lot of stuff

Author: caetra

Diff for: features.txt

@@ -0,0 +1,57 @@
+word_freq_make:         continuous.
+word_freq_address:      continuous.
+word_freq_all:          continuous.
+word_freq_3d:           continuous.
+word_freq_our:          continuous.
+word_freq_over:         continuous.
+word_freq_remove:       continuous.
+word_freq_internet:     continuous.
+word_freq_order:        continuous.
+word_freq_mail:         continuous.
+word_freq_receive:      continuous.
+word_freq_will:         continuous.
+word_freq_people:       continuous.
+word_freq_report:       continuous.
+word_freq_addresses:    continuous.
+word_freq_free:         continuous.
+word_freq_business:     continuous.
+word_freq_email:        continuous.
+word_freq_you:          continuous.
+word_freq_credit:       continuous.
+word_freq_your:         continuous.
+word_freq_font:         continuous.
+word_freq_000:          continuous.
+word_freq_money:        continuous.
+word_freq_hp:           continuous.
+word_freq_hpl:          continuous.
+word_freq_george:       continuous.
+word_freq_650:          continuous.
+word_freq_lab:          continuous.
+word_freq_labs:         continuous.
+word_freq_telnet:       continuous.
+word_freq_857:          continuous.
+word_freq_data:         continuous.
+word_freq_415:          continuous.
+word_freq_85:           continuous.
+word_freq_technology:   continuous.
+word_freq_1999:         continuous.
+word_freq_parts:        continuous.
+word_freq_pm:           continuous.
+word_freq_direct:       continuous.
+word_freq_cs:           continuous.
+word_freq_meeting:      continuous.
+word_freq_original:     continuous.
+word_freq_project:      continuous.
+word_freq_re:           continuous.
+word_freq_edu:          continuous.
+word_freq_table:        continuous.
+word_freq_conference:   continuous.
+char_freq_;:            continuous.
+char_freq_(:            continuous.
+char_freq_[:            continuous.
+char_freq_!:            continuous.
+char_freq_$:            continuous.
+char_freq_#:            continuous.
+capital_run_length_average: continuous.
+capital_run_length_longest: continuous.
+capital_run_length_total:   continuous.

Diff for: get_data.py

@@ -0,0 +1,50 @@
+# Script to read in the spambase.data files and get a format we can use
+
+import pickle
+import csv
+import svmlight_loader
+
+filename = 'spambase.train'
+
+f = open(filename, 'r')
+
+data = []
+freader = csv.reader(f, delimiter=',')
+for row in freader:
+    data.append(row)
+    
+f.close()
+
+#print data
+
+# There are 58 columns in the data...
+# 57 are attributes
+# 48 are frequency of a word
+# 6 are frequency of a punctuation mark
+# 3 are data on sequences of characters
+# Last is label
+num_attributes = 57
+
+attributes = []
+labels = []
+for example in data:
+    attributes.append(example[:num_attributes])
+    labels.append(example[num_attributes])
+    
+# convert the strings to numbers
+for row in range(len(attributes)):
+    for col in range(num_attributes):
+        attributes[row][col] = float(attributes[row][col])
+        
+for x in range(len(labels)):
+    labels[x] = float(labels[x])
+    
+print attributes[0]
+attr_out = open('train_data.pickle', 'w')
+label_out = open('train_label.pickle', 'w')
+
+pickle.dump(attributes, attr_out)
+pickle.dump(labels, label_out)
+
+attr_out.close()
+label_out.close()

