move most codes to uci_housing #9660

doc/fluid/getstarted/quickstart_cn.rst

@@ -25,94 +25,31 @@ PaddlePaddle支持使用pip快速安装，目前支持CentOS 6以上, Ubuntu 14.
 创建一个 housing.py 并粘贴此Python代码：
 
   .. code-block:: python
-
-     import sys
-     
-     import math
-     import numpy
-     
-     import paddle.fluid as fluid
-     import paddle.fluid.core as core
      import paddle
+     import paddle.fluid as fluid
      
-     def train(save_dirname):
-         x = fluid.layers.data(name='x', shape=[13], dtype='float32')
-         y_predict = fluid.layers.fc(input=x, size=1, act=None)
-         y = fluid.layers.data(name='y', shape=[1], dtype='float32')
-     
-         cost = fluid.layers.square_error_cost(input=y_predict, label=y)
-         avg_cost = fluid.layers.mean(cost)
-     
-         sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.001)
-         optimize_ops, params_grads = sgd_optimizer.minimize(avg_cost)
-     
-         BATCH_SIZE = 20
-     
-         train_reader = paddle.batch(
-             paddle.reader.shuffle(paddle.dataset.uci_housing.train(), buf_size=500), batch_size=BATCH_SIZE)
-     
-         place = fluid.CPUPlace()
-         exe = fluid.Executor(place)
-     
-         feeder = fluid.DataFeeder(place=place, feed_list=[x, y])
-         exe.run(fluid.default_startup_program())
-     
-         main_program = fluid.default_main_program()
      
-         PASS_NUM = 100
-         for pass_id in range(PASS_NUM):
-             for data in train_reader():
-                 avg_loss_value, = exe.run(main_program,
-                                           feed=feeder.feed(data),
-                                           fetch_list=[avg_cost])
-                 if avg_loss_value[0] < 10.0:
-                     if save_dirname is not None:
-                         fluid.io.save_inference_model(save_dirname, ['x'],
-                                                       [y_predict], exe)
-                     return
-                 if math.isnan(float(avg_loss_value)):
-                     sys.exit("got NaN loss, training failed.")
-         raise AssertionError("Fit a line cost is too large, {0:2.2}".format(
-             avg_loss_value[0]))
+     x = fluid.layers.data(name='x', shape=[13], dtype='float32')
+     place = fluid.CPUPlace()
+     exe = fluid.Executor(place=place)
+     feeder = fluid.DataFeeder(place=place, feed_list=[x])
      
-     def infer(save_dirname):
-         place = fluid.CPUPlace()
-         exe = fluid.Executor(place)
+     with fluid.scope_guard(fluid.core.Scope()):
+         parameter_model = paddle.dataset.uci_housing.fluid_model()
      
-         probs = []
+         [inference_program, feed_target_names,fetch_targets] =  \
+             fluid.io.load_inference_model(parameter_model, exe)
      
-         inference_scope = fluid.core.Scope()
-         with fluid.scope_guard(inference_scope):
-             # Use fluid.io.load_inference_model to obtain the inference program desc,
-             # the feed_target_names (the names of variables that will be feeded
-             # data using feed operators), and the fetch_targets (variables that
-             # we want to obtain data from using fetch operators).
-             [inference_program, feed_target_names,
-              fetch_targets] = fluid.io.load_inference_model(save_dirname, exe)
+         predict_reader = paddle.batch(paddle.dataset.uci_housing.predict_reader(), batch_size=20)
      
-             # The input's dimension should be 2-D and the second dim is 13
-             # The input data should be >= 0
-             batch_size = 10
-             tensor_x = numpy.random.uniform(0, 10,
-                                             [batch_size, 13]).astype("float32")
-             assert feed_target_names[0] == 'x'
-             results = exe.run(inference_program,
-                               feed={feed_target_names[0]: tensor_x},
+         results = []
+         for data in predict_reader():
+             result = exe.run(inference_program,
+                               feed=feeder.feed(data),
                                fetch_list=fetch_targets)
-             probs.append(results)
+             results.append(result)
      
-         for i in xrange(len(probs)):
-             print(probs[i][0] * 1000)
-             print('Predicted price: ${0}'.format(probs[i][0] * 1000))
-     
-     def main():
-         # Directory for saving the trained model
-         save_dirname = "fit_a_line.inference.model"
-     
-         train(save_dirname)
-         infer(save_dirname)
-     
-     if __name__=="__main__":
-         main()
-
+         for res in results:
+             for i in xrange(len(res[0])):
+                 print 'Predicted price: ${:,.2f}'.format(res[0][i][0] * 1000)
 执行 :code:`python housing.py` 瞧！ 它应该打印出预测住房数据的清单。

doc/fluid/getstarted/quickstart_en.rst

@@ -28,93 +28,33 @@ code:
 
