From 641daf06c0bbf98ebec16b29f0b3575b083d434e Mon Sep 17 00:00:00 2001
From: schneefux <schneefux+commit@schneefux.xyz>
Date: Fri, 29 Jan 2016 13:15:41 +0100
Subject: weiter

---
 boston.py | 89 +++++++++++++++++++++++++++------------------------------------
 1 file changed, 38 insertions(+), 51 deletions(-)

diff --git a/boston.py b/boston.py
index 3a339ab..ede5202 100644
--- a/boston.py
+++ b/boston.py
@@ -18,58 +18,47 @@ x_train, x_test, y_train, y_test = train_test_split(
 )
 
 
-sess = tf.InteractiveSession()
+with tf.device('/cpu:0'):
+    sess = tf.InteractiveSession()
 
-x = tf.placeholder(tf.float32, [None, 13], name="input")
-y_ = tf.placeholder(tf.float32, [1, None], name="target")
-fact = tf.placeholder(tf.float32, [1, None], name="factor")  # max(x) - min(x)
-offs = tf.placeholder(tf.float32, [1, None], name="offset")  # min(x)
+    input_matrix = tf.placeholder(tf.float32, [None, 13], name="input")
+    real = tf.placeholder(tf.float32, [1, None], name="target")
+    fact = tf.placeholder(tf.float32, [1, None], name="factor")
+    # ^ max(input_matrix) - min(input_matrix)
+    offs = tf.placeholder(tf.float32, [1, None], name="offset")
+    # ^ min(input_matrix)
 
-fitted_y_ = tf.div(tf.sub(y_, offs), fact)  # input scaled
+    fitted_real = tf.div(tf.sub(real, offs), fact)  # input scaled
 
-W = tf.Variable(tf.zeros([13]), name="weight")
-b = tf.Variable(0.0, name="bias")
+    weights = tf.Variable(tf.truncated_normal([13], stddev=0.1), name="weight")
+    bias = tf.Variable(0.0, name="bias")
 
-weighted = tf.mul(x, W)
-combined_weights = tf.reduce_sum(weighted, 1)  # sum w_n*x
-y = tf.nn.sigmoid(tf.add(combined_weights, b))
-unfitted_y = tf.add(tf.mul(y, fact), offs)  # un-scale prediction
+    weighted = tf.reduce_sum(tf.mul(input_matrix, weights), 1)
+    # ^ sum ([13]weights*input_matrix)
+    fitted_prediction = tf.sigmoid(tf.add(weighted, bias))
+    prediction = tf.add(tf.mul(fitted_prediction, fact), offs)
+    # ^ un-scale prediction
 
-# debug
-#unfitted_y = tf.Print(unfitted_y, [unfitted_y], "est: ")
-#foo = tf.add(y_, 0)
-#foo = tf.Print(foo, [foo], "real: ")
-#
-# debug
-#y = tf.Print(y, [y], "est: ")
-#foo = tf.add(fitted_y_, 0)
-#fitted_y_ = tf.Print(fitted_y_, [fitted_y_], "real: ")
-#
-
-sqr = tf.square(tf.sub(unfitted_y, y_))
-
-# debug
-#sqr = tf.Print(sqr, [sqr], "sqr: ")
-#
-
-mean = tf.reduce_mean(sqr)
-rmse = tf.sqrt(mean)
+    diff = tf.sub(prediction, real)  # for testing
 
-difference = tf.abs(tf.reduce_sum(tf.sub(y, fitted_y_)))
+    sqr = tf.square(diff)
+    mean = tf.reduce_mean(sqr)
+    mse = mean
 
-# debug
-#rmse = tf.Print(rmse, [rmse], "rmse: ")
-#
+    difference = tf.abs(
+        tf.reduce_sum(tf.sub(fitted_prediction, fitted_real)))
 
-rmse_summary = tf.scalar_summary("rmse", rmse)
-diff_summary = tf.scalar_summary("diff", difference)
-merged = tf.merge_all_summaries()
-writer = tf.train.SummaryWriter("/tmp/boston_logs", sess.graph_def)
+    mse_summary = tf.scalar_summary("mse", mse)
+    diff_summary = tf.scalar_summary("max diff", tf.reduce_max(diff))
+    diff_summary = tf.scalar_summary("mean diff", tf.reduce_mean(diff))
+    merged = tf.merge_all_summaries()
+    writer = tf.train.SummaryWriter("/tmp/boston_logs", sess.graph_def)
 
-# all variables have to be specified here
-sess.run(tf.initialize_all_variables())
+    # all variables have to be specified here
+    sess.run(tf.initialize_all_variables())
 
-train_step = tf.train.GradientDescentOptimizer(0.005).minimize(rmse)
+    mse = tf.Print(mse, [mse], "mse: ")
+    train_step = tf.train.GradientDescentOptimizer(0.0001).minimize(mse)
 
 
 last = 0
@@ -90,25 +79,23 @@ while next_last < len(x_train):
     xt = x_train[last:next_last]
     yt = [y_train[last:next_last]]
 
-    for i in range(0, 1000):  # 100 epochs
+    for i in range(0, 100):  # 100 epochs
         if i % 100 == 0:
-            feed = {x: x_test, y_: [y_test], fact: factor, offs: offset}
-            result = sess.run([merged, rmse, difference], feed_dict=feed)
+            feed = {input_matrix: x_test, real: [y_test], fact: factor, offs: offset}
+            result = sess.run([merged, mse, difference], feed_dict=feed)
             writer.add_summary(result[0], i)
 
         sess.run(train_step,
-                 feed_dict={x: xt, y_: yt, fact: factor, offs: offset})
+                 feed_dict={input_matrix: xt, real: yt, fact: factor, offs: offset})
 
     last = next_last
 
 
 print("finished training")
 
-#rdiff = tf.reduce_mean(tf.sub(y, y_))
-diff = tf.sub(unfitted_y, y_)
 yt = [y_test]
-# debug?
+# debug
 print(" --------- ")
 print("mean difference to test data: ")
-print(sess.run(rmse, feed_dict={x: x_test, y_: yt, fact: factor, offs: offset}))
-print(sess.run(diff, feed_dict={x: x_test, y_: yt, fact: factor, offs: offset}))
+print(sess.run(mse, feed_dict={input_matrix: x_test, real: yt, fact: factor, offs: offset}))
+print(sess.run(diff, feed_dict={input_matrix: x_test, real: yt, fact: factor, offs: offset}))
-- 
cgit v1.3.1