time when the meter was engaged
           - name: tpep_dropoff_datetime
@@ -79,22 +74,38 @@ sources:
           - name: dolocationid
             description: TLC Taxi Zone where the meter was disengaged
           - name: ratecodeid
-            description: Rate code (1=Standard, 2=JFK, 3=Newark, 4=Nassau/Westchester, 5=Negotiated, 6=Group)
+            description: Rate code
           - name: store_and_fwd_flag
             description: Trip record held in vehicle memory (Y/N)
           - name: payment_type
-            description: Payment method (1=Credit card, 2=Cash, 3=No charge, 4=Dispute, 5=Unknown, 6=Voided)
+            description: Payment method
           - name: fare_amount
             description: Time and distance fare
           - name: extra
             description: Miscellaneous extras and surcharges
           - name: mta_tax
             description: MTA tax
           - name: tip_amount
-            description: Tip amount (credit card only)
+            description: Tip amount
           - name: tolls_amount
             description: Total tolls paid
           - name: improvement_surcharge
             description: Improvement surcharge
           - name: total_amount
             description: Total amount charged
+
+      - name: fhv_tripdata
+        description: Raw FHV trip records 2019
+        columns:
+          - name: dispatching_base_num
+            description: TLC Base License Number
+          - name: pickup_datetime
+            description: Date and time of pickup
+          - name: dropOff_datetime
+            description: Date and time of dropoff
+          - name: PUlocationID
+            description: TLC Taxi Zone where trip started
+          - name: DOlocationID
+            description: TLC Taxi Zone where trip ended
+          - name: SR_Flag
+            description: Shared ride flag
diff --git a/04-analytics-engineering/taxi_rides_ny/models/staging/stg_fhv_tripdata.sql b/04-analytics-engineering/taxi_rides_ny/models/staging/stg_fhv_tripdata.sql
@@ -0,0 +1,19 @@
+with source as (
+    select * from {{ source('raw', 'fhv_tripdata') }}
+),
+
+renamed as (
+    select
+  
802E
      dispatching_base_num,
+        cast(pickup_datetime as timestamp) as pickup_datetime,
+        cast(dropOff_datetime as timestamp) as dropoff_datetime,
+        cast(PUlocationID as integer) as pickup_location_id,
+        cast(DOlocationID as integer) as dropoff_location_id,
+        SR_Flag as sr_flag
+    from source
+    where dispatching_base_num is not null
+      and pickup_datetime >= '2019-01-01'
+      and pickup_datetime < '2020-01-01'
+)
+
+select * from renamed
diff --git a/04-analytics-engineering/taxi_rides_ny/models/staging/stg_green_tripdata.sql b/04-analytics-engineering/taxi_rides_ny/models/staging/stg_green_tripdata.sql
@@ -36,8 +36,11 @@ renamed as (
 )
 
 select * from renamed
+-- Filter to 2019-2020 data only (homework requirement)
+where pickup_datetime >= '2019-01-01' 
+  and pickup_datetime < '2021-01-01'
 
--- Sample records for dev environment using deterministic date filter
+-- Additional dev sampling
 {% if target.name == 'dev' %}
-where pickup_datetime >= '2019-01-01' and pickup_datetime < '2019-02-01'
-{% endif %}
+  and pickup_datetime < '2019-02-01'
+{% endif %}
diff --git a/04-analytics-engineering/taxi_rides_ny/models/staging/stg_yellow_tripdata.sql b/04-analytics-engineering/taxi_rides_ny/models/staging/stg_yellow_tripdata.sql
@@ -35,8 +35,11 @@ renamed as (
 )
 
 select * from renamed
+-- Filter to 2019-2020 data only (homework requirement)
+where pickup_datetime >= '2019-01-01' 
+  and pickup_datetime < '2021-01-01'
 
--- Sample records for dev environment using deterministic date filter
+-- Additional dev sampling
 {% if target.name == 'dev' %}
-where pickup_datetime >= '2019-01-01' and pickup_datetime < '2019-02-01'
-{% endif %}
+  and pickup_datetime < '2019-02-01'
+{% endif %}
diff --git a/04-analytics-engineering/taxi_rides_ny/package-lock.yml b/04-analytics-engineering/taxi_rides_ny/package-lock.yml
@@ -1,8 +1,8 @@
 packages:
-  - name: dbt_utils
-    package: dbt-labs/dbt_utils
-    version: 1.3.3
-  - name: codegen
-    package: dbt-labs/codegen
-    version: 0.14.0
-sha1_hash: 01f31e0d658d76121f50e62b998342ebf138df11
+- package: dbt-labs/codegen
+  name: codegen
+  version: 0.14.0
+- package: dbt-labs/dbt_utils
+  name: dbt_utils
+  version: 1.3.3
+sha1_hash: 41a9a95a7d1e8d4dff67de764f3b1b8e9094807c