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 stat_dataframe function nested in create_distribution_table utility function #1834

Merged
merged 2 commits into from
Jan 18, 2018
Merged

Fix stat_dataframe function nested in create_distribution_table utility function #1834

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3b1d9c7
Fix stat_dataframe nested function
martinholmer Jan 17, 2018
36c1537
Add checks of dist/diff-table column order
martinholmer Jan 18, 2018
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
22 changes: 14 additions & 8 deletions taxcalc/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -310,14 +310,16 @@ def stat_dataframe(gpdf):
Nested function that returns statistics DataFrame derived from the
specified grouped Dataframe object, gpdf.
"""
sdf = pd.DataFrame()
unweighted_columns = set(['s006', 'num_returns_StandardDed',
'num_returns_ItemDed', 'num_returns_AMT'])
for col in unweighted_columns:
sdf[col] = gpdf.apply(unweighted_sum, col)
weighted_columns = set(DIST_TABLE_COLUMNS) - unweighted_columns
for col in weighted_columns:
sdf[col] = gpdf.apply(weighted_sum, col)
unweighted_columns = ['s006', 'num_returns_StandardDed',
'num_returns_ItemDed', 'num_returns_AMT']
stats = list()
for col in DIST_TABLE_COLUMNS:
if col in unweighted_columns:
stats.append(gpdf.apply(unweighted_sum, col))
else:
stats.append(gpdf.apply(weighted_sum, col))
sdf = pd.DataFrame(data=np.column_stack(stats),
columns=DIST_TABLE_COLUMNS)
return sdf

# main logic of create_distribution_table
Expand Down Expand Up @@ -369,6 +371,8 @@ def stat_dataframe(gpdf):
dist_table[col] /= dist_table['s006']
# set print display format for float table elements
pd.options.display.float_format = '{:8,.0f}'.format
# ensure dist_table columns are in correct order
assert dist_table.columns.values.tolist() == DIST_TABLE_COLUMNS
return dist_table


Expand Down Expand Up @@ -536,6 +540,8 @@ def weighted_share_of_total(gpdf, colname, total):
diffs[col] *= 100.0
# set print display format for float table elements
pd.options.display.float_format = '{:10,.2f}'.format
# ensure diffs columns are in correct order
assert diffs.columns.values.tolist() == DIFF_TABLE_COLUMNS
return diffs


Expand Down