further breaking up code

.gitignore

@@ -250,4 +250,5 @@ backend/node_modules
 node_modules/
 backend/.idea
 open_uprn/.idea/
+conservation_areas/.idea/
 

.idea/Model.iml

@@ -6,7 +6,7 @@
       <sourceFolder url="file://$MODULE_DIR$/model_data" isTestSource="false" />
       <sourceFolder url="file://$MODULE_DIR$/open_uprn" isTestSource="false" />
     </content>
-    <orderEntry type="jdk" jdkName="Python 3.10 (hestia-data)" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="Python 3.10 (conservation_areas)" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
 </module>

.idea/misc.xml

@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (hestia-data)" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (conservation_areas)" project-jdk-type="Python SDK" />
   <component name="PythonCompatibilityInspectionAdvertiser">
     <option name="version" value="3" />
   </component>

conservation_areas/ConservationAreaClient.py

@@ -1,7 +1,8 @@
 from enum import Enum
 import geopandas as gpd
 from shapely.geometry import Point
-from model_data.utils import setup_logger
+from utils.logger import setup_logger
+from datatypes.datatypes import OpenUprnCoordinateData
 
 logger = setup_logger()
 
@@ -39,7 +40,13 @@ class ConservationAreaClient:
         self.gov_data = gpd.read_file(self.gov_path)
         self.gov_data = self.gov_data.drop(columns=["dataset"])
 
-    def is_in_conservation_area(self, coordinates: dict):
+    def is_in_conservation_area(self, coordinates: OpenUprnCoordinateData):
+
+        """
+        Check if a property is in a conservation area
+        :param coordinates: dictionary, which should have the OpenUprnCoordinateData format
+        :return:
+        """
 
         if not coordinates:
             raise ValueError("Coordinates have not been set, run get_coordinates() first")

conservation_areas/app.py

@@ -0,0 +1,53 @@
+"""
+This application reads in the open uprn data from a static location and loads it into
+our database for querying from other services
+"""
+
+import os
+from conservation_areas.ConservationAreaClient import ConservationAreaClient
+
+
+def app():
+    conservation_area_client = ConservationAreaClient(
+        historic_england_path=os.path.abspath(
+            os.path.dirname(__file__)
+        ) + "/model_data/local_data/Historic_Eng_Conservation_Areas/Conservation_Areas.shp",
+        gov_path=os.path.abspath(
+            os.path.dirname(__file__)
+        ) + "/model_data/local_data/gov-conservation-area.geojson"
+    )
+    conservation_area_client.read()
+
+    # We need to iterate through the open uprn data and check if the coordinates are in a conservation area
+    open_uprn_data = [
+        {'UPRN': 6032920, 'X_COORDINATE': 535110.0, 'Y_COORDINATE': 181819.0, 'LATITUDE': 51.5191407,
+         'LONGITUDE': -0.0540506},
+        {'UPRN': 6038625, 'X_COORDINATE': 535374.0, 'Y_COORDINATE': 182784.0, 'LATITUDE': 51.5277492,
+         'LONGITUDE': -0.0498772},
+        {'UPRN': 34153991, 'X_COORDINATE': 523238.74, 'Y_COORDINATE': 178003.02, 'LATITUDE': 51.4875579,
+         'LONGITUDE': -0.226392},
+        {'UPRN': 10008299676, 'X_COORDINATE': 533285.0, 'Y_COORDINATE': 184711.0, 'LATITUDE': 51.5455629,
+         'LONGITUDE': -0.0792445},
+        {'UPRN': 10008299677, 'X_COORDINATE': 533285.0, 'Y_COORDINATE': 184711.0, 'LATITUDE': 51.5455629,
+         'LONGITUDE': -0.0792445},
+        {'UPRN': 100021039066, 'X_COORDINATE': 535506.0, 'Y_COORDINATE': 185624.0, 'LATITUDE': 51.5532385,
+         'LONGITUDE': -0.0468833},
+        {'UPRN': 100021226060, 'X_COORDINATE': 529247.0, 'Y_COORDINATE': 187959.0, 'LATITUDE': 51.5756908,
+         'LONGITUDE': -0.1362513},
+        {'UPRN': 200003489276, 'X_COORDINATE': 533210.0, 'Y_COORDINATE': 179442.0, 'LATITUDE': 51.4982309,
+         'LONGITUDE': -0.0823165}
+    ]
+
+    result = [conservation_area_client.is_in_conservation_area(coordinates) for coordinates in open_uprn_data]
+
+    conservation_area_client
+
+    uprns = [
+        int(x) for x in
+        ['34153991', '6038625', '100021039066', '100021226060', '10008299676', '10008299677', '6032920', '200003489276']
+    ]
+
+    open_uprn_client.data[open_uprn_client.data["UPRN"].isin(
+        uprns
+    )].to_dict("records")
+    # TODO: Add a method to write to the database

conservation_areas/requirements.txt

@@ -0,0 +1,16 @@
+attrs==23.1.0
+certifi==2023.5.7
+click==8.1.6
+click-plugins==1.1.1
+cligj==0.7.2
+fiona==1.9.4.post1
+geopandas==0.13.2
+numpy==1.25.1
+packaging==23.1
+pandas==2.0.3
+pyproj==3.6.0
+python-dateutil==2.8.2
+pytz==2023.3
+shapely==2.0.1
+six==1.16.0
+tzdata==2023.3

