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

Fix deprecated Pandas syntax (up to v2.2.2) #164

Merged
merged 5 commits into from
Jun 4, 2024
Merged

Fix deprecated Pandas syntax (up to v2.2.2) #164

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
f8ccdfb
use string representations of the function names.
tompollard Jun 4, 2024
beef5d8
unique with argument that is not not a Series, Index, ExtensionArray,…
tompollard Jun 4, 2024
f7ebfaa
Fix Chained Assignment Error.
tompollard Jun 4, 2024
4f049e4
Use iloc to index by position.
tompollard Jun 4, 2024
5c28200
Add note on future deprecation of incompatible dtypes.
tompollard Jun 4, 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
8 changes: 4 additions & 4 deletions tableone/tableone.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -889,8 +889,8 @@ def _create_cont_describe(self,
df_cont : pandas DataFrame
Summarise the continuous variables.
"""
aggfuncs = [pd.Series.count, np.mean, np.median, self._std,
self._q25, self._q75, min, max, self._t1_summary]
aggfuncs = ['count', 'mean', 'median', self._std,
self._q25, self._q75, 'min', 'max', self._t1_summary]

if self._dip_test:
aggfuncs.append(self._hartigan_dip)
Expand Down Expand Up @@ -1173,7 +1173,7 @@ def _create_smd_table(self, data: pd.DataFrame) -> pd.DataFrame:
n1=self.cont_describe['count'][p[0]].loc[v],
n2=self.cont_describe['count'][p[1]].loc[v],
unbiased=False)
df[colname.format(p[0], p[1])].loc[v] = smd
df.loc[v, colname.format(p[0], p[1])] = smd
except AttributeError:
pass

Expand All @@ -1187,7 +1187,7 @@ def _create_smd_table(self, data: pd.DataFrame) -> pd.DataFrame:
n1=self.cat_describe.loc[[v]]['freq'][p[0]].sum(),
n2=self.cat_describe.loc[[v]]['freq'][p[1]].sum(),
unbiased=False)
df[colname.format(p[0], p[1])].loc[v] = smd # type: ignore
df.loc[v, colname.format(p[0], p[1])] = smd # type: ignore
except AttributeError:
pass

Expand Down
12 changes: 8 additions & 4 deletions tests/unit/test_tableone.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,7 +119,11 @@ def data_mixed(n=20):

mu, sigma = 50, 5
data_mixed['mixed numeric data'] = np.random.normal(mu, sigma, n)

# FutureWarning: Setting an item of incompatible dtype is deprecated
# and will raise an error in a future version of pandas.
data_mixed.loc[1, 'mixed numeric data'] = 'could not measure'

return data_mixed


Expand Down Expand Up @@ -483,15 +487,15 @@ def test_tableone_row_sort_pn(self, data_pn):

# a call to .index.levels[0] automatically sorts the levels
# instead, call values and use pd.unique as it preserves order
tableone_rows = pd.unique([x[0] for x in table.tableone.index.values])
tableone_rows = pd.Series([x[0] for x in table.tableone.index.values]).unique()

# default should not sort
for i, c in enumerate(columns):
# i+1 because we skip the first row, 'n'
assert tableone_rows[i+1] == c

table = TableOne(df, columns=columns, sort=True, label_suffix=False)
tableone_rows = pd.unique([x[0] for x in table.tableone.index.values])
tableone_rows = pd.Series([x[0] for x in table.tableone.index.values]).unique()
for i, c in enumerate(sorted(columns, key=lambda s: s.lower())):
# i+1 because we skip the first row, 'n'
assert tableone_rows[i+1] == c
Expand Down Expand Up @@ -967,7 +971,7 @@ def test_compute_standardized_mean_difference_continuous(self, data_pn):
'LOS': '0.121'}

for k in exp_smd:
smd = t.tableone.loc[k, 'Grouped by MechVent']['SMD (0,1)'][0]
smd = t.tableone.loc[k, 'Grouped by MechVent']['SMD (0,1)'].iloc[0]
assert smd == exp_smd[k]

def test_compute_standardized_mean_difference_categorical(self, data_pn):
Expand Down Expand Up @@ -995,7 +999,7 @@ def test_compute_standardized_mean_difference_categorical(self, data_pn):
'death': '0.017'}

for k in exp_smd:
smd = t.tableone.loc[k, 'Grouped by MechVent']['SMD (0,1)'][0]
smd = t.tableone.loc[k, 'Grouped by MechVent']['SMD (0,1)'].iloc[0]
assert smd == exp_smd[k]

def test_order_of_order_categorical_columns(self):
Expand Down
Loading