goesgcp 2.0.1__py3-none-any.whl → 2.0.3__py3-none-any.whl

goesgcp/main.py

@@ -13,6 +13,9 @@ from datetime import datetime, timedelta, timezone
 from pyproj import CRS, Transformer
 from google.api_core.exceptions import GoogleAPIError
 
+import warnings
+warnings.filterwarnings('ignore')
+
 
 def list_blobs(connection, bucket_name, prefix):
     """
@@ -31,7 +34,7 @@ def get_directory_prefix(year, julian_day, hour):
 
 
 def get_files_period(connection, bucket_name, base_prefix, pattern, 
-                     start, end, bt_hour=[0, 23], bt_min=[0, 60], freq='10 min'):
+                     start, end, bt_hour=[], bt_min=[], freq=None):
     """
     Fetches files from a GCP bucket within a specified time period and returns them as a DataFrame.
 
@@ -54,11 +57,11 @@ def get_files_period(connection, bucket_name, base_prefix, pattern,
     files_metadata = []
 
     # Generate the list of dates from start to end
-    current_time = start
-    while current_time < end:
-        year = current_time.year
-        julian_day = str(current_time.timetuple().tm_yday).zfill(3)  # Julian day
-        hour = current_time.hour
+    temp = start
+    while temp <= end:
+        year = temp.year
+        julian_day = str(temp.timetuple().tm_yday).zfill(3)  # Julian day
+        hour = temp.hour
 
         # Generate the directory prefix
         prefix = f"{base_prefix}/{get_directory_prefix(year, julian_day, hour)}"
@@ -71,38 +74,42 @@ def get_files_period(connection, bucket_name, base_prefix, pattern,
             if pattern in blob.name:
                 files_metadata.append({
                     'file_name': blob.name,
-                    'last_modified': blob.updated
                 })
 
         # Move to the next hour
-        current_time += timedelta(hours=1)
+        temp += timedelta(hours=1)
 
     # Create a DataFrame from the list of files
     df = pd.DataFrame(files_metadata)
 
     if df.empty:
-        print("No files found matching the pattern.")
-        return pd.DataFrame()
+        print("No files found matching the pattern and time range.")
+        print(prefix)
+        sys.exit(1)
     
+    # Transform file_name to datetime
+    df['last_modified'] = pd.to_datetime(df['file_name'].str.extract(r'(\d{4}\d{3}\d{2}\d{2})').squeeze(), format='%Y%j%H%M')
+
     # Ensure 'last_modified' is in the correct datetime format without timezone
-    df['last_modified'] = pd.to_datetime(df['last_modified']).dt.tz_localize(None)
-    start = pd.to_datetime(start).tz_localize(None)
-    end = pd.to_datetime(end).tz_localize(None)
-    
-    # Filter the DataFrame based on the date range
-    df = df[(df['last_modified'] >= start) & (df['last_modified'] < end)]
+    df['last_modified'] = pd.to_datetime(df['last_modified']).dt.tz_localize('UTC')
+
+    # Filter the DataFrame based on the date range (inclusive)
+    df = df[(df['last_modified'] >= start) & (df['last_modified'] <= end)]
 
     # Filter the DataFrame based on the hour range
-    df['hour'] = df['last_modified'].dt.hour
-    df = df[(df['hour'] >= bt_hour[0]) & (df['hour'] <= bt_hour[1])]
+    if len(bt_hour) > 1:
+        df['hour'] = df['last_modified'].dt.hour
+        df = df[(df['hour'] >= bt_hour[0]) & (df['hour'] <= bt_hour[1])]
 
     # Filter the DataFrame based on the minute range
-    df['minute'] = df['last_modified'].dt.minute
-    df = df[(df['minute'] >= bt_min[0]) & (df['minute'] <= bt_min[1])]
+    if len(bt_min) > 1:
+        df['minute'] = df['last_modified'].dt.minute
+        df = df[(df['minute'] >= bt_min[0]) & (df['minute'] <= bt_min[1])]
 
     # Filter the DataFrame based on the frequency
-    df['freq'] = df['last_modified'].dt.floor(freq)
-    df = df.groupby('freq').first().reset_index()
+    if freq is not None:
+        df['freq'] = df['last_modified'].dt.floor(freq)
+        df = df.groupby('freq').first().reset_index()
 
     return df['file_name'].tolist()
 
