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

Jump to bottom

fix(parsers):India parser updated for new data format #7089

Merged
merged 2 commits into from
Aug 19, 2024
Merged

fix(parsers):India parser updated for new data format #7089

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8b0ccfa
fix(parsers):India parser updated for new data format
Aug 19, 2024
8eeff54
fix(parsers):Reformatted
Aug 19, 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
38 changes: 28 additions & 10 deletions parsers/IN.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -347,21 +347,37 @@ def fetch_consumption(
).to_list()


def format_ren_production_data(url: str, zone_key: str) -> dict[str, Any]:
def format_ren_production_data(
url: str, zone_key: str, target_datetime: datetime
) -> dict[str, Any]:
"""Formats daily renewable production data for each zone"""
df_ren = pd.read_excel(url, engine="openpyxl", header=5, skipfooter=2)
df_ren = df_ren.dropna(axis=0, how="all")
df_ren = df_ren.rename(
columns={
df_ren.columns[1]: "region",
df_ren.columns[2]: "wind",
df_ren.columns[3]: "solar",
df_ren.columns[4]: "unknown",
}
)

# They changed format of the data from 2024/07/01
if target_datetime < datetime(2024, 7, 1, 0, 0, tzinfo=IN_TZ):
df_ren = df_ren.rename(
columns={
df_ren.columns[1]: "region",
df_ren.columns[2]: "wind",
df_ren.columns[3]: "solar",
df_ren.columns[4]: "unknown",
}
)
else:
df_ren = df_ren.rename(
columns={
df_ren.columns[0]: "region",
df_ren.columns[1]: "wind",
df_ren.columns[2]: "solar",
df_ren.columns[3]: "unknown",
}
)

df_ren.loc[:, "zone_key"] = (
df_ren["region"].apply(lambda x: x if "Region" in x else np.nan).backfill()
)

df_ren["zone_key"] = df_ren["zone_key"].str.strip()
df_ren["zone_key"] = df_ren["zone_key"].map(CEA_REGION_MAPPING)

Expand All @@ -372,6 +388,7 @@ def format_ren_production_data(url: str, zone_key: str) -> dict[str, Any]:
renewable_production = {
key: round(zone_data.get(key) / CONVERSION_GWH_MW, 3) for key in zone_data.index
}

return renewable_production


Expand All @@ -395,6 +412,7 @@ def fetch_cea_production(
for elem in all_data
if target_datetime.strftime("%Y-%m-%d") in elem["date"]
]

if len(target_elem) > 0:
if target_elem[0]["link"] == "file_not_found":
raise ParserException(
Expand All @@ -406,7 +424,7 @@ def fetch_cea_production(
formatted_url = target_url.split("^")[0]
r: Response = session.get(formatted_url)
renewable_production = format_ren_production_data(
url=r.url, zone_key=zone_key
url=r.url, zone_key=zone_key, target_datetime=target_datetime
)
return renewable_production
else:
Expand Down
Loading