diff --git a/neural_network.py b/neural_network.py
index d045de8..d3c525d 100644
--- a/neural_network.py
+++ b/neural_network.py
@@ -118,8 +118,8 @@ model.add(Dense(units=29, activation='sigmoid'))
 # Configure the learning process.
 
 model.compile(optimizer='sgd',
-             loss='mean_squared_error',
-             metrics=['accuracy'])
+        loss='mean_squared_error',
+        metrics=['accuracy'])
 
 
 for i in range(29):
@@ -158,41 +158,41 @@ for i in range(11, 29):
 
     with open('/pub/faculty_share/daugher/datafiles/data/18states.bin', 'rb') as f:
 
-    for i in range(2000):
-	data = f.read(8)
+        for i in range(2000):
+            data = f.read(8)
 
-	data = f.read(8)
+        data = f.read(8)
 
-	counter = 0
+        counter = 0
 
-	testing = []
+        testing = []
 
-	testing_target = []
+        testing_target = []
 
-	while(data):
-	    bin_data = reduce(format_input, list(data), [])
-	    bin_data.reverse()
-	    bin_data = bin_data[16:]
+        while(data):
+            bin_data = reduce(format_input, list(data), [])
+            bin_data.reverse()
+            bin_data = bin_data[16:]
 
-	    testing.append(bin_data)
+            testing.append(bin_data)
 
-	    pos_data = reduce(format_pos, enumerate(list(data)), [])
-	    pos_data.reverse()
-	    pos_data = pos_data[1:]
+            pos_data = reduce(format_pos, enumerate(list(data)), [])
+            pos_data.reverse()
+            pos_data = pos_data[1:]
 
-	    state_pos = []
+            state_pos = []
 
-	    for p in pos_data:
-		state_pos.append(p[1])
+            for p in pos_data:
+                state_pos.append(p[1])
 
-	    testing_target_pos = reduce(generate_pos, pos_data, [])
+            testing_target_pos = reduce(generate_pos, pos_data, [])
 
-	    testing_target.append(format_man_dist(man_dist_state(state_pos, testing_target_pos)))
+            testing_target.append(format_man_dist(man_dist_state(state_pos, testing_target_pos)))
+
+            counter += 1
+            data = f.read(8)
 
-	    counter += 1
-	    data = f.read(8)
 
-        
         # Evaluate accuracy
 
         loss_and_metrics = model.evaluate(np.array(testing),np.array(testing_target), batch_size=1000)
@@ -200,7 +200,7 @@ for i in range(11, 29):
         # Generating predictions:
 
         predictions = model.predict(np.array(testing), batch_size=1000)
-        
+
         output = []
 
         for p in range(len(predictions)):