@@ -135,7 +142,7 @@ def get_recent_files(connection, bucket_name, base_prefix, pattern, min_files):
 
         # Filter blobs based on the pattern
         for blob in blobs:
-            if pattern in blob.name:  # You can use "re" here for more complex patterns
+            if pattern in blob.name:
                 files.append((blob.name, blob.updated))
 
         # Go back one hour
@@ -153,13 +160,22 @@ def crop_reproject(args):
     Crops and reprojects a GOES-16 file to EPSG:4326.
     """
 
-    file, output = args
+    file, output, var_name, lat_min, lat_max, lon_min, lon_max, resolution, save_format = args
 
     # Open the file
     ds = xr.open_dataset(file, engine="netcdf4")
 
+    if var_name is None:
+        # Get all variables are 2D
+        var_names = [var for var in ds.data_vars if len(ds[var].dims) == 2]
+
+        # Remove DQF variables
+        var_names = [var for var in var_names if 'DQF' not in var]
+    else:
+        var_names = [var_name]
+
     # Select only var_name and goes_imager_projection
-    ds = ds[[var_name, "goes_imager_projection"]]
+    ds = ds[var_names + ["goes_imager_projection"]]
 
     # Get projection
     sat_height = ds["goes_imager_projection"].attrs["perspective_point_height"]
@@ -208,24 +224,27 @@ def crop_reproject(args):
     except:
         pass
 
-    # Reproject to EPSG:4326
-    ds = ds.rio.reproject("EPSG:4326", resolution=resolution)
-
-    # Rename lat/lon coordinates
-    ds = ds.rename({"x": "lon", "y": "lat"})
+    try:
+        # Reproject to EPSG:4326
+        ds = ds.rio.reproject("EPSG:4326", resolution=resolution)
 
-    # Add resolution to attributes
-    ds[var_name].attrs['resolution'] = "x={:.2f} y={:.2f} degree".format(resolution, resolution) 
+        # Rename lat/lon coordinates
+        ds = ds.rename({"x": "lon", "y": "lat"})
 
-    # Crop using lat/lon coordinates, in parallel
-    ds = ds.rio.clip_box(minx=lon_min, miny=lat_min, maxx=lon_max, maxy=lat_max)
+        # Add resolution to attributes
+        for var in var_names:
+            ds[var].attrs['resolution'] = "x={:.2f} y={:.2f} degree".format(resolution, resolution)
+            ds[var].attrs['comments'] = 'Cropped and reprojected to EPSG:4326 by goesgcp'
 
-    # Add comments
-    ds[var_name].attrs['comments'] = 'Cropped and reprojected to EPSG:4326 by goesgcp'
+        # Crop using lat/lon coordinates, in parallel
+        ds = ds.rio.clip_box(minx=lon_min, miny=lat_min, maxx=lon_max, maxy=lat_max)
 
-    # Add global metadata comments
-    ds.attrs['comments'] = "Data processed by goesgcp, author: Helvecio B. L. Neto (helvecioblneto@gmail.com)"
-        
+        # Add global metadata comments
+        ds.attrs['comments'] = "Data processed by goesgcp, author: Helvecio B. L. Neto (helvecioblneto@gmail.com)"
+    except Exception as e:
+        print(f"Error processing file {file}: {e}")
+        pass    
+    
     if save_format == 'by_date':
         file_datetime = datetime.strptime(ds.time_coverage_start, 
                                           "%Y-%m-%dT%H:%M:%S.%fZ")
@@ -241,28 +260,27 @@ def crop_reproject(args):
         output_directory = f"{output}{year}/{julian_day}/"
     else:
         output_directory = output
+        
 
     # Create the output directory
     pathlib.Path(output_directory).mkdir(parents=True, exist_ok=True)
 
     # Save the file
     output_file = f"{output_directory}{file.split('/')[-1]}"
-    ds.to_netcdf(output_file, mode='w', format='NETCDF4_CLASSIC')
+    ds.to_netcdf(output_file, mode='w')
 
-    # Fechar o dataset
     ds.close()
-    return
 
 
 def process_file(args):
-    """ Downloads and processes a file in parallel. """
-
-    bucket_name, blob_name, local_path = args
+    """
+    Downloads and processes a GOES-16 file.
+    """
+    
+    bucket_name, blob_name, local_path, output_path, var_name, lat_min, lat_max, lon_min, lon_max, resolution, \
+    save_format, retries = args
 
