Spaces:
Sleeping
Sleeping
File size: 7,953 Bytes
cbdae8d db198b2 cbdae8d db198b2 cbdae8d db198b2 cbdae8d db198b2 cbdae8d db198b2 cbdae8d db198b2 cbdae8d db198b2 cbdae8d db198b2 cbdae8d db198b2 cbdae8d db198b2 cbdae8d db198b2 cbdae8d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 | import fnmatch
import json
import re
import unicodedata
import zipfile
from pathlib import Path
import pandas as pd
from data.schema import Col
ROOT_DIR = Path(__file__).resolve().parent.parent
DEFAULT_CONFIG = ROOT_DIR / "config.json"
# ============================================================
# CONFIG
# ============================================================
def load_config(
path: str | Path | None = None,
) -> dict:
with open(path or DEFAULT_CONFIG, encoding="utf-8") as f:
return json.load(f)
def resolve_source_path(
config: dict,
path: str | Path | None = None,
) -> Path:
"""
Explicit path if given, otherwise the configured one
(relative paths resolve against the project root).
"""
path = Path(path or config["source"]["path"])
if not path.is_absolute():
path = ROOT_DIR / path
if not path.exists():
raise FileNotFoundError(
f"Source file not found: {path}"
)
return path
# ============================================================
# ZIP ACCESS
# ============================================================
def slugify(text: str) -> str:
"""
'Parque Eólico de Coll del Moro' -> 'parque_eolico_de_coll_del_moro'
"""
ascii_text = (
unicodedata.normalize("NFKD", str(text))
.encode("ascii", "ignore")
.decode("ascii")
)
return re.sub(
r"[^a-z0-9]+", "_", ascii_text.lower()
).strip("_")
def read_parquets(
zip_path: str | Path,
pattern: str,
) -> dict[str, pd.DataFrame]:
"""
Read every parquet in the zip whose file name matches
`pattern` (shell-style). Returns {file name: DataFrame}.
"""
frames = {}
with zipfile.ZipFile(zip_path) as z:
for member in z.namelist():
name = Path(member).name
if fnmatch.fnmatch(name, pattern):
with z.open(member) as f:
frames[name] = pd.read_parquet(f)
if not frames:
raise ValueError(
f"No file matching '{pattern}' in {Path(zip_path).name}."
)
return frames
def _require_columns(df, columns, source):
missing = set(columns.values()) - set(df.columns)
if missing:
raise ValueError(
f"{source} is missing columns {sorted(missing)}. "
"Check the column mapping in config.json."
)
def _to_local_date(series, timezone):
"""
Timestamps -> tz-naive calendar dates in the market timezone.
"""
series = pd.to_datetime(series)
if series.dt.tz is None:
series = series.dt.tz_localize("UTC")
return (
series.dt.tz_convert(timezone)
.dt.tz_localize(None)
.dt.normalize()
)
# ============================================================
# PRICES
# ============================================================
def load_prices(
zip_path: str | Path,
config: dict,
) -> tuple[pd.DataFrame, pd.DataFrame]:
"""
Load forward-curve prices from the zip.
Returns
-------
prices : pd.DataFrame
Index = pricing date, columns = factor_id.
delivery : pd.DataFrame
Index = factor_id. Delivery period of every factor
(tz-aware), taken from its most recent quote.
"""
source = config["source"]
cfg = source["prices"]
cols = cfg["columns"]
frames = read_parquets(zip_path, cfg["file_pattern"])
raw = pd.concat(frames.values(), ignore_index=True)
_require_columns(raw, cols, "Price file")
raw = raw.copy()
raw[Col.DATE] = _to_local_date(
raw[cols["date"]], source["timezone"]
)
raw[Col.FACTOR] = raw[cols["tenor"]].map(
lambda tenor: cfg["factor_id_template"].format(tenor=tenor)
)
if raw.duplicated([Col.DATE, Col.FACTOR]).any():
raise ValueError(
"Price file contains duplicated (date, tenor) quotes."
)
prices = (
raw.pivot(
index=Col.DATE,
columns=Col.FACTOR,
values=cols["price"],
)
.sort_index()
.rename_axis(columns=None)
)
latest = (
raw.sort_values(Col.DATE)
.groupby(Col.FACTOR)
.last()
)
delivery = pd.DataFrame(
{
Col.DELIVERY_START: pd.to_datetime(
latest[cols["delivery_start"]], utc=True
),
Col.DELIVERY_END: pd.to_datetime(
latest[cols["delivery_end"]], utc=True
),
}
).loc[prices.columns]
return prices, delivery
# ============================================================
# GENERATION
# ============================================================
def load_generation(
zip_path: str | Path,
config: dict,
) -> dict[str, pd.DataFrame]:
"""
Load metered generation per plant.
Returns {plant slug: DataFrame} with columns
delivery_start, delivery_end (tz-aware UTC) and the
average power in MW over each interval.
"""
cfg = config["source"]["generation"]
cols = cfg["columns"]
unit_regex = re.compile(cfg["unit_from_filename_regex"])
generation = {}
for name, raw in read_parquets(
zip_path, cfg["file_pattern"]
).items():
_require_columns(raw, cols, name)
match = unit_regex.search(name)
if match is None:
raise ValueError(
f"Cannot extract the plant name from '{name}'. "
"Check 'unit_from_filename_regex' in config.json."
)
slug = slugify(match.group("unit"))
if slug in generation:
raise ValueError(
f"More than one generation file for plant '{slug}'."
)
if cfg.get("status_filter"):
raw = raw[raw[cols["status"]].isin(cfg["status_filter"])]
df = pd.DataFrame(
{
Col.DELIVERY_START: pd.to_datetime(
raw[cols["start"]], utc=True
),
Col.DELIVERY_END: pd.to_datetime(
raw[cols["end"]], utc=True
),
Col.POWER_MW: (
raw[cols["quantity"]].astype(float)
* cfg["quantity_to_mw"]
),
}
).sort_values(Col.DELIVERY_START)
if df[Col.DELIVERY_START].duplicated().any():
raise ValueError(
f"{name} contains duplicated delivery intervals."
)
if (df[Col.POWER_MW] < 0).any():
raise ValueError(
f"{name} contains negative generation."
)
generation[slug] = df.reset_index(drop=True)
return generation
def load_units(
zip_path: str | Path,
config: dict,
) -> pd.DataFrame:
"""
Load plant master data. Index = plant slug.
"""
cfg = config["source"]["units"]
cols = cfg["columns"]
raw = pd.concat(
read_parquets(zip_path, cfg["file_pattern"]).values(),
ignore_index=True,
)
_require_columns(raw, cols, "Generation units file")
unknown_units = (
set(raw[cols["capacity_unit"]].dropna())
- set(cfg["capacity_to_mw"])
)
if unknown_units:
raise ValueError(
f"Unknown capacity units {sorted(unknown_units)}. "
"Add them to 'capacity_to_mw' in config.json."
)
units = pd.DataFrame(
{
Col.PLANT: raw[cols["name"]],
Col.TECHNOLOGY: raw[cols["technology"]],
Col.COUNTRY: raw[cols["country"]],
Col.CAPACITY_MW: (
raw[cols["capacity"]].astype(float)
* raw[cols["capacity_unit"]].map(cfg["capacity_to_mw"])
),
}
)
units.index = units[Col.PLANT].map(slugify)
if units.index.duplicated().any():
raise ValueError(
"Generation units file contains duplicated plants."
)
return units
|