In [8]:

    

# high level machine learning API(tf.contrib.learn)
import tensorflow as tf

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os
import urllib

import numpy as np

# data sets
IRIS_TRAINING = "iris_training.csv"
IRIS_TRAINING_URL = "http://download.tensorflow.org/data/iris_training.csv"

IRIS_TEST = "iris_test.csv"
IRIS_TEST_URL = "http://download.tensorflow.org/data/iris_test.csv"


def main():
    # if the training and test sets aren't stored locally, download them
    if not os.path.exists(IRIS_TRAINING):
        raw = urllib.urlopen(IRIS_TRAINING_URL).read()
        with open(IRIS_TRAINING, "w") as f:
            f.write(raw)
        
    if not os.path.exists(IRIS_TEST):
        raw = urllib.urlopen(IRIS_TEST_URL).read()
        with open(IRIS_TEST, "w") as f:
            f.write(raw)
    
    # load datasets
    training_set = tf.contrib.learn.datasets.base.load_csv_with_header(
        filename=IRIS_TRAINING,
        target_dtype=np.int,
        features_dtype=np.float32)
    
    test_set = tf.contrib.learn.datasets.base.load_csv_with_header(
        filename=IRIS_TEST,
        target_dtype=np.int,
        features_dtype=np.float32)
    
    # specify that all features have real-value date
    feature_columns = [tf.contrib.layers.real_valued_column("", dimension=4)]
    
    # builder 3 layer DNN with 10, 20, 10 units respectively.
    classifier = tf.contrib.learn.DNNClassifier(feature_columns=feature_columns,
                                               hidden_units=[10,20,10],
                                               n_classes=3,
                                               model_dir="/tmp/iris_model")
    
    # define the training inputs
    def get_train_inputs():
        x = tf.constant(training_set.data)
        y = tf.constant(training_set.target)
        
        return x, y
    
    # fit model
    classifier.fit(input_fn=get_train_inputs, steps=2000)
    
    # define the test inputs
    def get_test_inputs():
        x = tf.constant(test_set.data)
        y = tf.constant(test_set.target)
        
        return x, y
    
    # evaluate accuracy
    accuracy_score = classifier.evaluate(input_fn=get_test_inputs,
                                        steps=1)["accuracy"]
    print("\n Test accuracy: {0:f}\n".format(accuracy_score))
    
    # classfy two new flower samples
    def new_samples():
        return np.array(
        [[6.4, 3.2, 4.5, 1.5],
        [5.8, 3.1, 5.0, 1.7]], dtype=np.float32)
    
    predictions = list(classifier.predict(input_fn=new_samples))
    
    print(
        "New sample, class predictions: {}\n"
        .format(predictions))
    
if __name__ == "__main__":
    main()


    

    




INFO:tensorflow:Using default config.
INFO:tensorflow:Using config: {'_save_checkpoints_secs': 600, '_num_ps_replicas': 0, '_keep_checkpoint_max': 5, '_tf_random_seed': None, '_task_type': None, '_environment': 'local', '_is_chief': True, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x10d0c3690>, '_tf_config': gpu_options {
  per_process_gpu_memory_fraction: 1
}
, '_task_id': 0, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_evaluation_master': '', '_keep_checkpoint_every_n_hours': 10000, '_master': ''}
WARNING:tensorflow:From /Users/lipingzhang/anaconda/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/head.py:1362: scalar_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30.
Instructions for updating:
Please switch to tf.summary.scalar. Note that tf.summary.scalar uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on the scope they are created in. Also, passing a tensor or list of tags to a scalar summary op is no longer supported.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Saving checkpoints for 1 into /tmp/iris_model/model.ckpt.
INFO:tensorflow:loss = 1.17298, step = 1
INFO:tensorflow:global_step/sec: 1176.13
INFO:tensorflow:loss = 0.173284, step = 101
INFO:tensorflow:global_step/sec: 1340.8
INFO:tensorflow:loss = 0.112588, step = 201
INFO:tensorflow:global_step/sec: 1293.85
INFO:tensorflow:loss = 0.081251, step = 301
INFO:tensorflow:global_step/sec: 1311.18
INFO:tensorflow:loss = 0.071414, step = 401
INFO:tensorflow:global_step/sec: 1330.47
INFO:tensorflow:loss = 0.0645444, step = 501
INFO:tensorflow:global_step/sec: 1344.99
INFO:tensorflow:loss = 0.0594761, step = 601
INFO:tensorflow:global_step/sec: 1329.82
INFO:tensorflow:loss = 0.0565678, step = 701
INFO:tensorflow:global_step/sec: 1317.54
INFO:tensorflow:loss = 0.0535153, step = 801
INFO:tensorflow:global_step/sec: 1326.58
INFO:tensorflow:loss = 0.0515885, step = 901
INFO:tensorflow:global_step/sec: 1317.51
INFO:tensorflow:loss = 0.0500845, step = 1001
INFO:tensorflow:global_step/sec: 1308.78
INFO:tensorflow:loss = 0.0486503, step = 1101
INFO:tensorflow:global_step/sec: 1278.71
INFO:tensorflow:loss = 0.0474363, step = 1201
INFO:tensorflow:global_step/sec: 1201.6
INFO:tensorflow:loss = 0.0455893, step = 1301
INFO:tensorflow:global_step/sec: 1304.31
INFO:tensorflow:loss = 0.0448189, step = 1401
INFO:tensorflow:global_step/sec: 1304.39
INFO:tensorflow:loss = 0.0446906, step = 1501
INFO:tensorflow:global_step/sec: 1327.69
INFO:tensorflow:loss = 0.0424548, step = 1601
INFO:tensorflow:global_step/sec: 1310.14
INFO:tensorflow:loss = 0.0430387, step = 1701
INFO:tensorflow:global_step/sec: 1303.1
INFO:tensorflow:loss = 0.0409709, step = 1801
INFO:tensorflow:global_step/sec: 1269.55
INFO:tensorflow:loss = 0.0401204, step = 1901
INFO:tensorflow:Saving checkpoints for 2000 into /tmp/iris_model/model.ckpt.
INFO:tensorflow:Loss for final step: 0.0429132.
WARNING:tensorflow:From /Users/lipingzhang/anaconda/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/head.py:1362: scalar_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30.
Instructions for updating:
Please switch to tf.summary.scalar. Note that tf.summary.scalar uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on the scope they are created in. Also, passing a tensor or list of tags to a scalar summary op is no longer supported.
INFO:tensorflow:Starting evaluation at 2017-10-25-22:14:33
INFO:tensorflow:Evaluation [1/1]
INFO:tensorflow:Finished evaluation at 2017-10-25-22:14:34
INFO:tensorflow:Saving dict for global step 2000: accuracy = 0.966667, auc = 0.998333, global_step = 2000, loss = 0.0736693
WARNING:tensorflow:Skipping summary for global_step, must be a float or np.float32.

 Test accuracy: 0.966667

New sample, class predictions: [1, 2]

In [ ]:

    




    

In [ ]: