Upload 2 files

api.py

@@ -0,0 +1,84 @@
+from sentinelsat import SentinelAPI, read_geojson, geojson_to_wkt
+from datetime import datetime, timedelta,date
+import zipfile
+import rasterio
+from rasterio.plot import show
+from PIL import Image
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+import os
+from glob import glob
+from tqdm import tqdm
+#from haversine import haversine, Unit
+#from xml.etree import ElementTree as et
+import xmltodict
+import json
+import warnings
+import shutil
+from shapely.geometry import Point
+from shapely.geometry.polygon import Polygon
+warnings.filterwarnings('ignore')
+
+##
+def unzip():
+    files = glob('*.zip')
+    for file in files:
+         with zipfile.ZipFile(file, 'r') as zip_ref:
+            zip_ref.extractall()
+
+
+##
+def select_best_cloud_coverage_tile():
+    tile_names = {}
+    cld_prob = []
+    folders = glob('*.SAFE')
+    for fold in folders:
+        metadata_path = fold+"/MTD_MSIL2A.xml"
+        xml_file=open(metadata_path,"r")
+        xml_string=xml_file.read()
+        python_dict=xmltodict.parse(xml_string)
+        cld = float(python_dict["n1:Level-2A_User_Product"]["n1:Quality_Indicators_Info"]["Cloud_Coverage_Assessment"])
+        tile_names[cld] = fold
+        cld_prob.append(cld)
+    name = tile_names[min(cld_prob)]
+    dates = name.split('_')[2][:8]
+    acquisition_date = datetime.strptime(dates, "%Y%m%d")
+    today = datetime.now()
+    delta = (today - acquisition_date)
+    days_ago = delta.days
+    return name,min(cld_prob),days_ago
+
+##
+def find_good_tile(df, point):
+    for row in tqdm(df.itertuples(),total=len(df)):
+        tile_name = row.tiles
+        coordinate = row.coords
+        x = coordinate.replace(']','')
+        x = x.replace('[','')
+        x = x.replace("'",'')
+        tab = [[float(x.split(",")[i]),float(x.split(",")[i+1])] for i in range(0,len(x.split(",")),2)]
+        polygon = Polygon(tab)
+        result  = polygon.contains(point)
+        if result:
+            print(tile_name)
+            return "S2B_MSIL2A_20230104T103329_N0509_R108_T30NUL_20230104T132032.SAFE.zip" #tile_name
+        
+    return "S2B_MSIL2A_20230104T103329_N0509_R108_T30NUL_20230104T132032.SAFE.zip" #404
+
+##
+def delete_tiles():
+        files = glob('*.zip')
+        folders1 = glob('*.SAFE')
+        folders2 = glob("*.tmp")
+        for f in files:
+            os.remove(f)
+        for fold in folders1:
+            shutil.rmtree(fold, ignore_errors=True)
+
+        for fold in folders2:
+            shutil.rmtree(fold, ignore_errors=True)
+
+
+
+

