climdata 0.0.6__tar.gz → 0.0.7__tar.gz

{climdata-0.0.6 → climdata-0.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: climdata
-Version: 0.0.6
+Version: 0.0.7
 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-0.0.7}/climdata/__init__.py

@@ -2,11 +2,13 @@
 
 __author__ = """Kaushik Muduchuru"""
 __email__ = "kaushik.reddy.m@gmail.com"
-__version__ = "0.0.6"
+__version__ = "0.0.7"
 
 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-0.0.7}/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-0.0.7/climdata/datasets/CMIPCloud.py

@@ -0,0 +1,120 @@
+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 save_csv(self, filename):
+        if self.ds is not None:
+            df = self.ds.to_dataframe().reset_index()
+            df.to_csv(filename, index=False)
+            print(f"Saved CSV to {filename}")

climdata-0.0.6/climdata/datasets/CMIP.py → climdata-0.0.7/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-0.0.7}/climdata.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: climdata
-Version: 0.0.6
+Version: 0.0.7
 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-0.0.7}/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

{climdata-0.0.6 → climdata-0.0.7}/examples/extract_dwd_loc.ipynb

@@ -282,6 +282,245 @@
    "execution_count": null,
    "id": "cfe88f29",
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "            <style>\n",
+       "                .geemap-dark {\n",
+       "                    --jp-widgets-color: white;\n",
+       "                    --jp-widgets-label-color: white;\n",
+       "                    --jp-ui-font-color1: white;\n",
+       "                    --jp-layout-color2: #454545;\n",
+       "                    background-color: #383838;\n",
+       "                }\n",
+       "\n",
+       "                .geemap-dark .jupyter-button {\n",
+       "                    --jp-layout-color3: #383838;\n",
+       "                }\n",
+       "\n",
+       "                .geemap-colab {\n",
+       "                    background-color: var(--colab-primary-surface-color, white);\n",
+       "                }\n",
+       "\n",
+       "                .geemap-colab .jupyter-button {\n",
+       "                    --jp-layout-color3: var(--colab-primary-surface-color, white);\n",
+       "                }\n",
+       "            </style>\n",
+       "            "
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import argparse\n",
+    "import climdata\n",
+    "from hydra import initialize, compose\n",
+    "import pandas as pd\n",
+    "from climdata import CMIP\n",
+    "\n",
+    "with initialize(config_path=\"../climdata/conf\", version_base=None):\n",
+    "    cfg = compose(\n",
+    "        config_name=\"config\",\n",
+    "        overrides=[\n",
+    "            f\"weather.parameter={variables[0]}\",  # Just for bounds/region\n",
+    "            f\"region={region}\",\n",
+    "        ],\n",
+    "    )\n",
+    "\n",
+    "cmip = climdata.CMIP(\n",
+    "    experiment_id = \"historical\",\n",
+    "    source_id = \"MIROC6\",\n",
+    "    table_id = \"day\",\n",
+    "    variables = [\"tasmax\", \"tasmin\", \"pr\"],\n",
+    "    region_bounds = cfg.bounds[cfg.region]\n",
+    "    )\n",
+    "cmip.fetch()      # gets file lists\n",
+    "cmip.load()       # loads and merges datasets\n",
+    "cmip.extract(point = (52,15))\n",
+    "ds = cmip._subset_time(cfg.time_range.start_date, cfg.time_range.end_date)\n",
+    "cmip.save_netcdf(\"cmip_loc.nc\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8a29e214",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "            <style>\n",
+       "                .geemap-dark {\n",
+       "                    --jp-widgets-color: white;\n",
+       "                    --jp-widgets-label-color: white;\n",
+       "                    --jp-ui-font-color1: white;\n",
+       "                    --jp-layout-color2: #454545;\n",
+       "                    background-color: #383838;\n",
+       "                }\n",
+       "\n",
+       "                .geemap-dark .jupyter-button {\n",
+       "                    --jp-layout-color3: #383838;\n",