 
   .. code-block:: python
-    import sys
-    
-    import math
-    import numpy
-    
-    import paddle.fluid as fluid
-    import paddle.fluid.core as core
-    import paddle
-    
-    def train(save_dirname):
-        x = fluid.layers.data(name='x', shape=[13], dtype='float32')
-        y_predict = fluid.layers.fc(input=x, size=1, act=None)
-        y = fluid.layers.data(name='y', shape=[1], dtype='float32')
-    
-        cost = fluid.layers.square_error_cost(input=y_predict, label=y)
-        avg_cost = fluid.layers.mean(cost)
-    
-        sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.001)
-        optimize_ops, params_grads = sgd_optimizer.minimize(avg_cost)
-    
-        BATCH_SIZE = 20
-    
-        train_reader = paddle.batch(
-            paddle.reader.shuffle(paddle.dataset.uci_housing.train(), buf_size=500), batch_size=BATCH_SIZE)
-    
-        place = fluid.CPUPlace()
-        exe = fluid.Executor(place)
-    
-        feeder = fluid.DataFeeder(place=place, feed_list=[x, y])
-        exe.run(fluid.default_startup_program())
-    
-        main_program = fluid.default_main_program()
-    
-        PASS_NUM = 100
-        for pass_id in range(PASS_NUM):
-            for data in train_reader():
-                avg_loss_value, = exe.run(main_program,
-                                          feed=feeder.feed(data),
-                                          fetch_list=[avg_cost])
-                if avg_loss_value[0] < 10.0:
-                    if save_dirname is not None:
-                        fluid.io.save_inference_model(save_dirname, ['x'],
-                                                      [y_predict], exe)
-                    return
-                if math.isnan(float(avg_loss_value)):
-                    sys.exit("got NaN loss, training failed.")
-        raise AssertionError("Fit a line cost is too large, {0:2.2}".format(
-            avg_loss_value[0]))
-    
-    def infer(save_dirname):
-        place = fluid.CPUPlace()
-        exe = fluid.Executor(place)
-    
-        probs = []
-    
-        inference_scope = fluid.core.Scope()
-        with fluid.scope_guard(inference_scope):
-            # Use fluid.io.load_inference_model to obtain the inference program desc,
-            # the feed_target_names (the names of variables that will be feeded
-            # data using feed operators), and the fetch_targets (variables that
-            # we want to obtain data from using fetch operators).
-            [inference_program, feed_target_names,
-             fetch_targets] = fluid.io.load_inference_model(save_dirname, exe)
-    
-            # The input's dimension should be 2-D and the second dim is 13
-            # The input data should be >= 0
-            batch_size = 10
-            tensor_x = numpy.random.uniform(0, 10,
-                                            [batch_size, 13]).astype("float32")
-            assert feed_target_names[0] == 'x'
-            results = exe.run(inference_program,
-                              feed={feed_target_names[0]: tensor_x},
-                              fetch_list=fetch_targets)
-            probs.append(results)
-    
-        for i in xrange(len(probs)):
-            print(probs[i][0] * 1000)
-            print('Predicted price: ${0}'.format(probs[i][0] * 1000))
-    
-    def main():
-        # Directory for saving the trained model
-        save_dirname = "fit_a_line.inference.model"
-    
-        train(save_dirname)
-        infer(save_dirname)
-    
-    if __name__=="__main__":
-        main()
+     import paddle
+     import paddle.fluid as fluid
+     
+     
+     x = fluid.layers.data(name='x', shape=[13], dtype='float32')
+     place = fluid.CPUPlace()
+     exe = fluid.Executor(place=place)
+     feeder = fluid.DataFeeder(place=place, feed_list=[x])
+     
+     with fluid.scope_guard(fluid.core.Scope()):
+         parameter_model = paddle.dataset.uci_housing.fluid_model()
+     
+         [inference_program, feed_target_names,fetch_targets] =  \
+             fluid.io.load_inference_model(parameter_model, exe)
+     
+         predict_reader = paddle.batch(paddle.dataset.uci_housing.predict_reader(), batch_size=20)
+     
+         results = []
+         for data in predict_reader():
+             result = exe.run(inference_program,
+                               feed=feeder.feed(data),
+                               fetch_list=fetch_targets)
+             results.append(result)
+     
+         for res in results:
+             for i in xrange(len(res[0])):
+                 print 'Predicted price: ${:,.2f}'.format(res[0][i][0] * 1000)
+
 Run :code:`python housing.py` and voila! It should print out a list of predictions
 for the test housing data.

python/paddle/dataset/uci_housing.py

@@ -19,7 +19,11 @@ https://archive.ics.uci.edu/ml/machine-learning-databases/housing/ and
 parse training set and test set into paddle reader creators.
 """
 
+import os
+
 import numpy as np
+import tempfile
+import tarfile
 import os
 import paddle.dataset.common
 
@@ -34,8 +38,9 @@ feature_names = [
 
 UCI_TRAIN_DATA = None
 UCI_TEST_DATA = None
-URL_MODEL = 'https://github.com/PaddlePaddle/book/raw/develop/01.fit_a_line/fit_a_line.tar'
-MD5_MODEL = '52fc3da8ef3937822fcdd87ee05c0c9b'
+
+FLUID_URL_MODEL = 'https://github.com/PaddlePaddle/book/raw/develop/01.fit_a_line/fluid/fit_a_line.fluid.tar'
+FLUID_MD5_MODEL = '6e6dd637ccd5993961f68bfbde46090b'
 
 
 def feature_range(maximums, minimums):
@@ -112,6 +117,33 @@ def test():
 
     return reader
 
+def fluid_model():
+    parameter_tar = paddle.dataset.common.download(FLUID_URL_MODEL, 'uci_housing', FLUID_MD5_MODEL, 'fit_a_line.fluid.tar')
+
+    tar = tarfile.TarFile(parameter_tar, mode='r')
+    dirpath = tempfile.mkdtemp()
+    tar.extractall(path=dirpath)
+
+    return dirpath
+
+def predict_reader():
+    """
+    UCI_HOUSING test set creator.
+
+    It returns a reader creator, each sample in the reader is features after
+    normalization and price number.
+
+    :return: Test reader creator
+    :rtype: callable
+    """
+    global UCI_TEST_DATA
+    load_data(paddle.dataset.common.download(URL, 'uci_housing', MD5))
+
+    def reader():
+        for d in UCI_TEST_DATA:
+            yield (d[:-1],)
+
+    return reader
 
 def fetch():
     paddle.dataset.common.download(URL, 'uci_housing', MD5)