Resample DINO data and modify Jumper.ipynb to make it compatible

Notebooks/Resample_ssh.ipynb

@@ -0,0 +1,118 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "id": "37c00295-e62d-446f-aaa8-6bb4d88fd617",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import xarray as xr\n",
+    "import numpy as np\n",
+    "import cftime\n",
+    "\n",
+    "# Load the dataset with time decoding\n",
+    "ds_monthly = xr.open_dataset('DINO_1m_grid_T.nc', decode_times=True, use_cftime=True)\n",
+    "\n",
+    "\n",
+    "# Resample the dataset to yearly frequency and compute the mean\n",
+    "ds_yearly = ds_monthly.resample(time_counter='YE').mean()\n",
+    "\n",
+    "# Save the resampled dataset to a new NetCDF file\n",
+    "ds_yearly.to_netcdf('DINO_1m_To_1y_grid_T.nc')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "id": "0a3d4608-5a7f-428f-b433-2b33da3b9ecc",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<xarray.Dataset> Size: 20MB\n",
+      "Dimensions:       (time_counter: 50, y: 199, x: 62)\n",
+      "Coordinates:\n",
+      "    nav_lat       (y, x) float32 49kB ...\n",
+      "    nav_lon       (y, x) float32 49kB ...\n",
+      "  * time_counter  (time_counter) int64 400B 0 360 720 1080 ... 16920 17280 17640\n",
+      "Dimensions without coordinates: y, x\n",
+      "Data variables:\n",
+      "    ssh           (time_counter, y, x) float32 2MB ...\n",
+      "    sst           (time_counter, y, x) float32 2MB ...\n",
+      "    sss           (time_counter, y, x) float32 2MB ...\n",
+      "    saltflx       (time_counter, y, x) float32 2MB ...\n",
+      "    qns           (time_counter, y, x) float32 2MB ...\n",
+      "    qsr           (time_counter, y, x) float32 2MB ...\n",
+      "    mldr10_1      (time_counter, y, x) float32 2MB ...\n",
+      "    mldr10_1max   (time_counter, y, x) float32 2MB ...\n",
+      "Attributes:\n",
+      "    name:         DINO_1m_grid_T\n",
+      "    description:  ocean T grid variables monthly\n",
+      "    title:        ocean T grid variables monthly\n",
+      "    Conventions:  CF-1.6\n",
+      "    timeStamp:    2024-Nov-02 12:56:48 GMT\n",
+      "    uuid:         4580aece-1ad3-4429-9fa2-2417c992e848\n",
+      "\n",
+      "---------------\n",
+      "\n",
+      "<xarray.DataArray 'time_counter' (time_counter: 50)> Size: 400B\n",
+      "array([    0,   360,   720,  1080,  1440,  1800,  2160,  2520,  2880,  3240,\n",
+      "        3600,  3960,  4320,  4680,  5040,  5400,  5760,  6120,  6480,  6840,\n",
+      "        7200,  7560,  7920,  8280,  8640,  9000,  9360,  9720, 10080, 10440,\n",
+      "       10800, 11160, 11520, 11880, 12240, 12600, 12960, 13320, 13680, 14040,\n",
+      "       14400, 14760, 15120, 15480, 15840, 16200, 16560, 16920, 17280, 17640])\n",
+      "Coordinates:\n",
+      "  * time_counter  (time_counter) int64 400B 0 360 720 1080 ... 16920 17280 17640\n",
+      "Attributes:\n",
+      "    axis:           T\n",
+      "    standard_name:  time\n",
+      "    long_name:      Time axis\n",
+      "    time_origin:    1900-01-01 00:00:00\n",
+      "    bounds:         time_counter_bounds\n",
+      "    units:          days since 0001-12-30 00:00:00.000000\n",
+      "    calendar:       360_day\n"
+     ]
+    }
+   ],
+   "source": [
+    "ds_yearly_from_file =  xr.open_dataset('DINO_1m_To_1y_grid_T.nc', decode_times=False)\n",
+    "\n",
+    "print(ds_yearly_from_file)\n",
+    "print('\\n---------------\\n')\n",
+    "print(ds_yearly_from_file['time_counter'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4df47882-f2c2-47aa-b165-da157f498a85",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [conda env:netcdf]",
+   "language": "python",
+   "name": "conda-env-netcdf-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

lib/forecast.py

@@ -114,7 +114,7 @@ def getData(path,term):
         """
         grid = []
         for file in sorted(os.listdir(path)):
-            if term+"." in file: #add param!=""
+            if term[1] in file: #add param!=""
                 grid.append(path+"/"+file)
         return grid
 
@@ -126,10 +126,10 @@ def getAttributes(self):
         self.time_dim  = list(array.dims)[0]
         self.y_size    = array.sizes['y']
         self.x_size    = array.sizes['x']
-        if "deptht" in array[self.term].dims:
+        if "deptht" in array[self.term[0]].dims:
             self.z_size = array.sizes['deptht']
             self.shape = (self.z_size,self.y_size,self.x_size)
-        elif "olevel" in array[self.term].dims:
+        elif "olevel" in array[self.term[0]].dims:
             self.z_size = array.sizes['olevel']
             self.shape = (self.z_size,self.y_size,self.x_size)
         else:
@@ -162,7 +162,7 @@ def loadFile(self,file):
             (xarray.DataArray) : The loaded simulation data.
         """
         array = xr.open_dataset(file, decode_times=False,chunks={"time": 200, "x":120})
-        array = array[self.term]
+        array = array[self.term[0]]
         self.len = self.len + array.sizes[self.time_dim]
         #print(self.len)
         #if self.ye:
@@ -206,7 +206,7 @@ def getSSCA(self,array):
         Parameters:
             array (xarray.Dataset): The last dataset containing simulation data in the simulation file. 
         """
-        array = array[self.term].values
+        array = array[self.term[0]].values
         n = np.shape(array)[0]//12 *12
         array = array[-n:]
         ssca  = np.array(array).reshape((n//12, 12)+ self.shape) #np.array(array[self.term])
@@ -260,7 +260,8 @@ def getPC(self,n):
         Returns:
             (numpy.ndarray): The principal component map.
         """
-        map_ = np.zeros((np.product(self.shape)), dtype=float)
+        # map_ = np.zeros((np.product(self.shape)), dtype=float)
+        map_ = np.zeros((np.prod(self.shape)), dtype=float)
         map_[~self.bool_mask] = np.nan
         map_[self.bool_mask]  = self.pca.components_[n]
         map_ = map_.reshape(self.shape)

requirements.txt

@@ -0,0 +1,9 @@
+numpy==2.0.2
+pandas==2.2.2
+python-dateutil==2.9.0.post0
+pytz==2024.1
+six==1.16.0
+matplotlib==3.9.2
+scipy==1.13.1
+xarray[complete]==2024.7.0
+scikit-learn==1.5.1