Created
July 12, 2021 17:31
-
-
Save achad4/ac1f06eb4838ae86411542841a631b8f to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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[ | |
(cert_ramp_seasonality_df.month_num == dt.month) ] | |
.fillna(0) | |
.iloc[0]["total_new_certs_per_carrier"] | |
.astype(int) | |
) | |
#NEW SALES EXPECTATIONS DRIVEN BY BUSINESS STAKEHOLDERS | |
running_new_launched_units += new_units_per_month | |
ramp_perc = ( | |
cert_ramp_seasonality_df[ | |
(cert_ramp_seasonality_df.month_num == dt.month) | |
] | |
.fillna(0) | |
.iloc[0]["avg_new_cert_perc"] | |
) | |
cohort_size += int(ramp_perc * running_new_launched_units) | |
#ONCE WE KNOW HOW MANY LEASES WE EXPECT LET'S SAMPLE FROM THE HISTORICAL DATA AND SIMULATE THEIR LIFECYCLES | |
cohort = ( | |
lease_df | |
.sample(cohort_size, replace=True) | |
.reset_index() | |
) | |
cohort.move_in_date = dt | |
surv_samples = trained_survival_curve_for_propert.sample(cohort_size) | |
surv_samples["offsets"] = surv_samples.months_into_term.apply( | |
lambda x: pd.offsets.DateOffset(months=x) | |
) | |
cohort.move_out_date = ( | |
cohort.move_in_date + surv_samples["offsets"] | |
) | |
#THIS DATAFRAME WILL BECOME OUR "SYNTHETIC LEASE" DIMENSION | |
synth_certs = pd.concat([synth_certs] + [cohort]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment