Created data preprocessor class stub

Author: wtsimple

data_preprocessor.py

@@ -0,0 +1,2 @@
+class DataPreprocessor(object):
+    pass

tests/test_data_loader.py

@@ -19,14 +19,16 @@
                 "native_country",
                 "income"]
 
+TEST_DATA_PATH = "data/data_example_for_tests.csv"
+
 
 @pytest.fixture
 def data_loader():
     return DataLoader()
 
 
-def test_data_loader_loads_data(data_loader):
-    df = data_loader.load_relative(path="data/data_example_for_tests.csv", columns=COLUMN_NAMES)
+def test_data_loader_loads_data_frame(data_loader):
+    df = data_loader.load_relative(path=TEST_DATA_PATH, columns=COLUMN_NAMES)
     assert isinstance(df, DataFrame)
     assert df.columns == COLUMN_NAMES
     # Check some values from the first row

tests/test_data_preprocessor.py

@@ -0,0 +1,15 @@
+"""The preprocessor is expected to clean and encode the data,
+making it ready for modelling"""
+
+import pytest
+
+from data_preprocessor import DataPreprocessor
+
+
+@pytest.fixture
+def preprocessor():
+    return DataPreprocessor()
+
+
+def test_data_preprocessor_x(preprocessor):
+    pass

todo_list.md

@@ -1,5 +1,5 @@
 - [x] start and configure Spark
-- [ ] load_relative data from the files
+- [x] load data from the files
 - [ ] prepare data for classification models
     - [ ] string encode the factor columns
     - [ ] one-hot encode the numerically encoded factor columns