-    # Download options
-    retries = 5
     attempt = 0
-
     while attempt < retries:
         try:
             # Connect to the bucket
@@ -282,31 +300,28 @@ def process_file(args):
                     log_file.write(f"Failed to download {blob_name} after {retries} attempts. Error: {e}\n")
 
     # Crop the file
-    crop_reproject((local_path, output_path))
+    crop_reproject((local_path, output_path, var_name, lat_min, lat_max, lon_min, lon_max, resolution, save_format))
 
     # Remove the local file
     pathlib.Path(local_path).unlink()
 
+# Create connection
+storage_client = storage.Client.create_anonymous_client()
 
 def main():
     ''' Main function to download and process GOES-16 files. '''
 
-
-    global output_path, var_name, \
-          lat_min, lat_max, lon_min, lon_max, \
-          max_attempts, parallel, recent, resolution, storage_client, \
-            satellite, product, op_mode, channel, save_format
-
     epilog = """
     Example usage:
     
-    - To download recent 3 files from the GOES-16 satellite for the ABI-L2-CMIPF product:
+    - To download recent 3 files from the GOES-16 satellite for the ABI-L2-CMIPF product,
+    change resolution to 0.045, and crop the files between latitudes -35 and 5 and longitudes -80 and -30:
 
-    goesgcp --satellite goes16 --product ABI-L2-CMIP --recent 3
+    goesgcp --satellite goes-16 --product ABI-L2-CMIPF --recent 3 --resolution 0.045 --lat_min -35 --lat_max 5 --lon_min -80 --lon_max -30
 
     - To download files from the GOES-16 satellite for the ABI-L2-CMIPF product between 2022-12-15 and 2022-12-20:
 
-    goesgcp --start '2022-12-15 00:00:00' --end '2022-12-20 10:00:00' --bt_hour 5 6 --save_format by_date --resolution 0.045 --lat_min -35 --lat_max 5 --lon_min -80 --lon_max -30
+    goesgcp --satellite goes-16 --product ABI-L2-CMIPF --start '2022-12-15 09:00:00' --end '2022-12-15 09:50:00' --resolution 0.045 --lat_min -35 --lat_max 5 --lon_min -80 --lon_max -30
 
     """
 
@@ -329,16 +344,16 @@ def main():
     ]
 
     # Set arguments
-    parser = argparse.ArgumentParser(description='Converts GOES-16 L2 data to netCDF',
+    parser = argparse.ArgumentParser(description='Download and process GOES Satellite data files from GCP.',
                                     epilog=epilog,
                                     formatter_class=argparse.RawDescriptionHelpFormatter)
     
     # Satellite and product settings
     parser.add_argument('--satellite', type=str, default='goes-16', choices=['goes-16', 'goes-18'], help='Name of the satellite (e.g., goes16)')
-    parser.add_argument('--product', type=str, default='ABI-L2-CMIP', help='Name of the satellite product', choices=product_names)
-    parser.add_argument('--var_name', type=str, default='CMI', help='Variable name to extract (e.g., CMI)')
+    parser.add_argument('--product', type=str, default='ABI-L2-CMIPF', help='Name of the satellite product', choices=product_names)
+    parser.add_argument('--var_name', type=str, default=None, help='Variable name to extract (e.g., CMI)')
     parser.add_argument('--channel', type=int, default=13, help='Channel to use (e.g., 13)')
-    parser.add_argument('--op_mode', type=str, default='M6C', help='Operational mode to use (e.g., M6C)')
+    parser.add_argument('--op_mode', type=str, default='M6', help='Operational mode to use (e.g., M6C)')
 
     # Recent files settings
     parser.add_argument('--recent', type=int, help='Number of recent files to download (e.g., 3)')
@@ -378,7 +393,7 @@ def main():
     satellite = args.satellite
     product = args.product
     op_mode = args.op_mode
-    channel = str(args.channel).zfill(2)
+    channel = args.channel
     var_name = args.var_name
     lat_min = args.lat_min
     lat_max = args.lat_max
@@ -407,9 +422,6 @@ def main():
     # Create output directory
     pathlib.Path(output_path).mkdir(parents=True, exist_ok=True)
 
