Update LinearRegression_1.py

03_linear_regression/LinearRegression_1.py

@@ -10,6 +10,7 @@ class LinearRegressionLS(LinearRegression):
     """
     solve linear regression problem via least squares
     """
+
     X: np.array
     Y: np.array
     w: np.array
@@ -21,19 +22,19 @@ class LinearRegressionLS(LinearRegression):
         self.w = np.random.rand(2)
 
     def homogeneous(self, xlist):
-        """ build homogeneous coordinates """
+        """build homogeneous coordinates"""
         raise NotImplementedError
 
     def linout(self, xlist):
-        """ linear output for given data """
+        """linear output for given data"""
         raise NotImplementedError
 
     def loss_sq(self, X, Y):
-        """ loss function: (half) sum of square errors """
+        """loss function: (half) sum of square errors"""
         raise NotImplementedError
 
     def solve(self, lr, nepoch):
-        """ form normal equation """
+        """form normal equation"""
         XtX = np.dot(self.X.T, self.X)
         XtY = np.dot(self.X.T, self.Y)
         # print(XtX.shape, XtY.shape)
@@ -46,6 +47,7 @@ class LinearRegressionGD1(LinearRegression):
     solve linear regression problem via gradient descent,
     using single weight vector
     """
+
     X: np.array
     Y: np.array
     w: np.array
@@ -57,19 +59,20 @@ class LinearRegressionGD1(LinearRegression):
         self.w = np.random.rand(2)
 
     def homogeneous(self, xlist):
-        """ build homogeneous coordinates """
+        """build homogeneous coordinates"""
         raise NotImplementedError
 
     def linout(self, xlist):
-        """ linear output for given data """
+        """linear output for given data"""
         raise NotImplementedError
 
     def loss_sq(self, X, Y):
-        """ loss function: (half) sum of square errors """
+        """loss function: (half) sum of square errors"""
         raise NotImplementedError
 
     def gd(self, lr):
-        """ gradient descent update """
+        """gradient descent update"""
+
         def gradient(Y_hat, Y, X):
             return np.sum((Y_hat - Y) * X, axis=0)
 
@@ -79,10 +82,10 @@ class LinearRegressionGD1(LinearRegression):
         self.w -= lr * grad
 
     def solve(self, lr, nepoch):
-        """ iterative solver """
+        """iterative solver"""
         for epoch in range(num_epochs):
             self.gd(lr)
-            print(f'epoch {epoch + 1}, loss {self.loss_sq(self.X, self.Y)}')
+            print(f"epoch {epoch + 1}, loss {self.loss_sq(self.X, self.Y)}")
 
 
 class LinearRegressionGD2(LinearRegression):
@@ -99,20 +102,20 @@ class LinearRegressionGD2(LinearRegression):
         self.b = np.min(ylist)
 
     def linout(self, xlist):
-        """ linear output for given data """
+        """linear output for given data"""
         raise NotImplementedError
 
     def loss_sq(self, X, Y):
-        """ loss function: (half) sum of square errors """
+        """loss function: (half) sum of square errors"""
         raise NotImplementedError
 
     def gd(self, lr):
-        """ gradient descent update """
+        """gradient descent update"""
+
         def gradient(Y_hat, Y, X):
             return np.array(
-                [np.sum((Y_hat - Y) * X, axis=0),
-                 np.sum((Y_hat - Y), axis=0)
-                ])
+                [np.sum((Y_hat - Y) * X, axis=0), np.sum((Y_hat - Y), axis=0)]
+            )
 
         Y_hat = self.linout(self.X)
         # print(Y_hat)
@@ -121,27 +124,40 @@ class LinearRegressionGD2(LinearRegression):
         self.b -= lr * grad[1]
 
     def solve(self, lr, nepoch):
-        """ iterative solver """
+        """iterative solver"""
         for epoch in range(num_epochs):
             self.gd(lr)
-            print(f'epoch {epoch + 1}, loss {self.loss_sq(self.X, self.Y)}')
+            print(f"epoch {epoch + 1}, loss {self.loss_sq(self.X, self.Y)}")
 
 
 if __name__ == "__main__":
-    hp = [14213, 13448, 13870, 16192, 16415, 21501, 25910, 24866, 28981, 32926, 36741, 40974]
-    hp = [x / 10000. for x in hp]
+    hp = [
+        14213,
+        13448,
+        13870,
+        16192,
+        16415,
+        21501,
+        25910,
+        24866,
+        28981,
+        32926,
+        36741,
+        40974,
+    ]
+    hp = [x / 10000.0 for x in hp]
 
     lr = 0.001
     num_epochs = 10
 
     ls = LinearRegressionLS(hp)
     ls.solve(lr, num_epochs)
-    print(f'next prediction (LS): {ls.linout([len(hp)])}')
+    print(f"next prediction (LS): {ls.linout([len(hp)])}")
 
     gd1 = LinearRegressionGD1(hp)
     gd1.solve(lr, num_epochs)
-    print(f'next prediction year (GD1): {gd1.linout([len(hp)])}')
+    print(f"next prediction year (GD1): {gd1.linout([len(hp)])}")
 
     gd2 = LinearRegressionGD1(hp)
     gd2.solve(lr, num_epochs)
-    print(f'next prediction year (GD2): {gd2.linout([len(hp)])}')
+    print(f"next prediction year (GD2): {gd2.linout([len(hp)])}")