Implement skip if file exists (#85)

g4brielvs · web-flow · commit ef390478dbfd · 2024-07-18T10:14:16.000-04:00
* Fix skip if exists

* Fix link

* Update README.md
diff --git a/README.md b/README.md
@@ -5,11 +5,11 @@
 [![docs](https://github.com/worldbank/blackmarblepy/actions/workflows/gh-pages.yml/badge.svg)](https://github.com/worldbank/blackmarblepy/actions/workflows/gh-pages.yml)
 [![tests](https://github.com/worldbank/blackmarblepy/actions/workflows/tests.yml/badge.svg)](https://github.com/worldbank/blackmarblepy/actions/workflows/tests.yml)
 [![pre-commit.ci status](https://results.pre-commit.ci/badge/github/worldbank/blackmarblepy/main.svg)](https://results.pre-commit.ci/latest/github/worldbank/blackmarblepy/main)
-[![downloads](https://static.pepy.tech/badge/blackmarblepy/month)](https://pepy.tech/project/blackmarblepy)
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.10667907.svg)](https://zenodo.org/doi/10.5281/zenodo.10667907)
+[![Downloads](https://static.pepy.tech/badge/blackmarblepy)](https://pepy.tech/project/blackmarblepy)
 [![GitHub Repo stars](https://img.shields.io/github/stars/worldbank/blackmarblepy)](https://github.com/worldbank/blackmarblepy)
 
-**BlackMarblePy** is a Python package that provides a simple way to use nighttime lights data from NASA's Black Marble project. [Black Marble](https://blackmarble.gsfc.nasa.gov) is a [NASA Earth Science Data Systems (ESDS)](https://www.earthdata.nasa.gov) project that provides a product suite of daily, monthly and yearly global [nighttime lights](https://www.earthdata.nasa.gov/learn/backgrounders/nighttime-lights). This package automates the process of downloading all relevant tiles from the [NASA LAADS DAAC](https://www.earthdata.nasa.gov/eosdis/daacs/laads) to cover a region of interest, converting the raw files (in HDF5 format), to georeferenced rasters, and mosaicing rasters together when needed.
+**BlackMarblePy** is a Python package that provides a simple way to use nighttime lights data from NASA's Black Marble project. [Black Marble](https://blackmarble.gsfc.nasa.gov) is a [NASA Earth Science Data Systems (ESDS)](https://www.earthdata.nasa.gov) project that provides a product suite of daily, monthly and yearly global [nighttime lights](https://www.earthdata.nasa.gov/learn/backgrounders/nighttime-lights). This package automates the process of downloading all relevant tiles from the [NASA LAADS DAAC](https://www.earthdata.nasa.gov/eosdis/daacs/laads) to cover a region of interest, converting the raw files (in HDF5 format), to georeferenced rasters, and mosaicking rasters together when needed.
 
