From b09211ca6398a941eb94074cf1c00555216a87e7 Mon Sep 17 00:00:00 2001
From: Gregory Ditzler <gditzler@Gregorys-MacBook-Pro.local>
Date: Tue, 26 Mar 2013 16:04:54 -0400
Subject: only one file needed for test

---
 test/test.py | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

(limited to 'test')

diff --git a/test/test.py b/test/test.py
index 0a9633a..ab10737 100644
--- a/test/test.py
+++ b/test/test.py
@@ -12,6 +12,48 @@ def check_result(selected_features, n_relevant):
 			success = False
 	return success
 
+def read_digits(fname='digit.txt'):
+	'''
+		read_digits(fname='digit.txt')
+
+		read a data file that contains the features and class labels. 
+		each row of the file is a feature vector with the class 
+		label appended. 
+	'''
+	import csv
+	import numpy as np
+
+	fw = csv.reader(open(fname,'rb'), delimiter='\t')
+	data = []
+	for line in fw: 
+		data.append( [float(x) for x in line] )
+	data = np.array(data)
+	labels = data[:,len(data.transpose())-1]
+	data = data[:,:len(data.transpose())-1]
+	return data, labels
+
+def uniform_data(n_observations = 1000, n_features = 50, n_relevant = 5):
+	import numpy as np
+	xmax = 10
+	xmin = 0
+	data = 1.0*np.random.randint(xmax + 1, size = (n_features, n_observations))
+	labels = np.zeros(n_observations)
+	delta = n_relevant * (xmax - xmin) / 2.0
+
+	for m in range(n_observations):
+		zz = 0.0
+		for k in range(n_relevant):
+			zz += data[k, m]
+		if zz > delta:
+			labels[m] = 1
+		else:
+			labels[m] = 2
+	data = data.transpose()
+	
+	return data, labels
+
+
+
 
 
 n_relevant = 5
-- 
cgit v1.2.3