python-esios 2.3.0__tar.gz → 2.4.1__tar.gz

python_esios-2.4.1/.release-please-manifest.json

@@ -0,0 +1,3 @@
+{
+  ".": "2.4.1"
+}

{python_esios-2.3.0 → python_esios-2.4.1}/CHANGELOG.md

@@ -1,5 +1,20 @@
 # Changelog
 
+## [2.4.1](https://github.com/datons/python-esios/compare/python-esios-v2.4.0...python-esios-v2.4.1) (2026-05-19)
+
+
+### Bug Fixes
+
+* **i90:** detect separator columns dynamically by header label ([1a9bf77](https://github.com/datons/python-esios/commit/1a9bf778eeb769aac836a945787c951c624f3806))
+* **i90:** detect separator columns dynamically by header label ([d6c747f](https://github.com/datons/python-esios/commit/d6c747f4db44b5667abf12f075ef468eca3eec20))
+
+## [2.4.0](https://github.com/datons/python-esios/compare/python-esios-v2.3.0...python-esios-v2.4.0) (2026-03-23)
+
+
+### Features
+
+* concurrent & adaptive chunk fetching for indicators ([1ef2590](https://github.com/datons/python-esios/commit/1ef2590cf870e13e57792cbb734e10f8d6449744))
+
 ## [2.3.0](https://github.com/datons/python-esios/compare/python-esios-v2.2.0...python-esios-v2.3.0) (2026-03-16)
 
 

{python_esios-2.3.0 → python_esios-2.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-esios
-Version: 2.3.0
+Version: 2.4.1
 Summary: A Python wrapper for the ESIOS API (Spanish electricity market)
 Project-URL: Homepage, https://github.com/datons/python-esios
 Project-URL: Repository, https://github.com/datons/python-esios
@@ -85,7 +85,7 @@ from esios import ESIOSClient
 client = ESIOSClient()
 
 # Get indicator data as DataFrame
-handle = client.indicators.get(600)  # PVPC price
+handle = client.indicators.get(600)  # Day-ahead spot price (OMIE)
 df = handle.historical("2025-01-01", "2025-01-31")
 
 # Search indicators
@@ -99,8 +99,8 @@ client.archives.download(1, start="2025-01-01", end="2025-01-31", output_dir="./
 
 | ID | Name | Description |
 |----|------|-------------|
-| 600 | PVPC | Voluntary price for small consumers |
-| 1001 | Day-ahead price | OMIE spot market price |
+| 600 | Day-ahead price | OMIE spot market price |
+| 1001 | PVPC | Voluntary price for small consumers (2.0TD) |
 | 10033 | Demand | Real-time electricity demand |
 | 10034 | Wind generation | Real-time wind generation |
 | 10035 | Solar PV generation | Real-time solar generation |

{python_esios-2.3.0 → python_esios-2.4.1}/README.md

@@ -50,7 +50,7 @@ from esios import ESIOSClient
 client = ESIOSClient()
 
 # Get indicator data as DataFrame
-handle = client.indicators.get(600)  # PVPC price
+handle = client.indicators.get(600)  # Day-ahead spot price (OMIE)
 df = handle.historical("2025-01-01", "2025-01-31")
 
 # Search indicators
@@ -64,8 +64,8 @@ client.archives.download(1, start="2025-01-01", end="2025-01-31", output_dir="./
 
 | ID | Name | Description |
 |----|------|-------------|
-| 600 | PVPC | Voluntary price for small consumers |
-| 1001 | Day-ahead price | OMIE spot market price |
+| 600 | Day-ahead price | OMIE spot market price |
+| 1001 | PVPC | Voluntary price for small consumers (2.0TD) |
 | 10033 | Demand | Real-time electricity demand |
 | 10034 | Wind generation | Real-time wind generation |
 | 10035 | Solar PV generation | Real-time solar generation |

{python_esios-2.3.0 → python_esios-2.4.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "python-esios"
-version = "2.3.0"
+version = "2.4.1"
 description = "A Python wrapper for the ESIOS API (Spanish electricity market)"
 readme = "README.md"
 license = "GPL-3.0-only"
@@ -53,3 +53,9 @@ packages = ["src/esios"]
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 pythonpath = ["src"]
+
+[dependency-groups]
+dev = [
+    "kaleido>=1.2.0",
+    "plotly>=6.6.0",
+]

{python_esios-2.3.0 → python_esios-2.4.1}/src/esios/.agents/skills/esios/SKILL.md

@@ -60,8 +60,8 @@ print(sheet.frequency)    # "hourly" or "hourly-quarterly"
 
 | ID | Name | Description | Geos |
 |----|------|-------------|------|
-| 600 | Precio mercado spot | OMIE spot market price | ES, PT, FR, DE, BE, NL |
-| 1001 | Precio mercado diario | Day-ahead market price | ES |
+| 600 | Precio mercado SPOT Diario | OMIE spot / day-ahead market price | ES, PT, FR, DE, BE, NL |
+| 1001 | PVPC T. 2.0TD | Término de facturación de energía activa del PVPC (voluntary price for small consumers) | Península, Canarias, Baleares, Ceuta, Melilla |
 | 10033 | Demanda real | Real-time electricity demand | ES |
 | 10034 | Generación eólica | Real-time wind generation | ES |
 | 10035 | Generación solar FV | Real-time solar PV generation | ES |

