From 8f99431df30ad7b1701d0ce8dc8b710f2042178f Mon Sep 17 00:00:00 2001
From: Khalim Conn-Kowlessar <kconnkowlessar@gmail.com>
Date: Fri, 16 Jun 2023 09:36:02 +0100
Subject: [PATCH] Added unit tests for land registry

---
 model_data/Need.py                            | 32 ------------
 model_data/app.py                             |  9 ----
 model_data/tests/test_land_registry_client.py | 49 +++++++++++++++++++
 3 files changed, 49 insertions(+), 41 deletions(-)
 delete mode 100644 model_data/Need.py
 create mode 100644 model_data/tests/test_land_registry_client.py

diff --git a/model_data/Need.py b/model_data/Need.py
deleted file mode 100644
index 50e30e54..00000000
--- a/model_data/Need.py
+++ /dev/null
@@ -1,32 +0,0 @@
-import pandas as pd
-from model_data.utils import setup_logger
-
-logger = setup_logger()
-
-
-class Need:
-    """
-    Contains methods to read and interface with the NEED dataset.
-
-    Current iterations of this data is the 2021 anonymised dataset, which can be found here:
-    https://www.gov.uk/government/statistics/national-energy-efficiency-data-framework-need-anonymised-data-2021
-    """
-
-    def __init__(self, local_authorities, path):
-        self.local_authorities = local_authorities
-        self.path = path
-
-    def read(self) -> pd.DataFrame:
-        """
-        Reads the NEED dataset from a csv file.
-        :param path:    path to the csv file
-        :return:        pandas dataframe containing the data
-        """
-        logger.info("Reading NEED data - could take a moment")
-        df = pd.read_csv(self.path)
-        df = df[df["REGION"].isin(self.local_authorities)]
-
-        z = df[df["REGION"].str.contains("E9")]
-
-        type(df["REGION"].values[0])
-        return df
diff --git a/model_data/app.py b/model_data/app.py
index 424c19ca..c5a019c9 100644
--- a/model_data/app.py
+++ b/model_data/app.py
@@ -91,15 +91,6 @@ def handler():
     #
     # df.to_dict("records")
 
-    from model_data.Need import Need
-    import os
-
-    need_client = Need(
-        local_authorities=local_authorities,
-        path=os.path.abspath(os.path.dirname(__file__)) + "/model_data/local_data/need_2021_anon_dataset_4million.csv"
-    )
-    need_data = need_client.read()
-
     ## Land registry
     from model_data.LandRegistryClient import LandRegistryClient
     import os
diff --git a/model_data/tests/test_land_registry_client.py b/model_data/tests/test_land_registry_client.py
new file mode 100644
index 00000000..97a30641
--- /dev/null
+++ b/model_data/tests/test_land_registry_client.py
@@ -0,0 +1,49 @@
+import pandas as pd
+from unittest.mock import patch, call
+from model_data.LandRegistryClient import LandRegistryClient
+
+
+class TestLandRegistryClient:
+    @patch('pandas.read_csv')
+    @patch('fuzzywuzzy.fuzz.ratio')
+    def test_read(self, mock_fuzz, mock_read_csv):
+        # setup mocks
+        mock_read_csv.return_value = pd.DataFrame([
+            ['1', '815000', '2022-06-28', 'SW6 3JA', 'F', 'N', 'L', 'FLAT', 'GROUND FLOOR', '6 DYMOCK STREET', None,
+             'LONDON', 'HAMMERSMITH AND FULHAM', 'GREATER LONDON', 'A', 'Y'],
+            ['2', '200', '2023-03-04', 'N16 0EG', 'S', 'N', 'F', '25', None, 'DEFOE ROAD', None, 'LONDON', 'HACKNEY',
+             'GREATER LONDON', 'B', 'Y'],
+            ['3', '300', '2023-03-05', 'N16 0EG', 'O', 'Y', 'L', '26', None, 'DEFOE ROAD', None, 'LONDON', 'HACKNEY',
+             'GREATER LONDON', 'A', 'N']
+        ], columns=LandRegistryClient.COLUMN_NAMES)
+        mock_fuzz.side_effect = [70, 100, 50]
+
+        # setup client
+        addresses = [{
+            'postcode': 'SW6 3JA', 'address1': 'GROUND FLOOR', 'address2': 'FLAT 6 DYMOCK STREET', 'address3': 'FULHAM',
+            'address': 'Ground Floor Flat, 6 Dymock Street, Fulham', 'uprn': '34063921'
+        }]
+        client = LandRegistryClient(['path_to_data.csv'], addresses)
+
+        # call read
+        result = client.read()
+
+        # assertions
+        mock_read_csv.assert_called_once_with('path_to_data.csv', header=None)
+
+        assert mock_fuzz.call_args_list == [
+            call('GROUND FLOOR FLAT 6 DYMOCK STREET ', 'GROUND FLOOR FLAT 6 DYMOCK STREET FULHAM'),
+            call('GROUND FLOOR FLAT 6 DYMOCK STREET ', 'GROUND FLOOR FLAT 6 DYMOCK STREET FULHAM')
+        ]
+
+        pd.testing.assert_frame_equal(result, pd.DataFrame({
+            'price': ["815000"],
+            'date_of_transfer': ['2022-06-28'],
+            'property_type': ['F'],
+            'old_new': ['N'],
+            'duration': ['L'],
+            'ppd_category_type': ['A'],
+            'record_status': ['Y'],
+            'uprn': ['34063921'],
+            'address': ['Ground Floor Flat, 6 Dymock Street, Fulham']
+        }))