python3

Author: lazyprogrammer

ann_logistic_extra/ann_predict.py

@@ -1,3 +1,9 @@
+from __future__ import print_function, division
+from builtins import range
+# Note: you may need to update your version of future
+# sudo pip install -U future
+
+
 import numpy as np
 from process import get_data
 
@@ -22,10 +28,11 @@ def forward(X, W1, b1, W2, b2):
     return softmax(Z.dot(W2) + b2)
 
 P_Y_given_X = forward(X, W1, b1, W2, b2)
+print("P_Y_given_X.shape:", P_Y_given_X.shape)
 predictions = np.argmax(P_Y_given_X, axis=1)
 
 # calculate the accuracy
 def classification_rate(Y, P):
     return np.mean(Y == P)
 
-print "Score:", classification_rate(Y, predictions)
+print("Score:", classification_rate(Y, predictions))

ann_logistic_extra/ann_train.py

@@ -1,3 +1,9 @@
+from __future__ import print_function, division
+from builtins import range
+# Note: you may need to update your version of future
+# sudo pip install -U future
+
+
 import numpy as np
 import matplotlib.pyplot as plt
 
@@ -7,7 +13,7 @@
 def y2indicator(y, K):
     N = len(y)
     ind = np.zeros((N, K))
-    for i in xrange(N):
+    for i in range(N):
         ind[i, y[i]] = 1
     return ind
 
@@ -56,7 +62,7 @@ def cross_entropy(T, pY):
 train_costs = []
 test_costs = []
 learning_rate = 0.001
-for i in xrange(10000):
+for i in range(10000):
     pYtrain, Ztrain = forward(Xtrain, W1, b1, W2, b2)
     pYtest, Ztest = forward(Xtest, W1, b1, W2, b2)
 
@@ -72,10 +78,10 @@ def cross_entropy(T, pY):
     W1 -= learning_rate*Xtrain.T.dot(dZ)
     b1 -= learning_rate*dZ.sum(axis=0)
     if i % 1000 == 0:
-        print i, ctrain, ctest
+        print(i, ctrain, ctest)
 
-print "Final train classification_rate:", classification_rate(Ytrain, predict(pYtrain))
-print "Final test classification_rate:", classification_rate(Ytest, predict(pYtest))
+print("Final train classification_rate:", classification_rate(Ytrain, predict(pYtrain)))
+print("Final test classification_rate:", classification_rate(Ytest, predict(pYtest)))
 
 legend1, = plt.plot(train_costs, label='train cost')
 legend2, = plt.plot(test_costs, label='test cost')

ann_logistic_extra/logistic_predict.py

@@ -1,3 +1,9 @@
+from __future__ import print_function, division
+from builtins import range
+# Note: you may need to update your version of future
+# sudo pip install -U future
+
+
 import numpy as np
 from process import get_binary_data
 
@@ -22,4 +28,4 @@ def forward(X, W, b):
 def classification_rate(Y, P):
     return np.mean(Y == P)
 
-print "Score:", classification_rate(Y, predictions)
+print("Score:", classification_rate(Y, predictions))

ann_logistic_extra/logistic_softmax_train.py

@@ -1,3 +1,9 @@
+from __future__ import print_function, division
+from builtins import range
+# Note: you may need to update your version of future
+# sudo pip install -U future
+
+
 import numpy as np
 import matplotlib.pyplot as plt
 
@@ -7,7 +13,7 @@
 def y2indicator(y, K):
     N = len(y)
     ind = np.zeros((N, K))
-    for i in xrange(N):
+    for i in range(N):
         ind[i, y[i]] = 1
     return ind
 
@@ -52,7 +58,7 @@ def cross_entropy(T, pY):
 train_costs = []
 test_costs = []
 learning_rate = 0.001
-for i in xrange(10000):
+for i in range(10000):
     pYtrain = forward(Xtrain, W, b)
     pYtest = forward(Xtest, W, b)
 
@@ -65,10 +71,10 @@ def cross_entropy(T, pY):
     W -= learning_rate*Xtrain.T.dot(pYtrain - Ytrain_ind)
     b -= learning_rate*(pYtrain - Ytrain_ind).sum(axis=0)
     if i % 1000 == 0:
-        print i, ctrain, ctest
+        print(i, ctrain, ctest)
 
-print "Final train classification_rate:", classification_rate(Ytrain, predict(pYtrain))
-print "Final test classification_rate:", classification_rate(Ytest, predict(pYtest))
+print("Final train classification_rate:", classification_rate(Ytrain, predict(pYtrain)))
+print("Final test classification_rate:", classification_rate(Ytest, predict(pYtest)))
 
 legend1, = plt.plot(train_costs, label='train cost')
 legend2, = plt.plot(test_costs, label='test cost')

ann_logistic_extra/logistic_train.py

@@ -1,3 +1,9 @@
+from __future__ import print_function, division
+from builtins import range
+# Note: you may need to update your version of future
+# sudo pip install -U future
+
+
 import numpy as np
 import matplotlib.pyplot as plt
 
@@ -37,7 +43,7 @@ def cross_entropy(T, pY):
 train_costs = []
 test_costs = []
 learning_rate = 0.001
-for i in xrange(10000):
+for i in range(10000):
     pYtrain = forward(Xtrain, W, b)
     pYtest = forward(Xtest, W, b)
 
@@ -50,10 +56,10 @@ def cross_entropy(T, pY):
     W -= learning_rate*Xtrain.T.dot(pYtrain - Ytrain)
     b -= learning_rate*(pYtrain - Ytrain).sum()
     if i % 1000 == 0:
-        print i, ctrain, ctest
+        print(i, ctrain, ctest)
 
-print "Final train classification_rate:", classification_rate(Ytrain, np.round(pYtrain))
-print "Final test classification_rate:", classification_rate(Ytest, np.round(pYtest))
+print("Final train classification_rate:", classification_rate(Ytrain, np.round(pYtrain)))
+print("Final test classification_rate:", classification_rate(Ytest, np.round(pYtest)))
 
 legend1, = plt.plot(train_costs, label='train cost')
 legend2, = plt.plot(test_costs, label='test cost')

ann_logistic_extra/process.py

@@ -1,3 +1,9 @@
+from __future__ import print_function, division
+from builtins import range
+# Note: you may need to update your version of future
+# sudo pip install -U future
+
+
 import numpy as np
 import pandas as pd
 import os
@@ -30,7 +36,7 @@ def get_data():
     X2[:,0:(D-1)] = X[:,0:(D-1)] # non-categorical
 
     # one-hot
-    for n in xrange(N):
+    for n in range(N):
         t = int(X[n,D-1])
         X2[n,t+D-1] = 1