python_esios-2.4.1/src/esios/constants.py

@@ -0,0 +1,30 @@
+"""Constants for the ESIOS API client."""
+
+ESIOS_API_URL = "https://api.esios.ree.es"
+
+DEFAULT_HEADERS = {
+    "Accept": "application/json; application/vnd.esios-api-v1+json",
+    "Content-Type": "application/json",
+    "Host": "api.esios.ree.es",
+}
+
+DEFAULT_TIMEOUT = 30.0  # seconds
+
+MAX_RETRIES = 3
+RETRY_MIN_WAIT = 2  # seconds
+RETRY_MAX_WAIT = 10  # seconds
+
+# ESIOS API chunk sizes for historical data fetching.
+# High-geo indicators (40+ geos) timeout (504) at >21 days.
+# Low-geo indicators handle 6+ months per request in <0.1s.
+CHUNK_SIZE_DAYS = 21  # Legacy default, kept for backward compat
+CHUNK_SIZE_DAYS_LOW_GEO = 180  # 6 months for indicators with few geos
+CHUNK_SIZE_DAYS_HIGH_GEO = 21  # Conservative for indicators with many geos
+HIGH_GEO_THRESHOLD = 15  # Indicators with >= this many geos use smaller chunks
+
+# Concurrent chunk fetching within a single indicator.
+# 4 workers gives ~17-95x speedup over sequential with no errors.
+# Diminishing returns past 4 (ESIOS server becomes the bottleneck).
+DEFAULT_CHUNK_WORKERS = 4
+
+TIMEZONE = "Europe/Madrid"

{python_esios-2.3.0 → python_esios-2.4.1}/src/esios/managers/indicators.py

@@ -3,13 +3,20 @@
 from __future__ import annotations
 
 import logging
+from concurrent.futures import ThreadPoolExecutor, as_completed
 from datetime import timedelta
 from typing import Any
 
 import pandas as pd
 
 from esios.cache import CacheStore
-from esios.constants import CHUNK_SIZE_DAYS, TIMEZONE
+from esios.constants import (
+    CHUNK_SIZE_DAYS_HIGH_GEO,
+    CHUNK_SIZE_DAYS_LOW_GEO,
+    DEFAULT_CHUNK_WORKERS,
+    HIGH_GEO_THRESHOLD,
+    TIMEZONE,
+)
 from esios.managers.base import BaseManager
 from esios.models.indicator import Indicator
 from esios.processing.dataframes import to_dataframe
@@ -131,6 +138,88 @@ class IndicatorHandle:
             f"Available: {', '.join(available)}"
         )
 
+    @property
+    def _chunk_days(self) -> int:
+        """Choose chunk size based on indicator's geo count.
+
+        ESIOS API times out (504) for high-geo indicators (40+ geos) with
+        windows larger than ~3 weeks. Low-geo indicators handle 6+ months
+        per request in <0.1s.
+
+        When geos are unknown (empty metadata), uses the conservative
+        chunk size to avoid timeouts on first fetch.
+        """
+        geo_count = len(self.geos)
+        if geo_count == 0:
+            # Unknown geo count — be conservative
+            return CHUNK_SIZE_DAYS_HIGH_GEO
+        if geo_count >= HIGH_GEO_THRESHOLD:
+            return CHUNK_SIZE_DAYS_HIGH_GEO
+        return CHUNK_SIZE_DAYS_LOW_GEO
+
+    def _fetch_one(
+        self, start: str, end: str, base_params: dict[str, Any],
+    ) -> list[dict]:
+        """Fetch a single date-range chunk from the ESIOS API."""
+        params = {
+            **base_params,
+            "start_date": start,
+            "end_date": end + "T23:59:59",
+        }
+        logger.debug("Fetch %s → %s", start, end)
+        data = self._manager._get(f"indicators/{self.id}", params=params)
+        return data.get("indicator", {}).get("values", [])
+
+    def _fetch_chunks(
+        self,
+        gaps: list,
+        base_params: dict[str, Any],
+        max_workers: int = DEFAULT_CHUNK_WORKERS,
+    ) -> list[dict]:
+        """Fetch all gap chunks concurrently, return values in order.
+
+        Builds a list of (start, end) chunks from the gaps, then fetches
+        them in parallel using a thread pool. Results are reassembled in
+        chronological order.
+        """
+        chunk_delta = timedelta(days=self._chunk_days)
+
+        # Build chunk list
+        chunks: list[tuple[str, str]] = []
+        for gap in gaps:
+            current = gap.start
+            while current <= gap.end:
+                chunk_end = min(current + chunk_delta, gap.end)
+                chunks.append((
+                    current.strftime("%Y-%m-%d"),
+                    chunk_end.strftime("%Y-%m-%d"),
+                ))
+                current = chunk_end + timedelta(days=1)
+
+        if not chunks:
+            return []
+
+        if len(chunks) == 1:
+            return self._fetch_one(chunks[0][0], chunks[0][1], base_params)
+
+        # Fetch concurrently, preserve order
+        results: list[list[dict] | None] = [None] * len(chunks)
+        with ThreadPoolExecutor(max_workers=max_workers) as pool:
+            futures = {
+                pool.submit(self._fetch_one, s, e, base_params): i
+                for i, (s, e) in enumerate(chunks)
+            }
+            for future in as_completed(futures):
+                idx = futures[future]
+                results[idx] = future.result()
+
+        # Flatten in chronological order
+        all_values: list[dict] = []
+        for chunk_values in results:
+            if chunk_values:
+                all_values.extend(chunk_values)
+        return all_values
+
     def historical(
         self,
         start: str,
@@ -143,11 +232,15 @@ class IndicatorHandle:
         time_trunc: str | None = None,
         geo_trunc: str | None = None,
         column_name: str | None = None,
+        chunk_workers: int = DEFAULT_CHUNK_WORKERS,
     ) -> pd.DataFrame:
         """Fetch historical values as a DataFrame with DatetimeIndex.
 
