Comment out plotting clipped SAR image

eo_learn/main_eoLearn.py

@@ -79,9 +79,9 @@ CLIENT_ID =     'fa722f2a-4dec-487e-aebd-16a03646379a'
 CLIENT_SECRET = ']GsJ)JrZ<s:iXxK4KerK{vfvG-e;_3TB[eXIX+8,'
 
 start = '2022-01-01'
-end = '2022-04-01'
+end = '2022-07-01'
 coordinates = (-72.243484,19.697338,-72.154221,19.773160)
-dest_name = "CapHaitien_JanFebMar2022_completeFilterLee5x5"
+dest_name = "CapHaitien_Jan2022Jun2022"
 resolution = 4
 
 # Visualise results (y/n)? And if so, which band(s) (VV, VH, VVVH, DEM)?

urban_areas/main1_precipDownload.py

@@ -55,16 +55,16 @@ from urban_areas.py.s13CalculatePrecipSum import calculatePrecipSum
 # =============================================================================
 # DEFINE INPUT PARAMETERS
 # =============================================================================
-start = '2020-01-01'
-end = '2022-06-30'
-coordinates = (-72.190141,19.721568,-72.173747,19.739352)
-dest_name = "CapHaitien_Jan2020Jun2022"
-grid = 3
+start = '2022-01-01'
+end = '2022-07-01'
+coordinates = (-72.225786,19.719889,-72.173258,19.765477)
+dest_name = "CapHaitien_Jan2022Jun2022"
+grid = 4
 sum_days = 14
 
 # Visualise coordinates (y/n)? If so, define SAR_path
 visualise = "y"
-SAR_path = 'CapHaitien_Jan2020Jun2022'
+SAR_path = 'CapHaitien_Jan2022Jun2022'
 
 # =============================================================================
 # EXECUTE STEPS

urban_areas/main2_urbanSAR.py

@@ -61,9 +61,9 @@ from Urban_areas.py.s23OutlierDetection import visualOutlierDetection, statistic
 # =============================================================================
 # PARAMETERS FOR RASTER CLIPPING
 # Make 'coordinates' an empty tuple to take SAR image as extent 
-SAR_path = 'SAR/CapHaitien_try1'
+SAR_path = 'CapHaitien_Jan2022Jun2022'
 urban_raster = 'urban_areas/GHS_BUILT_S_E2018_GLOBE_R2022A_HAITI.tif' 
-coordinates = (-72.221598,19.733007,-72.192072,19.757579)
+coordinates = (-72.225786,19.719889,-72.173258,19.765477)
 
 # Show boundingbox in map? (y/n) (not exported to output)
 show_bbox = 'y'
@@ -71,7 +71,7 @@ show_bbox = 'y'
 # =============================================================================
 # PARAMETERS FOR VISUALISATION
 # Add file name of the precipitation data that should be linked to the mean vv (including '.CSV')
-precipitation_csv = 'precipitation_data/daily_precipitation_avg14days_CapHaitien_Jan2020Jun2022.CSV'
+precipitation_csv = 'precipitation_data/daily_precipitation_avg14days_CapHaitien_Jan2022Jun2022.CSV'
 
 # =============================================================================
 # EXECUTE RASTER CLIPPING
@@ -94,18 +94,18 @@ file_name, path_mean_vv = exportToCSV(mean_values, dates, SAR_path)
 # =============================================================================
 # VISUALISE RESULTS AND OUTLIER DETECTION
 # =============================================================================
-# # STEP 1: LINEPLOTS OF MEAN VV BACKSCATTER, AVG PRECIPITATION, AND SUM PRECIPITATION
-# df_total, days, mean_VV, sum_xdays, title_name = visualiseData(SAR_path, precipitation_csv, file_name, path_mean_vv)
+# STEP 1: LINEPLOTS OF MEAN VV BACKSCATTER, AVG PRECIPITATION, AND SUM PRECIPITATION
+df_total, days, mean_VV, sum_xdays, title_name = visualiseData(SAR_path, precipitation_csv, file_name, path_mean_vv)
 
-# # STEP 2: VISUAL OUTLIER DETECTION
-# output_dir = visualOutlierDetection(title_name, df_total, days, mean_VV, sum_xdays)
+# STEP 2: VISUAL OUTLIER DETECTION
+output_dir = visualOutlierDetection(title_name, df_total, days, mean_VV, sum_xdays)
 
-# # STEP 3: STATISTICAL OUTLIER DETECTION
-# df_outlier, LR_columns = statisticalOutlierDetection(df_total, mean_VV, sum_xdays)
-# visualiseStatisticalOutliers(output_dir, title_name, df_outlier, LR_columns, mean_VV, sum_xdays, days)
+# STEP 3: STATISTICAL OUTLIER DETECTION
+df_outlier, LR_columns = statisticalOutlierDetection(df_total, mean_VV, sum_xdays)
+visualiseStatisticalOutliers(output_dir, title_name, df_outlier, LR_columns, mean_VV, sum_xdays, days)
 
-# # STEP 4: EXPORT OUTLIER DETECTION DF
-# exportOutlierDetection(output_dir, df_outlier, title_name)
+# STEP 4: EXPORT OUTLIER DETECTION DF
+exportOutlierDetection(output_dir, df_outlier, title_name)
 
 
 print(f"----- {round((time.time() - start_time), 2)} seconds -----")

urban_areas/py/s21UrbanClipping.py

@@ -54,9 +54,11 @@ def createBbox(coordinates, SAR_path, show_bbox='n'):
     
     if show_bbox == 'y':
         # Plot bbox and first SAR image
-        fig, ax = plt.subplots(figsize=(5,5))
+        fig, ax = plt.subplots(figsize=(20,20))
         rio.plot.show(SAR, ax=ax)
-        gdf.plot(ax=ax, facecolor='none', edgecolor='red')    
+        gdf.plot(ax=ax, facecolor='none', edgecolor='red', linewidth=5)
+        plt.axis("off")
+        plt.show()
     
     return gdf
 
@@ -207,23 +209,8 @@ def clipSAR(SAR_path, gpd_urban, coordinates):
         # ax.imshow(SAR_clipped) 
         # plt.axis('off')
         # plt.title(f'VV backscatter urban areas ({tif[0:10]})', fontdict={'fontsize': 30})
+        # # plt.savefig(f"Urban_areas/output/{tif[0:10]}.png", dpi=300)
         # plt.show()
-        
-        
-        
-    
-    mosaic, output = merge(raster_to_mosaic)
-    output_meta = SAR_clipped.meta.copy()
-    output_meta.update(
-        {"driver": "GTiff",
-            "height": mosaic.shape[1],
-            "width": mosaic.shape[2],
-            "transform": output,
-        }
-    )
-    output_path = os.path.join('Urban_areas', 'output')
-    with rio.open(output_path, 'w', **output_meta) as m:
-        m.write(mosaic)
     
     return list_of_means, list_of_dates