update

Author: kiat

Code-Example-016.1-LogisticRegression-without-lib.ipynb

@@ -42,7 +42,7 @@
     "n_feature = 2 # the number of features\n",
     "n_components = 2 # the number of clusters\n",
     "\n",
-    "n=1000 # the number of total samples"
+    "n = 1000 # the number of total samples"
    ]
   },
   {
@@ -207,21 +207,21 @@
     "    I/P\n",
     "    ----------\n",
     "    X : 2D array where each row represent the training example and each column represent the feature ndarray. \n",
-    "        Dimension(m x n)\n",
-    "        m= number of training examples\n",
-    "        n= number of features (including X_0 column of ones)\n",
-    "    y : 1D array of labels/target value for each traing example. dimension(1 x m)\n",
+    "        Dimension (n x d)\n",
+    "        n = number of training examples\n",
+    "        d = number of features (including X_0 column of ones)\n",
+    "    y : 1D array of labels/target value for each traing example. dimension(1 x n)\n",
     "\n",
-    "    weights : 1D array of fitting parameters or weights. Dimension (1 x n)\n",
+    "    weights : 1D array of fitting parameters or weights. Dimension (1 x d)\n",
     "\n",
     "    O/P\n",
     "    -------\n",
     "    cost : The cost of using theta as the parameter for linear regression to fit the data points in X and y.\n",
     "    \"\"\"\n",
-    "    m, n = X.shape\n",
+    "    n, d = X.shape\n",
     "    x_dot_weights = X.dot(weights)\n",
     "\n",
-    "    cost = 1.0 / m * (-y.T.dot(np.log(sigmoid(x_dot_weights))) - (1 - y).T.dot(np.log(1 - sigmoid(x_dot_weights))))\n",
+    "    cost = 1.0 / n * (-y.T.dot(np.log(sigmoid(x_dot_weights))) - (1 - y).T.dot(np.log(1 - sigmoid(x_dot_weights))))\n",
     "\n",
     "    return cost"
    ]
@@ -250,10 +250,10 @@
     "    -------\n",
     "    grad: (numpy array)The gradient of the cost with respect to the parameters theta\n",
     "    \"\"\"\n",
-    "    m, n = X.shape\n",
+    "    n, d = X.shape\n",
     "    x_dot_weights = X.dot(weights)\n",
     "\n",
-    "    grad = (1.0 / m )* (sigmoid(x_dot_weights) - y).T.dot(X)\n",
+    "    grad = (1.0 / n )* (sigmoid(x_dot_weights) - y).T.dot(X)\n",
     "\n",
     "    return grad"
    ]
@@ -463,9 +463,9 @@
     "    I/P\n",
     "    ----------\n",
     "    X : 2D array where each row represent the training example and each column represent the feature ndarray. \n",
-    "        Dimension(m x n)\n",
-    "        m= number of training examples\n",
-    "        n= number of features (including X_0 column of ones)\n",
+    "        Dimension(n x d)\n",
+    "        n= number of training examples\n",
+    "        d= number of features (including X_0 column of ones)\n",
     "\n",
     "    theta : 1D array of fitting parameters or weights. Dimension (1 x n)\n",
     "\n",