gca-sprint report outcome; uv docker config

App/functions/report-python-cloud-run/.dockerignore

@@ -0,0 +1,10 @@
+.venv/
+*__pycache__/
+*.pyc
+*.pyo
+*.pyd
+*.pyw
+*.pyz
+*.pyj
+*.pyx
+*.pyd

App/functions/report-python-cloud-run/Dockerfile

@@ -12,23 +12,35 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# Use the official lightweight Python image.
-# https://hub.docker.com/_/python
-FROM python:3.11-slim
-
-# Allow statements and log messages to immediately appear in the Knative logs
-ENV PYTHONUNBUFFERED True
-
-# Copy local code to the container image.
-ENV APP_HOME /app
-WORKDIR $APP_HOME
-COPY . ./
-
-# Install production dependencies.
-RUN pip install -r requirements.txt
-
-# Run the web service on container startup. Here we use the gunicorn
-# webserver, with one worker process and 8 threads.
-# For environments with multiple CPU cores, increase the number of workers
-# to be equal to the cores available.
-CMD exec gunicorn --bind :$PORT --workers 1 --threads 8 --timeout 0 main:app
+# Use the official uv python image
+# Use a Python image with uv pre-installed
+FROM ghcr.io/astral-sh/uv:python3.11-bookworm
+
+# Install the project into `/app`
+WORKDIR /app
+
+# Enable bytecode compilation
+ENV UV_COMPILE_BYTECODE=1
+
+# Copy from the cache instead of linking since it's a mounted volume
+ENV UV_LINK_MODE=copy
+RUN apt-get update && apt-get install -y libgdal-dev libgl1
+
+# Install the project's dependencies using the lockfile and settings
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,source=uv.lock,target=uv.lock \
+    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    uv sync --frozen --no-install-project --no-dev
+
+# Then, add the rest of the project source code and install it
+# Installing separately from its dependencies allows optimal layer caching
+ADD . /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen --no-dev
+
+# Place executables in the environment at the front of the path
+ENV PATH="/app/.venv/bin:$PATH"
+
+# CMD uv run --with waitress waitress-serve main:app
+# CMD uv run python main.py
+CMD uv run --with gunicorn gunicorn --bind :8080 --workers 1 --threads 8 --timeout 0 main:app

App/functions/report-python-cloud-run/docker-compose.yml

@@ -0,0 +1,9 @@
+services:
+  report-service:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    env_file:
+      - .env.prod
+    ports:
+      - "8080:8080"

App/functions/report-python-cloud-run/main.py

@@ -73,4 +73,4 @@ def return_html():
 
 
 if __name__ == "__main__":
-    app.run(debug=True, host="0.0.0.0", port=int(os.environ.get("PORT", 8080)))
+    app.run(host="0.0.0.0", port=int(os.environ.get("PORT", 8080)))

App/functions/report-python-cloud-run/pyproject.toml

@@ -0,0 +1,28 @@
+[project]
+name = "gca-report"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "flask>=3.1.0",
+    "geopandas>=1.0.1",
+    "ipykernel>=6.29.5",
+    "jinja2>=3.1.4",
+    "langchain>=0.3.11",
+    "matplotlib>=3.9.3",
+    "numba>=0.60.0",
+    "openai>=1.57.1",
+    "opencv-python>=4.10.0.84",
+    "pymupdf>=1.25.1",
+    "pystac-client>=0.7",
+    "resilientplotterclass",
+    "rioxarray>=0.16.0",
+    "sentence-transformers>=3.3.1",
+    "weasyprint>=63.1",
+    "xarray>=2024.4.0",
+    "zarr>=2.18.2",
+]
+
+[tool.uv.sources]
+resilientplotterclass = { git = "https://github.com/Deltares-research/ResilientPlotterClass" }

