cubexpress 0.1.8__tar.gz → 0.1.9__tar.gz

{cubexpress-0.1.8 → cubexpress-0.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cubexpress
-Version: 0.1.8
+Version: 0.1.9
 Summary: Efficient processing of cubic Earth-observation (EO) data.
 Home-page: https://github.com/andesdatacube/cubexpress
 License: MIT

{cubexpress-0.1.8 → cubexpress-0.1.9}/cubexpress/__init__.py

@@ -1,6 +1,6 @@
 from cubexpress.conversion import lonlat2rt, geo2utm
 from cubexpress.geotyping import RasterTransform, Request, RequestSet
-from cubexpress.cloud_utils import cloud_table
+from cubexpress.cloud_utils import s2_cloud_table
 from cubexpress.cube import get_cube
 from cubexpress.request import table_to_requestset
 
@@ -15,7 +15,7 @@ __all__ = [
     "RequestSet",
     "geo2utm",
     "get_cube",
-    "cloud_table",
+    "s2_cloud_table",
     "table_to_requestset"
 ]
 

{cubexpress-0.1.8 → cubexpress-0.1.9}/cubexpress/cloud_utils.py

@@ -27,25 +27,30 @@ def _cloud_table_single_range(
     start: str,
     end: str
 ) -> pd.DataFrame:
-    """Return raw cloud-table rows for a single *start–end* interval.
+    """
+    Build a daily cloud-score table for a square Sentinel-2 footprint.
 
     Parameters
     ----------
-    lon, lat
-        Centre coordinates in decimal degrees.
-    edge_size, scale
-        ROI size in pixels (*edge_size*) and pixel resolution in metres
-        (*scale*), fed into :pyfunc:`cubexpress.geospatial._square_roi`.
-    start, end
-        ISO-dates (``YYYY-MM-DD``) delimiting the query.
-    collection
-        Sentinel-2 collection name to query.
+    lon, lat : float
+        Point at the centre of the requested region (°).
+    edge_size : int
+        Side length of the square region in Sentinel-2 pixels (10 m each).
+    start, end : str
+        ISO-8601 dates delimiting the period, e.g. ``"2024-06-01"``.
 
     Returns
     -------
     pandas.DataFrame
-        Columns: **day** (str), **cloudPct** (float), **images** (str
-        concatenation of asset IDs separated by ``-``). No filtering applied.
+        One row per image with columns:
+        * ``id`` – Sentinel-2 ID
+        * ``cs_cdf`` – Cloud Score Plus CDF (0–1)
+        * ``date`` – acquisition date (YYYY-MM-DD)
+        * ``high_null_flag`` – 1 if cloud score missing
+
+    Notes
+    -----
+    Missing ``cs_cdf`` values are filled with the mean of the same day.
     """
 
     center = ee.Geometry.Point([lon, lat])
@@ -64,6 +69,8 @@ def _cloud_table_single_range(
         .linkCollection(csp, ["cs_cdf"])
         .select(["cs_cdf"])
     )
+
+    # image IDs for every expected date
     ids = ic.aggregate_array("system:index").getInfo()
     df_ids = pd.DataFrame({"id": ids})
 
@@ -93,6 +100,7 @@ def _cloud_table_single_range(
         .drop(columns=["longitude", "latitude", "time"])
     )
 
+    # fill missing scores with daily mean
     df["cs_cdf"] = df["cs_cdf"].fillna(df.groupby("date")["cs_cdf"].transform("mean"))
 
     return df
@@ -101,11 +109,12 @@ def _cloud_table_single_range(
 def s2_cloud_table(
     lon: float,
     lat: float,
-    edge_size: int = 2048,
-    start: str = "2017-01-01",
-    end: str = "2024-12-31",
-    cscore: float = 0.5,
-    cache: bool = True,
+    edge_size: int,
+    start: str,
+    end: str,
+    max_cscore: float = 1.0,
+    min_cscore: float = 0.0,
+    cache: bool = False,
     verbose: bool = True,
 ) -> pd.DataFrame:
     """Build (and cache) a per-day cloud-table for the requested ROI.
@@ -206,7 +215,7 @@ def s2_cloud_table(
     
     result = (
         df_full.query("@start <= date <= @end")
-        .query("cs_cdf > @cscore")
+        .query("@min_cscore <= cs_cdf <= @max_cscore")
         .reset_index(drop=True)
     )
 
@@ -221,4 +230,4 @@ def s2_cloud_table(
             "collection": collection
         }
     )
-    return result
+    return result

{cubexpress-0.1.8 → cubexpress-0.1.9}/cubexpress/cube.py

@@ -16,17 +16,22 @@ from __future__ import annotations
 import pathlib
 import concurrent.futures
 from typing import Dict, Any
-
 import ee
+
+
 from cubexpress.downloader import download_manifest, download_manifests
 from cubexpress.geospatial import quadsplit_manifest, calculate_cell_size
-from cubexpress.geotyping import RequestSet
+from cubexpress.request import table_to_requestset
+import pandas as pd
 
 
 def get_geotiff(
     manifest: Dict[str, Any],
     full_outname: pathlib.Path | str,
+    join: bool = True,
+    eraser: bool = True,
     nworks: int = 4,
+    verbose: bool = True,
 ) -> None:
     """Download *manifest* to *full_outname*, retrying with tiled requests.
 
