main.py

from detectree2model.predictions.predict import run_detectree2
from polygons_processing.postpprocess_detectree2 import postprocess
from generate_tree_images.generate_tree_images import generate_tree_images
from classification.classification_predict import classify
import os
import json

def row_to_feature(row):
    feature = {
        "id": row["id"],
        "type": "Feature",
        "properties": {"Confidence_score": row["Confidence_score"]},
        "geometry": {"type": "Polygon", "coordinates": [row["coordinates"]]},
        "species": row['species']
    }
    return feature

def export_geojson(df, filename):
    features = [row_to_feature(row) for idx, row in df.iterrows()]

    feature_collection = {
        "type": "FeatureCollection",
        "crs": {"type": "name", "properties": {"name": "urn:ogc:def:crs:EPSG::32720"}},
        "features": features,
    }

    output_geojson = json.dumps(feature_collection)

    with open(f"{filename}.geojson", "w") as f:
        f.write(output_geojson)

    print(f"GeoJSON data exported to '{filename}.geojson' file.")

"""
tif_input: the file containing a tif that we are analyzing

tif_file_name: the file name of the tif input. tif_input is the folder in which the tif file lies 
(detectree2 works with that) but generate_tree_images requires path including the file hence the file name is needed

output_directory: the directory were all in-between and final files are stored

generate_tree_images stores the cutout tree images in a separate folder
"""

tif_input = "/Users/jonathanseele/ETH/Hackathons/EcoHackathon/WeCanopy/test/"
tif_file_name = "TreeCrownVectorDataset_761588_9673769_20_20_32720"

current_directory = os.getcwd()
output_directory = os.path.join(current_directory, "outputs")
if not os.path.exists(output_directory):
    os.makedirs(output_directory)

run_detectree2(tif_input, store_path=output_directory)

processed_output_df = postprocess(output_directory + '/detectree2_delin.geojson')
processed_geojson = output_directory + '/processed_delin.geojson'

generate_tree_images(processed_geojson, tif_input)
output_folder = './tree_images'

all_top_3_list = []  # Initialize an empty list to accumulate all top_3 lists

for file_name in os.listdir(output_folder):
    file_path = os.path.join(output_folder, file_name)
    probs = classify(file_path)
    top_3 = probs.head(3)
    top_3_list = [[cls, prob] for cls, prob in top_3.items()]
    
    # Accumulate the top_3_list for each file
    all_top_3_list.append(top_3_list)

# Assign the accumulated top_3_list to the 'species' column of the dataframe
processed_output_df['species'] = all_top_3_list

final_output_path = 'result'
export_geojson(processed_output_df, final_output_path)