Remove now obsolete tmd/utils/cloud.py module

README.md

@@ -16,7 +16,7 @@ CSV-formatted files from IRS/SOI: `puf_2015.csv` and
 To generate the TMD files from the PUF files, do this:
 
 1. Copy the two 2015 PUF files to the `tmd/storage/input` folder
-2. Run `make data`
+2. Run `make data` in the repository's top-level folder
 
 The `make data` command creates and tests the three `tmd*csv*` data
 files, which are located in the `tmd/storage/output` folder.

tmd/datasets/cps.py

@@ -276,8 +276,11 @@ class CPS(Dataset):
     data_format = Dataset.ARRAYS
 
     def generate(self):
-        """Generates the Current Population Survey dataset for PolicyEngine US microsimulations.
-        Technical documentation and codebook here: https://www2.census.gov/programs-surveys/cps/techdocs/cpsmar21.pdf
+        """
+        Generates a Current Population Survey dataset for PolicyEngine-US
+          microsimulations.
+        Technical documentation and codebook at this URL:
+          https://www2.census.gov/programs-surveys/cps/techdocs/cpsmar21.pdf
         """
 
         raw_data = self.raw_cps(require=True).load()

tmd/datasets/puf.py

@@ -275,7 +275,7 @@ class PUF(Dataset):
     data_format = Dataset.ARRAYS
 
     def generate(self, puf: pd.DataFrame, demographics: pd.DataFrame):
-        print("Importing PolicyEngine US variable metadata...")
+        print("Importing PolicyEngine-US variable metadata...")
 
         itmded_dump = False
         if itmded_dump:

tmd/datasets/taxcalc_dataset.py

@@ -1,5 +1,5 @@
 # Create a Tax-Calculator-compatible dataset from
-# any PolicyEngine hierarchical dataset.
+# any PolicyEngine-US hierarchical dataset.
 
 from typing import Type
 import yaml

tmd/datasets/tmd.py

@@ -26,7 +26,7 @@ def create_tmd_2021():
     nonfiler = ~(sim.calculate("tax_unit_is_filer", period=2022).values > 0)
     tc_cps_21 = tc_cps_21[nonfiler]
 
-    print("Combining PUF and CPS nonfilers...")
+    print("Combining PUF filers and CPS nonfilers...")
     combined = pd.concat([tc_puf_21, tc_cps_21], ignore_index=True)
 
     # ensure RECID values are unique

tmd/utils/trace.py

@@ -16,7 +16,7 @@ def trace1(loc: str, vdf: pd.DataFrame) -> None:
     Returns:
         None
     """
-    tracing = True
+    tracing = False
     if not tracing:
         return
     filer = vdf.data_source == 1