checkpoint

1 files changed, 44 insertions, 14 deletions

diff --git a/boston.py b/boston.py
index 55c814e..2491ea5 100644
--- a/boston.py
+++ b/boston.py
@@ -11,29 +11,52 @@ data, target = dataset.data, dataset.target
 data_scaler = preprocessing.MinMaxScaler()
 target_scaler = preprocessing.MinMaxScaler()
 
+print(target)
 data = data_scaler.fit_transform(data)
 target = target_scaler.fit_transform(target)
 
+target_scale = [target_scaler.inverse_transform([1])]  # TODO hack
+target_offset = [target_scaler.inverse_transform([0])]
+
 np.random.seed(0)
 
 x_train, x_test, y_train, y_test = train_test_split(
-    data, target, train_size=0.85
+    data, target, train_size=0.8
 )
 
+sess = tf.InteractiveSession()
+
 
 x = tf.placeholder(tf.float32, [None, 13], name="input")
-W = tf.Variable(tf.zeros([13, 1]), name="weight")
-b = tf.Variable(tf.zeros([1]), name="bias")
+y_ = tf.placeholder(tf.float32, [1, None], name="target")
+tscal = tf.placeholder(tf.float32, [1, 1], name="scaler")
+toffs = tf.placeholder(tf.float32, [1, 1], name="offset")
+
+W = tf.Variable(tf.zeros([13]), name="weight")
+b = tf.Variable(0.0, name="bias")
+
+sess.run(tf.initialize_all_variables())
 
-y = tf.add(tf.matmul(x, W), b)
+weighted = tf.mul(x, W)
+combined_weights = tf.reduce_sum(weighted, 1)
+y = tf.nn.sigmoid(tf.add(combined_weights, b))
 
-y_ = tf.placeholder(tf.float32, name="target")
-rmsle = tf.reduce_mean(tf.sqrt(tf.log(y_) - tf.log(y)))
-train_step = tf.train.GradientDescentOptimizer(0.1).minimize(rmsle)
+tscal = tf.transpose(tscal)
 
-init = tf.initialize_all_variables()
-sess = tf.Session()
-sess.run(init)
+scaled_y = tf.add(tf.mul(y, tscal), toffs)
+scaled_y_ = tf.add(tf.mul(y_, tscal), toffs)
+
+foo = tf.add(y_, 0)
+foo = tf.Print(foo, [foo], "y_: ")
+scaled_y_ = tf.Print(scaled_y_, [scaled_y_], "scaled_y_: ")
+scaled_y = tf.add(scaled_y, foo) # delme
+
+diff = tf.square(tf.sub(tf.log(scaled_y + 1), tf.log(scaled_y_ + 1)))
+mean = tf.reduce_mean(diff)
+sqrt = tf.sqrt(mean)
+rmsle = tf.reduce_mean(sqrt)
+
+train_step = tf.train.GradientDescentOptimizer(0.01).minimize(rmsle)
 
 last = 0
 batchsize = 50
@@ -45,11 +68,18 @@ while next_last < len(x_train):
         next_last = len(x_train)
 
     xt = x_train[last:next_last]
-    yt = y_train[last:next_last]
-    sess.run(train_step, feed_dict={x: xt, y_: yt})
+    yt = [y_train[last:next_last]]  #[[_] for _ in y_train[last:next_last]]
+
+    print("yt " + str(yt[0:3]))
+    print("tsc " + str(target_scaler.inverse_transform(yt[0:3])))
+    print("calc " + str([el * target_scale + target_offset for el in yt[0:3]]))
+    sess.run(train_step, feed_dict={x: xt, y_: yt, tscal: target_scale, toffs: target_offset})
     last = next_last
 
 print("finished training")
 
-diff = tf.sub(y, y_)
-print(sess.run(diff, feed_dict={x: x_test, y_: y_test}))
+#diff = tf.reduce_mean(tf.sub(scaled_y, scaled_y_))
+yt = [y_test]
+print(" --------- ")
+print("mean difference to test data: ")
+print(sess.run(rmsle, feed_dict={x: x_test, y_: yt, tscal: target_scale, toffs: target_offset}))