Converting MFP CSV to YAML schedule

environment.yml

@@ -12,6 +12,7 @@ dependencies:
   - pip
   - pyyaml
   - copernicusmarine >= 2
+  - openpyxl >= 3.1.5
 
   # linting
   - pre-commit

src/virtualship/cli/commands.py

@@ -16,16 +16,26 @@
     hash_to_filename,
 )
 from virtualship.expedition.do_expedition import _get_schedule, do_expedition
-from virtualship.utils import SCHEDULE, SHIP_CONFIG
+from virtualship.utils import SCHEDULE, SHIP_CONFIG, mfp_to_yaml
 
 
 @click.command()
 @click.argument(
     "path",
     type=click.Path(exists=False, file_okay=False, dir_okay=True),
 )
-def init(path):
-    """Initialize a directory for a new expedition, with an example schedule and ship config files."""
+@click.option(
+    "--mfp_file",
+    type=str,
+    default=None,
+    help='Partially initialise a project from an exported xlsx or csv file from NIOZ\' Marine Facilities Planning tool (specifically the "Export Coordinates > DD" option). User edits are required after initialisation.',
+)
+def init(path, mfp_file):
+    """
+    Initialize a directory for a new expedition, with an example schedule and ship config files.
+
+    If --mfp_file is provided, it will generate the schedule from the MPF file instead.
+    """
     path = Path(path)
     path.mkdir(exist_ok=True)
 
@@ -43,7 +53,16 @@ def init(path):
         )
 
     config.write_text(utils.get_example_config())
-    schedule.write_text(utils.get_example_schedule())
+
+    if mfp_file:
+        # Generate schedule.yaml from the MPF file
+        click.echo(f"Generating schedule from {mfp_file}...")
+        mfp_to_yaml(
+            mfp_file, str(path)
+        )  # Pass the path to save in the correct directory
+    else:
+        # Create a default example schedule
+        schedule.write_text(utils.get_example_schedule())
 
     click.echo(f"Created '{config.name}' and '{schedule.name}' at {path}.")
 

src/virtualship/utils.py

@@ -1,7 +1,10 @@
+import os
 from functools import lru_cache
 from importlib.resources import files
 from typing import TextIO
 
+import numpy as np
+import pandas as pd
 import yaml
 from pydantic import BaseModel
 
@@ -37,3 +40,99 @@ def _dump_yaml(model: BaseModel, stream: TextIO) -> str | None:
 def _generic_load_yaml(data: str, model: BaseModel) -> BaseModel:
     """Load a yaml string into a pydantic model."""
     return model.model_validate(yaml.safe_load(data))
+
+
+def mfp_to_yaml(excel_file_path: str, save_directory: str):
+    """
+    Generates a YAML file (`schedule.yaml`) with spatial and temporal information based on instrument data from MFP excel file.
+
+    Parameters
+    ----------
+    - excel_file_path (str): Path to the Excel file containing coordinate and instrument data.
+    - save_directory (str): Directory where `schedule.yaml` will be saved.
+
+    The function:
+    1. Reads instrument and location data from the Excel file.
+    2. Determines the maximum depth and buffer based on the instruments present.
+    3. Ensures longitude and latitude values remain valid after applying buffer adjustments.
+    4. Saves `schedule.yaml` in the specified directory.
+
+    """
+    # Read data from Excel
+    coordinates_data = pd.read_excel(
+        excel_file_path,
+        usecols=["Station Type", "Name", "Latitude", "Longitude", "Instrument"],
+    )
+    coordinates_data = coordinates_data.dropna()
+
+    # Define maximum depth and buffer for each instrument
+    instrument_properties = {
+        "CTD": {"depth": 5000, "buffer": 1},
+        "DRIFTER": {"depth": 1, "buffer": 5},
+        "ARGO_FLOAT": {"depth": 2000, "buffer": 5},
+    }
+
+    # Extract unique instruments from dataset
+    unique_instruments = np.unique(
+        np.hstack(coordinates_data["Instrument"].apply(lambda a: a.split(", ")).values)
+    )
+
+    # Determine the maximum depth based on the unique instruments
+    maximum_depth = max(
+        instrument_properties.get(inst, {"depth": 0})["depth"]
+        for inst in unique_instruments
+    )
+    minimum_depth = 0
+
+    # Determine the buffer based on the maximum buffer of the instruments present
+    buffer = max(
+        instrument_properties.get(inst, {"buffer": 0})["buffer"]
+        for inst in unique_instruments
+    )
+
+    # Adjusted spatial range
+    min_longitude = coordinates_data["Longitude"].min() - buffer
+    max_longitude = coordinates_data["Longitude"].max() + buffer
+    min_latitude = coordinates_data["Latitude"].min() - buffer
+    max_latitude = coordinates_data["Latitude"].max() + buffer
+
+    # Template for the YAML output
+    yaml_output = {
+        "space_time_region": {
+            "spatial_range": {
+                "minimum_longitude": min_longitude,
+                "maximum_longitude": max_longitude,
+                "minimum_latitude": min_latitude,
+                "maximum_latitude": max_latitude,
+                "minimum_depth": minimum_depth,
+                "maximum_depth": maximum_depth,
+            },
+            "time_range": {
+                "start_time": "",  # Blank start time
+                "end_time": "",  # Blank end time
+            },
+        },
+        "waypoints": [],
+    }
+
+    # Populate waypoints
+    for _, row in coordinates_data.iterrows():
+        instruments = row["Instrument"].split(", ")
+        for instrument in instruments:
+            waypoint = {
+                "instrument": instrument,
+                "location": {
+                    "latitude": row["Latitude"],
+                    "longitude": row["Longitude"],
+                },
+                "time": "",  # Blank time
+            }
+            yaml_output["waypoints"].append(waypoint)
+
+    # Ensure save directory exists
+    os.makedirs(save_directory, exist_ok=True)
+
+    # Save the YAML file
+    yaml_file_path = os.path.join(save_directory, SCHEDULE)
+    with open(yaml_file_path, "w") as file:
+        yaml.dump(yaml_output, file, default_flow_style=False)