         Uses local parquet cache when enabled. Only fetches missing date ranges
-        from the API. Automatically chunks requests exceeding ~3 weeks.
+        from the API. Automatically chunks requests and fetches concurrently.
+
+        Chunk size adapts to the indicator's geo count: 180 days for low-geo
+        indicators, 21 days for high-geo (≥15 geos) to avoid ESIOS timeouts.
 
         When multiple geo_ids are present (e.g. indicator 600 returns data for
         several countries), the result is pivoted so each geo becomes a column
@@ -158,6 +251,8 @@ class IndicatorHandle:
                 Useful for single-column results where a stable name like
                 ``"value"`` is preferred over the default geo_name or
                 indicator ID.
+            chunk_workers: Number of concurrent threads for fetching chunks.
+                Defaults to 4. Set to 1 for sequential fetching.
         """
         base_params: dict[str, Any] = {
             "locale": locale,
@@ -211,24 +306,8 @@ class IndicatorHandle:
             from esios.cache import DateRange
             gaps = [DateRange(start_date, end_date)]
 
-        # -- Fetch missing ranges ----------------------------------------------
-        all_values: list[dict] = []
-        chunk_delta = timedelta(days=CHUNK_SIZE_DAYS)
-
-        for gap in gaps:
-            current = gap.start
-            gap_end = gap.end
-            while current <= gap_end:
-                chunk_end = min(current + chunk_delta, gap_end)
-                params = {
-                    **base_params,
-                    "start_date": current.strftime("%Y-%m-%d"),
-                    "end_date": chunk_end.strftime("%Y-%m-%d") + "T23:59:59",
-                }
-                logger.debug("Fetch %s → %s", params["start_date"], params["end_date"])
-                data = self._manager._get(f"indicators/{self.id}", params=params)
-                all_values.extend(data.get("indicator", {}).get("values", []))
-                current = chunk_end + timedelta(days=1)
+        # -- Fetch missing ranges (concurrent + adaptive chunk size) -----------
+        all_values = self._fetch_chunks(gaps, base_params, max_workers=chunk_workers)
 
         # Learn any new geo mappings from the response
         self._enrich_geo_map(all_values)

{python_esios-2.3.0 → python_esios-2.4.1}/src/esios/processing/i90.py

@@ -33,6 +33,43 @@ def _any_value_greater_than_30(series: np.ndarray) -> bool:
     return any(v > 30 for v in series if isinstance(v, (int, float, np.integer, np.floating)) and not np.isnan(v))
 
 
+# Labels that REE uses for the cells sitting between the index columns and the
+# per-period value columns of an I90 sheet. Match is exact (case-insensitive,
+# trimmed). The count of these cells per sheet has varied across REE format
+# revisions — historically 2 ("Hora" / "Cuarto de Hora del dia" + "Total");
+# from Oct 2025 the MTU 15-min transition dropped "Total" on several sheets,
+# leaving 1. Counting them dynamically keeps the parser resilient to either.
+_SEPARATOR_LABELS = frozenset({
+    "cuarto de hora del dia",
+    "hora del dia",
+    "hora",
+    "total",
+    "indicadores",
+})
+
+
+def _count_header_separators(row: np.ndarray, idx_col_start: int) -> int:
+    """Count separator cells immediately preceding the time-value block.
+
+    Walks ``row`` backwards from ``idx_col_start - 1``, incrementing on each
+    cell whose text matches a known separator label and stopping at the first
+    non-matching cell or NaN. A NaN cell signals the start of the index-column
+    placeholder zone in double-header layouts (where index labels live on the
+    other header row, leaving the date row blank under each index position).
+    """
+    n = 0
+    for i in range(idx_col_start - 1, -1, -1):
+        cell = row[i]
+        if cell is None or (isinstance(cell, float) and np.isnan(cell)):
+            break
+        text = str(cell).strip().lower()
+        if text in _SEPARATOR_LABELS:
+            n += 1
+            continue
+        break
+    return n
+
+
 class I90Book:
     """Represents an I90DIA workbook (XLS) with lazy sheet preprocessing.
 
