[TensorFlow实战练习]3-高层API-tf.contrib.learn练习

前面两个练习都是用TensorFlow Core写的，相对于数据流图的概念比较清晰。TensorFlow本身也封装了很多高层API，方面我们做开发方便。很多模型和函数都有（东西太多了完全看不完啊）。

因为是封装后的模型，就不怎么逐步解释了。主要是process-fit-evaluate-predict过程。

直接贴代码 本来是跟着书学习的，奈何现在的是API是1.1。0.6的教程有太多的不一样。

下面贴的是TensorFlow1.1的高层API练习。一个分类一个回归。

植物种类的分类

# -*- coding: UTF-8 -*
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os
import urllib

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 = 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 data
  feature_columns = [tf.contrib.layers.real_valued_column("", dimension=4)]

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

  # Classify 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 Samples, Class Predictions:    {}\n"
      .format(predictions))

if __name__ == "__main__":
    main()

波士顿房价回归

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

import itertools

import pandas as pd
import tensorflow as tf
import warnings
warnings.filterwarnings("ignore")
tf.logging.set_verbosity(tf.logging.INFO)

COLUMNS = ["crim", "zn", "indus", "nox", "rm", "age",
           "dis", "tax", "ptratio", "medv"]
FEATURES = ["crim", "zn", "indus", "nox", "rm",
            "age", "dis", "tax", "ptratio"]
LABEL = "medv"

training_set = pd.read_csv("../data/boston_train.csv", skipinitialspace=True,
                           skiprows=1, names=COLUMNS)
test_set = pd.read_csv("../data/boston_test.csv", skipinitialspace=True,
                       skiprows=1, names=COLUMNS)
prediction_set = pd.read_csv("../data/boston_predict.csv", skipinitialspace=True,
                             skiprows=1, names=COLUMNS)

feature_cols = [tf.contrib.layers.real_valued_column(k)
                  for k in FEATURES]

regressor = tf.contrib.learn.DNNRegressor(feature_columns=feature_cols,
                                          hidden_units=[10, 10],
                                          model_dir="/tmp/boston_model")

def input_fn(data_set):
  feature_cols = {k: tf.constant(data_set[k].values)
                  for k in FEATURES}
  labels = tf.constant(data_set[LABEL].values)
  return feature_cols, labels

#fit
regressor.fit(input_fn=lambda: input_fn(training_set), steps=5000)

#evaluate
ev = regressor.evaluate(input_fn=lambda: input_fn(test_set), steps=1)

loss_score = ev["loss"]
print("Loss: {0:f}".format(loss_score))

#predict
y = regressor.predict(input_fn=lambda: input_fn(prediction_set))
# .predict() returns an iterator; convert to a list and print predictions
predictions = list(itertools.islice(y, 6))
print ("Predictions: {}".format(str(predictions)))