Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix: improve recovery/uncontamination rate #67

Merged
merged 4 commits into from
Nov 5, 2024
Merged

fix: improve recovery/uncontamination rate #67

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
2db6f5d
fix: improve recovery/uncontamination rate
jacobdadams Nov 4, 2024
d4b3954
chore: replace infs with nans
jacobdadams Nov 5, 2024
51f4674
chore: delete commented line
jacobdadams Nov 5, 2024
07fa5f0
chore: rename paper
jacobdadams Nov 5, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 18 additions & 19 deletions src/wmrc/summarize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
Calender_Year__c to create dataframes of the reports that will be used to update the AGOL feature services.
"""

import numpy as np
import pandas as pd

try:
Expand Down Expand Up @@ -198,8 +199,9 @@ def recovery_rates_by_tonnage(records: helpers.SalesForceRecords) -> pd.Series:
"""Calculates a yearly recovery rate based on the Salesforce records.

Recovery rate is opposite of contaminated rate (5% contamination = 95% uncontaminated). Rate is
calculated by using the contamination rate to determine contaminated tonnage and comparing that to the total
tonnage handled by facilities reporting a contamination rate.
calculated by calculating the total in-state MSW recycled per facility and the total received, which comes from
dividing that amount by the recovery rate per facility, and then dividing the sums of those two values across all
facilities.

Args:
records (helpers.SalesForceRecords): Helper object containing the Salesforce records
Expand All @@ -208,34 +210,31 @@ def recovery_rates_by_tonnage(records: helpers.SalesForceRecords) -> pd.Series:
pd.Series: recovery rates per year with index name data_year and series name
"annual_recycling_uncontaminated_rate"
"""
#: First, create a modifier to account for material from out-of-state
#: Create our various modifiers
records.df["in_state_modifier"] = (100 - records.df["Out_of_State__c"]) / 100
records.df["msw_modifier"] = records.df["Municipal_Solid_Waste__c"] / 100
records.df["recovery_rate"] = (100 - records.df["Annual_Recycling_Contamination_Rate__c"]) / 100

#: Calculate contaminated tonnage
records.df["recycling_tons_contaminated"] = (
records.df["Annual_Recycling_Contamination_Rate__c"]
/ 100
* records.df["Combined_Total_of_Material_Recycled__c"]
#: Amount of material recycled
records.df["in_state_msw_recycled"] = (
records.df["Combined_Total_of_Material_Recycled__c"]
* records.df["in_state_modifier"]
* records.df["msw_modifier"]
)

#: Calculate total tonnage from facilities reporting a contamination rate
records.df["recycling_tons_report_contamination_total"] = pd.NA
records.df.loc[~records.df["recycling_tons_contaminated"].isnull(), "recycling_tons_report_contamination_total"] = (
records.df["Combined_Total_of_Material_Recycled__c"] * records.df["in_state_modifier"]
#: Amount of material received derived from recovery rate
records.df["in_state_msw_received_for_recycling"] = (
records.df["in_state_msw_recycled"] / records.df["recovery_rate"]
)

#: Invert to get uncontaminated rate
#: Uncontaminated rates by year
clean_rates = records.df.groupby("Calendar_Year__c").apply(
lambda year_df: (
1
- (
year_df["recycling_tons_contaminated"].sum()
/ year_df["recycling_tons_report_contamination_total"].sum()
)
year_df["in_state_msw_recycled"].sum() / year_df["in_state_msw_received_for_recycling"].sum() * 100
)
* 100
)

clean_rates.replace([np.inf, -np.inf], np.nan, inplace=True) #: Can arise from division by np.nan
clean_rates.name = "annual_recycling_uncontaminated_rate"
clean_rates.index.name = "data_year"
clean_rates.index = clean_rates.index.map(helpers.convert_to_int)
Expand Down
44 changes: 35 additions & 9 deletions tests/test_summarize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,17 +82,43 @@ def test_recovery_rates_by_tonnage_happy_path(self, mocker):
{
"Calendar_Year__c": [2022, 2022, 2023, 2023],
"Out_of_State__c": [0, 0, 0, 0],
"Annual_Recycling_Contamination_Rate__c": [10, 0, 10, 20],
"Combined_Total_of_Material_Recycled__c": [100, 100, 100, 100],
"Municipal_Solid_Waste__c": [100, 100, 100, 100],
"Annual_Recycling_Contamination_Rate__c": [50, 0, 50, 50],
"Combined_Total_of_Material_Recycled__c": [50, 100, 50, 40],
}
)

output_series = summarize.recovery_rates_by_tonnage(records)

test_df = pd.Series(
{
2022: 95.0,
2023: 85.0,
2022: 75.0,
2023: 50.0,
},
name="annual_recycling_uncontaminated_rate",
)
test_df.index.name = "data_year"

pd.testing.assert_series_equal(output_series, test_df)

def test_recovery_rates_by_tonnage_replaces_inf_with_zero(self, mocker):
records = mocker.Mock()
records.df = pd.DataFrame(
{
"Calendar_Year__c": [2022, 2022, 2023, 2023],
"Out_of_State__c": [0, 0, 0, 0],
"Municipal_Solid_Waste__c": [100, 100, 100, 100],
"Annual_Recycling_Contamination_Rate__c": [np.nan, np.nan, 50, 50],
"Combined_Total_of_Material_Recycled__c": [50, 100, 50, 40],
}
)

output_series = summarize.recovery_rates_by_tonnage(records)

test_df = pd.Series(
{
2022: np.nan,
2023: 50.0,
},
name="annual_recycling_uncontaminated_rate",
)
Expand All @@ -104,20 +130,20 @@ def test_recovery_rates_by_tonnage_uses_out_of_state_modifier(self, mocker):
records = mocker.Mock()
records.df = pd.DataFrame(
{
"facility_name": ["foo", "bar", "foo", "bar"],
"Calendar_Year__c": [2022, 2022, 2023, 2023],
"Out_of_State__c": [0, 100, 0, 100],
"Annual_Recycling_Contamination_Rate__c": [10, 0, 10, 20],
"Combined_Total_of_Material_Recycled__c": [100, 100, 100, 100],
"Municipal_Solid_Waste__c": [100, 100, 100, 100],
"Annual_Recycling_Contamination_Rate__c": [50, 0, 50, 50],
"Combined_Total_of_Material_Recycled__c": [50, 100, 50, 40],
}
)

output_series = summarize.recovery_rates_by_tonnage(records)

test_df = pd.Series(
{
2022: 90.0,
2023: 90.0,
2022: 50.0,
2023: 50.0,
},
name="annual_recycling_uncontaminated_rate",
)
Expand Down