+       "                }\n",
+       "\n",
+       "                .geemap-colab {\n",
+       "                    background-color: var(--colab-primary-surface-color, white);\n",
+       "                }\n",
+       "\n",
+       "                .geemap-colab .jupyter-button {\n",
+       "                    --jp-layout-color3: var(--colab-primary-surface-color, white);\n",
+       "                }\n",
+       "            </style>\n",
+       "            "
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Saved NetCDF to cmip_box.nc\n"
+     ]
+    }
+   ],
+   "source": [
+    "import argparse\n",
+    "import climdata\n",
+    "from hydra import initialize, compose\n",
+    "import pandas as pd\n",
+    "from climdata import CMIP\n",
+    "\n",
+    "region=\"europe\"\n",
+    "\n",
+    "with initialize(config_path=\"../climdata/conf\", version_base=None):\n",
+    "    cfg = compose(\n",
+    "        config_name=\"config\",\n",
+    "        overrides=[\n",
+    "            f\"weather.parameter={variables[0]}\",  # Just for bounds/region\n",
+    "            f\"region={region}\",\n",
+    "        ],\n",
+    "    )\n",
+    "\n",
+    "cmip = climdata.CMIP(\n",
+    "    experiment_id = \"historical\",\n",
+    "    source_id = \"MIROC6\",\n",
+    "    table_id = \"day\",\n",
+    "    variables = [\"tasmax\", \"tasmin\", \"pr\"],\n",
+    "    region_bounds = cfg.bounds[cfg.region]\n",
+    "    )\n",
+    "cmip.fetch()      # gets file lists\n",
+    "cmip.load()       # loads and merges datasets\n",
+    "\n",
+    "cmip.extract(box = cmip.region_bounds)\n",
+    "ds = cmip._subset_time(cfg.time_range.start_date, cfg.time_range.end_date)\n",
+    "cmip.save_netcdf(\"cmip_box.nc\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "dcf86cc2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "            <style>\n",
+       "                .geemap-dark {\n",
+       "                    --jp-widgets-color: white;\n",
+       "                    --jp-widgets-label-color: white;\n",
+       "                    --jp-ui-font-color1: white;\n",
+       "                    --jp-layout-color2: #454545;\n",
+       "                    background-color: #383838;\n",
+       "                }\n",
+       "\n",
+       "                .geemap-dark .jupyter-button {\n",
+       "                    --jp-layout-color3: #383838;\n",
+       "                }\n",
+       "\n",
+       "                .geemap-colab {\n",
+       "                    background-color: var(--colab-primary-surface-color, white);\n",
+       "                }\n",
+       "\n",
+       "                .geemap-colab .jupyter-button {\n",
+       "                    --jp-layout-color3: var(--colab-primary-surface-color, white);\n",
+       "                }\n",
+       "            </style>\n",
+       "            "
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'CMIP/MIROC/MIROC6/historical/r4i1p1f1/day/europe/'"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"/\".join(cmip.col_subsets[0].df.zstore[0].split('/')[4:-4]+[region])+'/'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d0b5a84f",
+   "metadata": {},
+   "source": [
+    "\n",
+    "\n",
+    "**Usage Example:**\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fc2f2a85",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ds = cmip.load()\n",
+    "ds_time = cmip.subset_time(\"2000-01-01\", \"2005-12-31\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d254a1ee",
+   "metadata": {},
+   "source": [
+    "\n",
+    "\n",
+    "You can combine this with `_subset()` for both spatial and temporal subsetting.  \n",
+    "Let me know if you want a combined function!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "da13620c",
+   "metadata": {},
    "outputs": [],
    "source": []
   }

{climdata-0.0.6 → climdata-0.0.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "climdata"
-version = "0.0.6"
+version = "0.0.7"
 dynamic = [
     "dependencies",
 ]
@@ -52,7 +52,7 @@ universal = true
 
 
 [tool.bumpversion]
-current_version = "0.0.6"
+current_version = "0.0.7"
 commit = true
 tag = true