aimacode · norvig · Jul 24, 2017 · Jul 22, 2017 · Jul 22, 2017
diff --git a/learning.py b/learning.py
@@ -4,7 +4,7 @@
     removeall, unique, product, mode, argmax, argmax_random_tie, isclose, gaussian,
     dotproduct, vector_add, scalar_vector_product, weighted_sample_with_replacement,
     weighted_sampler, num_or_str, normalize, clip, sigmoid, print_table,
-    open_data, sigmoid_derivative, probability
+    open_data, sigmoid_derivative, probability, norm, matrix_multiplication
 )
 
 import copy
@@ -377,6 +377,66 @@ def predict(example):
 # ______________________________________________________________________________
 
 
+def truncated_svd(X, num_val=2, max_iter=1000):
+    """Computes the first component of SVD"""
+
+    def normalize_vec(X, n = 2):
+        """Normalizes two parts (:m and m:) of the vector"""
+        X_m = X[:m]
+        X_n = X[m:]
+        norm_X_m = norm(X_m, n)
+        Y_m = [x/norm_X_m for x in X_m]
+        norm_X_n = norm(X_n, n)
+        Y_n = [x/norm_X_n for x in X_n]
+        return Y_m + Y_n
+
+    def remove_component(X):
+        """Removes components of already obtained eigen vectors from X"""
+        X_m = X[:m]
+        X_n = X[m:]
+        for eivec in eivec_m:
+            coeff = dotproduct(X_m, eivec)
+            X_m = [x1 - coeff*x2 for x1, x2 in zip(X_m, eivec)]
+        for eivec in eivec_n:
+            coeff = dotproduct(X_n, eivec)
+            X_n = [x1 - coeff*x2 for x1, x2 in zip(X_n, eivec)]
+        return X_m + X_n
+
+    m, n = len(X), len(X[0])
+    A = [[0 for _ in range(n + m)] for _ in range(n + m)]
+    for i in range(m):
+        for j in range(n):
+            A[i][m + j] = A[m + j][i] = X[i][j]
+
+    eivec_m = []
+    eivec_n = []
+    eivals = []
+
+    for _ in range(num_val):
+        X = [random.random() for _ in range(m + n)]
+        X = remove_component(X)
+        X = normalize_vec(X)
+
+        for _ in range(max_iter):
+            old_X = X
+            X = matrix_multiplication(A, [[x] for x in X])
+            X = [x[0] for x in X]
+            X = remove_component(X)
+            X = normalize_vec(X)
+            # check for convergence
+            if norm([x1 - x2 for x1, x2 in zip(old_X, X)]) <= 1e-10:
+                break
+
+        projected_X = matrix_multiplication(A, [[x] for x in X])
+        projected_X = [x[0] for x in projected_X]
+        eivals.append(norm(projected_X, 1)/norm(X, 1))
+        eivec_m.append(X[:m])
+        eivec_n.append(X[m:])
+    return (eivec_m, eivec_n, eivals)
+
+# ______________________________________________________________________________
+
+
 class DecisionFork:
     """A fork of a decision tree holds an attribute to test, and a dict
     of branches, one for each of the attribute's values."""

diff --git a/tests/test_learning.py b/tests/test_learning.py
@@ -115,6 +115,34 @@ def test_k_nearest_neighbors():
     assert kNN([7.5, 4, 6, 2]) == "virginica"
 
 
+def test_truncated_svd():
+    test_mat = [[17, 0],
+                [0, 11]]
+    _, _, eival = truncated_svd(test_mat)
+    assert isclose(abs(eival[0]), 17)
+    assert isclose(abs(eival[1]), 11)
+
+    test_mat = [[17, 0],
+                [0, -34]]
+    _, _, eival = truncated_svd(test_mat)
+    assert isclose(abs(eival[0]), 34)
+    assert isclose(abs(eival[1]), 17)
+
+    test_mat = [[1, 0, 0, 0, 2],
+                [0, 0, 3, 0, 0],
+                [0, 0, 0, 0, 0],
+                [0, 2, 0, 0, 0]]
+    _, _, eival = truncated_svd(test_mat)
+    assert isclose(abs(eival[0]), 3)
+    assert isclose(abs(eival[1]), 5**0.5)
+
+    test_mat = [[3, 2, 2],
+                [2, 3, -2]]
+    _, _, eival = truncated_svd(test_mat)
+    assert isclose(abs(eival[0]), 5)
+    assert isclose(abs(eival[1]), 3)
+
+
 def test_decision_tree_learner():
     iris = DataSet(name="iris")
     dTL = DecisionTreeLearner(iris)

diff --git a/tests/test_utils.py b/tests/test_utils.py
@@ -161,25 +161,6 @@ def test_gaussian():
     assert gaussian(3,1,3) == 0.3989422804014327
 
 
-def test_truncated_svd():
-    test_mat = [[17, 0],
-                [0, 11]]
-    _, _, eival = truncated_svd(test_mat)
-    assert isclose(eival, 17)
-
-    test_mat = [[17, 0],
-                [0, -34]]
-    _, _, eival = truncated_svd(test_mat)
-    assert isclose(eival, -34)
-
-    test_mat = [[1, 0, 0, 0, 2],
-                [0, 0, 3, 0, 0],
-                [0, 0, 0, 0, 0],
-                [0, 2, 0, 0, 0]]
-    _, _, eival = truncated_svd(test_mat)
-    assert isclose(eival, 3)
-
-
 def test_sigmoid_derivative():
     value = 1
     assert sigmoid_derivative(value) == 0

diff --git a/utils.py b/utils.py
@@ -275,41 +275,6 @@ def gaussian(mean, st_dev, x):
     return 1/(math.sqrt(2*math.pi)*st_dev)*math.e**(-0.5*(float(x-mean)/st_dev)**2)
 
 
-def truncated_svd(X, max_iter=1000):
-    """Computes the first component of SVD"""
-
-    def normalize_vec(X, n = 2):
-        """Returns normalized vector"""
-        norm_X = norm(X, n)
-        Y = [x/norm_X for x in X]
-        return Y
-
-    m, n = len(X), len(X[0])
-    A = [[0 for _ in range(n + m)] for _ in range(n + m)]
-    for i in range(m):
-        for j in range(n):
-            A[i][j] = A[m + j][n + i] = X[i][j]
-
-    X = [random.random() for _ in range(n + m)]
-    X = normalize_vec(X)
-    for _ in range(max_iter):
-        old_X = X
-        X = matrix_multiplication(A, [[x] for x in X])
-        X = [x[0] for x in X]
-        X = normalize_vec(X)
-        # check for convergence
-        if norm([x1 - x2 for x1, x2 in zip(old_X, X)]) <= 1e-10:
-            break
-
-    projected_X = matrix_multiplication(A, [[x] for x in X])
-    projected_X = [x[0] for x in projected_X]
-    eival = norm(projected_X, 1)/norm(X, 1)
-    eivec_n = normalize_vec(X[:n])
-    eivec_m = normalize_vec(X[n:])
-
-    return (eivec_m, eivec_n, eival)
-
-
 try:  # math.isclose was added in Python 3.5; but we might be in 3.4
     from math import isclose
 except ImportError: