Mahsa branch

models/core/fct_lab_times.sql

@@ -0,0 +1,13 @@
+with lap_times as (
+    select 
+        {{ dbt_utils.generate_surrogate_key(['race_id', 'driver_id', 'lap']) }} as lap_times_id,
+        race_id                                                                 as race_id,
+        driver_id                                                               as driver_id,
+        lap                                                                     as lap,
+        driver_position                                                         as driver_position,
+        lap_time_formatted                                                      as lap_time_formatted,
+        official_laptime                                                        as official_laptime,
+        lap_time_milliseconds                                                   as lap_time_milliseconds
+    from {{ ref('stg_lap_times') }}
+)
+select * from lap_times

models/marts/aggregates/agg_lap_times_moving_avg_2.py

@@ -0,0 +1,17 @@
+import pandas as pd
+
+def model(dbt, session):
+    # dbt configuration
+    dbt.config(packages=["pandas"])
+
+    # get upstream data
+    lap_times = dbt.ref("mrt_lap_times_years").to_pandas()
+
+    # describe the data
+    lap_times["LAP_TIME_SECONDS"] = lap_times["LAP_TIME_MILLISECONDS"]/1000
+    lap_time_trends = lap_times.groupby(by="RACE_YEAR")["LAP_TIME_SECONDS"].mean().to_frame()
+    lap_time_trends.reset_index(inplace=True)
+    lap_time_trends["LAP_MOVING_AVG_5_YEARS"] = lap_time_trends["LAP_TIME_SECONDS"].rolling(5).mean()
+    lap_time_trends.columns = lap_time_trends.columns.str.upper()
+
+    return lap_time_trends.round(1)

models/marts/mrt_lab_times_years.sql

@@ -0,0 +1,19 @@
+with lap_times as (
+select * from {{ ref('fct_lap_times') }}
+    ),
+    races as (
+    select * from {{ ref('dim_races') }}
+    ),
+    expanded_lap_times_by_year as (
+        select 
+            lap_times.race_id, 
+            driver_id, 
+            race_year,
+            lap,
+            lap_time_milliseconds 
+        from lap_times
+        left join races
+            on lap_times.race_id = races.race_id
+        where lap_time_milliseconds is not null 
+    )
+    select * from expanded_lap_times_by_year

models/ml/prep_encoding_splitting/covariate_encoding.py

@@ -5,7 +5,7 @@
 
 def model(dbt, session):
   # dbt configuration
-  dbt.config(packages=["pandas","numpy","scikit-learn"])
+  dbt.config(packages=["pandas==1.5.3","numpy","scikit-learn"])
 
   # get upstream data
   data = dbt.ref("ml_data_prep").to_pandas()

models/ml/prep_encoding_splitting/ml_data_prep.py

@@ -2,7 +2,7 @@
 
 def model(dbt, session):
     # dbt configuration
-    dbt.config(packages=["pandas"])
+    dbt.config(packages=["pandas==1.5.3"])
 
     # get upstream data
     fct_results = dbt.ref("mrt_results_circuits").to_pandas()