def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
date_columns=[
*expand_args.get("date_columns", []),
"authoredOn",
"dispenseRequest.validityPeriod.start",
"dispenseRequest.validityPeriod.end",
],
code_columns=[
*expand_args.get("code_columns", []),
"medicationCodeableConcept",
],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
Frame.codeable_like_column_expander("context"),
Frame.codeable_like_column_expander("note"),
(
"dispenseRequest",
lambda r: pd.json_normalize(r).add_prefix(
"dispenseRequest."),
),
],
)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
date_columns=[
*expand_args.get("date_columns", []),
"period.start",
"period.end",
],
code_columns=[
*expand_args.get("code_columns", []),
"class",
"priority",
"participant",
"length",
"hospitalization",
],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
Frame.codeable_like_column_expander("period"),
Frame.codeable_like_column_expander("reason"),
Frame.codeable_like_column_expander("location"),
Frame.codeable_like_column_expander("serviceProvider"),
],
)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
Frame.codeable_like_column_expander("presentedForm"),
Frame.codeable_like_column_expander("result"),
],
)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
date_columns=[*expand_args.get("date_columns", []), "dateTime"],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("sourceReference"),
Frame.codeable_like_column_expander("actor"),
Frame.codeable_like_column_expander("patient"),
],
)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
date_columns=[*expand_args.get("date_columns", []), "date"],
code_columns=[*expand_args.get("code_columns", []), "vaccineCode"],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("patient"),
Frame.codeable_like_column_expander("encounter"),
],
)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
code_columns=[
*expand_args.get("code_columns", []),
"procedureCode",
],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("patient"),
Frame.codeable_like_column_expander("context"),
],
)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
code_columns=[*expand_args.get("code_columns", []), "type"],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
Frame.codeable_like_column_expander("context"),
(
"requester",
lambda r: pd.json_normalize(r).add_prefix("requester."),
),
],
)
def transform_results(data_frame: pd.DataFrame, **expand_args):
args = {
**expand_args,
"code_columns": [
*expand_args.get("code_columns", []),
"specimen",
"repository",
],
"custom_columns": [
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("patient"),
Frame.codeable_like_column_expander("referenceSeq"),
],
}
return Frame.expand(data_frame, **args)
def transform_results(data_frame: pd.DataFrame, params={}, **expand_args):
def expand_id(id_column: pd.Series):
return pd.concat(
[
id_column,
id_column.str.split(":", expand=True).rename(columns={
0: "variant_set_id",
2: "gene"
})[["variant_set_id", "gene"]],
],
axis=1,
)
args = {
**expand_args,
"custom_columns": [
*expand_args.get("custom_columns", []),
*[
Frame.codeable_like_column_expander(k) for k in [
"clinvar",
"cosmic",
"vcf",
"ensemblCanon",
"dbnsfp",
]
],
("id", expand_id),
],
}
return Frame.expand(data_frame, **args)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
date_columns=[*expand_args.get("date_columns", []), "date"],
code_columns=[
*expand_args.get("code_columns", []),
"type",
"author",
],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
Frame.codeable_like_column_expander("text"),
Frame.codeable_like_column_expander("relatesTo"),
],
)
def transform_results(data_frame: pd.DataFrame, **expand_args):
args = {
**expand_args,
"code_columns": [
*expand_args.get("code_columns", []),
"component",
"interpretation",
],
"custom_columns": [
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
Frame.codeable_like_column_expander("related"),
Frame.codeable_like_column_expander("performer"),
Frame.codeable_like_column_expander("context"),
],
}
return Frame.expand(data_frame, **args)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
date_columns=[
*expand_args.get("date_columns", []),
"occurrencePeriod.start",
"occurrencePeriod.end",
"occurrenceDateTime",
"authoredOn",
],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
Frame.codeable_like_column_expander("context"),
Frame.codeable_like_column_expander("occurrencePeriod"),
Frame.codeable_like_column_expander("note"),
],
)
def transform_results(data_frame: pd.DataFrame, **expand_args):
args = {
**expand_args,
"date_columns": [
*expand_args.get("date_columns", []),
"performedPeriod.start",
"performedPeriod.end",
],
"custom_columns": [
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
Frame.codeable_like_column_expander("performedPeriod"),
Frame.codeable_like_column_expander("context"),
Frame.codeable_like_column_expander("managingOrganization"),
],
}
return Frame.expand(data_frame, **args)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
date_columns=[
*expand_args.get("date_columns", []),
"effectiveDateTime",
],
code_columns=[
*expand_args.get("code_columns", []),
