第一阶段-入门详细图文讲解tensorflow1.4 -（七）tf.estimator的IRIS

tf.estimator是tensorflow高级API。可以很容易建立神经网络分类器。应用于iris数据集。根据萼片/花瓣的几何描述，进行分类。并且用来预测未知样本属于的花种类。

    A training set of 120 samples (iris_training.csv)
    A test set of 30 samples (iris_test.csv).

step1，加载数据

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

import os
from six.moves.urllib.request import urlopen

import tensorflow as tf
import numpy as np

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"
#下载数据
if not os.path.exists(IRIS_TRAINING):
  raw = urlopen(IRIS_TRAINING_URL).read()
  with open(IRIS_TRAINING,'wb') as f:
    f.write(raw)

if not os.path.exists(IRIS_TEST):
  raw = urlopen(IRIS_TEST_URL).read()
  with open(IRIS_TEST,'wb') as f:
    f.write(raw)
# 加载数据集
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)

step2，构建一个深度神经网络分类器

# 数据格式为一维张量
feature_columns = [tf.feature_column.numeric_column("x", shape=[4])]

# 建立一个3层DNN网络，每层节点数10,20,10.
classifier = tf.estimator.DNNClassifier(feature_columns=feature_columns,
                                        hidden_units=[10, 20, 10],
                                        n_classes=3,
                                        model_dir="/tmp/iris_model")

step3，描述输入数据流

# Define the training inputs
train_input_fn = tf.estimator.inputs.numpy_input_fn(
    x={"x": np.array(training_set.data)},
    y=np.array(training_set.target),
    num_epochs=None,
    shuffle=True)

step4，将iris数据集填充到DNN分类器中

# Train model.
classifier.train(input_fn=train_input_fn, steps=2000)
等价于：
classifier.train(input_fn=train_input_fn, steps=1000)
classifier.train(input_fn=train_input_fn, steps=1000)

step5，计算模型准确度

# Define the test inputs
test_input_fn = tf.estimator.inputs.numpy_input_fn(
    x={"x": np.array(test_set.data)},
    y=np.array(test_set.target),
    num_epochs=1,
    shuffle=False)

# Evaluate accuracy.
accuracy_score = classifier.evaluate(input_fn=test_input_fn)["accuracy"]

print("\nTest Accuracy: {0:f}\n".format(accuracy_score))

step6，预测未知样本

# Classify two new flower samples.
new_samples = np.array(
    [[6.4, 3.2, 4.5, 1.5],
     [5.8, 3.1, 5.0, 1.7]], dtype=np.float32)
predict_input_fn = tf.estimator.inputs.numpy_input_fn(
    x={"x": new_samples},
    num_epochs=1,
    shuffle=False)

predictions = list(classifier.predict(input_fn=predict_input_fn))
predicted_classes = [p["classes"] for p in predictions]

print(
    "New Samples, Class Predictions:    {}\n"
    .format(predicted_classes))

整理以上代码：

# -*- coding: utf-8 -*-
"""
Created on Tue Dec 19 15:54:41 2017

@author: suncl
"""

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

import os
from six.moves.urllib.request import urlopen

import numpy as np
import tensorflow as tf

# 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 = urlopen(IRIS_TRAINING_URL).read()
    with open(IRIS_TRAINING, "wb") as f:
      f.write(raw)

  if not os.path.exists(IRIS_TEST):
    raw = urlopen(IRIS_TEST_URL).read()
    with open(IRIS_TEST, "wb") 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 data
  feature_columns = [tf.feature_column.numeric_column("x", shape=[4])]

  # Build 3 layer DNN with 10, 20, 10 units respectively.
  classifier = tf.estimator.DNNClassifier(feature_columns=feature_columns,
                                          hidden_units=[10, 20, 10],
                                          n_classes=3,
                                          model_dir="/tmp/iris_model")
  # Define the training inputs
  train_input_fn = tf.estimator.inputs.numpy_input_fn(
      x={"x": np.array(training_set.data)},
      y=np.array(training_set.target),
      num_epochs=None,
      shuffle=True)

  # Train model.
  classifier.train(input_fn=train_input_fn, steps=2000)

  # Define the test inputs
  test_input_fn = tf.estimator.inputs.numpy_input_fn(
      x={"x": np.array(test_set.data)},
      y=np.array(test_set.target),
      num_epochs=1,
      shuffle=False)

  # Evaluate accuracy.
  accuracy_score = classifier.evaluate(input_fn=test_input_fn)["accuracy"]

  print("\nTest Accuracy: {0:f}\n".format(accuracy_score))

  # Classify two new flower samples.
  new_samples = np.array(
      [[6.4, 3.2, 4.5, 1.5],
       [5.8, 3.1, 5.0, 1.7]], dtype=np.float32)
  predict_input_fn = tf.estimator.inputs.numpy_input_fn(
      x={"x": new_samples},
      num_epochs=1,
      shuffle=False)

  predictions = list(classifier.predict(input_fn=predict_input_fn))
  predicted_classes = [p["classes"] for p in predictions]

  print(
      "New Samples, Class Predictions:    {}\n"
      .format(predicted_classes))

if __name__ == "__main__":
    main()

本blog结束。