climdata 0.0.6__tar.gz → 0.1.0__tar.gz

{climdata-0.0.6 → climdata-0.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: climdata
-Version: 0.0.6
+Version: 0.1.0
 Summary: This project automates the fetching and extraction of weather data from multiple sources — such as MSWX, DWD HYRAS, ERA5-Land, NASA-NEX-GDDP, and more — for a given location and time range.
 Author-email: Kaushik Muduchuru <kaushik.reddy.m@gmail.com>
 License: MIT License

{climdata-0.0.6 → climdata-0.1.0}/climdata/__init__.py

@@ -2,11 +2,13 @@
 
 __author__ = """Kaushik Muduchuru"""
 __email__ = "kaushik.reddy.m@gmail.com"
-__version__ = "0.0.6"
+__version__ = "0.1.0"
 
 from .utils.utils_download import * # etc.
 from .utils.config import load_config
 from .datasets.DWD import DWDmirror as DWD
 from .datasets.MSWX import MSWXmirror as MSWX
 from .datasets.ERA5 import ERA5Mirror as ERA5
+from .datasets.CMIPlocal import CMIPmirror as CMIPlocal
+from .datasets.CMIPCloud import CMIPCloud as CMIP
 

{climdata-0.0.6 → climdata-0.1.0}/climdata/conf/config.yaml

@@ -33,5 +33,6 @@ time_range:
 
 output:
   out_dir: "./climdata/data/"
-  filename: "{provider}_{parameter}_LAT{lat}_LON{lon}_{start}_{end}.csv"
+  filename_csv: "{provider}_{parameter}_LAT_{lat}_LON_{lon}_{start}_{end}.csv"
+  filename_zarr: "{provider}_{parameter}_LAT{lat_range}_LON{lon_range}_{start}_{end}.zarr"
   fmt: 'standard' # 'standard', 'ICASA', 'simplace', 'monica'