@@ -221,6 +258,11 @@ class I90Sheet:
             return pd.DataFrame()
 
         columns_date = self._normalize_datetime_columns(columns_prior[idx_col_start:])
+        # _normalize_datetime_columns sets _n_columns_totals from the time-block
+        # content (NaN-filler vs sequential). Override with a header-label count
+        # so the index slice survives REE format revisions that add or drop a
+        # "Total" column without touching the time-axis encoding.
+        self._n_columns_totals = _count_header_separators(columns_prior, idx_col_start)
         columns_variable = columns[idx_col_start:]
         columns_index = columns[: idx_col_start - self._n_columns_totals]
 
@@ -230,6 +272,7 @@ class I90Sheet:
         self, idx_col_start: int, columns: np.ndarray
     ) -> tuple[np.ndarray, np.ndarray, np.ndarray, None]:
         columns_date = self._normalize_datetime_columns(columns[idx_col_start:])
+        self._n_columns_totals = _count_header_separators(columns, idx_col_start)
         columns_index = columns[: idx_col_start - self._n_columns_totals]
         return columns, columns_index, columns_date, None
 

{python_esios-2.3.0 → python_esios-2.4.1}/tests/conftest.py

@@ -26,12 +26,12 @@ def client(mock_httpx):
 
 @pytest.fixture
 def sample_indicator_response():
-    """Sample API response for GET /indicators/600."""
+    """Sample API response for GET /indicators/1001."""
     return {
         "indicator": {
-            "id": 600,
-            "name": "PVPC T. Defecto",
-            "short_name": "PVPC",
+            "id": 1001,
+            "name": "Término de facturación de energía activa del PVPC 2.0TD",
+            "short_name": "PVPC T. 2.0TD",
             "description": "<p>Precio voluntario para el pequeño consumidor</p>",
             "values": [
                 {
@@ -39,16 +39,16 @@ def sample_indicator_response():
                     "datetime": "2025-01-01T00:00:00.000+01:00",
                     "datetime_utc": "2024-12-31T23:00:00Z",
                     "tz_time": "2025-01-01T00:00:00.000+01:00",
-                    "geo_id": 3,
-                    "geo_name": "España",
+                    "geo_id": 8741,
+                    "geo_name": "Península",
                 },
                 {
                     "value": 115.3,
                     "datetime": "2025-01-01T01:00:00.000+01:00",
                     "datetime_utc": "2025-01-01T00:00:00Z",
                     "tz_time": "2025-01-01T01:00:00.000+01:00",
-                    "geo_id": 3,
-                    "geo_name": "España",
+                    "geo_id": 8741,
+                    "geo_name": "Península",
                 },
             ],
         }
@@ -61,10 +61,10 @@ def sample_indicators_list_response():
     return {
         "indicators": [
             {
-                "id": 600,
-                "name": "PVPC T. Defecto",
-                "short_name": "PVPC",
-                "description": "<p>Precio voluntario</p>",
+                "id": 1001,
+                "name": "Término de facturación de energía activa del PVPC 2.0TD",
+                "short_name": "PVPC T. 2.0TD",
+                "description": "<p>Precio voluntario para el pequeño consumidor</p>",
             },
             {
                 "id": 10034,

