Skip to content

Fix parsing of one-to-one metadata #388

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

Draft
marcellevstek wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

Fix parsing of one-to-one metadata #388

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
36 changes: 26 additions & 10 deletions src/resdk/tables/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -351,7 +351,7 @@ def _get_relations(self) -> pd.DataFrame:
for partition in relation.partitions:
value = ""
if partition["label"] and partition["position"]:
value = f'{partition["label"]} / {partition["position"]}'
value = f"{partition['label']} / {partition['position']}"
elif partition["label"]:
value = partition["label"]
elif partition["position"]:
Expand All @@ -371,6 +371,19 @@ def _get_orange_object(self) -> Data:
)

def _get_orange_data(self) -> pd.DataFrame:
def map_and_filter_samples(
df: pd.DataFrame, column_name: str, mapping: dict
) -> pd.DataFrame:
"""Map a predefined column name to a column named ``sample_id``, drop the original
and return the constructed DataFrame.
Omit samples for which mapping is not defined. These samples do not
have any data objects with the defined process type.
"""
df = df[df[column_name].isin(mapping.keys())]
df["sample_id"] = df[column_name].map(mapping)
df = df.drop(columns=[column_name])
return df

try:
orange_meta = self._get_orange_object()
except LookupError:
Expand Down Expand Up @@ -402,29 +415,32 @@ def _get_orange_data(self) -> pd.DataFrame:
df = df.rename(columns={"mS#Sample ID": "sample_id"})
elif "Sample slug" in df.columns:
mapping = {s.slug: s.id for s in self._samples}
df["sample_id"] = [mapping[value] for value in df["Sample slug"]]
df = df.drop(columns=["Sample slug"])
df = map_and_filter_samples(
df=df, column_name="Sample slug", mapping=mapping
)
elif "mS#Sample slug" in df.columns:
mapping = {s.slug: s.id for s in self._samples}
df["sample_id"] = [mapping[value] for value in df["mS#Sample slug"]]
df = df.drop(columns=["mS#Sample slug"])
df = map_and_filter_samples(
df=df, column_name="mS#Sample slug", mapping=mapping
)
elif "Sample name" in df.columns or "Sample name" in df.columns:
mapping = {s.name: s.id for s in self._samples}
if len(mapping) != len(self._samples):
raise ValueError(
"Duplicate sample names. Cannot map orange table data to other metadata"
)
df["sample_id"] = [mapping[value] for value in df["Sample name"]]
df = df.drop(columns=["Sample name"])
df = map_and_filter_samples(
df=df, column_name="Sample name", mapping=mapping
)
elif "mS#Sample name" in df.columns:
mapping = {s.name: s.id for s in self._samples}
if len(mapping) != len(self._samples):
raise ValueError(
"Duplicate sample names. Cannot map orange table data to other metadata"
)
df["sample_id"] = [mapping[value] for value in df["mS#Sample name"]]
df = df.drop(columns=["mS#Sample name"])

df = map_and_filter_samples(
df=df, column_name="mS#Sample name", mapping=mapping
)
return df.set_index("sample_id")

def _download_metadata(self) -> pd.DataFrame:
Expand Down
10 changes: 10 additions & 0 deletions test_meta.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
import resdk
from resdk.tables import QCTables

res = resdk.Resolwe(url="https://qa.genialis.io")
res.login()

collection = res.collection.get("validation-run-208")
qt = QCTables(collection=collection)

qt.meta
Loading