datatypes/datatypes.py

@@ -0,0 +1,10 @@
+from dataclasses import dataclass
+
+
+@dataclass
+class OpenUprnCoordinateData:
+    UPRN: int
+    X_COORDINATE: float
+    Y_COORDINATE: float
+    LATITUDE: float
+    LONGITUDE: float

model_data/BoreholeClient.py

@@ -1,7 +1,7 @@
 import math
 from tqdm import tqdm
 from dbfread import DBF
-from model_data.utils import setup_logger
+from utils.logger import setup_logger
 
 logger = setup_logger()
 

model_data/LandRegistryClient.py

@@ -2,7 +2,7 @@ from typing import List, Dict
 import pandas as pd
 from tqdm import tqdm
 import string
-from model_data.utils import setup_logger
+from utils.logger import setup_logger
 from fuzzywuzzy import fuzz
 import numpy as np
 

model_data/analysis/SapModel.py

@@ -13,7 +13,7 @@ from model_data.EpcClean import EpcClean
 
 from statsmodels.stats.outliers_influence import variance_inflation_factor
 from tqdm import tqdm
-from model_data.utils import setup_logger
+from utils.logger import setup_logger
 
 logger = setup_logger()
 

model_data/app.py

@@ -2,7 +2,7 @@ from tqdm import tqdm
 import os
 from model_data.BoreholeClient import BoreholeClient
 from model_data.LandRegistryClient import LandRegistryClient
-from model_data.ConservationAreaClient import ConservationAreaClient
+from conservation_areas.ConservationAreaClient import ConservationAreaClient
 
 from model_data.temp_inputs import input_data
 from model_data.Property import Property

model_data/tests/test_utils.py

@@ -1,7 +1,8 @@
 import logging
 from io import StringIO
 from unittest.mock import patch
-from model_data.utils import setup_logger, is_percentage_or_number, correct_spelling
+from model_data.utils import is_percentage_or_number, correct_spelling
+from utils.logger import setup_logger
 
 
 class TestLogger:

model_data/utils.py

@@ -1,4 +1,3 @@
-import logging
 import re
 from textblob import TextBlob
 
@@ -6,40 +5,6 @@ from textblob import TextBlob
 PERCENTAGE_PATTERN = re.compile(r'^\d+%?$')
 
 
-def setup_logger(log_file=None, level=logging.INFO, overwrite_handler=False):
-    # Create a logger and set the logging level
-    logger = logging.getLogger()
-    logger.setLevel(level)
-
-    # if logger already has handlers, just return it
-    if logger.hasHandlers() and not overwrite_handler:
-        return logger
-
-    # Define the log message format
-    log_format = "%(asctime)s [%(levelname)s] %(message)s"
-    date_format = "%Y-%m-%d %H:%M:%S"
-    formatter = logging.Formatter(log_format, datefmt=date_format)
-
-    # Create a file handler and set the file path and format
-    if log_file:
-        file_handler = logging.FileHandler(log_file)
-        file_handler.setLevel(level)
-        file_handler.setFormatter(formatter)
-        logger.addHandler(file_handler)
-
-    # Create a console handler and set the format
-    console_handler = logging.StreamHandler()
-    console_handler.setLevel(level)
-
-    # Set the formatter for the handlers
-    console_handler.setFormatter(formatter)
-
-    # Add the handlers to the logger
-    logger.addHandler(console_handler)
-
-    return logger
-
-
 def is_percentage_or_number(s):
     # re.match returns None if the string does not match the pattern
     return PERCENTAGE_PATTERN.match(s) is not None

open_uprn/OpenUprnClient.py

@@ -1,5 +1,5 @@
 import pandas as pd
-from model_data.utils import setup_logger
+from utils.logger import setup_logger
 
 logger = setup_logger()
 

open_uprn/app.py

@@ -15,12 +15,4 @@ def app():
     )
     open_uprn_client.read()
 
-    uprns = [
-        int(x) for x in
-        ['34153991', '6038625', '100021039066', '100021226060', '10008299676', '10008299677', '6032920', '200003489276']
-    ]
-
-    open_uprn_client.data[open_uprn_client.data["UPRN"].isin(
-        uprns
-    )].to_dict("records")
     # TODO: Add a method to write to the database

utils/logger.py

@@ -0,0 +1,35 @@
+import logging
+
+
+def setup_logger(log_file=None, level=logging.INFO, overwrite_handler=False):
+    # Create a logger and set the logging level
+    logger = logging.getLogger()
+    logger.setLevel(level)
+
+    # if logger already has handlers, just return it
+    if logger.hasHandlers() and not overwrite_handler:
+        return logger
+
+    # Define the log message format
+    log_format = "%(asctime)s [%(levelname)s] %(message)s"
+    date_format = "%Y-%m-%d %H:%M:%S"
+    formatter = logging.Formatter(log_format, datefmt=date_format)
+
+    # Create a file handler and set the file path and format
+    if log_file:
+        file_handler = logging.FileHandler(log_file)
+        file_handler.setLevel(level)
+        file_handler.setFormatter(formatter)
+        logger.addHandler(file_handler)
+
+    # Create a console handler and set the format
+    console_handler = logging.StreamHandler()
+    console_handler.setLevel(level)
+
+    # Set the formatter for the handlers
+    console_handler.setFormatter(formatter)
+
+    # Add the handlers to the logger
+    logger.addHandler(console_handler)
+
+    return logger