def export_to_string(project_id, export_type="csv"):
fp_lock = get_lock_path(project_id)
as_data = read_data(project_id)
with SQLiteLock(fp_lock, blocking=True, lock_name="active"):
proba = read_proba(project_id)
if proba is None:
proba = np.flip(np.arange(len(as_data)))
else:
proba = np.array(proba)
labels = read_current_labels(project_id, as_data=as_data)
pool_idx = np.where(labels == LABEL_NA)[0]
one_idx = np.where(labels == 1)[0]
zero_idx = np.where(labels == 0)[0]
proba_order = np.argsort(-proba[pool_idx])
ranking = np.concatenate((one_idx, pool_idx[proba_order], zero_idx),
axis=None)
if export_type == "csv":
return as_data.to_csv(fp=None, labels=labels, ranking=ranking)
if export_type == "excel":
get_tmp_path(project_id).mkdir(exist_ok=True)
fp_tmp_export = Path(get_tmp_path(project_id), "export_result.xlsx")
return as_data.to_excel(fp=fp_tmp_export,
labels=labels,
ranking=ranking)
else:
raise ValueError("This export type isn't implemented.")
def export_to_string(project_id, export_type="csv"):
# read the dataset into a ASReview data object
as_data = read_data(project_id)
# set the lock to safely read labeled, pool, and proba
fp_lock = get_lock_path(project_id)
with SQLiteLock(
fp_lock,
blocking=True,
lock_name="active",
project_id=project_id
):
proba = read_proba(project_id)
pool = read_pool(project_id)
labeled = read_label_history(project_id)
# get the record_id of the inclusions and exclusions
inclusion_record_id = [int(x[0]) for x in labeled if x[1] == 1]
exclusion_record_id = [int(x[0]) for x in labeled if x[1] == 0]
# order the pool from high to low proba
if proba is not None:
pool_ordered = proba.loc[pool, :] \
.sort_values("proba", ascending=False).index.values
else:
pool_ordered = pool_ordered
# get the ranking of the 3 subcategories
ranking = np.concatenate(
(
# add the inclusions first
inclusion_record_id,
# add the ordered pool second
pool_ordered,
# add the exclusions last
exclusion_record_id
),
axis=None
)
# export the data to file
if export_type == "csv":
return as_data.to_csv(fp=None, labels=labeled, ranking=ranking)
if export_type == "tsv":
return as_data.to_csv(
fp=None, sep="\t", labels=labeled, ranking=ranking)
if export_type == "excel":
get_tmp_path(project_id).mkdir(exist_ok=True)
fp_tmp_export = Path(get_tmp_path(project_id), "export_result.xlsx")
return as_data.to_excel(
fp=fp_tmp_export, labels=labeled, ranking=ranking)
else:
raise ValueError("This export type isn't implemented.")
def export_results(project_id):
# get the export args
file_type = request.args.get('file_type', None)
logging.info(f"Start exporting results to '{file_type}'")
print(f"Start exporting results to '{file_type}'")
if file_type == "csv":
dataset_str = export_to_string(project_id, export_type="csv")
return Response(
dataset_str,
mimetype="text/csv",
headers={
"Content-disposition":
f"attachment; filename=asreview_result_{project_id}.csv"
})
else: # excel
dataset_str = export_to_string(project_id, export_type="excel")
fp_tmp_export = Path(get_tmp_path(project_id), "export_result.xlsx")
return send_file(
fp_tmp_export,
mimetype=
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", # noqa
as_attachment=True,
attachment_filename=f"asreview_result_{project_id}.xlsx",
cache_timeout=0)
def export_results(project_id):
# get the export args
file_type = request.args.get('file_type', None)
if file_type == "csv":
dataset_str = export_to_string(project_id, export_type="csv")
return Response(
dataset_str,
mimetype="text/csv",
headers={
"Content-disposition":
f"attachment; filename=asreview_result_{project_id}.csv"
})
elif file_type == "tsv":
dataset_str = export_to_string(project_id, export_type="tsv")
return Response(
dataset_str,
mimetype="text/tab-separated-values",
headers={
"Content-disposition":
f"attachment; filename=asreview_result_{project_id}.tsv"
})
else: # excel
dataset_str = export_to_string(project_id, export_type="excel")
fp_tmp_export = Path(get_tmp_path(project_id), "export_result.xlsx")
return send_file(
fp_tmp_export,
mimetype=
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", # noqa
as_attachment=True,
download_name=f"asreview_result_{project_id}.xlsx",
max_age=0)
