Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
3 changes: 2 additions & 1 deletion Makefile
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,8 @@ puf-files: data/cps-matched-puf.csv \

data/cps-matched-puf.csv: taxdata/puf/finalprep.py \
taxdata/puf/impute_itmexp.py \
taxdata/puf/impute_pencon.py
taxdata/puf/impute_pencon.py\
createpuf.py
python createpuf.py
# Above recipe also makes data/puf.csv

Expand Down
332 changes: 0 additions & 332 deletions Manifest.toml

This file was deleted.

4 changes: 0 additions & 4 deletions Project.toml

This file was deleted.

3 changes: 2 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,8 @@ To run the scripts that produce `puf.csv` and `cps.csv.gz`, activate the

`Julia` must also be installed to solve for the PUF and CPS weights. You
can download `Julia` from their [website](https://julialang.org/downloads/)
or by using `homebrew`.
or by using `homebrew`. After installing Julia, you will need to also install
these three packages: `JuMP, Cbc, NPZ`.

Data-Preparation Documentation and Workflow
-------------------------------------------
Expand Down
8 changes: 1 addition & 7 deletions createpuf.py
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,6 @@ def dataprep(data):
print("Prepping PUF")
puf2011 = pd.read_csv(Path(DATA_PATH, "puf2011.csv"))
raw_puf = puf.preppuf(puf2011, PUF_YEAR)
# raw_puf.to_csv(Path(DATA_PATH, "raw_puf.csv"), index=False)

# rename CPS file to match PUF
print("Prepping CPS")
Expand All @@ -118,12 +117,6 @@ def dataprep(data):
raw_cps["e19800"] = raw_cps["charitable"] * cash
raw_cps["e20100"] = raw_cps["charitable"] * non_cash

# cap number of dependents in CPS to line up with PUF
# raw_cps["depne"] = np.where(
# raw_cps["mars"] == 2,
# np.minimum(5, raw_cps["depne"]),
# np.minimum(3, raw_cps["depne"]),
# )
raw_cps = dataprep(raw_cps)
raw_puf = dataprep(raw_puf)
raw_cps["recid"] = range(1, len(raw_cps.index) + 1)
Expand Down Expand Up @@ -166,6 +159,7 @@ def dataprep(data):
data.drop(list(data.filter(regex=".*_cps")), axis=1, inplace=True)
# add back non-filers
print("Adding non-filers")
nonfilers.rename(columns={"s006": "matched_weight"}, inplace=True)
data = pd.concat([data, nonfilers], sort=False, ignore_index=True)
data = data.fillna(0.0)
data.reset_index(inplace=True)
Expand Down
Binary file modified puf_stage2/puf_weights.csv.gz
Binary file not shown.
Loading