Updated chapter 11

Author: nfmcclure

11_More_with_TensorFlow/01_Visualizing_Computational_Graphs/01_using_tensorboard.py

@@ -11,19 +11,21 @@
 import numpy as np
 import matplotlib.pyplot as plt
 import tensorflow as tf
+from tensorflow.python.framework import ops
+ops.reset_default_graph()
 
 # Initialize a graph session
 sess = tf.Session()
 
 # Create a visualizer object
-summary_writer = tf.summary.FileWriter('tensorboard', tf.get_default_graph())
+summary_writer = tf.summary.FileWriter('tensorboard', sess.graph)
 
 # Create tensorboard folder if not exists
 if not os.path.exists('tensorboard'):
     os.makedirs('tensorboard')
 print('Running a slowed down linear regression. '
       'Run the command: $tensorboard --logdir="tensorboard"  '
-      ' Then navigate to http://127.0.0.0:6006')
+      ' Then navigate to http://127.0.0.1:6006')
 
 # You can also specify a port option with --port 6006
 
@@ -69,9 +71,8 @@
 
 # Visualize a histogram (errors)
 with tf.name_scope('Loss_and_Residuals'):
-    tf.summary.histogram('Histogram_Errors', l1_loss)
-    tf.summary.histogram('Histogram_Residuals', residuals)
-
+    tf.summary.histogram('Histogram_Errors', tf.squeeze(l1_loss))
+    tf.summary.histogram('Histogram_Residuals', tf.squeeze(residuals))
 
 
 # Declare summary merging operation
@@ -92,7 +93,7 @@
     test_loss, test_resids = sess.run([l1_loss, residuals], feed_dict={x_graph_input: x_data_test,
                                                                        y_graph_input: y_data_test})
 
-    if (i+1)%10==0:
+    if (i + 1) % 10 == 0:
         print('Generation {} of {}. Train Loss: {:.3}, Test Loss: {:.3}.'.format(i+1, generations, train_loss, test_loss))
 
     log_writer = tf.summary.FileWriter('tensorboard')
@@ -118,7 +119,7 @@ def gen_linear_plot(slope):
 # Add the batch dimension
 image = tf.expand_dims(image, 0)
 # Add image summary
-image_summary_op = tf.summary.image("Linear Plot", image)
+image_summary_op = tf.summary.image("Linear_Plot", image)
 image_summary = sess.run(image_summary_op)
 log_writer.add_summary(image_summary, i)
-log_writer.close()
+log_writer.close()

11_More_with_TensorFlow/02_Working_with_a_Genetic_Algorithm/02_genetic_algorithm.py

@@ -58,7 +58,7 @@
 
 # Get best fit individual
 best_val = tf.reduce_min(top_vals)
-best_ind = tf.arg_min(top_vals, 0)
+best_ind = tf.argmin(top_vals, 0)
 best_individual = tf.gather(population, best_ind)
 
 # Get parents
@@ -108,11 +108,11 @@
     best_individual_val = sess.run(best_individual, feed_dict=feed_dict)
 
     if i % 5 == 0:
-       best_fit = sess.run(best_val, feed_dict = feed_dict)
-       print('Generation: {}, Best Fitness (lowest MSE): {:.2}'.format(i, -best_fit))
+         best_fit = sess.run(best_val, feed_dict = feed_dict)
+         print('Generation: {}, Best Fitness (lowest MSE): {:.2}'.format(i, -best_fit))
 
 plt.plot(truth, label="True Values")
 plt.plot(np.squeeze(best_individual_val), label="Best Individual")
 plt.axis((0, features, -1.25, 1.25))
 plt.legend(loc='upper right')
-plt.show()
+plt.show()

11_More_with_TensorFlow/03_Clustering_Using_KMeans/03_k_means.py

@@ -23,7 +23,7 @@
 
 # Set k-means parameters
 # There are 3 types of iris flowers, see if we can predict them
-k=3 
+k = 3
 generations = 25
 
 data_points = tf.Variable(iris.data)
@@ -41,9 +41,10 @@
 point_matrix = tf.reshape(tf.tile(data_points, [1, k]), [num_pts, k, num_feats])
 distances = tf.reduce_sum(tf.square(point_matrix - centroid_matrix), axis=2)
 