"type",
"subtype",
],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("agent"),
Frame.codeable_like_column_expander("source"),
Frame.codeable_like_column_expander("entity"),
],
)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
date_columns=[
*expand_args.get("date_columns", []),
"effectivePeriod.start",
"effectivePeriod.end",
],
code_columns=[
*expand_args.get("code_columns", []),
"medicationCodeableConcept",
],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
Frame.codeable_like_column_expander("context"),
Frame.codeable_like_column_expander("prescription"),
Frame.codeable_like_column_expander("dosage"),
Frame.codeable_like_column_expander("effectivePeriod"),
],
)
def transform_results(data_frame: pd.DataFrame, **expand_args):
args = {
**expand_args,
"date_columns":
[*expand_args.get("date_columns", []), "startDate"],
"custom_columns": [
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
],
}
return Frame.expand(data_frame, **args)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
date_columns=[
*expand_args.get("date_columns", []),
"onsetDateTime",
"assertedDate",
"onsetPeriod.start",
"onsetPeriod.end",
],
code_columns=[
*expand_args.get("code_columns", []),
"bodySite",
"stage",
],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
Frame.codeable_like_column_expander("onsetPeriod"),
Frame.codeable_like_column_expander("context"),
],
)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
code_columns=[
*expand_args.get("code_columns", []),
"collection",
"type",
],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
],
)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
code_columns=[
*expand_args.get("code_columns", []),
"medicationCodeableConcept",
"quantity",
"dosageInstruction",
"daysSupply",
],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
],
)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
date_columns=[
*expand_args.get("date_columns", []),
"effectiveDateTime",
],
code_columns=[
*expand_args.get("code_columns", []),
"medicationCodeableConcept",
],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
],
)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
code_columns=[*expand_args.get("code_columns", []), "type"],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
# TODO: Properly parse content column
#
# Example:
# [{'attachment': {'contentType': 'application/gzip',
# 'url': 'https://api.us.lifeomic.com/v1/files/<uuid>',
# 'size': 182539,
# 'title': 'helix-source-files/normalized/<filename>.vcf.gz'}}]
],
)
def transform_results(data_frame: pd.DataFrame, **expand_args):
args = {
**expand_args,
"code_columns": [
*expand_args.get("code_columns", []),
"contained",
"maritalStatus",
],
"custom_columns": [
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("managingOrganization"),
("address", expand_address_column),
("name", expand_name_column),
],
}
return Frame.expand(data_frame, **args)
def transform_results(df: pd.DataFrame, **expand_args):
return Frame.expand(
df,
date_columns=[
*expand_args.get("date_columns", []),
"occurrenceDateTime",
],
code_columns=[*expand_args.get("code_columns", []), "bodySite"],
custom_columns=[
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("subject"),
(
"content",
lambda r: pd.json_normalize(r).add_prefix("content."),
),
],
)
def transform_results(
data_frame: pd.DataFrame, params: dict, **expand_args
):
args = {
**expand_args,
"code_columns": [
*expand_args.get("code_columns", []),
"bodySite",
"patient",
],
"custom_columns": [
*expand_args.get("custom_columns", []),
Frame.codeable_like_column_expander("sourceFile"),
],
}
df = Frame.expand(data_frame, **args)
if "sets" in df.columns:
df = (
pd.concat(
data_frame.apply(
lambda x: pd.DataFrame(
[{"index": x.name, **s} for s in x.sets]
),
axis=1,
).values
)
.join(df.drop(["sets"], axis=1), on="index", rsuffix=".test")
.drop(["index"], axis=1)
.reset_index(drop=True)
)
test_type = params.get("type", None)
if test_type and len(df) > 0:
# TODO: Remove when API fixed
# NOTE: The API does not filter the returned sets because it is a
# nested structure. Since it's not a boatload of information, we opt
# to filter client-side for now.
return df[df.setType == test_type].reset_index(drop=True)
return df
def get_data_frame(document_id: str,
raw: bool = False,
auth_args: Auth = Auth.shared()):
auth = Auth(auth_args)
document = Document.get(document_id, auth_args=auth_args)
file_id = pipe(
document.get("content", []),
c.filter(lambda c: c.get("format", {}).get("code") ==
"ocr-text-file-id"),
c.first,
c.get("attachment", default={}),
c.get("url"),
iffy(isa(str), lambda url: url.split("/")[-1]),
)
if file_id is None:
raise ValueError(
f"No block file found for document: '{document_id}'")
files = Files(auth.session())
filename = files.download(file_id, "/tmp/")
frame = pd.read_json(filename, lines=True)
os.remove(filename)
if raw or len(frame) == 0:
return frame
return Block.sort(
frame.drop(["Geometry"], axis=1).join(
pd.json_normalize(frame.Geometry)).pipe(
partial(
Frame.expand,
custom_columns=[
Frame.codeable_like_column_expander("Polygon")
],
)).set_index("Id"))