Update file 1_prepare_data.ipynb

3f31b5d7 · David Akim · 76404c15 · 3f31b5d7
Commit 3f31b5d7 authored 2 years ago by David Akim
--- a/1_prepare_data.ipynb
+++ b/1_prepare_data.ipynb
 {
 "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Configurar directorios"
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": 1,
@@ -12,6 +20,14 @@
    "FIREDESTDIR = 'processed_fire_data/' # directory to save .npy files for each time step and variable for fire data"
   ]
  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Cargar bibliotecas"
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": 2,
@@ -24,6 +40,14 @@
    "from tqdm.notebook import tqdm"
   ]
  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Variables de configuración"
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": 3,
@@ -37,14 +61,11 @@
   ]
  },
  {
-   "cell_type": "code",
-   "execution_count": 4,
+   "attachments": {},
+   "cell_type": "markdown",
   "metadata": {},
-   "outputs": [],
   "source": [
-    "#root = nc.Dataset(FIREDATADIR + f\"2002.nc\", 'r')\n",
-    "#root['fdimrk']\n",
-    "#root.close()\n"
+    "# Procesar datos ERA5"
   ]
  },
  {
@@ -138,7 +159,7 @@
    }
   ],
   "source": [
-    "# Processing ERA 5 data\n",
+    "# Processing ERA5 data\n",
    "for var in vars:\n",
    "  if not os.path.exists(DESTDIR + f\"{var}\"):\n",
    "    os.makedirs(DESTDIR + f\"{var}\")\n",
@@ -157,6 +178,14 @@
    "        t += 1"
   ]
  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Procesar datos de índice de peligro de incendio"
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": 6,
@@ -178,7 +207,7 @@
    }
   ],
   "source": [
-    "# Processing Fire data\n",
+    "# Processing Fire danger index data\n",
    "for var in fire_vars:\n",
    "  if not os.path.exists(FIREDESTDIR + f\"{var}\"):\n",
    "    os.makedirs(FIREDESTDIR + f\"{var}\")\n",
@@ -195,6 +224,14 @@
    "        t += 1"
   ]
  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Guardar información de latitud/longitud"
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": 7,

+%% Cell type:markdown id: tags:
+
+# Configurar directorios
+
 %% Cell type:code id: tags:

 ``` python
 DATADIR = 'era5/' # directory containing downloaded era5 data
 FIREDATADIR = 'fire_danger/' # directory containing fire data
 DESTDIR = 'processed_era5/' # directory to save .npy files for each time step and variable
 FIREDESTDIR = 'processed_fire_data/' # directory to save .npy files for each time step and variable for fire data
 ```

+%% Cell type:markdown id: tags:
+
+# Cargar bibliotecas
+
 %% Cell type:code id: tags:

 ``` python
 import numpy as np
 import netCDF4 as nc
 import os
 from tqdm.notebook import tqdm
 ```

+%% Cell type:markdown id: tags:
+
+# Variables de configuración
+
 %% Cell type:code id: tags:

 ``` python
 vars = ['u10','v10','t2m','lai_hv','lai_lv','tp'] #considered variables (see 0_download_data.ipynb for long names)
 months = [(1,31),(2,28),(12,31)] # months + days in month in dowloaded era5 .nc files
 years = np.arange(2002,2023) # downloaded years
 fire_vars = ['fdimrk'] # fire data variables
 ```

-%% Cell type:code id: tags:
+%% Cell type:markdown id: tags:

-``` python
-#root = nc.Dataset(FIREDATADIR + f"2002.nc", 'r')
-#root['fdimrk']
-#root.close()
-```
+# Procesar datos ERA5

 %% Cell type:code id: tags:

 ``` python
-# Processing ERA 5 data
+# Processing ERA5 data
 for var in vars:
  if not os.path.exists(DESTDIR + f"{var}"):
    os.makedirs(DESTDIR + f"{var}")

  for year in tqdm(years):
    root = nc.Dataset(DATADIR + f"{year:d}.nc", 'r')
    v = root.variables[var][:,:-9,:-5] #crop to get to a size suitable for the considered Unet-like model, here 140x140
    v = v.data
    root.close()
    if var in ['tp']: #change unit from m to mm for precipitation
      v = 1000 * v
    t = 0 # time step within v array that I am working on
    for month, days in months:
      for day in range(days):
        np.save(DESTDIR + f"{var}/{year}_{month:02d}_{day+1:02d}.npy",v[t])
        t += 1
 ```

 %% Output







+%% Cell type:markdown id: tags:
+
+# Procesar datos de índice de peligro de incendio
+
 %% Cell type:code id: tags:

 ``` python
-# Processing Fire data
+# Processing Fire danger index data
 for var in fire_vars:
  if not os.path.exists(FIREDESTDIR + f"{var}"):
    os.makedirs(FIREDESTDIR + f"{var}")

  for year in tqdm(years):
    root = nc.Dataset(FIREDATADIR + f"{year:d}.nc", 'r')
    v = root.variables[var][:,:-9,:-5] #crop to get to a size suitable for the considered Unet-like model, here 140x140
    v = v.data
    root.close()
    t = 0 # time step within v array that I am working on
    for month, days in months:
      for day in range(days):
        np.save(FIREDESTDIR + f"{var}/{year}_{month:02d}_{day+1:02d}.npy",v[t])
        t += 1
 ```

 %% Output


+%% Cell type:markdown id: tags:
+
+# Guardar información de latitud/longitud
+
 %% Cell type:code id: tags:

 ``` python
 root = nc.Dataset(DATADIR + f"2002.nc", 'r') #constant in time -> take from any year
 lat = root.variables['latitude'][:-9].data #crop to get to a size suitable for the considered Unet-like model
 lon = root.variables['longitude'][:-5].data
 np.save(DESTDIR + 'lat.npy', lat)
 np.save(DESTDIR + 'lon.npy', lon)
 ```