added more tests

am-tropin · Nov 15, 2023 · e32f0b8 · e32f0b8
1 parent c1837d1
commit e32f0b8
Show file tree

Hide file tree

Showing 9 changed files with 26,320 additions and 27 deletions.
diff --git a/.DS_Store b/.DS_Store
diff --git a/app/functions/.ipynb_checkpoints/function_store-checkpoint.ipynb b/app/functions/.ipynb_checkpoints/function_store-checkpoint.ipynb
@@ -39,7 +39,9 @@
    "id": "ef151508",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "APARTMENTS_FILE = \"poland_apartments_completed.csv\""
+   ]
   },
   {
    "cell_type": "code",
@@ -49,7 +51,7 @@
    "outputs": [],
    "source": [
     "def load_data():\n",
-    "    price_df4 = pd.read_csv(\"poland_apartments_completed.csv\")\n",
+    "    price_df4 = pd.read_csv(APARTMENTS_FILE)\n",
     "    cat_features = ['city', 'district'] # 'floor', 'rooms'?\n",
     "    num_features = ['floor', 'rooms', 'sq', 'year', 'radius']\n",
     "    target = ['price']\n",
@@ -339,7 +341,8 @@
    "source": [
     "def check_city_district_radius_floor_rooms(city, district, radius, floor, rooms):\n",
     "    \n",
-    "    price_df4 = pd.read_csv(\"poland_apartments_completed.csv\")\n",
+    "#     price_df4 = pd.read_csv(APARTMENTS_FILE)\n",
+    "    price_df4 = load_data()[0]\n",
     "    floor_values = list(set(price_df4['floor']))\n",
     "    rooms_values = list(set(price_df4['rooms']))\n",
     "    \n",

diff --git a/app/functions/function_store.ipynb b/app/functions/function_store.ipynb
@@ -39,7 +39,9 @@
    "id": "ef151508",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "APARTMENTS_FILE = \"poland_apartments_completed.csv\""
+   ]
   },
   {
    "cell_type": "code",
@@ -49,7 +51,7 @@
    "outputs": [],
    "source": [
     "def load_data():\n",
-    "    price_df4 = pd.read_csv(\"poland_apartments_completed.csv\")\n",
+    "    price_df4 = pd.read_csv(APARTMENTS_FILE)\n",
     "    cat_features = ['city', 'district'] # 'floor', 'rooms'?\n",
     "    num_features = ['floor', 'rooms', 'sq', 'year', 'radius']\n",
     "    target = ['price']\n",
@@ -339,7 +341,8 @@
    "source": [
     "def check_city_district_radius_floor_rooms(city, district, radius, floor, rooms):\n",
     "    \n",
-    "    price_df4 = pd.read_csv(\"poland_apartments_completed.csv\")\n",
+    "#     price_df4 = pd.read_csv(APARTMENTS_FILE)\n",
+    "    price_df4 = load_data()[0]\n",
     "    floor_values = list(set(price_df4['floor']))\n",
     "    rooms_values = list(set(price_df4['rooms']))\n",
     "    \n",

diff --git a/app/functions/function_store.py b/app/functions/function_store.py
@@ -33,14 +33,14 @@
 # In[ ]:
 
 
-
+APARTMENTS_FILE = "poland_apartments_completed.csv"
 
 
 # In[ ]:
 
 
 def load_data():
-    price_df4 = pd.read_csv("poland_apartments_completed.csv")
+    price_df4 = pd.read_csv(APARTMENTS_FILE)
     cat_features = ['city', 'district'] # 'floor', 'rooms'?
     num_features = ['floor', 'rooms', 'sq', 'year', 'radius']
     target = ['price']
@@ -272,7 +272,8 @@ def experiment_initialization(experiment_name):
 
 def check_city_district_radius_floor_rooms(city, district, radius, floor, rooms):
 
-    price_df4 = pd.read_csv("poland_apartments_completed.csv")
+#     price_df4 = pd.read_csv(APARTMENTS_FILE)
+    price_df4 = load_data()[0]
     floor_values = list(set(price_df4['floor']))
     rooms_values = list(set(price_df4['rooms']))
 

