[i] added todos and get INCA RR data in func

FHSTP/prep.py

@@ -2,8 +2,8 @@
 # Title: Data Preparation for LINK Configs and Transmissions
 # Author: Fabian Kovac <ds191008@fhstp.ac.at>
 # Team: University of Applied Sciences St. Pölten
-# Version: 1.1
-# Last changed: 2021-06-21
+# Version: 1.2
+# Last changed: 2021-06-22
 #
 
 import sys
@@ -201,8 +201,8 @@ def utm_to_lambert(lon: np.array, lat: np.array) -> tuple:
     return x, y
 
 
-def lambert_to_inca_coords(x: np.array, y: np.array) -> tuple:
-    """Convert x and y of Lambert Conic Conformal Projection to INCA coordinates
+def lambert_to_inca_idx(x: np.array, y: np.array) -> tuple:
+    """Convert x and y of Lambert Conic Conformal Projection to INCA index
     (rounded lambert coordinates)
     
     Parameters:
@@ -216,23 +216,24 @@ def lambert_to_inca_coords(x: np.array, y: np.array) -> tuple:
     return np.round(x/1000, decimals = 0).astype(int), np.round(y/1000, decimals = 0).astype(int)
 
 
-def get_inca_indices(datetimes: np.array, x: np.array, y: np.array) -> np.array:
-    """Get indices of INCA RR data based on Lamber Conic Conformal Coordinates
+def get_inca_data(inca_data: np.array, datetimes: np.array, x: np.array, y: np.array) -> np.array:
+    """Get INCA RR data based on Lamber Conic Conformal Coordinates
     
     Parameters:
+        inca_data (np.array): Tensor containing INCA RR data
         datetimes (np.array): Vector containing datetimes of transmissions
         x (np.array): Vector containing x values of LINK
         y (np.array): Vector containing y values of LINK
     
     Returns:
-        idx_times, idx, idy (np.array): Three vectors containing indices to INCA RR data
+        inca_RR (np.array): Vector containing INCA RR data based on datetimes and lambert coordinates
 	"""
     
     # convert utm coordinates to lambert conic conformal projection
     lccX, lccY = utm_to_lambert(x, y)
     
     # convert lambert coordinates to INCA indices
-    idx, idy = lambert_to_inca_coords(lccX, lccY)
+    idx, idy = lambert_to_inca_idx(lccX, lccY)
     
     
     # generate times of day in 15min (window) intervals
@@ -242,11 +243,20 @@ def get_inca_indices(datetimes: np.array, x: np.array, y: np.array) -> np.array:
     # generate times of LINK data
     link_times = datetimes.map(lambda x: f'{x[-4:-2]}:{x[-2:]}')
     
-    # get LINK indices of INCA times
+    # get INCA indices of LINK times
     idx_times = np.searchsorted(inca_times, link_times)
     
-    # return INCA data based on time indices and lambert coordinates    
-    return idx_times, idx, idy
+    
+    # get INCA RR data based on time indices and lambert coordinates
+    inca_RR = inca_data[idx_times, idy, idx]
+    
+    # TODO: discuss retrieving INCA RR data
+    # currently data is based on the exact point of the link
+    # maybe get mean RR of 5x5 km grid around point?
+    # maybe get RR data based on conv2d with a 5x5 gaussian filter around point?
+    # --> let's discuss!
+    
+    return inca_RR
 
 
 def prep() -> None:
@@ -260,7 +270,7 @@ def prep() -> None:
     
     _log('\n******************************** READ FILES ********************************')
     
-    # read files
+    # read config and transmission files
     df_config = pd.read_csv(file_config, sep = ';')
     _log(f'Read config file with shape {df_config.shape}')
     df_trans = pd.read_csv(file_trans, sep = ';')
@@ -449,13 +459,10 @@ def prep() -> None:
     inca_data = load_inca_data(dir_inca)
     _log(f'Loaded INCA data from {str(dir_inca).split("/")[-1]}')
     
-    idx_times, IxStart, IyStart = get_inca_indices(df_link['DateTime'], df_link['XStart'], df_link['YStart'])
-    _, IxEnd, IyEnd = get_inca_indices(df_link['DateTime'], df_link['XEnd'], df_link['YEnd'])
-    _log('Calculated INCA RR indices based on lambert coordinates and datetimes')
-    
-    df_link['RRStart'] = inca_data[idx_times, IyStart, IxStart]
-    df_link['RREnd'] = inca_data[idx_times, IyEnd, IxEnd]
-    _log('Set INCA RR data based on lambert coordinates')
+    # set INCA RR data based on datetime and coordinates
+    df_link['RRStart'] = get_inca_data(inca_data, df_link['DateTime'], df_link['XStart'], df_link['YStart'])
+    df_link['RREnd'] = get_inca_data(inca_data, df_link['DateTime'], df_link['XEnd'], df_link['YEnd'])
+    _log('Merged INCA RR data to LINK dataframe')
     
     
     _log('\n******************************** SAVE FILES ********************************')