 ## Features
 
@@ -140,7 +140,7 @@ Robert Marty
 
 ## Citation
 
-When using **BlackMarblePy**, your support is much appreciated! Please consider using the following citation or download [bibliography.bib](bibliography.bib):
+When using **BlackMarblePy**, your support is much appreciated! Please consider using the following citation or download [bibliography.bib](https://raw.githubusercontent.com/worldbank/blackmarblepy/main/docs/bibliography.bib):
 
 ```bibtex
 @misc{blackmarblepy,
diff --git a/notebooks/blackmarblepy.ipynb b/notebooks/blackmarblepy.ipynb
diff --git a/src/blackmarble/download.py b/src/blackmarble/download.py
@@ -134,6 +134,7 @@ async def get_manifest(
     def _download_file(
         self,
         name: str,
+        skip_if_exists: bool = True,
     ):
         """Download NASA Black Marble file
 
@@ -150,25 +151,25 @@ def _download_file(
         url = f"{self.URL}{name}"
         name = name.split("/")[-1]
 
-        with open(filename := Path(self.directory, name), "wb+") as f:
-            with httpx.stream(
-                "GET",
-                url,
-                headers={"Authorization": f"Bearer {self.bearer}"},
-            ) as response:
-                total = int(response.headers["Content-Length"])
-                with tqdm(
-                    total=total,
-                    unit="B",
-                    unit_scale=True,
-                    leave=None,
-                ) as pbar:
-                    pbar.set_description(f"Retrieving {name}...")
-                    for chunk in response.iter_raw():
-                        f.write(chunk)
-                        pbar.update(len(chunk))
-
-                return filename
+        if not (filename := Path(self.directory, name)).exists() or not skip_if_exists:
+            with open(filename, "wb+") as f:
+                with httpx.stream(
+                    "GET",
+                    url,
+                    headers={"Authorization": f"Bearer {self.bearer}"},
+                ) as response:
+                    total = int(response.headers["Content-Length"])
+                    with tqdm(
+                        total=total,
+                        unit="B",
+                        unit_scale=True,
+                        leave=None,
+                    ) as pbar:
+                        pbar.set_description(f"Downloading {name}...")
+                        for chunk in response.iter_raw():
+                            f.write(chunk)
+                            pbar.update(len(chunk))
+        return filename
 
     def download(
         self,
@@ -177,12 +178,13 @@ def download(
         date_range: List[datetime.date],
         skip_if_exists: bool = True,
     ):
-        """Download (in parallel) from NASA Black Marble archive
+        """
+        Downloads files asynchronously from NASA Black Marble archive.
 
         Parameters
         ----------
         gdf: geopandas.GeoDataFrame
-            Region of Interest
+             Region of Interest. Converted to EPSG:4326 and intersected with Black Mable tiles
 
         product: Product
             Nasa Black Marble Product Id (e.g, VNP46A1)
@@ -192,22 +194,32 @@ def download(
 
         skip_if_exists: bool, default=True
             Whether to skip downloading data if file already exists
+
+        Returns
+        -------
+        list: List[pathlib.Path]
+            List of downloaded H5 filenames.
         """
+        # Convert to EPSG:4326 and intersect with self.TILES
         gdf = geopandas.overlay(
             gdf.to_crs("EPSG:4326").dissolve(), self.TILES, how="intersection"
         )
 
+        # Fetch manifest data asynchronously
         bm_files_df = asyncio.run(self.get_manifest(gdf, product_id, date_range))
+
+        # Filter files to those intersecting with Black Marble tiles
         bm_files_df = bm_files_df[
             bm_files_df["name"].str.contains("|".join(gdf["TileID"]))
         ]
-        names = bm_files_df["fileURL"].tolist()
 
-        args = [(name,) for name in names]
+        # Prepare arguments for parallel download
+        names = bm_files_df["fileURL"].tolist()
+        args = [(name, skip_if_exists) for name in names]
         return pqdm(
             args,
             self._download_file,
-            n_jobs=16,
+            n_jobs=4,  # os.cpu_count(),
             argument_type="args",
             desc="Downloading...",
         )
diff --git a/src/blackmarble/extract.py b/src/blackmarble/extract.py
@@ -20,9 +20,8 @@ def bm_extract(
     variable: Optional[str] = None,
     drop_values_by_quality_flag: List[int] = [],
     check_all_tiles_exist: bool = True,