-    # Create connection
-    storage_client = storage.Client.create_anonymous_client()
-
     # Check if the bucket exists
     try:
         storage_client.get_bucket(bucket_name)
@@ -417,6 +429,13 @@ def main():
         print(f"Bucket {bucket_name} not found. Exiting...")
         sys.exit(1)
 
+    # Check if the channel exists
+    if not channel:
+        channel = ''
+    else:
+        channel = str(channel).zfill(2)
+        channel = f"C{channel}"
+
     # Set pattern for the files
     pattern = "OR_"+product+"-"+op_mode+channel+"_G" + satellite[-2:]
 
@@ -445,7 +464,9 @@ def main():
     
     if parallel: # Run in parallel
         # Create a list of tasks
-        tasks = [(bucket_name, file, f"tmp/{file.split('/')[-1]}") for file in files_list]
+        tasks = [(bucket_name, file, f"tmp/{file.split('/')[-1]}", output_path, var_name, 
+        lat_min, lat_max, lon_min, lon_max, resolution,
+        save_format, max_attempts) for file in files_list]
 
         # Download files in parallel
         with Pool(processes=args.processes) as pool:
@@ -455,11 +476,12 @@ def main():
     else: # Run in serial
         for file in files_list:
             local_path = f"tmp/{file.split('/')[-1]}"
-            process_file((bucket_name, file, local_path))
+            process_file((bucket_name, file, local_path, output_path, var_name,
+            lat_min, lat_max, lon_min, lon_max, resolution,
+            save_format, max_attempts))
             loading_bar.update(1)
         loading_bar.close()
 
-    # Remove temporary directory
     shutil.rmtree('tmp/')
 
 if __name__ == '__main__':

{goesgcp-2.0.1.dist-info → goesgcp-2.0.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: goesgcp
-Version: 2.0.1
+Version: 2.0.3
 Summary: A package to download and process GOES-16/17 data
 Home-page: https://github.com/helvecioneto/goesgcp
 Author: Helvecio B. L. Neto
@@ -41,18 +41,18 @@ Dynamic: summary
 <!-- badges: end -->
 
 
-`goesgcp` is a Python utility designed for downloading and reprojecting GOES-R satellite data. This script leverages the `google.cloud` library for accessing data from the Google Cloud Platform (GCP) and `pyproj` for reprojecting data to EPSG:4326, as well as cropping it to a user-defined bounding box.
+`goesgcp` is a Python utility designed for downloading and reprojecting GOES-R satellite data. This script leverages the `google.cloud` library for accessing data from the Google Cloud Platform (GCP) and `rioxarray` for reprojecting data to EPSG:4326 (rectangular grid), as well cropping it to a user-defined bounding box.
 
 ## Features
 
-- **Download GOES-R satellite data**: Supports GOES-16 and GOES-17.
+- **Download GOES-R satellite data**: Supports GOES-16 and GOES-18.
 - **Reprojection and cropping**: Reprojects data to EPSG:4326 and crops to a specified bounding box.
 - **Flexible command-line interface**: Customize download options, variables, channels, time range, and output format.
 - **Efficient processing**: Handles large datasets with optimized performance.
 
 ## Installation
 
-Install the necessary dependencies via `pip`:
+Install the package via `pip`:
 
 ```bash
 pip install goesgcp
@@ -61,7 +61,7 @@ pip install goesgcp
 
 ## Usage
 
-### Command-Line Arguments
+### Available Command-Line Arguments
 
 The script uses the `argparse` module for handling command-line arguments. Below are the available options:
 
@@ -89,7 +89,7 @@ goesgcp [OPTIONS]
 | `--save_format`       | Format for saving output files (default: `by_date`).                      |
 
 #### Available GOES Products
-A comprehensive list of available GOES products can be found at the following link: [https://github.com/awslabs/open-data-docs/tree/main/docs/noaa/noaa-goes16](https://github.com/awslabs/open-data-docs/tree/main/docs/noaa/noaa-goes16)
+A comprehensive list of available GOES products can be found at the following link: [https://console.cloud.google.com/storage/browser/gcp-public-data-goes-16](https://console.cloud.google.com/storage/browser/gcp-public-data-goes-16)
 
 ### Examples
 
@@ -97,14 +97,14 @@ A comprehensive list of available GOES products can be found at the following li
 In the example below, the command downloads the 3 most recent files from the GOES-16 satellite for the product ABI-L2-CMIPF. It focuses on the variable CMI (Cloud and Moisture Imagery) from channel 13, which is commonly used for infrared observations. The downloaded files are saved to the specified output directory output/.
 
