Merge pull request #6 from KhaosResearch/v1.2

v1.2

- Now seasons are not hardcoded, instead defined in a json file referenced in SEASONS_FILE environment variable.
- It is possible now to use any number of seasons or any date interval for using landcoverpy
- Added seasons example files
- Improved RAM usage when creating the tile dataframe, now pd.concat is not used.
- Beta windowing read-write in prediction is now available! Right now it has only been tested splitting the rasters in (5,5) slices, since there are problems with windowing different spatial resolution images, i.e. 20m 10m sentinel2-bands.
- An example for calling the predict workflow using windowing is `workflow(execution_mode=ExecutionMode.LAND_COVER_PREDICTION, window_slices=(5,5))`. This reduces maximum RAM usage from 64GB to 8GB.
- It is pending to improve the windowing allowing different window slices OR allow using use_block_windows.
- Workflow main script splitted in train predict to improve readibility

.env.template

@@ -49,13 +49,8 @@ SL_LABELS_FILE=<SL_LABELS_FILE>
 # For running in a distributed environment
 DASK_CLUSTER_IP=<DASK_CLUSTER_IP>
 
-# Dates used for each season
-SPRING_START=<SPRING_START>
-SPRING_END=<SPRING_END>
-SUMMER_START=<SUMMER_START>
-SUMMER_END=<SUMMER_END>
-AUTUMN_START=<AUTUMN_START>
-AUTUMN_END=<AUTUMN_END>
+# File containing the definition of the seasons
+SEASONS_FILE=<SEASONS_FILE>
 
 # Product filtering parameters
 MAX_CLOUD=<MAX_CLOUD>

README.md

@@ -16,7 +16,7 @@ A research article describing the methodology followed on this workflow can be f
 
 ## Installation
 
-Currently, the package is not available on PyPI, so you need to install it from the source code. To do so, you can clone the repository and install it using pip:
+The package is not available on PyPI, so you need to install it from the source code. To do so, you can clone the repository and install it using pip:
 
 ```bash
 git clone https://github.com/KhaosResearch/landcoverpy.git
@@ -30,12 +30,6 @@ For development purposes, you can install the package in editable mode:
 pip install -e .
 ```
 
-In the future, the package will be available on PyPI, so you will be able to install it using pip:
-
-```bash
-pip install landcoverpy
-```
-
 ## Usage
 
 An usage example can be found at the [main usage notebook](notebooks/main_usage.ipynb).

example_inputs/seasons_file/one_season.json

@@ -0,0 +1,6 @@
+{
+    "april": {
+        "start": "2021-04-01",
+        "end": "2021-04-30"
+    }
+}

example_inputs/seasons_file/seasons.json

@@ -0,0 +1,14 @@
+{
+    "spring": {
+        "start": "2021-03-01",
+        "end": "2021-04-30"
+    },
+    "summer": {
+        "start": "2021-06-01",
+        "end": "2021-07-31"
+    },
+    "autumn": {
+        "start": "2021-10-01",
+        "end": "2021-11-30"
+    }
+}