python_esios-2.4.1/tests/test_i90.py

@@ -0,0 +1,319 @@
+"""Tests for I90 file processing — frequency detection and column normalisation."""
+
+from __future__ import annotations
+
+from unittest.mock import MagicMock
+
+import numpy as np
+import pytest
+
+from esios.processing.i90 import (
+    I90Sheet,
+    _any_value_greater_than_30,
+    _count_header_separators,
+)
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+
+def _make_sheet() -> I90Sheet:
+    """Return a bare I90Sheet instance backed by mocked objects."""
+    wb = MagicMock()
+    sheet = MagicMock()
+    sheet.to_python.return_value = [[""]]
+    wb.get_sheet_by_name.return_value = sheet
+    return I90Sheet("test", wb, "I90DIA_20241001.xls", {})
+
+
+def _full_nan_filler_columns(n_hours: int = 24) -> np.ndarray:
+    """Build NaN-filler quarterly columns: [1, NaN, NaN, NaN, 2, NaN, …]."""
+    cols: list = []
+    for h in range(1, n_hours + 1):
+        cols.append(h)
+        cols.extend([np.nan, np.nan, np.nan])
+    return np.array(cols, dtype=object)
+
+
+def _full_hq_columns(n_hours: int = 24) -> np.ndarray:
+    """Build explicit H-Q columns: ['1-1', '1-2', '1-3', '1-4', '2-1', …]."""
+    return np.array(
+        [f"{h}-{q}" for h in range(1, n_hours + 1) for q in range(1, 5)],
+        dtype=object,
+    )
+
+
+def _mixed_hq_columns(n_hours: int = 24) -> np.ndarray:
+    """First quarter is unlabelled ('1', '2', …); rest carry '-Q' suffix."""
+    cols: list = []
+    for h in range(1, n_hours + 1):
+        cols.append(str(h))
+        for q in range(2, 5):
+            cols.append(f"{h}-{q}")
+    return np.array(cols, dtype=object)
+
+
+# ---------------------------------------------------------------------------
+# _any_value_greater_than_30
+# ---------------------------------------------------------------------------
+
+
+class TestAnyValueGreaterThan30:
+    def test_returns_true_for_value_above_30(self):
+        assert _any_value_greater_than_30(np.array([1, 31, 24])) is True
+
+    def test_returns_false_for_all_values_24_or_less(self):
+        assert _any_value_greater_than_30(np.arange(1, 25)) is False
+
+    def test_works_with_numpy_int64(self):
+        """numpy 2.x broke isinstance(np.int64, int) — make sure we handle it."""
+        arr = np.array([1, 2, 31, 96], dtype=np.int64)
+        assert _any_value_greater_than_30(arr) is True
+
+    def test_ignores_nan(self):
+        arr = np.array([np.nan, 5.0, 20.0])
+        assert _any_value_greater_than_30(arr) is False
+
+    def test_sequential_quarterly_1_to_96(self):
+        assert _any_value_greater_than_30(np.arange(1, 97)) is True
+
+
+# ---------------------------------------------------------------------------
+# _normalize_datetime_columns — hourly (unchanged behaviour)
+# ---------------------------------------------------------------------------
+
+
+class TestNormalizeHourly:
+    def test_sequential_1_to_24(self):
+        s = _make_sheet()
+        cols = np.array([float(i) for i in range(1, 25)], dtype=object)
+        result = s._normalize_datetime_columns(cols)
+        assert list(result) == list(range(1, 25))
+        assert not _any_value_greater_than_30(result)
+
+    def test_n_columns_totals_is_2_when_no_nan(self):
+        s = _make_sheet()
+        cols = np.array([float(i) for i in range(1, 25)], dtype=object)
+        s._normalize_datetime_columns(cols)
+        assert s._n_columns_totals == 2
+
+
+# ---------------------------------------------------------------------------
+# _normalize_datetime_columns — quarterly (new behaviour)
+# ---------------------------------------------------------------------------
+
+
+class TestNormalizeQuarterlySequential:
+    """Columns already in 1–96 sequential form (already worked before the fix)."""
+
+    def test_sequential_1_to_96(self):
+        s = _make_sheet()
+        cols = np.array([float(i) for i in range(1, 97)], dtype=object)
+        result = s._normalize_datetime_columns(cols)
+        assert list(result) == list(range(1, 97))
+        assert _any_value_greater_than_30(result)
+
+
+class TestNormalizeQuarterlyHQFormat:
+    """Columns in explicit 'H-Q' dash notation: '1-1', '1-2', …, '24-4'."""
+
+    def test_full_day_96_periods(self):
+        s = _make_sheet()
+        result = s._normalize_datetime_columns(_full_hq_columns())
+        assert len(result) == 96
+        assert list(result) == list(range(1, 97))
+        assert _any_value_greater_than_30(result)
+
+    def test_time_deltas_are_correct(self):
+        """period 1 → 0 min (00:00), period 96 → 1425 min (23:45)."""
+        s = _make_sheet()
+        result = s._normalize_datetime_columns(_full_hq_columns())
+        time_deltas = (result - 1) * 15
+        assert time_deltas[0] == 0
+        assert time_deltas[-1] == 1425
+
+    def test_mixed_hq_first_quarter_unlabelled(self):
+        """'1', '1-2', '1-3', '1-4', '2', '2-2', … is treated the same."""
+        s = _make_sheet()
+        result = s._normalize_datetime_columns(_mixed_hq_columns())
+        assert len(result) == 96
+        assert list(result) == list(range(1, 97))
+        assert _any_value_greater_than_30(result)
+
+    def test_n_columns_totals_is_2_for_explicit_hq(self):
+        s = _make_sheet()
+        s._normalize_datetime_columns(_full_hq_columns())
+        assert s._n_columns_totals == 2
+
+
+class TestNormalizeQuarterlyNaNFiller:
+    """Columns in NaN-filler form: [1, NaN, NaN, NaN, 2, NaN, …]."""
+
+    def test_full_day_96_periods(self):
+        s = _make_sheet()
+        result = s._normalize_datetime_columns(_full_nan_filler_columns())
+        assert len(result) == 96
+        assert list(result) == list(range(1, 97))
+        assert _any_value_greater_than_30(result)
+
+    def test_time_deltas_are_correct(self):
+        s = _make_sheet()
+        result = s._normalize_datetime_columns(_full_nan_filler_columns())
+        time_deltas = (result - 1) * 15
+        assert time_deltas[0] == 0
+        assert time_deltas[-1] == 1425
+
+    def test_n_columns_totals_is_3_when_nan_present(self):
+        s = _make_sheet()
+        s._normalize_datetime_columns(_full_nan_filler_columns())
+        assert s._n_columns_totals == 3
+
+
+# ---------------------------------------------------------------------------
+# _count_header_separators — header-label-based separator counting
+#
+# Headers below are calques of real REE I90 layouts. The counter walks back
+# from idx_col_start, counting cells whose text equals a known separator
+# label ('Cuarto de Hora del dia', 'Hora', 'Total', 'Indicadores', 'Hora del
