Skip to content

Port public R queries #31

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

Merged
merged 13 commits into from
Jul 16, 2024
Merged

Port public R queries #31

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
3dae260
Port public R queries
rzats Jun 11, 2024
3adce47
Add private calls
rzats Jun 17, 2024
0aea6a8
test: add secrets, convert dfs
dshemetov Jun 22, 2024
75bace1
test: convert more test calls to df
dshemetov Jun 22, 2024
563c58e
lint
dshemetov Jul 9, 2024
722c8df
Test datetime cols and improve datetime handling
rzats Jul 9, 2024
78d3532
dtype handling in tests
rzats Jul 15, 2024
a4b3b70
Merge branch 'dev' into rzatserkovnyi/test-epidata-calls
dshemetov Jul 15, 2024
2943320
fix: remove print statement
dshemetov Jul 15, 2024
b46d128
fix: typos in endpoint fields
dshemetov Jul 16, 2024
a1acdba
fix: update tests and df type casting
dshemetov Jul 16, 2024
56c6a6e
lint: format
dshemetov Jul 16, 2024
3bb41f4
lint: lint
dshemetov Jul 16, 2024
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
18 changes: 9 additions & 9 deletions epidatpy/_endpoints.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,7 +109,7 @@ def pub_covid_hosp_facility_lookup(
EpidataFieldInfo("city", EpidataFieldType.text),
EpidataFieldInfo("zip", EpidataFieldType.text),
EpidataFieldInfo("hospital_subtype", EpidataFieldType.text),
EpidataFieldInfo("fip_code", EpidataFieldType.text),
EpidataFieldInfo("fips_code", EpidataFieldType.text),
EpidataFieldInfo("is_metro_micro", EpidataFieldType.int),
],
)
Expand Down Expand Up @@ -553,7 +553,7 @@ def pub_ecdc_ili(
[
EpidataFieldInfo("region", EpidataFieldType.text),
EpidataFieldInfo("release_date", EpidataFieldType.date),
EpidataFieldInfo("issue", EpidataFieldType.date),
EpidataFieldInfo("issue", EpidataFieldType.epiweek),
EpidataFieldInfo("epiweek", EpidataFieldType.epiweek),
EpidataFieldInfo("lag", EpidataFieldType.int),
EpidataFieldInfo("incidence_rate", EpidataFieldType.float),
Expand Down Expand Up @@ -584,15 +584,15 @@ def pub_flusurv(
[
EpidataFieldInfo("release_date", EpidataFieldType.text),
EpidataFieldInfo("location", EpidataFieldType.text),
EpidataFieldInfo("issue", EpidataFieldType.date),
EpidataFieldInfo("issue", EpidataFieldType.date_or_epiweek),
EpidataFieldInfo("epiweek", EpidataFieldType.epiweek),
EpidataFieldInfo("lag", EpidataFieldType.int),
EpidataFieldInfo("rage_age_0", EpidataFieldType.float),
EpidataFieldInfo("rage_age_1", EpidataFieldType.float),
EpidataFieldInfo("rage_age_2", EpidataFieldType.float),
EpidataFieldInfo("rage_age_3", EpidataFieldType.float),
EpidataFieldInfo("rage_age_4", EpidataFieldType.float),
EpidataFieldInfo("rage_overall", EpidataFieldType.float),
EpidataFieldInfo("rate_age_0", EpidataFieldType.float),
EpidataFieldInfo("rate_age_1", EpidataFieldType.float),
EpidataFieldInfo("rate_age_2", EpidataFieldType.float),
EpidataFieldInfo("rate_age_3", EpidataFieldType.float),
EpidataFieldInfo("rate_age_4", EpidataFieldType.float),
EpidataFieldInfo("rate_overall", EpidataFieldType.float),
],
)

Expand Down
8 changes: 7 additions & 1 deletion epidatpy/_parse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,11 @@ def parse_api_date(value: Union[str, int, float, None]) -> Optional[date]:
if value is None:
return value
v = str(value)
return datetime.strptime(v, "%Y%m%d").date()
if len(v) == 10: # yyyy-mm-dd
d = datetime.strptime(v, "%Y-%m-%d").date()
else:
d = datetime.strptime(v, "%Y%m%d").date()
return d


def parse_api_week(value: Union[str, int, float, None]) -> Optional[date]:
Expand All @@ -23,6 +27,8 @@ def parse_api_date_or_week(value: Union[str, int, float, None]) -> Optional[date
v = str(value)
if len(v) == 6:
d = Week.fromstring(v).startdate()
elif len(v) == 10: # yyyy-mm-dd
d = datetime.strptime(v, "%Y-%m-%d").date()
else:
d = datetime.strptime(v, "%Y%m%d").date()
return d
Expand Down
22 changes: 16 additions & 6 deletions epidatpy/request.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,9 +137,9 @@ def df(
df = DataFrame(rows, columns=columns or None)

data_types: Dict[str, Any] = {}
time_fields: List[str] = []
time_fields: List[EpidataFieldInfo] = []
for info in self.meta:
if not pred(info.name) or df[info.name].isnull().all():
if not pred(info.name):
continue
if info.type == EpidataFieldType.bool:
data_types[info.name] = bool
Expand All @@ -154,17 +154,27 @@ def df(
EpidataFieldType.epiweek,
EpidataFieldType.date_or_epiweek,
):
data_types[info.name] = "Int64"
time_fields.append(info.name)
data_types[info.name] = "string"
time_fields.append(info)
elif info.type == EpidataFieldType.float:
data_types[info.name] = "Float64"
else:
data_types[info.name] = "string"
if data_types:
df = df.astype(data_types)
if not disable_date_parsing:
for field in time_fields:
df[field] = to_datetime(df[field], format="%Y%m%d", errors="ignore")
for info in time_fields:
if info.type == EpidataFieldType.epiweek:
continue
try:
df[info.name] = to_datetime(df[info.name], format="%Y-%m-%d")
continue
except ValueError:
pass
try:
df[info.name] = to_datetime(df[info.name], format="%Y%m%d")
except ValueError:
pass
return df


Expand Down
Loading
Loading