Diff for: get_data_reduced.py

@@ -0,0 +1,51 @@
+# Script to read in the spambase.data files and get a format we can use
+
+import pickle
+import csv
+import svmlight_loader
+
+filename = 'spambase.test'
+
+f = open(filename, 'r')
+
+data = []
+freader = csv.reader(f, delimiter=',')
+for row in freader:
+    data.append(row)
+    
+f.close()
+
+#print data
+
+# There are 58 columns in the data...
+# 57 are attributes
+# 48 are frequency of a word
+# 6 are frequency of a punctuation mark
+# 3 are data on sequences of characters
+# Last is label
+num_attributes = 57
+
+attributes = []
+labels = []
+for example in data:
+    #attributes.append(example[:num_attributes])
+    attributes.append(example[:54])
+    labels.append(example[num_attributes])
+    
+# convert the strings to numbers
+for row in range(len(attributes)):
+    for col in range(54):
+        attributes[row][col] = float(attributes[row][col])
+        
+for x in range(len(labels)):
+    labels[x] = float(labels[x])
+    
+print attributes[0]
+attr_out = open('test_data_reduced.pickle', 'w')
+label_out = open('test_label.pickle', 'w')
+
+pickle.dump(attributes, attr_out)
+pickle.dump(labels, label_out)
+
+attr_out.close()
+label_out.close()

Diff for: neural_network_1_hidden.py

@@ -12,7 +12,7 @@ def sigmoid(x):
 def sigmoid_derivative(x):
     return sigmoid(x) * (1 - sigmoid(x))
 
-class NeuralNetwork:
+class NeuralNetwork_1HL:
 
     def __init__(self, num_inputs, num_hidden_neurons, num_outputs):
         self.num_inputs = num_inputs
@@ -81,17 +81,17 @@ def get_output(self, inputs):
         return self.feed_forward(inputs)[1][1]
 
 # main program ########################################################################## 
-xor_net = NeuralNetwork(2, 3, 1)
-a = np.array([1.,1.])
-b = np.array([1.,0.])
-c = np.array([0.,1.])
-d = np.array([0.,0.])
-examples = [a, b, c, d]
-labels = [np.array([0.]), np.array([1.]), np.array([1.]), np.array([0.])]
+# xor_net = NeuralNetwork_1HL(2, 3, 1)
+# a = np.array([1.,1.])
+# b = np.array([1.,0.])
+# c = np.array([0.,1.])
+# d = np.array([0.,0.])
+# examples = [a, b, c, d]
+# labels = [np.array([0.]), np.array([1.]), np.array([1.]), np.array([0.])]
 
-xor_net.train_network(4, examples, labels, 5000, 0.3)
+# xor_net.train_network(4, examples, labels, 5000, 0.3)
 
-print xor_net.get_output(a)
-print xor_net.get_output(b)
-print xor_net.get_output(c)
-print xor_net.get_output(d)
+# print xor_net.get_output(a)
+# print xor_net.get_output(b)
+# print xor_net.get_output(c)
+# print xor_net.get_output(d)

Diff for: neural_network_2_hidden.py

@@ -11,7 +11,7 @@ def sigmoid(x):
 def sigmoid_derivative(x):
     return sigmoid(x) * (1 - sigmoid(x))
 
-class NeuralNetwork:
+class NeuralNetwork_2HL:
 
     def __init__(self, num_inputs, num_hidden_first, num_hidden_second, num_outputs):
         self.num_inputs = num_inputs
@@ -98,17 +98,17 @@ def get_output(self, inputs):
         return self.feed_forward(inputs)[1][2]
 
 # main program ########################################################################## 
-xor_net = NeuralNetwork(2, 3, 3, 1)
-a = np.array([1.,1.])
-b = np.array([1.,0.])
-c = np.array([0.,1.])
-d = np.array([0.,0.])
-examples = [a, b, c, d]
-labels = [np.array([0.]), np.array([1.]), np.array([1.]), np.array([0.])]
+# xor_net = NeuralNetwork_2HL(2, 3, 3, 1)
+# a = np.array([1.,1.])
+# b = np.array([1.,0.])
+# c = np.array([0.,1.])
+# d = np.array([0.,0.])
+# examples = [a, b, c, d]
+# labels = [np.array([0.]), np.array([1.]), np.array([1.]), np.array([0.])]
 
-xor_net.train_network(4, examples, labels, 5000, 0.3)
+# xor_net.train_network(4, examples, labels, 5000, 0.3)
 
-print xor_net.get_output(a)
-print xor_net.get_output(b)
-print xor_net.get_output(c)
-print xor_net.get_output(d)
+# print xor_net.get_output(a)
+# print xor_net.get_output(b)
+# print xor_net.get_output(c)
+# print xor_net.get_output(d)