sgd

Author: codebasics

DeepLearningML/8_sgd_vs_gd/gd_and_sgd.ipynb

@@ -0,0 +1,20 @@
+import numpy as np
+
+def gradient_descent(x,y,epochs):
+    m_curr = b_curr = 0
+    n = len(x)
+    learning_rate = 0.08
+
+    for i in range(epochs):
+        y_predicted = m_curr * x + b_curr
+        cost = (1/n) * sum([val**2 for val in (y-y_predicted)])
+        md = -(2/n)*sum(x*(y-y_predicted))
+        bd = -(2/n)*sum(y-y_predicted)
+        m_curr = m_curr - learning_rate * md
+        b_curr = b_curr - learning_rate * bd
+        print ("m {}, b {}, cost {} iteration {}".format(m_curr,b_curr,cost, i))
+
+x = np.array([1,2,3,4,5])
+y = np.array([5,7,9,11,13])
+
+gradient_descent(x,y, 500)

DeepLearningML/8_sgd_vs_gd/gradient_descent.ipynb

@@ -0,0 +1,7 @@
+area,bedrooms,age,price
+2600,3,20,550000
+3000,4,15,565000
+3200,3,18,610000
+3600,3,30,595000
+4000,5,8,760000
+4100,6,8,810000

DeepLearningML/8_sgd_vs_gd/gradient_descent.py

@@ -0,0 +1,21 @@
+area,bedrooms,price
+1056,2,39.07
+2600,4,120
+1440,3,62
+1521,3,75
+1200,2,51
+1170,2,38
+2732,4,135
+3300,4,155
+1310,3,50
+3700,5,167
+1800,3,82
+2785,4,140
+1000,2,38
+1100,2,40
+2250,3,101
+1175,2,42
+1180,3,48
+1540,3,60
+2770,3,102
+800,1,32