Minor fixes

Author: rushter

mla/base/base.py

@@ -2,9 +2,7 @@
 import numpy as np
 
 
-class BaseEstimator(object):
-    X = None
-    y = None
+class BaseEstimator:
     y_required = True
     fit_required = True
 
@@ -28,7 +26,7 @@ def _setup_input(self, X, y=None):
             X = np.array(X)
 
         if X.size == 0:
-            raise ValueError("Number of features must be > 0")
+            raise ValueError("Got an empty matrix.")
 
         if X.ndim == 1:
             self.n_samples, self.n_features = 1, X.shape
@@ -45,7 +43,7 @@ def _setup_input(self, X, y=None):
                 y = np.array(y)
 
             if y.size == 0:
-                raise ValueError("Number of targets must be > 0")
+                raise ValueError("The targets array must be no-empty.")
 
         self.y = y
 

mla/datasets/base.py

@@ -19,6 +19,8 @@ def load(dataset="training", digits=np.arange(10)):
         elif dataset == "test":
             fname_img = get_filename("data/mnist/t10k-images-idx3-ubyte")
             fname_lbl = get_filename("data/mnist/t10k-labels-idx1-ubyte")
+        else:
+            raise ValueError("Unexpected dataset name: %r" % dataset)
 
         flbl = open(fname_lbl, "rb")
         magic_nr, size = struct.unpack(">II", flbl.read(8))
@@ -36,7 +38,7 @@ def load(dataset="training", digits=np.arange(10)):
         images = zeros((N, rows, cols), dtype=uint8)
         labels = zeros((N, 1), dtype=int8)
         for i in range(len(ind)):
-            images[i] = array(img[ind[i] * rows * cols : (ind[i] + 1) * rows * cols]).reshape((rows, cols))
+            images[i] = array(img[ind[i] * rows * cols: (ind[i] + 1) * rows * cols]).reshape((rows, cols))
             labels[i] = lbl[ind[i]]
 
         return images, labels

mla/neuralnet/optimizers.py

@@ -198,6 +198,7 @@ def setup(self, network):
                 self.ms[i][n] = np.zeros_like(layer.parameters[n])
                 self.vs[i][n] = np.zeros_like(layer.parameters[n])
 
+
 class Adamax(Optimizer):
     def __init__(self, learning_rate=0.002, beta_1=0.9, beta_2=0.999, epsilon=1e-8):
 

mla/pca.py

@@ -47,7 +47,7 @@ def _decompose(self, X):
             Vh = Vh.T
 
         s_squared = s ** 2
-        variance_ratio = s_squared / (s_squared).sum()
+        variance_ratio = s_squared / s_squared.sum()
         logging.info("Explained variance ratio: %s" % (variance_ratio[0: self.n_components]))
         self.components = Vh[0: self.n_components]
 

mla/rbm.py

@@ -64,7 +64,7 @@ def _train(self):
                 positive_associations = np.dot(batch.T, positive_hidden)
 
                 negative_visible = sigmoid(np.dot(hidden_states, self.W.T) + self.bias_v)
-                negative_visible = self._sample(negative_visible)  # use the samped hidden state h1 to sample v1
+                negative_visible = self._sample(negative_visible)  # use the sampled hidden state h1 to sample v1
                 negative_hidden = sigmoid(np.dot(negative_visible, self.W) + self.bias_h)
                 negative_associations = np.dot(negative_visible.T, negative_hidden)
 

mla/svm/svm.py

@@ -73,15 +73,11 @@ def _train(self):
 
                 # Find intercept
                 b1 = (
-                    self.b
-                    - e_i
-                    - self.y[i] * (self.alpha[i] - alpha_io) * self.K[i, i]
+                    self.b - e_i - self.y[i] * (self.alpha[i] - alpha_io) * self.K[i, i]
                     - self.y[j] * (self.alpha[j] - alpha_jo) * self.K[i, j]
                 )
                 b2 = (
-                    self.b
-                    - e_j
-                    - self.y[j] * (self.alpha[j] - alpha_jo) * self.K[j, j]
+                    self.b - e_j - self.y[j] * (self.alpha[j] - alpha_jo) * self.K[j, j]
                     - self.y[i] * (self.alpha[i] - alpha_io) * self.K[i, j]
                 )
                 if 0 < self.alpha[i] < self.C:

requirements.txt

@@ -6,3 +6,4 @@ scipy>=0.18.0
 seaborn>=0.7.1
 six>=1.10.0
 autograd>=1.1.7
+gym