@@ -39,19 +44,26 @@ def get_geotiff(
     nworks
         Maximum worker threads when the image must be split; default **4**.
     """
+    full_outname = pathlib.Path(full_outname)
     try:
-        download_manifest(manifest, pathlib.Path(full_outname))
+        download_manifest(manifest, full_outname)
     except ee.ee_exception.EEException as err:
-        # Handle EE “too many pixels” error by recursive tiling.
+
         size = manifest["grid"]["dimensions"]["width"]  # square images assumed
         cell_w, cell_h, power = calculate_cell_size(str(err), size)
         tiled = quadsplit_manifest(manifest, cell_w, cell_h, power)
-        download_manifests(tiled, max_workers=nworks, full_outname=pathlib.Path(full_outname))
+        download_manifests(tiled, full_outname, join, eraser, nworks)
+
+    if verbose:
+        print(f"Downloaded {full_outname}")
 
 
 def get_cube(
-    requests: RequestSet,
+    table: pd.DataFrame,
     outfolder: pathlib.Path | str,
+    join: bool = True,
+    eraser: bool = True,
+    mosaic: bool = True,
     nworks: int = 4,
 ) -> None:
     """Download every request in *requests* to *outfolder* using a thread pool.
@@ -68,14 +80,18 @@ def get_cube(
     nworks
         Pool size for concurrent downloads; default **4**.
     """
-    out = pathlib.Path(outfolder)
+
+    requests = table_to_requestset(
+        table=table, 
+        mosaic=mosaic
+    )
 
     with concurrent.futures.ThreadPoolExecutor(max_workers=nworks) as pool:
         futures = []
         for _, row in requests._dataframe.iterrows():
-            outname = out / f"{row.id}.tif"
+            outname = pathlib.Path(outfolder) / f"{row.id}.tif"
             outname.parent.mkdir(parents=True, exist_ok=True)
-            futures.append(pool.submit(get_geotiff, row.manifest, outname, nworks))
+            futures.append(pool.submit(get_geotiff, row.manifest, outname, join, eraser, nworks))
 
         for fut in concurrent.futures.as_completed(futures):
             try:

{cubexpress-0.1.8 → cubexpress-0.1.9}/cubexpress/downloader.py

@@ -21,7 +21,10 @@ import ee
 import rasterio as rio
 from rasterio.io import MemoryFile
 import logging
+from rasterio.merge import merge
+from rasterio.enums import Resampling
 import os
+import shutil
 
 os.environ['CPL_LOG_ERRORS'] = 'OFF'
 logging.getLogger('rasterio._env').setLevel(logging.ERROR)
@@ -53,7 +56,7 @@ def download_manifest(ulist: Dict[str, Any], full_outname: pathlib.Path) -> None
                 blockxsize=256,
                 blockysize=256,
                 compress="ZSTD",
-                zstd_level=13,
+                # zstd_level=13,
                 predictor=2,
                 num_threads=20,
                 nodata=65535,
@@ -65,13 +68,12 @@ def download_manifest(ulist: Dict[str, Any], full_outname: pathlib.Path) -> None
             with rio.open(full_outname, "w", **profile) as dst:
                 dst.write(src.read())
 
-    print(f"{full_outname} downloaded successfully.")  # noqa: T201
-
-
 def download_manifests(
     manifests: List[Dict[str, Any]],
-    max_workers: int,
     full_outname: pathlib.Path,
+    join: bool = True,
+    eraser: bool = True,
+    max_workers: int = 4,
 ) -> None:
     """Download every manifest in *manifests* concurrently.
 
@@ -93,3 +95,41 @@ def download_manifests(
                 fut.result()
             except Exception as exc:  # noqa: BLE001
                 print(f"Error en una de las descargas: {exc}")  # noqa: T201
+    
+    if join:
+
+        dir_path = full_outname.parent / full_outname.stem
+        input_files = sorted(dir_path.glob("*.tif"))
+
+        if dir_path.exists() and len(input_files) > 1:
+
+            with rio.Env(GDAL_NUM_THREADS="8", NUM_THREADS="8"):
+                srcs = [rio.open(fp) for fp in input_files]
+                mosaic, out_transform = merge(
+                    srcs,
+                    nodata=65535,
+                    resampling=Resampling.nearest
+                )
+
+                meta = srcs[0].profile.copy()
+                meta["transform"] = out_transform
+                meta.update(
+                    height=mosaic.shape[1],
+                    width=mosaic.shape[2]
+                )
+
+                with rio.open(full_outname, "w", **meta) as dst:
+                    dst.write(mosaic)
+
+                for src in srcs:
+                    src.close()
+
+            if eraser:
+                # Delete a folder with pathlib
+                shutil.rmtree(dir_path) 
+
+            print("✅ Mosaico generado:", full_outname)
+            return full_outname
+
+        else:
+            return full_outname

{cubexpress-0.1.8 → cubexpress-0.1.9}/cubexpress/geotyping.py

@@ -482,7 +482,7 @@ class RequestSet(BaseModel):
             str: A string representation of the entire RasterTransformSet.
         """
         num_entries = len(self.requestset)
-        return f"RasterTransformSet({num_entries} entries)"
+        return f"RequestSet({num_entries} entries)"
 
     def __str__(self):
         return super().__repr__()

{cubexpress-0.1.8 → cubexpress-0.1.9}/cubexpress/request.py

@@ -5,13 +5,15 @@ from __future__ import annotations
 import ee
 import pandas as pd
 import pygeohash as pgh
-from typing import List
 
 from cubexpress.geotyping import Request, RequestSet
 from cubexpress.conversion import lonlat2rt
 
 
-def table_to_requestset(df: pd.DataFrame, *, mosaic: bool = True) -> RequestSet:
+def table_to_requestset(
+        table: pd.DataFrame, 
+        mosaic: bool = True
+    ) -> RequestSet:
     """Return a :class:`RequestSet` built from *df* (cloud_table result).
 
     Parameters
@@ -31,30 +33,30 @@ def table_to_requestset(df: pd.DataFrame, *, mosaic: bool = True) -> RequestSet:
     """
 
 
-    df_ = df.copy()
+    df = table.copy()
 
-    if df_.empty:
+    if df.empty:
         raise ValueError("cloud_table returned no rows; nothing to request.")
 
     rt = lonlat2rt(
-        lon=df_.attrs["lon"],
-        lat=df_.attrs["lat"],
-        edge_size=df_.attrs["edge_size"],
-        scale=df_.attrs["scale"],
+        lon=df.attrs["lon"],
+        lat=df.attrs["lat"],
+        edge_size=df.attrs["edge_size"],
+        scale=df.attrs["scale"],
     )
-    centre_hash = pgh.encode(df_.attrs["lat"], df_.attrs["lon"], precision=5)
+    centre_hash = pgh.encode(df.attrs["lat"], df.attrs["lon"], precision=5)
     reqs: list[Request] = []
 
     if mosaic:
         # group all asset IDs per day
         grouped = (
-            df_.groupby("date")["id"]   # Series con listas de ids por día
+            df.groupby("date")["id"]   # Series con listas de ids por día
             .apply(list)
         )
 
         for day, img_ids in grouped.items():
             ee_img = ee.ImageCollection(
-                [ee.Image(f"{df_.attrs['collection']}/{img}") for img in img_ids]
+                [ee.Image(f"{df.attrs['collection']}/{img}") for img in img_ids]
             ).mosaic()
 
             reqs.append(
@@ -62,11 +64,11 @@ def table_to_requestset(df: pd.DataFrame, *, mosaic: bool = True) -> RequestSet:
                     id=f"{day}_{centre_hash}",
                     raster_transform=rt,
                     image=ee_img,
-                    bands=df_.attrs["bands"],
+                    bands=df.attrs["bands"],
                 )
             )
     else:  # one request per asset
-        for _, row in df_.iterrows():
+        for _, row in df.iterrows():
             img_id = row["id"]
             day    = row["date"]
 
@@ -74,8 +76,8 @@ def table_to_requestset(df: pd.DataFrame, *, mosaic: bool = True) -> RequestSet:
                 Request(
                     id=f"{day}_{centre_hash}_{img_id}",
                     raster_transform=rt,
-                    image=f"{df_.attrs['collection']}/{img_id}",
-                    bands=df_.attrs["bands"],
+                    image=f"{df.attrs['collection']}/{img_id}",
+                    bands=df.attrs["bands"],
                 )
             )
 

{cubexpress-0.1.8 → cubexpress-0.1.9}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name        = "cubexpress"
-version     = "0.1.8"
+version     = "0.1.9"
 description = "Efficient processing of cubic Earth-observation (EO) data."
 authors     = [
   "Julio Contreras <contrerasnetk@gmail.com>",