Update lab-07-3-linear_regression_min_max.py

1. Changed the function name because there are many inquiries that it is confused with 'MinMaxScaler' of 'sklearn.preprocessing'.
2. Added normalized output.

lab-07-3-linear_regression_min_max.py

@@ -3,26 +3,41 @@
 tf.set_random_seed(777)  # for reproducibility
 
 
-def MinMaxScaler(data):
+def min_max_scaler(data):
     numerator = data - np.min(data, 0)
     denominator = np.max(data, 0) - np.min(data, 0)
     # noise term prevents the zero division
     return numerator / (denominator + 1e-7)
 
 
-xy = np.array([[828.659973, 833.450012, 908100, 828.349976, 831.659973],
-               [823.02002, 828.070007, 1828100, 821.655029, 828.070007],
-               [819.929993, 824.400024, 1438100, 818.97998, 824.159973],
-               [816, 820.958984, 1008100, 815.48999, 819.23999],
-               [819.359985, 823, 1188100, 818.469971, 818.97998],
-               [819, 823, 1198100, 816, 820.450012],
-               [811.700012, 815.25, 1098100, 809.780029, 813.669983],
-               [809.51001, 816.659973, 1398100, 804.539978, 809.559998]])
+xy = np.array(
+    [
+        [828.659973, 833.450012, 908100, 828.349976, 831.659973],
+        [823.02002, 828.070007, 1828100, 821.655029, 828.070007],
+        [819.929993, 824.400024, 1438100, 818.97998, 824.159973],
+        [816, 820.958984, 1008100, 815.48999, 819.23999],
+        [819.359985, 823, 1188100, 818.469971, 818.97998],
+        [819, 823, 1198100, 816, 820.450012],
+        [811.700012, 815.25, 1098100, 809.780029, 813.669983],
+        [809.51001, 816.659973, 1398100, 804.539978, 809.559998],
+    ]
+)
 
 # very important. It does not work without it.
-xy = MinMaxScaler(xy)
+xy = min_max_scaler(xy)
 print(xy)
 
+'''
+[[0.99999999 0.99999999 0.         1.         1.        ]
+ [0.70548491 0.70439552 1.         0.71881782 0.83755791]
+ [0.54412549 0.50274824 0.57608696 0.606468   0.6606331 ]
+ [0.33890353 0.31368023 0.10869565 0.45989134 0.43800918]
+ [0.51436    0.42582389 0.30434783 0.58504805 0.42624401]
+ [0.49556179 0.42582389 0.31521739 0.48131134 0.49276137]
+ [0.11436064 0.         0.20652174 0.22007776 0.18597238]
+ [0.         0.07747099 0.5326087  0.         0.        ]]
+'''
+
 x_data = xy[:, 0:-1]
 y_data = xy[:, [-1]]
 
@@ -40,29 +55,59 @@ def MinMaxScaler(data):
 cost = tf.reduce_mean(tf.square(hypothesis - Y))
 
 # Minimize
-optimizer = tf.train.GradientDescentOptimizer(learning_rate=1e-5)
-train = optimizer.minimize(cost)
+train = tf.train.GradientDescentOptimizer(learning_rate=1e-5).minimize(cost)
 
 # Launch the graph in a session.
-sess = tf.Session()
-# Initializes global variables in the graph.
-sess.run(tf.global_variables_initializer())
+with tf.Session() as sess:
+    # Initializes global variables in the graph.
+    sess.run(tf.global_variables_initializer())
 
-for step in range(101):
-    cost_val, hy_val, _ = sess.run(
-        [cost, hypothesis, train], feed_dict={X: x_data, Y: y_data})
-    print(step, "Cost: ", cost_val, "\nPrediction:\n", hy_val)
+    for step in range(101):
+        _, cost_val, hy_val = sess.run(
+            [train, cost, hypothesis], feed_dict={X: x_data, Y: y_data}
+        )
+        print(step, "Cost: ", cost_val, "\nPrediction:\n", hy_val)
 
 '''
-100 Cost:  0.152254
+0 Cost: 0.15230925 
+Prediction:
+ [[ 1.6346191 ]
+ [ 0.06613699]
+ [ 0.3500818 ]
+ [ 0.6707252 ]
+ [ 0.61130744]
+ [ 0.61464405]
+ [ 0.23171967]
+ [-0.1372836 ]]
+1 Cost: 0.15230872 
 Prediction:
- [[ 1.63450289]
- [ 0.06628087]
+ [[ 1.634618  ]
+ [ 0.06613836]
+ [ 0.35008252]
+ [ 0.670725  ]
+ [ 0.6113076 ]
+ [ 0.6146443 ]
+ [ 0.23172   ]
+ [-0.13728246]]
+...
+99 Cost: 0.1522546 
+Prediction:
+ [[ 1.6345041 ]
+ [ 0.06627947]
+ [ 0.35014683]
+ [ 0.670706  ]
+ [ 0.6113161 ]
+ [ 0.61466044]
+ [ 0.23175153]
+ [-0.13716647]]
+100 Cost: 0.15225402 
+Prediction:
+ [[ 1.6345029 ]
+ [ 0.06628093]
  [ 0.35014752]
  [ 0.67070574]
- [ 0.61131608]
- [ 0.61466062]
+ [ 0.61131614]
+ [ 0.6146606 ]
  [ 0.23175186]
  [-0.13716528]]
-
 '''