+# dia'), stopping at the first non-matching cell or NaN.
+# ---------------------------------------------------------------------------
+
+
+class TestCountHeaderSeparators:
+    def test_returns_zero_when_no_separators(self):
+        """If the cell right before the time block is a real index column."""
+        row = np.array(["Redespacho", "Tipo", "1.0", "2.0"], dtype=object)
+        assert _count_header_separators(row, idx_col_start=2) == 0
+
+    def test_pre_mtu_rr_price_layout_returns_2(self):
+        """I90DIA11 jun-2025: [Redespacho, Tipo, Cuarto de Hora del dia, Total, 1, …]."""
+        row = np.array(
+            ["Redespacho", "Tipo", "Cuarto de Hora del dia", "Total", "1.0", "2.0"],
+            dtype=object,
+        )
+        assert _count_header_separators(row, idx_col_start=4) == 2
+
+    def test_post_mtu_rr_price_layout_returns_1(self):
+        """I90DIA11 nov-2025: 'Total' dropped → [Redespacho, Cuarto de Hora del dia, 1, …]."""
+        row = np.array(
+            ["Redespacho", "Cuarto de Hora del dia", "1.0", "2.0"],
+            dtype=object,
+        )
+        assert _count_header_separators(row, idx_col_start=2) == 1
+
+    def test_pre_2024_hourly_layout_returns_2(self):
+        """I90DIA08 2014: [Redespacho, Tipo, …, Signo de Energía, Hora, Total, 00-01, …]."""
+        row = np.array(
+            [
+                "Redespacho", "Tipo", "Sentido", "Unidad de Programación",
+                "Tipo Oferta", "Tipo cálculo", "Tipo Restricción",
+                "Signo de Energía", "Hora", "Total", "00-01", "01-02",
+            ],
+            dtype=object,
+        )
+        assert _count_header_separators(row, idx_col_start=10) == 2
+
+    def test_post_mtu_rtr_price_layout_returns_1(self):
+        """I90DIA10 nov-2025: 'Total' dropped + index reordered."""
+        row = np.array(
+            [
+                "Redespacho", "Sentido", "Unidad de Programación", "Tipo Oferta",
+                "Tipo cálculo", "Signo de Energía", "Cuarto de Hora del dia",
+                "1.0", "2.0",
+            ],
+            dtype=object,
+        )
+        assert _count_header_separators(row, idx_col_start=7) == 1
+
+    def test_double_index_date_row_with_nan_index_placeholders(self):
+        """Double-header layout (e.g. I90DIA30 jun-2025): the date row carries
+        the separator labels; positions under each real index column are NaN.
+        The counter must stop at the first NaN (= start of the index zone).
+        """
+        row = np.array(
+            [np.nan, np.nan, np.nan, np.nan,
+             "Cuarto de Hora del dia", "Total", "1.0", "2.0"],
+            dtype=object,
+        )
+        assert _count_header_separators(row, idx_col_start=6) == 2
+
+    def test_double_index_post_mtu_dropped_total(self):
+        """I90DIA30 nov-2025 (single-index path post-MTU)."""
+        row = np.array(
+            ["Redespacho", "Sentido", "Tipo QH",
+             "Cuarto de Hora del dia", "1.0", "2.0"],
+            dtype=object,
+        )
+        assert _count_header_separators(row, idx_col_start=4) == 1
+
+    def test_match_is_case_insensitive(self):
+        row = np.array(["Redespacho", "TOTAL", "1.0"], dtype=object)
+        assert _count_header_separators(row, idx_col_start=2) == 1
+
+    def test_match_is_whitespace_tolerant(self):
+        row = np.array(["Redespacho", "  Total  ", "1.0"], dtype=object)
+        assert _count_header_separators(row, idx_col_start=2) == 1
+
+    def test_indicadores_counts_as_separator(self):
+        """Variable-row layout: [Redespacho, Tipo, Indicadores, Precio Marginal …, …]."""
+        row = np.array(
+            ["Redespacho", "Tipo", "Indicadores", "Precio Marginal", "1.0"],
+            dtype=object,
+        )
+        # idx_col_start = 4 → walk back from i=3
+        # i=3 'Precio Marginal' is not a separator → stop, return 0
+        assert _count_header_separators(row, idx_col_start=4) == 0
+        # But when adjacent to time block it counts:
+        row2 = np.array(["Redespacho", "Tipo", "Indicadores", "1.0"], dtype=object)
+        assert _count_header_separators(row2, idx_col_start=3) == 1
+
+    def test_unknown_label_immediately_after_index_stops_counter(self):
+        """Non-separator labels do not get absorbed even when next to time block."""
+        row = np.array(["Redespacho", "Foo Bar", "1.0"], dtype=object)
+        assert _count_header_separators(row, idx_col_start=2) == 0
+
+    def test_empty_string_breaks_counter(self):
+        row = np.array(["Redespacho", "", "Total", "1.0"], dtype=object)
+        # i=2 'Total' → sep, i=1 '' → break → returns 1
+        assert _count_header_separators(row, idx_col_start=3) == 1
+
+
+# ---------------------------------------------------------------------------
+# _preprocess_*_index — verify the dynamic counter overrides the heuristic
+# from _normalize_datetime_columns when slicing the index portion.
+# ---------------------------------------------------------------------------
+
+
+class TestPreprocessOverrideIntegration:
+    def test_single_index_post_mtu_layout_keeps_redespacho_in_index(self):
+        """I90DIA11 nov-2025 regression: pre-fix this consumed 'Redespacho' as
+        a 'Total' placeholder and returned an empty DataFrame. Post-fix the
+        index slice keeps it.
+        """
+        s = _make_sheet()
+        # Plant a quarterly time block to match real shape (96 periods).
+        time_block = np.array([float(i) for i in range(1, 97)], dtype=object)
+        columns = np.concatenate([
+            np.array(["Redespacho", "Cuarto de Hora del dia"], dtype=object),
+            time_block,
+        ])
+        result = s._preprocess_single_index(idx_col_start=2, columns=columns)
+        _, columns_index, _, _ = result
+        assert list(columns_index) == ["Redespacho"]
+        assert s._n_columns_totals == 1
+
+    def test_single_index_pre_mtu_layout_still_drops_total(self):
+        """I90DIA11 jun-2025 (and 2014-2024): two separators (Cuarto/Hora + Total)."""
+        s = _make_sheet()
+        time_block = np.array([float(i) for i in range(1, 97)], dtype=object)
+        columns = np.concatenate([
+            np.array(["Redespacho", "Tipo", "Cuarto de Hora del dia", "Total"],
+                     dtype=object),
+            time_block,
+        ])
+        result = s._preprocess_single_index(idx_col_start=4, columns=columns)
+        _, columns_index, _, _ = result
+        assert list(columns_index) == ["Redespacho", "Tipo"]
+        assert s._n_columns_totals == 2

