gradient descent tutorial

ML/3_gradient_descent/Exercise/ex_gradient_descent.py

@@ -0,0 +1,53 @@
+''' Good students always try to solve exercise on their own first and then look at the ready made solution
+    I know you are an awesome student !! :)
+    Hence you will look into this code only after you have done your due diligence.
+    If you are not an awesome student who is full of laziness then only you will come here
+    without writing single line of code on your own. In that case anyways you are going to
+    face my anger with fire and fury !!!
+'''
+
+import numpy as np
+import pandas as pd
+from sklearn.linear_model import LinearRegression
+import math
+
+def predict_using_sklean():
+    df = pd.read_csv("test_scores.csv")
+    r = LinearRegression()
+    r.fit(df[['math']],df.cs)
+    return r.coef_, r.intercept_
+
+def gradient_descent(x,y):
+    m_curr = 0
+    b_curr = 0
+    iterations = 1000000
+    n = len(x)
+    learning_rate = 0.0002
+
+    cost_previous = 0
+
+    for i in range(iterations):
+        y_predicted = m_curr * x + b_curr
+        cost = (1/n)*sum([value**2 for value 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
+        if math.isclose(cost, cost_previous, rel_tol=1e-20):
+            break
+        cost_previous = cost
+        print ("m {}, b {}, cost {}, iteration {}".format(m_curr,b_curr,cost, i))
+
+    return m_curr, b_curr
+
+if __name__ == "__main__":
+    df = pd.read_csv("test_scores.csv")
+    x = np.array(df.math)
+    y = np.array(df.cs)
+
+    m, b = gradient_descent(x,y)
+    print("Using gradient descent function: Coef {} Intercept {}".format(m, b))
+
+    m_sklearn, b_sklearn = predict_using_sklean()
+    print("Using sklearn: Coef {} Intercept {}".format(m_sklearn,b_sklearn))
+

ML/3_gradient_descent/Exercise/test_scores.csv

@@ -0,0 +1,11 @@
+name,math,cs
+david,92,98
+laura,56,68
+sanjay,88,81
+wei,70,80
+jeff,80,83
+aamir,49,52
+venkat,65,66
+virat,35,30
+arthur,66,68
+paul,67,73

ML/3_gradient_descent/gradient_descent.py

@@ -0,0 +1,21 @@
+import numpy as np
+
+def gradient_descent(x,y):
+    m_curr = b_curr = 0
+    iterations = 10000
+    n = len(x)
+    learning_rate = 0.08
+
+    for i in range(iterations):
+        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)