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

combined minmax date changes #115

Draft
wants to merge 5 commits into
base: util_fix
Choose a base branch
from
Draft

combined minmax date changes #115

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
15e068e
Fix grouping by lineage.
everaldorodrigo Mar 24, 2023
4c9b152
Fix grouping in prevalence.
everaldorodrigo Mar 27, 2023
f7fa3c3
Upgrade pandas.
everaldorodrigo Jun 28, 2023
9cee401
Filter by date min and max.
everaldorodrigo Jul 26, 2023
d2e2929
Merge branch 'master' into fix-lineages-min-max-date
everaldorodrigo Jul 26, 2023
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
2 changes: 1 addition & 1 deletion requirements_web.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
# git+https://github.com/biothings/[email protected]#egg=biothings[web_extra]

biothings[web_extra]==0.12.2
pandas==1.4.3
pandas==1.5.3
pyjwt[crypto]==2.4.0
scipy==1.9.0
Jinja2==3.1.2
Expand Down
4 changes: 2 additions & 2 deletions web/handlers/genomics/prevalence.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -264,7 +264,7 @@ def _get(self):
)
if query_window is not None:
df_response = df_response[df_response["date"] >= (dt.now() - timedelta(days = query_window))]
df_response = get_major_lineage_prevalence(df_response, "date", query_other_exclude, query_other_threshold, query_nday_threshold, query_ndays)
df_response = get_major_lineage_prevalence(df_response, "date", None, None, query_other_exclude, query_other_threshold, query_nday_threshold, query_ndays)
if not query_cumulative:
df_response = df_response.groupby("lineage").apply(compute_rolling_mean_all_lineages, "date", "lineage_count", "lineage_count_rolling", "lineage").reset_index()
df_response = df_response.groupby("date").apply(compute_total_count, "lineage_count_rolling", "total_count_rolling")
Expand All @@ -274,7 +274,7 @@ def _get(self):
df_response = df_response.fillna("None")
df_response = df_response[["date", "total_count", "lineage_count", "lineage", "prevalence", "prevalence_rolling"]]
else:
df_response = df_response.groupby("lineage").apply(expand_dates, df_response["date"].min(), df_response["date"].max(), "date", "lineage").reset_index()
df_response = df_response.groupby("lineage", group_keys=False).apply(expand_dates, df_response["date"].min(), df_response["date"].max(), "date", "lineage").reset_index()
df_response = df_response.groupby("date").apply(compute_total_count, "lineage_count", "total_count").reset_index()
df_response = df_response.groupby("lineage").agg({"total_count": "sum", "lineage_count": "sum"}).reset_index()
df_response.loc[:,"prevalence"] = df_response["lineage_count"]/df_response["total_count"]
Expand Down
10 changes: 7 additions & 3 deletions web/handlers/genomics/util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ def expand_dates(df, date_min, date_max, index_col, grp_col):
df
.set_index(index_col)
.reindex(idx, fill_value = 0)
.drop(grp_col, axis = 1)
.reset_index()
.rename(
columns = {
Expand Down Expand Up @@ -205,9 +204,14 @@ def classify_other_category(grp, keep_lineages):
})
return grp

def get_major_lineage_prevalence(df, index_col, keep_lineages = [], prevalence_threshold = 0.05, nday_threshold = 10, ndays = 180):
def get_major_lineage_prevalence(df, index_col, min_date = None, max_date = None, keep_lineages = [], prevalence_threshold = 0.05, nday_threshold = 10, ndays = 180):
date_limit = dt.today() - timedelta(days = ndays)
lineages_to_retain = df[(df["prevalence"] >= prevalence_threshold) & (df["date"] >= date_limit)]["lineage"].value_counts()
lineages_to_retain = df[
(df["prevalence"] >= prevalence_threshold)
& (df["date"] >= date_limit)
& ((min_date is None) | (df["date"] >= min_date))
& ((max_date is None) | (df["date"] <= max_date))
]["lineage"].value_counts()
num_unique_dates = df[df["date"] >= date_limit]["date"].unique().shape[0]
if num_unique_dates < nday_threshold:
nday_threshold = round((nday_threshold/ndays) * num_unique_dates)
Expand Down
8 changes: 6 additions & 2 deletions web/handlers/v2/genomics/prevalence_all_lineages_by_location.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,8 @@ async def _get(self):
query_other_exclude.split(",") if query_other_exclude is not None else []
)
query_cumulative = self.args.cumulative
min_date = self.args.min_date
max_date = self.args.max_date
query = {
"size": 0,
"aggs": {
Expand All @@ -54,7 +56,7 @@ async def _get(self):
}
query_obj = parse_location_id_to_query(query_location)
date_range_filter = create_date_range_filter(
"date_collected", self.args.min_date, self.args.max_date
"date_collected", min_date, max_date
)
query_obj = parse_time_window_to_query(date_range_filter, query_obj=query_obj)
if query_obj:
Expand Down Expand Up @@ -98,6 +100,8 @@ async def _get(self):
df_response = get_major_lineage_prevalence(
df_response,
"date",
min_date,
max_date,
query_other_exclude,
query_other_threshold,
query_nday_threshold,
Expand Down Expand Up @@ -138,7 +142,7 @@ async def _get(self):
]
else:
df_response = (
df_response.groupby("lineage")
df_response.groupby("lineage", group_keys=False)
.apply(
expand_dates,
df_response["date"].min(),
Expand Down