{python_esios-2.3.0 → python_esios-2.4.1}/tests/test_managers.py

@@ -20,7 +20,7 @@ class TestIndicatorsManager:
         df = client.indicators.list()
         assert isinstance(df, pd.DataFrame)
         assert len(df) == 3
-        assert "PVPC T. Defecto" in df["name"].values
+        assert "Término de facturación de energía activa del PVPC 2.0TD" in df["name"].values
 
     def test_search(self, client, mock_httpx, sample_indicators_list_response):
         response = MagicMock()
@@ -38,9 +38,9 @@ class TestIndicatorsManager:
         response.json.return_value = sample_indicator_response
         mock_httpx.get.return_value = response
 
-        handle = client.indicators.get(600)
-        assert handle.id == 600
-        assert handle.name == "PVPC T. Defecto"
+        handle = client.indicators.get(1001)
+        assert handle.id == 1001
+        assert handle.name == "Término de facturación de energía activa del PVPC 2.0TD"
 
     def test_historical_returns_dataframe(
         self, client, mock_httpx, sample_indicator_response
@@ -50,7 +50,7 @@ class TestIndicatorsManager:
         response.json.return_value = sample_indicator_response
         mock_httpx.get.return_value = response
 
-        handle = client.indicators.get(600)
+        handle = client.indicators.get(1001)
         df = handle.historical("2025-01-01", "2025-01-01")
         assert isinstance(df, pd.DataFrame)
         assert len(df) == 2
@@ -134,15 +134,15 @@ class TestIndicatorsCaching:
         mock_httpx.get.return_value = response
 
         # First call: hits API
-        handle1 = cached_client.indicators.get(600)
+        handle1 = cached_client.indicators.get(1001)
         assert mock_httpx.get.call_count == 1
-        assert handle1.id == 600
+        assert handle1.id == 1001
 
         # Second call: should use cached meta (no additional API call)
-        handle2 = cached_client.indicators.get(600)
+        handle2 = cached_client.indicators.get(1001)
         assert mock_httpx.get.call_count == 1  # No new API call
-        assert handle2.id == 600
-        assert handle2.name == "PVPC T. Defecto"
+        assert handle2.id == 1001
+        assert handle2.name == "Término de facturación de energía activa del PVPC 2.0TD"
 
     def test_get_persists_geos_to_registry(
         self, cached_client, mock_httpx,

{python_esios-2.3.0 → python_esios-2.4.1}/tests/test_models.py

@@ -8,13 +8,13 @@ from esios.models.offer_indicator import OfferIndicator
 class TestIndicator:
     def test_from_api(self):
         data = {
-            "id": 600,
+            "id": 1001,
             "name": "PVPC",
             "short_name": "PVPC",
             "description": "Precio voluntario",
         }
         ind = Indicator.from_api(data)
-        assert ind.id == 600
+        assert ind.id == 1001
         assert ind.name == "PVPC"
         assert ind.raw == data
 

python_esios-2.3.0/.release-please-manifest.json

@@ -1,3 +0,0 @@
-{
-  ".": "2.3.0"
-}

python_esios-2.3.0/src/esios/constants.py

@@ -1,20 +0,0 @@
-"""Constants for the ESIOS API client."""
-
-ESIOS_API_URL = "https://api.esios.ree.es"
-
-DEFAULT_HEADERS = {
-    "Accept": "application/json; application/vnd.esios-api-v1+json",
-    "Content-Type": "application/json",
-    "Host": "api.esios.ree.es",
-}
-
-DEFAULT_TIMEOUT = 30.0  # seconds
-
-MAX_RETRIES = 3
-RETRY_MIN_WAIT = 2  # seconds
-RETRY_MAX_WAIT = 10  # seconds
-
-# ESIOS API limits responses to ~3 weeks of data per request
-CHUNK_SIZE_DAYS = 21
-
-TIMEZONE = "Europe/Madrid"

