achad4

now = datetime.now()
start = now.replace(day=1, hour=0, minute=0, second=0, microsecond=0)
start = start + timedelta(days=31)
stop = start + timedelta(days=30 * 36)

synth_certs = pd.DataFrame()
for dt in rrule.rrule(rrule.MONTHLY, dtstart=start, until=stop):
#THE SEASONALITY CURVE IS MEASURED (in SQL) DIRECTLY FROM OUR DATA
cohort_size = (
cert_ramp_seasonality_df[

achad4

now = datetime.now()
start = now.replace(day=1, hour=0, minute=0, second=0, microsecond=0)
start = start + timedelta(days=31)
stop = start + timedelta(days=30 * 36)

synth_certs = pd.DataFrame()
for dt in rrule.rrule(rrule.MONTHLY, dtstart=start, until=stop):
#THE SEASONALITY CURVE IS MEASURED (in SQL) DIRECTLY FROM OUR DATA
cohort_size = (
cert_ramp_seasonality_df[

achad4

now = datetime.now()
start = now.replace(day=1, hour=0, minute=0, second=0, microsecond=0)
start = start + timedelta(days=31)
stop = start + timedelta(days=30 * 36)

synth_certs = pd.DataFrame()
for dt in rrule.rrule(rrule.MONTHLY, dtstart=start, until=stop):
#THE SEASONALITY CURVE IS MEASURED (in SQL) DIRECTLY FROM OUR DATA
cohort_size = (
cert_ramp_seasonality_df[

achad4

SELECT
  lease_dim_id,
  reporting_month AS simulated_default_month
FROM
(
  -- 
  SELECT
      *,
      ROW_NUMBER() OVER(PARTITION BY certificate_dim_id ORDER BY (RANDOM() * COALESCE(perc_losses_expected+in_month,0)) DESC) AS rnk
  FROM ll_fact_lease_ts ts

achad4

now = datetime.now()
start = now.replace(day=1, hour=0, minute=0, second=0, microsecond=0)
start = start + timedelta(days=31)
stop = start + timedelta(days=30 * 36)
 
synth_certs = pd.DataFrame()
for dt in rrule.rrule(rrule.MONTHLY, dtstart=start, until=stop):
   #THE SEASONALITY CURVE IS MEASURED (in SQL) DIRECTLY FROM OUR DATA
   cohort_size = (
       cert_ramp_seasonality_df[

achad4

WITH month_0 AS
         (
             SELECT user_id,
                    metric_a
             FROM analytics_table
             WHERE execution_date = < month_0 >
         ),
     month_1 AS
         (
             SELECT user_id,

achad4

WITH transaction AS (
    SELECT transaction_id,
           customer_id,
           state,
           amount_spent_usd
    FROM FACT_TABLE_TRANSACTION
),
     customer_spend AS (
         SELECT customer_id,
                state,

achad4

WITH transaction AS (
    SELECT transaction_id,
           customer_id,
           state,
           amount_spent_usd
    FROM < FACT_TABLE_TRANSACTION >
),
     customer_spend AS (
         SELECT customer_id,
                state,

achad4

from airflow.models import Variable
from airflow import DAG
from airflow.operators.python_operator import PythonOperator


def train_model(lookback_days=30: int):
    """
    Trains a model using data from the past <lookback_days> and persists to a model store
    """
    ...

achad4

from airflow.models import Variable
from airflow import DAG
from airflow.operators.python_operator import PythonOperator



MODEL_ENTRY_POINT = "customer_model.py"

# This dynamic configuration mechanism is not ideal but makes for an easy demo
model_version = Variable.get("model_version")