Starting playing around with libsvm. New data files (with no holes) for Jon.

1 files changed, 70 insertions, 0 deletions

diff --git a/data/class.py b/data/class.py
new file mode 100755
index 0000000..e7975f9
--- /dev/null
+++ b/data/class.py
@@ -0,0 +1,70 @@
+#! /usr/bin/python
+import copy
+import sys
+from svmutil import *
+
+lower = 0.1
+upper = 10
+
+def normalize_instances(instances, ranges = None) :
+    normalized_instances = copy.deepcopy(instances)
+    if ranges == None :
+        ranges_dict = dict()
+    for attribute in normalized_instances[0].keys() :  # we iterate on the attributes
+        column = [instance[attribute] for instance in normalized_instances]
+        if ranges != None :
+            minimum = ranges[attribute][0]
+            maximum = ranges[attribute][1]
+        else :
+            minimum = min(column)
+            maximum = max(column)
+            ranges_dict[attribute] = [minimum, maximum]
+        for i in range(len(column)) :
+            if column[i] == minimum :
+                column[i] = lower
+            elif column[i] == maximum :
+                column[i] = upper
+            else :
+                column[i] = lower + (upper-lower) * (column[i] - minimum) / (maximum - minimum)
+        # Copying normalized values in memory
+      
+        for elem, instance in zip(column, normalized_instances):
+            instance[attribute] = elem
+  
+    if ranges == None :
+        return normalized_instances, ranges_dict
+    else :
+        return normalized_instances
+
+
+def read_file(filename) :
+    y = []
+    x = []
+    for line in filename:
+        values = line.rstrip().split(',')
+        if values[0] != "# dir":
+            dict = {}
+            for i in range(9):
+                if float(values[i+5])!=-1.:
+                    dict[i+1] = float(values[i+5])
+            if len(dict)==9:
+                y += [int(values[1])]
+                x += [dict]
+                print line.rstrip()
+    #for a,b in zip(y,x):
+    #    result = str(a)
+    #    for i in range(9):
+    #        result += " "+str(i+1)+":"+str(b[i+1])
+    #    print result
+    #return (y,x)
+
+train_filename = sys.argv[1]
+#test_filename = sys.argv[2]
+y1,x1 = read_file(open(train_filename))
+#x1,ranges = normalize_instances(x1)
+#print ranges
+#exit(0)
+#model = svm_train(y1,x1)
+#y2,x2 = read_file(open(test_filename))
+#x2 = normalize_instances(x2,ranges)
+#p_labels,p_acc,p_vals = svm_predict(y2,x2,model)