climdata-0.1.0/climdata/datasets/CMIPCloud.py

@@ -0,0 +1,149 @@
+import intake
+import xarray as xr
+import pandas as pd
+
+class CMIPCloud:
+    def __init__(self, experiment_id, source_id, table_id, variables, region_bounds=None):
+        self.experiment_id = experiment_id
+        self.source_id = source_id
+        self.table_id = table_id
+        self.variables = variables
+        self.region_bounds = region_bounds
+        self.col_subsets = []
+        self.ds = None
+
+    def fetch(self):
+        """Collect intake catalog subsets for each variable."""
+        col = intake.open_esm_datastore("https://storage.googleapis.com/cmip6/pangeo-cmip6.json")
+        self.col_subsets = []
+        for var in self.variables:
+            query = dict(
+                experiment_id=[self.experiment_id],
+                source_id=self.source_id,
+                table_id=self.table_id,
+                variable_id=var,
+            )
+            col_subset = col.search(require_all_on=["source_id"], **query)
+            if len(col_subset.df) == 0:
+                continue
+            self.col_subsets.append(col_subset)
+        return self.col_subsets
+
+    def load(self):
+        """Load and merge datasets from collected col_subsets."""
+        datasets = []
+        for col_subset in self.col_subsets:
+            zstore_path = col_subset.df.zstore.values[0].replace('gs:/', "https://storage.googleapis.com")
+            ds_var = xr.open_zarr(zstore_path)
+            datasets.append(ds_var)
+        if datasets:
+            self.ds = xr.merge(datasets)
+        else:
+            self.ds = None
+        return self.ds
+
+    def extract(self, *, point=None, box=None, shapefile=None, buffer_km=0.0):
+        """
+        Extract a subset of the dataset by point, bounding box (dict), or shapefile.
+        """
+        import geopandas as gpd
+        from shapely.geometry import mapping
+
+        if self.ds is None:
+            raise ValueError("No dataset loaded. Call `load()` first.")
+
+        ds = self.ds
+
+        if point is not None:
+            lon, lat = point
+            if buffer_km > 0:
+                buffer_deg = buffer_km / 111
+                ds_subset = ds.sel(
+                    lon=slice(lon-buffer_deg, lon+buffer_deg),
+                    lat=slice(lat-buffer_deg, lat+buffer_deg)
+                )
+            else:
+                ds_subset = ds.sel(lon=lon, lat=lat, method="nearest")
+
+        elif box is not None:
+            # Accept dict: {'lat_min': ..., 'lat_max': ..., 'lon_min': ..., 'lon_max': ...}
+            ds_subset = ds.sel(
+                lon=slice(box['lon_min'], box['lon_max']),
+                lat=slice(box['lat_min'], box['lat_max'])
+            )
+
+        elif shapefile is not None:
+            if isinstance(shapefile, str):
+                gdf = gpd.read_file(shapefile)
+            else:
+                gdf = shapefile
+            if buffer_km > 0:
+                gdf = gdf.to_crs(epsg=3857)
+                gdf["geometry"] = gdf.buffer(buffer_km * 1000)
+                gdf = gdf.to_crs(epsg=4326)
+            geom = [mapping(g) for g in gdf.geometry]
+            import rioxarray
+            ds = ds.rio.write_crs("EPSG:4326", inplace=False)
+            ds_subset = ds.rio.clip(geom, gdf.crs, drop=True)
+
+        else:
+            raise ValueError("Must provide either point, box, or shapefile.")
+        self.ds = ds_subset
+        return ds_subset
+    def _subset_time(self, start_date, end_date):
+        """
+        Subset the dataset by time range.
+        Dates should be strings in 'YYYY-MM-DD' format.
+        """
+        if self.ds is None:
+            return None
+        ds_time = self.ds.sel(time=slice(start_date, end_date))
+        self.ds = ds_time
+        return ds_time
+
+    def save_netcdf(self, filename):
+        if self.ds is not None:
+            if "time" in self.ds.variables:
+                self.ds["time"].encoding.clear()
+            self.ds.to_netcdf(filename)
+            print(f"Saved NetCDF to {filename}")
+
+    def save_zarr(self, store_path):
+        if self.ds is not None:
+            self.ds.to_zarr(store_path, mode="w")
+            print(f"Saved Zarr to {store_path}")
+
+    def _format(self, df):
+        """
+        Format the dataframe for standardized output:
+        - Adds source_id, experiment_id, table_id, variable, value, units columns.
+        - Stacks variables into long format.
+        """
+        # Melt the dataframe to long format: variable, value
+        value_vars = [v for v in self.variables if v in df.columns]
+        id_vars = [c for c in df.columns if c not in value_vars]
+        df_long = df.melt(id_vars=id_vars, value_vars=value_vars,
+                          var_name="variable", value_name="value")
+
+        # Add units column (from attrs)
+        df_long["units"] = df_long["variable"].map(
+            lambda v: self.ds[v].attrs.get("units", "unknown") if v in self.ds.data_vars else "unknown"
+        )
+
+        # Add metadata columns if missing
+        df_long["source_id"] = self.source_id
+        df_long["experiment_id"] = self.experiment_id
+        df_long["table_id"] = self.table_id
+
+        # Reorder columns
+        cols = ["source_id", "experiment_id", "table_id", "time", "lat", "lon", "variable", "value", "units"]
+        df_long = df_long[[c for c in cols if c in df_long.columns]]
+
+        return df_long
+
+    def save_csv(self, filename):
+        if self.ds is not None:
+            df = self.ds.to_dataframe().reset_index()
+            df = self._format(df)
+            df.to_csv(filename, index=False)
+            print(f"Saved CSV to {filename}")

climdata-0.0.6/climdata/datasets/CMIP.py → climdata-0.1.0/climdata/datasets/CMIPlocal.py

@@ -14,7 +14,7 @@ from xclim.core import units
 warnings.filterwarnings("ignore", category=Warning)
 
 
-class CMIP:
+class CMIPmirror:
     def __init__(self, var_cfg: DictConfig, experiments):
         self.var_cfg = var_cfg
         self.files = []

{climdata-0.0.6 → climdata-0.1.0}/climdata.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: climdata
-Version: 0.0.6
+Version: 0.1.0
 Summary: This project automates the fetching and extraction of weather data from multiple sources — such as MSWX, DWD HYRAS, ERA5-Land, NASA-NEX-GDDP, and more — for a given location and time range.
 Author-email: Kaushik Muduchuru <kaushik.reddy.m@gmail.com>
 License: MIT License

{climdata-0.0.6 → climdata-0.1.0}/climdata.egg-info/SOURCES.txt

@@ -30,7 +30,8 @@ climdata.egg-info/top_level.txt
 climdata/conf/config.yaml
 climdata/conf/mappings/parameters.yaml
 climdata/conf/mappings/variables.yaml
-climdata/datasets/CMIP.py
+climdata/datasets/CMIPCloud.py
+climdata/datasets/CMIPlocal.py
 climdata/datasets/DWD.py
 climdata/datasets/ERA5.py
 climdata/datasets/MSWX.py