app.py

@@ -0,0 +1,145 @@
+import gradio as gr
+from api import *
+from processing import *
+import pandas as pd
+from indices import indices
+import xgboost as xgb
+#from lightgbm import LGBMRegressor
+from sklearn.preprocessing import StandardScaler
+from sklearn.decomposition import PCA
+import pickle as pk
+import json
+import boto3
+from shapely.geometry import MultiPolygon,shape
+from shapely.geometry import Point
+from shapely.geometry.polygon import Polygon
+from glob import glob
+import wget
+
+
+def predict(location_name,lat, lon):
+    cord = [lon,lat]
+    lon = round(lon,4)
+    lat = round(lat,4)
+    x1 = [lon,lat]
+    x2 = [lat,lon]
+    with open("data/CIV_0.json","r") as file:
+        data = json.load(file)
+    # extract ivory coast polygone
+    features = [data['features'][0]['geometry']['coordinates'][0]+data['features'][0]['geometry']['coordinates'][1]+data['features'][0]['geometry']['coordinates'][2]]
+    data['features'][0]['geometry']['coordinates'] = features
+    ci_polygone = data['features'][0]['geometry']['coordinates'][0][0]  
+    point1 = Point(x1)
+    point2 = Point(x2)
+    polygon = Polygon(ci_polygone)
+    result = polygon.contains(point1)
+
+    if not result:
+        return "Choisissez une zone de la CI","","","",""
+    
+    else:
+        df = pd.read_csv("data/frame.csv")
+        name = find_good_tile(df,point2)
+        if name ==404:
+            reponse = "Sentinel-2 ne dispose pas de données ce sur ce lieu à ce jour"
+            return reponse,"","","",""
+        else:
+            path = "https://data354-public-assets.s3.eu-west-3.amazonaws.com/cisentineldata/"
+            url = path+name
+            #wget.download(url)
+            unzip()
+            name,cld_prob,days_ago = select_best_cloud_coverage_tile()
+            bandes_path_10,bandes_path_20,bandes_path_60,tile_path,path_cld_20,path_cld_60 =paths(name)
+            # create image dataset
+            images_10 = extract_sub_image(bandes_path_10,tile_path,cord)
+
+            # bandes with 20m resolution
+            #path_cld_20
+            images_20 = extract_sub_image(bandes_path_20,tile_path,cord,20,1)
+
+            # bandes with 60m resolution
+            #path_cld_60
+            images_60 = extract_sub_image(bandes_path_60,tile_path,cord,60)
+            #
+            feature = images_10.tolist()+images_20.tolist()+images_60.tolist()
+            bands = ['B02', 'B03', 'B04', 'B05', 'B06', 'B07', 'B08', 'B8A', 'B11', 'B12','B01','B09']
+            print("feature : ",feature)
+            print("BANDES : ",bands)
+            
+            X = pd.DataFrame([feature],columns = bands)
+            print("==================== X SHAPE", X.shape)
+            ## Coordinate
+            cord_df = pd.DataFrame({"Latitude":[lat],
+                                    "Longitude":[lon]})
+            print("==================== cord_df SHAPE", cord_df.shape)
+            ## PCA dimension reduction
+            # later reload the pickle file
+            sdc_reload = pk.load(open("data/sdc.pkl",'rb'))
+            pca_reload = pk.load(open("data/pca.pkl",'rb'))
+            # standardization
+            X_pca = sdc_reload.transform(X)
+            # make pca
+            principalComponents = pca_reload .transform(X_pca)
+            principalDf = pd.DataFrame(data =principalComponents[:,:4],
+                           columns = ["PC1","PC2","PC3","PC4"])
+            print("==================== principalDf SHAPE", principalDf.shape)
+
+            # vegetation index calculation
+            X = indices(X)
+            # Drop all 12 bands of S2
+            tab = list(range(12))
+            X_index = X.drop(X.iloc[:,tab],axis=1)
+
+            print("=============SHAPE1",X_index.shape)
+
+            # Create predictive features
+            X_final =pd.concat([cord_df,principalDf,X_index],axis=1)
+            print("=============SHAPE2",X_final.shape)
+
+            # load the model from disk
+            filename = "data/finalized_model3.sav"
+            loaded_model = pk.load(open(filename, 'rb'))
+            # make prediction
+            biomass = loaded_model.predict(X_final)[0]
+            if biomass<0:
+                biomass =0.0
+            
+            carbon = 0.55*biomass
+
+            # NDVI
+            ndvi_index = ndvi(cord,name)
+
+            # deleted download files
+            #delete_tiles()
+
+            return str(cld_prob)+ " % cloud coverage", str(days_ago)+" days ago",str(biomass)+" t/ha", str(carbon)+" tC/ha","NDVI: "+ str(ndvi_index)
+
+# Create title, description and article strings
+title = "🌴BEEPAS : Biomass estimation to Evaluate the Environmental Performance of Agroforestry Systems🌴"
+description = "This application estimates the biomass of certain areas using AI and satellite images (S2)."
+article = "Created by data354."
+
+# Create examples list from "examples/" directory
+#example_list = [["examples/" + example] for example in os.listdir("examples")]
+example_list = [["Foret du banco :",5.379913, -4.050445],["Pharmacie Y4 :",5.363292, -3.9481601],["Treichville Bernabé :",5.293168, -3.999796],["Adjamé :",5.346938, -4.027849],["ile boulay :",5.280498,-4.089883]]
+
+
+outputs = [
+    gr.Textbox(label="Cloud coverage"),
+    gr.Textbox(label="Number of days since sensing"),
+    gr.Textbox(label="Above ground biomass density(AGBD) t/ha"),
+    gr.Textbox(label="Carbon stock density tC/ha "),
+    gr.Textbox(label="Mean NDVI"),]
+
+
+demo = gr.Interface(
+    fn=predict,
+    inputs=["text","number", "number"],
+    outputs=outputs, #[ "text", "text","text","text","text"],
+    examples=example_list,
+    title=title,
+    description=description,
+    article=article,
+    )
+
+demo.launch(share=True)