-    file_directory: Optional[Path] = None,
-    file_prefix: Optional[str] = None,
-    file_skip_if_exists: bool = True,
+    output_directory: Optional[Path] = None,
+    output_skip_if_exists: bool = True,
 ):
     """Extract and aggregate nighttime lights zonal statistics from `NASA Black Marble <https://blackmarble.gsfc.nasa.gov>`_.
 
@@ -76,13 +75,10 @@ def bm_extract(
     check_all_tiles_exist: bool, default=True
         Check whether all Black Marble nighttime light tiles exist for the region of interest. Sometimes not all tiles are available, so the full region of interest may not be covered. By default (True), it skips cases where not all tiles are available.
 
-    file_directory: pathlib.Path, optional
-        Where to produce output. By default, the output will be produced onto a temporary directory.
+    output_directory: pathlib.Path, optional
+        Directory to produce output. By default, the output will be produced onto a temporary directory.
 
-    file_directory_prefix: str, optional
-        Prefix
-
-    file_skip_if_exists: bool, default=True
+    outout_skip_if_exists: bool, default=True
         Whether to skip downloading or extracting data if the data file for that date already exists.
 
      bearer
@@ -102,9 +98,8 @@ def bm_extract(
         variable,
         drop_values_by_quality_flag,
         check_all_tiles_exist,
-        file_directory,
-        file_prefix,
-        file_skip_if_exists,
+        output_directory,
+        output_skip_if_exists,
     )
 
     results = []
diff --git a/src/blackmarble/raster.py b/src/blackmarble/raster.py
@@ -140,7 +140,6 @@ def h5_to_geotiff(
     variable: str = None,
     drop_values_by_quality_flag: List[int] = [255],
     output_directory: Path = None,
-    output_prefix: str = None,
 ):
     """
     Convert HDF5 file to GeoTIFF for a selected (or default) variable from NASA Black Marble data
@@ -164,9 +163,6 @@ def h5_to_geotiff(
     output_directory : Path, optional
         Directory to save the output GeoTIFF file. If None, uses the same directory as input file.
 
-    output_prefix : str, optional
-        Prefix for the output file name. If None, uses the input file name.
-
     Returns
     ------
     output_path: Path
@@ -265,9 +261,8 @@ def bm_raster(
     variable: Optional[str] = None,
     drop_values_by_quality_flag: List[int] = [],
     check_all_tiles_exist: bool = True,
-    file_directory: Optional[Path] = None,
-    file_prefix: Optional[str] = None,
-    file_skip_if_exists: bool = True,
+    output_directory: Optional[Path] = None,
+    output_skip_if_exists: bool = True,
 ):
     """Create a stack of nighttime lights rasters by retrieiving from `NASA Black Marble <https://blackmarble.gsfc.nasa.gov>`_ data.
 
@@ -318,13 +313,10 @@ def bm_raster(
     check_all_tiles_exist: bool, default=True
         Check whether all Black Marble nighttime light tiles exist for the region of interest. Sometimes not all tiles are available, so the full region of interest may not be covered. By default (True), it skips cases where not all tiles are available.
 
-    file_directory: pathlib.Path, optional
-        Where to produce output. By default, the output will be produced onto a temporary directory.
-
-    file_prefix: str, optional
-        Prefix
+    output_directory: pathlib.Path, optional
+        Directory to produce output. By default, the output will be produced onto a temporary directory.
 
-    file_skip_if_exists: bool, default=True
+    output_skip_if_exists: bool, default=True
         Whether to skip downloading or extracting data if the data file for that date already exists.
 
     Returns
@@ -348,9 +340,11 @@ def bm_raster(
             date_range = sorted(set([d.replace(day=1, month=1) for d in date_range]))
 
     # Download and construct Dataset
-    with file_directory if file_directory else tempfile.TemporaryDirectory() as d:
+    with output_directory if output_directory else tempfile.TemporaryDirectory() as d:
         downloader = BlackMarbleDownloader(bearer, d)
-        pathnames = downloader.download(gdf, product_id, date_range)
+        pathnames = downloader.download(
+            gdf, product_id, date_range, output_skip_if_exists
+        )
 
         datasets = []
         for date in tqdm(date_range, desc="COLLATING RESULTS | Processing..."):
@@ -364,7 +358,6 @@ def bm_raster(
                             f,
                             variable=variable,
                             drop_values_by_quality_flag=drop_values_by_quality_flag,
-                            output_prefix=file_prefix,
                             output_directory=d,
                         ),
                     )