App/functions/report-python-cloud-run/report/app.html

@@ -0,0 +1,39 @@
+<div class="section-grid">
+    <h>The State of the Coast Report, <span style="color:  rgb(0, 204, 150)">explained</span></h>
+    <p>The data of this report is obtained from various STACs and the content of this report is generated by the Azure AI.
+            This page explains the approach to process individual data from the STACs and relevant literature regarding the datasets. 
+            The datasets can be found in the following STACs:</p>
+    <p>https://raw.githubusercontent.com/openearth/global-coastal-atlas/subsidence_etienne/STAC/data/current/catalog.json</p>
+    <p>https://raw.githubusercontent.com/openearth/coclicodata/main/current/catalog.json</p>
+
+    <p>Coastal Types: The dataset indicates the sediment composition of a beach at certain transects, 
+        which are globally spaced shore-normal transects in every 500m. The transects can either labelled as sandy, muddy, vegetated, coastal cliff or other materials. 
+        This dataset is derived from satellite images and other parameters and generated by using a supervised random forest classifier. 
+        Details of the methodology can be referred to Breiman et al. (2001).</p>
+
+    <p>The Population: The dataset provides a global population count per pixel at approximately 100m resolution 
+        and it is based on the United Nation Development Programme (UNDP) 2020 estimates for in total 183 countries.</p>
+
+    <p>Historical Shoreline Change: The dataset provides the annual shoreline position over the period from 1984 to 2021 along 1.8 million transects in the world. 
+        The transects are 500m spaced shore-normal transects. The position of shoreline is derived from satellite images. 
+        Details of the methodology can be referred to XXXX.</p>
+
+    <p>SSP: SSP stands for Shared Socioeconomic Pathway, which was introduced in the IPCC 6th Assessment Report (AR6). 
+        This indicator describes different socioeconomic assumptions, such as population, economic growth, technological development and etc. 
+        Details can be referred to the AR6.</p>
+
+    <p>RCP: RCP stands for Representative Concentration Pathway, which was introduced in IPCC 5th Assessment Report (AR5).
+            RCP4.5 and 8.5 describe scenarios with intermediate or very high greenhouse gas (GHG) emission and other radiative forcings. 
+            RCP4.5 describes a scenario that the CO2 emission will remain around current levels until 2050 and fall but not reach net zero by 2100. 
+            RCP8.5 describes a scenario that the CO2 emission will become triple by 2075.</p>
+
+    <p>Sea Level Rise Projection: This is median projections of regional sea level rise from 2020 to 2150, relative to a 1995-2014 baseline. 
+        This projection data is originally from the AR6. The projections are based on several scenarios, including SSP126, SSP245 and SSP585. 
+        Details of the projection can be found in XXX.</p>
+
+    <p>Future Shoreline Projections: The average shoreline change rate is based on projection of locations of sandy shorelines relative to their reference locations in RCP4.5 and RCP8.5 scenarios. 
+        According to Luijendijk et al. (XXXX), the shoreline locations in 2021 and the projected shoreline locations in 2050 and 2100 are defined. 
+        The average shoreline change rate is calculated based on the spatial distance difference of the shoreline location between two referenced years and divided by the year difference. 
+        The future shoreline location is estimated based on XXXXX. Details can be found in “XXXX” (Luijendijk et al., XXXX ). 
+        The erosion and accretion classification system is the same as the one in the historical shoreline change.</p>
+</div>

App/functions/report-python-cloud-run/report/datasets/base_dataset.py

@@ -1,13 +1,30 @@
 from typing import Optional
 import xarray as xr
 
-from .datasetcontent import DatasetContent
-from .esl import get_esl_content
+from report.datasets.datasetcontent import DatasetContent
+
+from report.datasets.shoremon import (
+    get_sedclass_content,
+    get_shoremon_content,
+    get_shoremon_fut_content,
+)
+from report.datasets.popgpd import get_world_pop_content
+# from .subtreat import get_sub_threat_content
 
 
 def get_dataset_content(dataset_id: str, xarr: xr.Dataset) -> Optional[DatasetContent]:
     match dataset_id:
-        case "esl_gwl":
-            return get_esl_content(xarr)
+        # case "esl_gwl":
+        #     return get_esl_content(xarr)
+        case "sed_class":
+            return get_sedclass_content(xarr)
+        case "shore_mon":
+            return get_shoremon_content(xarr)
+        case "shore_mon_fut":
+            return get_shoremon_fut_content(xarr)
+        case "world_pop":
+            return get_world_pop_content(xarr)
+        # case "sub_threat":
+        #     return None
         case _:
             return None