 ```bash
-goesgcp --satellite goes-16 --product ABI-L2-CMIPF --var_name CMI --channel 13 --recent 3 --output "output/"
+goesgcp --satellite goes-16 --recent 3 --product ABI-L2-CMIPF --var_name CMI --channel 13 --output "output/"
 ```
 
 #### Download Data for a Specific Time Range
-This command retrieves GOES-16 satellite data for the product ABI-L2-CMIPF within the date range 2022-12-15 00:00:00 to 2022-12-20 10:00:00, focusing on hours 5:00 and 6:00 AM. The data is cropped to the geographic bounds of -35° to 5° latitude and -80° to -30° longitude, reprojected with a resolution of 0.045 degrees, and saved in a by_date format for easy organization.
+This command retrieves GOES-16 satellite data for the product ABI-L2-CMIPF within the date range 2022-12-15 00:00:00 to 2022-12-15 12:00:00, focusing on hours 5:00 and 6:00 AM. The data is cropped to the geographic bounds of -35° to 5° latitude and -80° to -30° longitude, reprojected with a resolution of 0.045 degrees, and saved in a by_date format for easy organization.
 
 ```bash
-goesgcp --satellite goes-16 --product ABI-L2-CMIPF --start '2022-12-15 00:00:00' --end '2022-12-20 10:00:00' --bt_hour 5 6 --save_format by_date --resolution 0.045 --lat_min -35 --lat_max 5 --lon_min -80 --lon_max -30
+goesgcp --satellite goes-16 --product ABI-L2-CMIPF --start '2022-12-15 00:00:00' --end '2022-12-15 12:00:00' --bt_hour 5 6 --save_format by_date --resolution 0.045 --lat_min -35 --lat_max 5 --lon_min -80 --lon_max -30
 ```
 
 ### Contributing

goesgcp-2.0.3.dist-info/RECORD

@@ -0,0 +1,8 @@
+goesgcp/__init__.py,sha256=MigXIT7A1M9YZuH2MyjKReSziFwzbZX2boVYsLosR6s,22
+goesgcp/main.py,sha256=wzWJpwrdncTCt9KP4BMj2Sanx05PZhnAl6JamQebMmY,19185
+goesgcp-2.0.3.dist-info/LICENSE,sha256=AHeZifD4UyBZI61Ug5lETXgX3Anp_XfAvFXQqrW9AnU,1078
+goesgcp-2.0.3.dist-info/METADATA,sha256=qtT9_SjuF8Lsn3UXO9i2p2oCrEXjr3GYqvQTenaGZbY,6161
+goesgcp-2.0.3.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+goesgcp-2.0.3.dist-info/entry_points.txt,sha256=6afMW51WnUR9VZ_xvDoiB8JQb2OFiLuzRtV6dPL__OQ,46
+goesgcp-2.0.3.dist-info/top_level.txt,sha256=C-C3vipI0AwEDW9nWFkJ6D0TkcKkIYlyyM15LMskUEc,8
+goesgcp-2.0.3.dist-info/RECORD,,

goesgcp-2.0.1.dist-info/RECORD

@@ -1,8 +0,0 @@
-goesgcp/__init__.py,sha256=MigXIT7A1M9YZuH2MyjKReSziFwzbZX2boVYsLosR6s,22
-goesgcp/main.py,sha256=F2Z0J4DVF2oeejlIN6WEXi3K8eueZxGWIH5JulEWhXE,18178
-goesgcp-2.0.1.dist-info/LICENSE,sha256=AHeZifD4UyBZI61Ug5lETXgX3Anp_XfAvFXQqrW9AnU,1078
-goesgcp-2.0.1.dist-info/METADATA,sha256=a1MA1uUCdoG5Ihpr8szCYyVpzjCkmSePv0EnNZTKaLo,6149
-goesgcp-2.0.1.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-goesgcp-2.0.1.dist-info/entry_points.txt,sha256=6afMW51WnUR9VZ_xvDoiB8JQb2OFiLuzRtV6dPL__OQ,46
-goesgcp-2.0.1.dist-info/top_level.txt,sha256=C-C3vipI0AwEDW9nWFkJ6D0TkcKkIYlyyM15LMskUEc,8
-goesgcp-2.0.1.dist-info/RECORD,,