python_esios-2.3.0/tests/test_i90.py

@@ -1,167 +0,0 @@
-"""Tests for I90 file processing — frequency detection and column normalisation."""
-
-from __future__ import annotations
-
-from unittest.mock import MagicMock
-
-import numpy as np
-import pytest
-
-from esios.processing.i90 import I90Sheet, _any_value_greater_than_30
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-
-def _make_sheet() -> I90Sheet:
-    """Return a bare I90Sheet instance backed by mocked objects."""
-    wb = MagicMock()
-    sheet = MagicMock()
-    sheet.to_python.return_value = [[""]]
-    wb.get_sheet_by_name.return_value = sheet
-    return I90Sheet("test", wb, "I90DIA_20241001.xls", {})
-
-
-def _full_nan_filler_columns(n_hours: int = 24) -> np.ndarray:
-    """Build NaN-filler quarterly columns: [1, NaN, NaN, NaN, 2, NaN, …]."""
-    cols: list = []
-    for h in range(1, n_hours + 1):
-        cols.append(h)
-        cols.extend([np.nan, np.nan, np.nan])
-    return np.array(cols, dtype=object)
-
-
-def _full_hq_columns(n_hours: int = 24) -> np.ndarray:
-    """Build explicit H-Q columns: ['1-1', '1-2', '1-3', '1-4', '2-1', …]."""
-    return np.array(
-        [f"{h}-{q}" for h in range(1, n_hours + 1) for q in range(1, 5)],
-        dtype=object,
-    )
-
-
-def _mixed_hq_columns(n_hours: int = 24) -> np.ndarray:
-    """First quarter is unlabelled ('1', '2', …); rest carry '-Q' suffix."""
-    cols: list = []
-    for h in range(1, n_hours + 1):
-        cols.append(str(h))
-        for q in range(2, 5):
-            cols.append(f"{h}-{q}")
-    return np.array(cols, dtype=object)
-
-
-# ---------------------------------------------------------------------------
-# _any_value_greater_than_30
-# ---------------------------------------------------------------------------
-
-
-class TestAnyValueGreaterThan30:
-    def test_returns_true_for_value_above_30(self):
-        assert _any_value_greater_than_30(np.array([1, 31, 24])) is True
-
-    def test_returns_false_for_all_values_24_or_less(self):
-        assert _any_value_greater_than_30(np.arange(1, 25)) is False
-
-    def test_works_with_numpy_int64(self):
-        """numpy 2.x broke isinstance(np.int64, int) — make sure we handle it."""
-        arr = np.array([1, 2, 31, 96], dtype=np.int64)
-        assert _any_value_greater_than_30(arr) is True
-
-    def test_ignores_nan(self):
-        arr = np.array([np.nan, 5.0, 20.0])
-        assert _any_value_greater_than_30(arr) is False
-
-    def test_sequential_quarterly_1_to_96(self):
-        assert _any_value_greater_than_30(np.arange(1, 97)) is True
-
-
-# ---------------------------------------------------------------------------
-# _normalize_datetime_columns — hourly (unchanged behaviour)
-# ---------------------------------------------------------------------------
-
-
-class TestNormalizeHourly:
-    def test_sequential_1_to_24(self):
-        s = _make_sheet()
-        cols = np.array([float(i) for i in range(1, 25)], dtype=object)
-        result = s._normalize_datetime_columns(cols)
-        assert list(result) == list(range(1, 25))
-        assert not _any_value_greater_than_30(result)
-
-    def test_n_columns_totals_is_2_when_no_nan(self):
-        s = _make_sheet()
-        cols = np.array([float(i) for i in range(1, 25)], dtype=object)
-        s._normalize_datetime_columns(cols)
-        assert s._n_columns_totals == 2
-
-
-# ---------------------------------------------------------------------------
-# _normalize_datetime_columns — quarterly (new behaviour)
-# ---------------------------------------------------------------------------
-
-
-class TestNormalizeQuarterlySequential:
-    """Columns already in 1–96 sequential form (already worked before the fix)."""
-
-    def test_sequential_1_to_96(self):
-        s = _make_sheet()
-        cols = np.array([float(i) for i in range(1, 97)], dtype=object)
-        result = s._normalize_datetime_columns(cols)
-        assert list(result) == list(range(1, 97))
-        assert _any_value_greater_than_30(result)
-
-
-class TestNormalizeQuarterlyHQFormat:
-    """Columns in explicit 'H-Q' dash notation: '1-1', '1-2', …, '24-4'."""
-
-    def test_full_day_96_periods(self):
-        s = _make_sheet()
-        result = s._normalize_datetime_columns(_full_hq_columns())
-        assert len(result) == 96
-        assert list(result) == list(range(1, 97))
-        assert _any_value_greater_than_30(result)
-
-    def test_time_deltas_are_correct(self):
-        """period 1 → 0 min (00:00), period 96 → 1425 min (23:45)."""
-        s = _make_sheet()
-        result = s._normalize_datetime_columns(_full_hq_columns())
-        time_deltas = (result - 1) * 15
-        assert time_deltas[0] == 0
-        assert time_deltas[-1] == 1425
-
-    def test_mixed_hq_first_quarter_unlabelled(self):
-        """'1', '1-2', '1-3', '1-4', '2', '2-2', … is treated the same."""
-        s = _make_sheet()
-        result = s._normalize_datetime_columns(_mixed_hq_columns())
-        assert len(result) == 96
-        assert list(result) == list(range(1, 97))
-        assert _any_value_greater_than_30(result)
-
-    def test_n_columns_totals_is_2_for_explicit_hq(self):
-        s = _make_sheet()
-        s._normalize_datetime_columns(_full_hq_columns())
-        assert s._n_columns_totals == 2
-
-
-class TestNormalizeQuarterlyNaNFiller:
-    """Columns in NaN-filler form: [1, NaN, NaN, NaN, 2, NaN, …]."""
-
-    def test_full_day_96_periods(self):
-        s = _make_sheet()
-        result = s._normalize_datetime_columns(_full_nan_filler_columns())
-        assert len(result) == 96
-        assert list(result) == list(range(1, 97))
-        assert _any_value_greater_than_30(result)
-
-    def test_time_deltas_are_correct(self):
-        s = _make_sheet()
-        result = s._normalize_datetime_columns(_full_nan_filler_columns())
-        time_deltas = (result - 1) * 15
-        assert time_deltas[0] == 0
-        assert time_deltas[-1] == 1425
-
-    def test_n_columns_totals_is_3_when_nan_present(self):
-        s = _make_sheet()
-        s._normalize_datetime_columns(_full_nan_filler_columns())
-        assert s._n_columns_totals == 3