Update app.py
Browse files
app.py
CHANGED
|
@@ -64,19 +64,30 @@ def predict(lat, lon):
|
|
| 64 |
timer('unzip data',start_time_unzip)
|
| 65 |
|
| 66 |
start_time_processing = timer('processing data',None)
|
|
|
|
|
|
|
| 67 |
name,cld_prob,days_ago = select_best_cloud_coverage_tile()
|
| 68 |
bandes_path_10,bandes_path_20,bandes_path_60,tile_path,path_cld_20,path_cld_60 =paths(name)
|
|
|
|
|
|
|
|
|
|
| 69 |
# create image dataset
|
| 70 |
images_10 = extract_sub_image(bandes_path_10,tile_path,cord)
|
|
|
|
| 71 |
|
|
|
|
| 72 |
# bandes with 20m resolution
|
| 73 |
#path_cld_20
|
| 74 |
images_20 = extract_sub_image(bandes_path_20,tile_path,cord,20,1)
|
| 75 |
-
|
|
|
|
|
|
|
| 76 |
# bandes with 60m resolution
|
| 77 |
#path_cld_60
|
| 78 |
images_60 = extract_sub_image(bandes_path_60,tile_path,cord,60)
|
|
|
|
| 79 |
#
|
|
|
|
| 80 |
feature = images_10.tolist()+images_20.tolist()+images_60.tolist()
|
| 81 |
bands = ['B02', 'B03', 'B04', 'B05', 'B06', 'B07', 'B08', 'B8A', 'B11', 'B12','B01','B09']
|
| 82 |
X = pd.DataFrame([feature],columns = bands)
|
|
@@ -88,11 +99,15 @@ def predict(lat, lon):
|
|
| 88 |
# make prediction
|
| 89 |
biomass = loaded_model.predict(X)[0]
|
| 90 |
carbon = 0.55*biomass
|
|
|
|
| 91 |
|
| 92 |
# NDVI
|
|
|
|
| 93 |
ndvi_index = ndvi(cord,name)
|
|
|
|
|
|
|
| 94 |
timer('processing data',start_time_processing)
|
| 95 |
-
|
| 96 |
# deleted download files
|
| 97 |
delete_tiles()
|
| 98 |
|
|
|
|
| 64 |
timer('unzip data',start_time_unzip)
|
| 65 |
|
| 66 |
start_time_processing = timer('processing data',None)
|
| 67 |
+
|
| 68 |
+
start_time_select_best_tile = timer('select best tile',None)
|
| 69 |
name,cld_prob,days_ago = select_best_cloud_coverage_tile()
|
| 70 |
bandes_path_10,bandes_path_20,bandes_path_60,tile_path,path_cld_20,path_cld_60 =paths(name)
|
| 71 |
+
timer('select best tile',start_time_select_best_tile)
|
| 72 |
+
|
| 73 |
+
start_time_10m = timer('create 10m image',None)
|
| 74 |
# create image dataset
|
| 75 |
images_10 = extract_sub_image(bandes_path_10,tile_path,cord)
|
| 76 |
+
timer('create 10m image',start_time_10m)
|
| 77 |
|
| 78 |
+
start_time_20m = timer('create 20m image',None)
|
| 79 |
# bandes with 20m resolution
|
| 80 |
#path_cld_20
|
| 81 |
images_20 = extract_sub_image(bandes_path_20,tile_path,cord,20,1)
|
| 82 |
+
start_time_20m = timer('create 20m image',start_time_20m)
|
| 83 |
+
|
| 84 |
+
start_time_60m = timer('create 60m image',None)
|
| 85 |
# bandes with 60m resolution
|
| 86 |
#path_cld_60
|
| 87 |
images_60 = extract_sub_image(bandes_path_60,tile_path,cord,60)
|
| 88 |
+
start_time_60m = timer('create 60m image',start_time_60m)
|
| 89 |
#
|
| 90 |
+
start_time_make_prediction = timer('make prediction',None)
|
| 91 |
feature = images_10.tolist()+images_20.tolist()+images_60.tolist()
|
| 92 |
bands = ['B02', 'B03', 'B04', 'B05', 'B06', 'B07', 'B08', 'B8A', 'B11', 'B12','B01','B09']
|
| 93 |
X = pd.DataFrame([feature],columns = bands)
|
|
|
|
| 99 |
# make prediction
|
| 100 |
biomass = loaded_model.predict(X)[0]
|
| 101 |
carbon = 0.55*biomass
|
| 102 |
+
timer('make prediction',start_time_make_prediction)
|
| 103 |
|
| 104 |
# NDVI
|
| 105 |
+
start_time_make_ndvi = timer('NDVI calculation',None)
|
| 106 |
ndvi_index = ndvi(cord,name)
|
| 107 |
+
timer('NDVI calculation',start_time_make_ndvi)
|
| 108 |
+
|
| 109 |
timer('processing data',start_time_processing)
|
| 110 |
+
|
| 111 |
# deleted download files
|
| 112 |
delete_tiles()
|
| 113 |
|