Skip to content

fix: pandas 2.x compatibility — rename, inplace, axis deprecations #150

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

Open
haoyu-haoyu wants to merge 1 commit into
base: master
Choose a base branch
from
Open

fix: pandas 2.x compatibility — rename, inplace, axis deprecations #150

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 mimic3benchmark/preprocessing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,7 +98,7 @@ def make_phenotype_label_matrix(phenotypes, stays=None):
phenotypes = phenotypes.pivot(index='ICUSTAY_ID', columns='HCUP_CCS_2015', values='VALUE')
if stays is not None:
phenotypes = phenotypes.reindex(stays.ICUSTAY_ID.sort_values())
return phenotypes.fillna(0).astype(int).sort_index(axis=0).sort_index(axis=1)
return phenotypes.fillna(0).astype(int).sort_index().sort_index(axis=1)


###################################
Expand All @@ -113,7 +113,7 @@ def read_itemid_to_variable_map(fn, variable_column='LEVEL2'):
var_map = var_map[(var_map.STATUS == 'ready')]
var_map.ITEMID = var_map.ITEMID.astype(int)
var_map = var_map[[variable_column, 'ITEMID', 'MIMIC LABEL']].set_index('ITEMID')
return var_map.rename({variable_column: 'VARIABLE', 'MIMIC LABEL': 'MIMIC_LABEL'}, axis=1)
return var_map.rename(columns={variable_column: 'VARIABLE', 'MIMIC LABEL': 'MIMIC_LABEL'})


def map_itemids_to_variables(events, var_map):
Expand All @@ -127,9 +127,9 @@ def read_variable_ranges(fn, variable_column='LEVEL2'):
var_ranges = dataframe_from_csv(fn, index_col=None)
# var_ranges = var_ranges[variable_column].apply(lambda s: s.lower())
var_ranges = var_ranges[columns]
var_ranges.rename(to_rename, axis=1, inplace=True)
var_ranges = var_ranges.rename(columns=to_rename)
var_ranges = var_ranges.drop_duplicates(subset='VARIABLE', keep='first')
var_ranges.set_index('VARIABLE', inplace=True)
var_ranges = var_ranges.set_index('VARIABLE')
return var_ranges.loc[var_ranges.notnull().all(axis=1)]


Expand Down
2 changes: 1 addition & 1 deletion mimic3benchmark/scripts/extract_episodes_from_subjects.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,7 @@
# no data for this episode
continue

episode = add_hours_elpased_to_events(episode, intime).set_index('HOURS').sort_index(axis=0)
episode = add_hours_elpased_to_events(episode, intime).set_index('HOURS').sort_index()
if stay_id in episodic_data.index:
episodic_data.loc[stay_id, 'Weight'] = get_first_valid_from_timeseries(episode, 'Weight')
episodic_data.loc[stay_id, 'Height'] = get_first_valid_from_timeseries(episode, 'Height')
Expand Down
6 changes: 3 additions & 3 deletions mimic3benchmark/subject.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ def read_stays(subject_path):
stays.DOB = pd.to_datetime(stays.DOB)
stays.DOD = pd.to_datetime(stays.DOD)
stays.DEATHTIME = pd.to_datetime(stays.DEATHTIME)
stays.sort_values(by=['INTIME', 'OUTTIME'], inplace=True)
stays = stays.sort_values(by=['INTIME', 'OUTTIME'])
return stays


Expand Down Expand Up @@ -53,11 +53,11 @@ def convert_events_to_timeseries(events, variable_column='VARIABLE', variables=[
metadata = events[['CHARTTIME', 'ICUSTAY_ID']].sort_values(by=['CHARTTIME', 'ICUSTAY_ID'])\
.drop_duplicates(keep='first').set_index('CHARTTIME')
timeseries = events[['CHARTTIME', variable_column, 'VALUE']]\
.sort_values(by=['CHARTTIME', variable_column, 'VALUE'], axis=0)\
.sort_values(by=['CHARTTIME', variable_column, 'VALUE'])\
.drop_duplicates(subset=['CHARTTIME', variable_column], keep='last')
timeseries = timeseries.pivot(index='CHARTTIME', columns=variable_column, values='VALUE')\
.merge(metadata, left_index=True, right_index=True)\
.sort_index(axis=0).reset_index()
.sort_index().reset_index()
for v in variables:
if v not in timeseries:
timeseries[v] = np.nan
Expand Down