test_c11_machine_learning.py

Author: wilsonify

src/data-scratch-library/tests/test_c11_machine_learning.py

@@ -6,6 +6,7 @@
 
 from dsl.c04_linear_algebra.e0402_matrices import make_random_matrix
 from dsl.c11_machine_learning import machine_learning
+from dsl.c11_machine_learning.machine_learning import split_data
 
 current_dir = os.path.dirname(__file__)
 parent_dir = os.path.join(current_dir, os.pardir)
@@ -63,13 +64,12 @@ def test_recall(tp, fp, fn, tn, expected):
 
 
 def test_split_data():
-    result = machine_learning.split_data(make_random_matrix(), 0.5)
+    result = split_data(make_random_matrix(), 0.5)
     assert len(result[0]) == pytest.approx(50, abs=10)
     assert len(result[1]) == pytest.approx(50, abs=10)
 
 
 def test_train_test_split():
-    print(make_random_matrix)
     x_train, x_test, y_train, y_test = machine_learning.train_test_split(make_random_matrix(), make_random_matrix(), 0.5)
     assert len(x_train) == pytest.approx(50, abs=10)
     assert len(x_test) == pytest.approx(50, abs=10)

src/data-scratch-library/tests/test_c14_simple_linear_regression/test_squared_error.py

@@ -0,0 +1,27 @@
+import random
+
+from dsl.c08_gradient_descent import negate, negate_all
+from dsl.c08_gradient_descent.e0805_stochastic_gd import maximize_stochastic
+from dsl.c14_simple_linear_regression.simple_linear_regression import squared_error
+from dsl.c15_multiple_regression.multiple_regression import squared_error_gradient
+
+
+def test_maximize_stochastic_squared_error():
+    x = [
+        [1, 49, 4, 0], [1, 41, 9, 0], [1, 40, 8, 0],
+        [1, 25, 6, 0], [1, 21, 1, 0], [1, 21, 0, 0],
+        [1, 19, 3, 0], [1, 19, 0, 0], [1, 18, 9, 0], [1, 18, 8, 0]
+    ]
+    y = [
+        68.77, 51.25, 52.08,
+        38.36, 44.54, 57.13,
+        51.4, 41.42, 31.22, 34.76,
+    ]
+    maximize_stochastic(
+        target_fn=negate(squared_error),
+        gradient_fn=negate_all(squared_error_gradient),
+        x=x,
+        y=y,
+        theta_0=[random.random() for _ in x[0]],
+        alpha_0=0.01
+    )