-#Find the group it belongs to with tf.argmin()
+# Find the group it belongs to with tf.argmin()
 centroid_group = tf.argmin(distances, 1)
 
+
 # Find the group average
 def data_group_avg(group_ids, data):
     # Sum each group
@@ -52,7 +53,8 @@ def data_group_avg(group_ids, data):
     num_total = tf.unsorted_segment_sum(tf.ones_like(data), group_ids, 3)
     # Calculate average
     avg_by_group = sum_total/num_total
-    return(avg_by_group)
+    return avg_by_group
+
 
 means = data_group_avg(centroid_group, data_points)
 
@@ -73,18 +75,20 @@ def data_group_avg(group_ids, data):
 
 [centers, assignments] = sess.run([centroids, cluster_labels])
 
+
 # Find which group assignments correspond to which group labels
 # First, need a most common element function
 def most_common(my_list):
-    return(max(set(my_list), key=my_list.count))
+    return max(set(my_list), key=my_list.count)
+
 
 label0 = most_common(list(assignments[0:50]))
 label1 = most_common(list(assignments[50:100]))
 label2 = most_common(list(assignments[100:150]))
 
-group0_count = np.sum(assignments[0:50]==label0)
-group1_count = np.sum(assignments[50:100]==label1)
-group2_count = np.sum(assignments[100:150]==label2)
+group0_count = np.sum(assignments[0:50] == label0)
+group1_count = np.sum(assignments[50:100] == label1)
+group2_count = np.sum(assignments[100:150] == label2)
 
 accuracy = (group0_count + group1_count + group2_count)/150.
 
@@ -108,17 +112,15 @@ def most_common(my_list):
 # Get k-means classifications for the grid points
 xx_pt = list(xx.ravel())
 yy_pt = list(yy.ravel())
-xy_pts = np.array([[x,y] for x,y in zip(xx_pt, yy_pt)])
+xy_pts = np.array([[x, y] for x, y in zip(xx_pt, yy_pt)])
 mytree = cKDTree(reduced_centers)
 dist, indexes = mytree.query(xy_pts)
 
 # Put the result into a color plot
 indexes = indexes.reshape(xx.shape)
 plt.figure(1)
 plt.clf()
-plt.imshow(indexes, interpolation='nearest',
-           extent=(xx.min(), xx.max(), yy.min(), yy.max()),
-           cmap=plt.cm.Paired,
+plt.imshow(indexes, interpolation='nearest', extent=(xx.min(), xx.max(), yy.min(), yy.max()), cmap=plt.cm.Paired,
            aspect='auto', origin='lower')
 
 # Plot each of the true iris data groups
@@ -128,12 +130,9 @@ def most_common(my_list):
     temp_group = reduced_data[(i*50):(50)*(i+1)]
     plt.plot(temp_group[:, 0], temp_group[:, 1], symbols[i], markersize=10, label=label_name[i])
 # Plot the centroids as a white X
-plt.scatter(reduced_centers[:, 0], reduced_centers[:, 1],
-            marker='x', s=169, linewidths=3,
-            color='w', zorder=10)
-plt.title('K-means clustering on Iris Dataset\n'
-          'Centroids are marked with white cross')
+plt.scatter(reduced_centers[:, 0], reduced_centers[:, 1], marker='x', s=169, linewidths=3, color='w', zorder=10)
+plt.title('K-means clustering on Iris Dataset Centroids are marked with white cross')
 plt.xlim(x_min, x_max)
 plt.ylim(y_min, y_max)
 plt.legend(loc='lower right')
-plt.show()
+plt.show()

11_More_with_TensorFlow/04_Solving_A_System_of_ODEs/04_solving_ode_system.py

@@ -64,4 +64,4 @@
 plt.plot(prey_values)
 plt.plot(predator_values)
 plt.legend(['Prey', 'Predator'], loc='upper right')
-plt.show()
+plt.show()