pull_from_geodatenviewer_list() and pull_geodatenviewer_meas()

measprocess/geospatial.py

 import time
 import warnings
-
 import geopandas as gpd
 import matplotlib.pyplot as plt
 import numpy as np
@@ -8,7 +7,13 @@ import overpy
 from scipy.spatial.distance import cdist
 from shapely.geometry import LineString, Point, Polygon, box
 from shapely.ops import unary_union
-
+import os
+import shutil
+import urllib.request
+import zipfile
+from typing import List
+import pandas as pd
+import tempfile
 
 def make_overpy_request(request_body: str, retries: int):
     for _ in range(retries):
@@ -311,3 +316,88 @@ def delete_indoor_meas(
     outdoor_meas_gdf = meas_gdf.drop(indoor_meas_gdf.index).reset_index()
 
     return outdoor_meas_gdf.geometry
+
+
+def pull_from_geodatenviewer_list(squares: List[str]) -> gpd.GeoDataFrame:
+    """
+    Downloads .zip files for specified squares from https://www.wien.gv.at/ma41datenviewer/public/,
+    extracts and combines all .shp files to single geopandas geodataframe, then deletes the dir_path directory.
+
+    :param dir_path: path to the directory where the files will be downloaded and extracted to
+    :param squares: list of integers denoting the squares to be downloaded
+
+    :return: geopandas geodataframe containing all data from .shp files
+    """
+
+    dir_path = tempfile.mkdtemp() # create temporary directory
+
+    # downloading .zip files
+    # example of single square with data: https://www.wien.gv.at/ma41datenviewer/downloads/ma41/geodaten/fmzk_bkm/103081_bkm.zip
+    for square_number in squares:
+        urllib.request.urlretrieve(
+            "https://www.wien.gv.at/ma41datenviewer/downloads/ma41/geodaten/fmzk_bkm/{}_bkm.zip".format(
+                square_number
+            ),
+            os.path.join(dir_path, "{}.zip".format(square_number)),
+        )
+
+    # extracting and deleting .zip files
+    for item in os.listdir(dir_path):  # loop through items in dir
+        if item.endswith(".zip"):
+            file_name = os.path.join(dir_path, item)
+            zip_ref = zipfile.ZipFile(file_name)  # create zipfile object
+            zip_ref.extractall(dir_path)  # extract file to dir
+            zip_ref.close()
+            os.remove(file_name)  # delete zipped file
+
+    # combine all .shp files
+    geo_df_all = pd.DataFrame()
+    for square in squares:
+        geo_df = gpd.read_file(os.path.join(dir_path, square + "_bkm.shp"))
+        geo_df_all = pd.concat([geo_df_all, geo_df], ignore_index=True)
+
+    shutil.rmtree(dir_path)  # deletes the directory containing all the files
+    return geo_df_all
+
+
+def pull_from_geodatenviewer_meas(measurement_coords: gpd.GeoSeries) -> gpd.GeoDataFrame:
+    '''
+    Downloads raster .zip file for Vienna Austria, extracts all raster polygon IDs containing measurements, 
+    then calls pull_from_geodatenviewer_list() to extract building polygons.
+
+    :param measurement_coords: geopandas geoseries containing measurements in EPSG:4326 projection
+
+    :return: geopandas geodataframe containing all data from .shp files
+    '''
+
+    if measurement_coords.crs != "EPSG:4326":
+        raise ValueError("Make sure to pass data with EPSG:4326 projection")
+
+    raster_path = tempfile.mkdtemp()
+    urllib.request.urlretrieve(
+            "https://data.wien.gv.at/daten/geo?service=WFS&request=GetFeature&version=1.1.0&typeName=ogdwien:MZKBLATT1000OGD&srsName=EPSG:4326&outputFormat=shape-zip",
+            os.path.join(raster_path, "raster.zip"),
+        )
+    
+    file_name = os.path.join(raster_path, "raster.zip")
+    zip_ref = zipfile.ZipFile(file_name)  # create zipfile object
+    zip_ref.extractall(raster_path)  # extract file to dir
+    zip_ref.close()
+    os.remove(file_name)  # delete zipped file
+
+    for file in os.listdir(raster_path):
+        if file.endswith(".shp"):
+            	raster_gdf = gpd.read_file(os.path.join(raster_path, file))
+    if raster_gdf.geometry.crs != 'EPSG:4326':
+        raise ValueError('Raster EPSG has changed, see https://www.data.gv.at/katalog/dataset/b2d17060-b2f4-4cd7-a2e5-64beccfeb4c1 for mor information.')
+
+    meas_gdf = gpd.GeoDataFrame(geometry=measurement_coords)
+
+    poly_gdf = gpd.sjoin(raster_gdf, meas_gdf, op = 'contains') # find all polygons from raster that contain measurements
+
+    polygonID_list = poly_gdf.MZK1000.unique()
+    return_gdf = pull_from_geodatenviewer_list(polygonID_list)
+
+    return return_gdf
+
+

measprocess/preprocess.py

@@ -4,12 +4,11 @@ import shutil
 import urllib.request
 import zipfile
 from typing import List
-
 import geopandas as gpd
 import numpy as np
 import pandas as pd
 from tqdm import tqdm
-
+import tempfile
 
 def link_dataframes(
     A: pd.DataFrame, B: pd.DataFrame, ref_col: str, metric=None, verbose=True
@@ -67,52 +66,3 @@ def link_dataframes(
     return combined, np.array(deviations)
 
 
-def pull_from_geodatenviewer(dir_path: str, squares: List[int]) -> gpd.GeoDataFrame:
-    """
-    Downloads .zip files for specified squares from https://www.wien.gv.at/ma41datenviewer/public/,
-    extracts and combines all .shp files to single geopandas geodataframe, then deletes the dir_path directory.
-
-    :param dir_path: path to the directory where the files will be downloaded and extracted to
-    :param squares: list of integers denoting the squares to be downloaded
-
-    :return: geopandas geodataframe containing all data from .shp files
-
-    ToDo: extend this function to select squares automatically based on measurement coordinates
-
-    """
-
-    # creates new directory if it doesn't exist
-    try:
-        os.makedirs(dir_path)
-    except FileExistsError:
-        raise Exception(
-            "The folder under this name already exists, choose another name for your directory."
-        )
-
-    # downloading .zip files
-    # example of single square with data: https://www.wien.gv.at/ma41datenviewer/downloads/ma41/geodaten/fmzk_bkm/103081_bkm.zip
-    for square_number in squares:
-        urllib.request.urlretrieve(
-            "https://www.wien.gv.at/ma41datenviewer/downloads/ma41/geodaten/fmzk_bkm/{}_bkm.zip".format(
-                square_number
-            ),
-            os.path.join(dir_path, "{}.zip".format(square_number)),
-        )
-
-    # extracting and deleting .zip files
-    for item in os.listdir(dir_path):  # loop through items in dir
-        if item.endswith(".zip"):
-            file_name = os.path.join(dir_path, item)
-            zip_ref = zipfile.ZipFile(file_name)  # create zipfile object
-            zip_ref.extractall(dir_path)  # extract file to dir
-            zip_ref.close()
-            os.remove(file_name)  # delete zipped file
-
-    # combine all .shp files
-    geo_df_all = pd.DataFrame()
-    for square in squares:
-        geo_df = gpd.read_file(os.path.join(dir_path, str(square) + "_bkm.shp"))
-        geo_df_all = pd.concat([geo_df_all, geo_df], ignore_index=True)
-
-    shutil.rmtree(dir_path)  # deletes the directory containing all the files
-    return geo_df_all