diff --git a/app/tests/.ipynb_checkpoints/test_function_store-checkpoint.ipynb b/app/tests/.ipynb_checkpoints/test_function_store-checkpoint.ipynb
@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 2,
    "id": "c4bf99d5",
    "metadata": {},
    "outputs": [],
@@ -42,17 +42,161 @@
     "from functions.function_store import training_loop # depend on other functions\n",
     "\n",
     "# 3. For predicting by input data with the best model\n",
-    "from functions.function_store import check_city_district_radius_floor_rooms # depend on \"poland_apartments_completed.csv\"\n",
-    "from functions.function_store import input_to_df # depend on other functions\n",
+    "from functions.function_store import check_city_district_radius_floor_rooms, input_to_df # depend on other functions\n",
     "from functions.function_store import select_best_model, main_predicting # depend on other functions\n",
     "from functions.function_store import set_regressors, predict_by_input # don't depend on any functions\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "id": "f9a4767d",
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(4315, 19)"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "APARTMENTS_FILE = \"test_file1.csv\"\n",
+    "\n",
+    "# test_df = pd.read_csv('test_file.csv')\n",
+    "# # test_df.shape\n",
+    "\n",
+    "# test1_df = test_df.groupby('city').apply(lambda x: x.sample(frac=0.2)).reset_index(drop=True)\n",
+    "# # test1_df.shape\n",
+    "# test1_df.to_csv(\"test_file1.csv\")\n",
+    "\n",
+    "# https://stackoverflow.com/questions/22472213/python-random-selection-per-group"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "34e8e6d0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Creating a fixture that grabs a file before running a test\n",
+    "@pytest.fixture\n",
+    "def grab_test_file():\n",
+    "    test_file = pd.read_csv(APARTMENTS_FILE)\n",
+    "    return test_file\n",
+    "\n",
+    "# # Using the fixture in a test function\n",
+    "# def test_file_content(grab_test_file):\n",
+    "#     assert grab_test_file.shape == (10, 5)\n",
+    "\n",
+    "# https://towardsdatascience.com/writing-better-code-through-testing-f3150abec6ca"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2e65b3c8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# def test_1_load_data(grab_test_file):\n",
+    "#     assert grab_test_file.shape == (4315, 19)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ed59d560",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def test_01_load_data():\n",
+    "    assert load_data()[0].shape == (4315, 19)\n",
+    "\n",
+    "def test_11_load_data():\n",
+    "    assert load_data()[1] == ['city', 'district']\n",
+    "\n",
+    "def test_21_load_data():\n",
+    "    assert load_data()[2] == ['floor', 'rooms', 'sq', 'year', 'radius']\n",
+    "    \n",
+    "def test_31_load_data():\n",
+    "    assert load_data()[3] == ['price']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "55c61f41",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4fb59c52",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fa394a88",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def test_1_check_city_district_radius_floor_rooms():\n",
+    "    assert check_city_district_radius_floor_rooms(\"Kraków\", \"Śródmieście\", 2, 3, 2) is False\n",
+    "    \n",
+    "    \n",
+    "#     assert check_city_district_radius_floor_rooms(\"Warszawa\", \"Śródmieście\", 2, 3, 2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3419a26d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# def check_city_district_radius_floor_rooms(city, district, radius, floor, rooms):\n",
+    "    \n",
+    "#     price_df4 = load_data()[0]\n",
+    "#     floor_values = list(set(price_df4['floor']))\n",
+    "#     rooms_values = list(set(price_df4['rooms']))\n",
+    "    \n",
+    "#     geo_df_for_check = price_df4.groupby(['city', 'district']).agg({'radius':['min','max']})\n",
+    "    \n",
+    "#     if (city, district) not in geo_df_for_check.index:\n",
+    "#         print(\"Invalid city and/or district!\")\n",
+    "#         return False\n",
+    "#     else:\n",
+    "#         min_radius = geo_df_for_check.loc[(city, district)][('radius', 'min')]\n",
+    "#         max_radius = geo_df_for_check.loc[(city, district)][('radius', 'max')]\n",
+    "#         if not (radius >= min_radius and radius <= max_radius):\n",
+    "#             print(\"The radius must be between {0} and {1}\".format(round(min_radius, 2), round(max_radius, 2)))\n",
+    "#             return False\n",
+    "#         elif floor not in floor_values:\n",
+    "#             print(\"The floor must be integer and between {0} and {1}\".format(floor_values.min(), floor_values.max()))\n",
+    "#             return False\n",
+    "#         elif rooms not in rooms_values:\n",
+    "#             print(\"The rooms must be integer and between {0} and {1}\".format(rooms_values.min(), rooms_values.max()))\n",
+    "#             return False\n",
+    "#         else:\n",
+    "#             return True"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7ff642d5",
+   "metadata": {},
    "outputs": [],
    "source": []
   },
@@ -79,7 +223,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "80cad016",
+   "id": "7a6256a5",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -115,7 +259,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "78174db7",
+   "id": "ad87745e",
    "metadata": {},
    "outputs": [],
    "source": []