tests fix

.github/workflows/checks.yml

@@ -28,9 +28,9 @@
 #       run: black . --check --diff
 #     - name: flake8
 #       run: |
-#         flake8 factfinder
+#         flake8 sloyka
 #         flake8 tests
 #     - name: isort
 #       run: |
-#         isort factfinder --check --diff
+#         isort sloyka --check --diff
 #         isort tests --check --diff

Makefile

@@ -1,4 +1,4 @@
-FILES = ./factfinder/src/*
+FILES = ./sloyka/src/*
 
 lint:
 	@echo "Running pylint check..."

examples/data_getter_example.ipynb

@@ -208,8 +208,8 @@
     "\n",
     "sys.path.append(project_root)\n",
     "\n",
-    "from factfinder.src.data_getter import GeoDataGetter\n",
-    "from factfinder.src.constants import OSM_TAGS\n",
+    "from  sloyka  import GeoDataGetter\n",
+    "from sloyka import OSM_TAGS\n",
     "\n",
     "geo_data_getter = GeoDataGetter()\n",
     "\n",

examples/geocoder_example.ipynb

@@ -30,7 +30,7 @@
     "folder = os.getcwd().split(\"\\\\examples\")[0]\n",
     "sys.path.append(folder)\n",
     "\n",
-    "from factfinder import Geocoder"
+    "from sloyka import Geocoder"
    ]
   },
   {

examples/pipeline_example.ipynb

@@ -8,7 +8,7 @@
    "source": [
     "import torch\n",
     "import pandas as pd\n",
-    "from factfinder import (\n",
+    "from sloyka import (\n",
     "    EventDetection,\n",
     "    Geocoder,\n",
     "    TextClassifier,\n",

tests/test_classifiers.py

@@ -1,9 +1,9 @@
 import pytest
 import torch
 import pandas as pd
-from sloyka.src.text_classifiers import TextClassifiers
+from sloyka import TextClassifiers
 
-path_to_file = "C:/Users/trolo/CodeNIRMA/sloyka/data/raw/Адмиралтейский.csv"
+path_to_file = "data/raw/Адмиралтейский.csv"
 
 @pytest.fixture
 def test_data():
@@ -21,26 +21,6 @@ def model():
         device_type=torch.device("cpu"),
     )
 
-def test_init():
-    # Arrange
-    repository_id = "Sandrro/text_to_subfunction_v10"
-    number_of_categories = 1
-    device_type = torch.device("cpu")
-
-    # Act
-    classifier = TextClassifiers(
-        repository_id, number_of_categories, device_type
-    )
-
-    # Assert
-    assert classifier.REP_ID == repository_id
-    assert classifier.CATS_NUM == number_of_categories
-    assert classifier.classifier.model.name_or_path == repository_id
-    assert (
-        classifier.classifier.tokenizer.name_or_path
-        == "cointegrated/rubert-tiny2"
-    )
-
 def test_cats_probs(model, test_data):
     expected_df = pd.DataFrame(
         {
@@ -57,74 +37,4 @@ def test_cats_probs(model, test_data):
         test_data["Текст"].progress_map(lambda x: model.run_text_classifier_topics(x)).to_list()
     )
     assert test_data["cats"].equals(expected_df["cats"])
-    assert test_data["probs"].equals(expected_df["probs"])
-
-@pytest.fixture
-def test_data():
-    df_predict = pd.read_csv(path_to_file, sep=";")
-    df_predict.rename(columns={"Текст комментария": "Текст"}, inplace=True)
-    df_predict = df_predict.dropna(subset=["Текст"])
-    df_predict = df_predict.head(3)
-    return df_predict
-
-@pytest.fixture
-def model():
-    return TextClassifiers(
-        repository_id="Sandrro/text_to_function_v2",
-        number_of_categories=1,
-        device_type=torch.device("cpu"),
-    )
-
-def test_init():
-    # Arrange
-    repository_id = "Sandrro/text_to_function_v2"
-    number_of_categories = 1
-    device_type = torch.device("cpu")
-
-    # Act
-    classifier = TextClassifiers(
-        repository_id, number_of_categories, device_type
-    )
-
-    # Assert
-    assert classifier.REP_ID == repository_id
-    assert classifier.CATS_NUM == number_of_categories
-    assert classifier.classifier.model.name_or_path == repository_id
-    assert (
-        classifier.classifier.tokenizer.name_or_path
-        == "cointegrated/rubert-tiny2"
-    )
-
-
-@pytest.mark.parametrize(
-    "text, expected_cats, expected_probs",
-    [
-        # Первый тестовый текст с одной категорией
-        ("Хочу окунуться в это пространство.", "Благоустройство", "0.874")
-    ],
-)
-
-# Определяем тестовую функцию
-# Создаем объект класса TextClassifier с параметрами по умолчанию
-def test_run(text, expected_cats, expected_probs, model):
-    # Вызываем метод run с входным текстом и получаем список с категориями и вероятностями
-    cats, probs = model.run_text_classifier(text)
-
-    # Проверяем, что категории и вероятности равны ожидаемым
-    assert cats == expected_cats
-    assert probs == expected_probs
-
-
-def test_cats_probs(model, test_data):
-    expected_df = pd.DataFrame(
-        {
-            "cats": ["Благоустройство", "Другое", "Транспорт"],
-            "probs": ["0.874", "0.538", "0.789"],
-        }
-    )
-
-    test_data[["cats", "probs"]] = pd.DataFrame(
-        test_data["Текст"].progress_map(lambda x: model.run_text_classifier(x)).to_list()
-    )
-    assert test_data["cats"].equals(expected_df["cats"])
-    assert test_data["probs"].equals(expected_df["probs"])
+    assert test_data["probs"].equals(expected_df["probs"])

tests/test_data_getters.py

@@ -31,7 +31,7 @@ def geo_data_getter():
 @pytest.mark.parametrize(
     "osm_id, tags, result_len",
     [
-        (421007, {tdict[0][0]: tdict[0][1]}, 294),
+        (421007, {tdict[0][0]: tdict[0][1]}, 305),
     ],
 )
 def test_process_data_and_assert(geo_data_getter, osm_id, tags, result_len):

tests/test_events_modelling.py

@@ -21,7 +21,7 @@ def test_event_detection(gdf):
     expected_risk = 0.405
     expected_messages = [4, 5, 3, 2]
     event_model = EventDetection()
-    messages, events, connections = event_model.run(
+    _, events, _ = event_model.run(
         gdf, path_to_population, "Санкт-Петербург", 32636, min_event_size=3
     )
     event_name = events.iloc[0]["name"]

tests/test_geocoder.py

@@ -1,6 +1,6 @@
 import pandas as pd
 import pytest
-from factfinder.src.geocoder import Geocoder
+from sloyka import Geocoder
 
 osm_city_level: int = 5
 osm_city_name: str = "Санкт-Петербург"

tests/test_location.py

@@ -1,20 +1,6 @@
 
-from sloyka.src.geocoder import Geocoder
-
-# def test_geocode_with_retry(input_address, geocode_result):
-#     result = Location().geocode_with_retry(input_address)
-#     assert result.address == geocode_result
-
-
-# def test_geocode_with_retry_empty_address():
-#     result = Location().geocode_with_retry("")
-#     assert result is None
-
-
-# def test_query(input_address, geocode_result):
-#     result = Location().query(input_address)
-#     assert result.address == geocode_result
-
+from sloyka import Geocoder
+import pytest
 
 @pytest.mark.parametrize(
     "input_address,geocode_result",