tensorflow基本使用

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27

from IPython import display
from matplotlib import cm
from matplotlib import gridspec
from matplotlib import pyplot as plt
import numpy as np
import pandas as pd
from sklearn import metrics
import tensorflow as tf
from tensorflow.python.data import Dataset

tf.logging.set_verbosity(tf.logging.ERROR)
pd.options.display.max_rows = 10
pd.options.display.float_format = '{:.1f}'.format

#随机初始化，避免随机梯度劣化
#/1000加快学习速率
california_housing_dataframe = california_housing_dataframe.reindex(
    np.random.permutation(california_housing_dataframe.index))
california_housing_dataframe["median_house_value"] /= 1000.0

# Define the input feature: total_rooms.
my_feature = california_housing_dataframe[["total_rooms"]] #X
# Configure a numeric feature column for total_rooms.
#使用一种称为“特征列”的结构来表示特征的数据类型。特征列仅存储对特征数据的描述；不包含特征数据本身
feature_columns = [tf.feature_column.numeric_column("total_rooms")]
# Define the label.
targets = california_housing_dataframe["median_house_value"] #Y

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12

# Use gradient descent as the optimizer for training the model.
# mini-batch gradient decent
my_optimizer=tf.train.GradientDescentOptimizer(learning_rate=0.0000001)
#梯度裁剪，设置梯度上限确保稳定性
my_optimizer = tf.contrib.estimator.clip_gradients_by_norm(my_optimizer, 5.0)

# Configure the linear regression model with our feature columns and optimizer.
# Set a learning rate of 0.0000001 for Gradient Descent.
linear_regressor = tf.estimator.LinearRegressor(
    feature_columns=feature_columns,
    optimizer=my_optimizer
)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32

def my_input_fn(features, targets, batch_size=1, shuffle=True, num_epochs=None):
    """Trains a linear regression model of one feature.
  
    Args:
      features: pandas DataFrame of features
      targets: pandas DataFrame of targets
      batch_size: Size of batches to be passed to the model
      shuffle: True or False. Whether to shuffle the data.
      num_epochs: Number of epochs for which data should be repeated. None = repeat indefinitely
    Returns:
      Tuple of (features, labels) for next data batch
    """
  
    # Convert pandas data into a dict of np arrays.
    features = {key:np.array(value) for key,value in dict(features).items()}                                           
 
    # Construct a dataset, and configure batching/repeating
    ds = Dataset.from_tensor_slices((features,targets)) # warning: 2GB limit
    ds = ds.batch(batch_size).repeat(num_epochs)
    #如果 shuffle 设置为 True，会对数据进行随机处理，以便数据在训练期间以随机方式传递到模型
    if shuffle:
      ds = ds.shuffle(buffer_size=10000)
    
    # Return the next batch of data
    features, labels = ds.make_one_shot_iterator().get_next()
    return features, labels

#训练
_ = linear_regressor.train(
    input_fn = lambda:my_input_fn(my_feature, targets),
    steps=100
)

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104

def train_model(learning_rate, steps, batch_size, input_feature="total_rooms"):
  """Trains a linear regression model of one feature.
  
  Args:
    learning_rate: A `float`, the learning rate.
    steps: A non-zero `int`, the total number of training steps. A training step
      consists of a forward and backward pass using a single batch.
    batch_size: A non-zero `int`, the batch size.
    input_feature: A `string` specifying a column from `california_housing_dataframe`
      to use as input feature.
  """
  
  periods = 10
  steps_per_period = steps / periods

  my_feature = input_feature
  my_feature_data = california_housing_dataframe[[my_feature]]
  my_label = "median_house_value"
  targets = california_housing_dataframe[my_label]

  # Create feature columns
  feature_columns = [tf.feature_column.numeric_column(my_feature)]
  
  # Create input functions
  training_input_fn = lambda:my_input_fn(my_feature_data, targets, batch_size=batch_size)
  prediction_input_fn = lambda: my_input_fn(my_feature_data, targets, num_epochs=1, shuffle=False)
  
  # Create a linear regressor object.
  my_optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
  my_optimizer = tf.contrib.estimator.clip_gradients_by_norm(my_optimizer, 5.0)
  linear_regressor = tf.estimator.LinearRegressor(
      feature_columns=feature_columns,
      optimizer=my_optimizer
  )

  # Set up to plot the state of our model's line each period.
  plt.figure(figsize=(15, 6))
  plt.subplot(1, 2, 1)
  plt.title("Learned Line by Period")
  plt.ylabel(my_label)
  plt.xlabel(my_feature)
  sample = california_housing_dataframe.sample(n=300)
  plt.scatter(sample[my_feature], sample[my_label])
  colors = [cm.coolwarm(x) for x in np.linspace(-1, 1, periods)]

  # Train the model, but do so inside a loop so that we can periodically assess
  # loss metrics.
  print "Training model..."
  print "RMSE (on training data):"
  root_mean_squared_errors = []
  for period in range (0, periods):
    # Train the model, starting from the prior state.
    linear_regressor.train(
        input_fn=training_input_fn,
        steps=steps_per_period
    )
    # Take a break and compute predictions.
    predictions = linear_regressor.predict(input_fn=prediction_input_fn)
    predictions = np.array([item['predictions'][0] for item in predictions])
    
    # Compute loss.
    root_mean_squared_error = math.sqrt(
        metrics.mean_squared_error(predictions, targets))
    # Occasionally print the current loss.
    print "  period %02d : %0.2f" % (period, root_mean_squared_error)
    # Add the loss metrics from this period to our list.
    root_mean_squared_errors.append(root_mean_squared_error)
    # Finally, track the weights and biases over time.
    # Apply some math to ensure that the data and line are plotted neatly.
    y_extents = np.array([0, sample[my_label].max()])
    
    weight = linear_regressor.get_variable_value('linear/linear_model/%s/weights' % input_feature)[0]
    bias = linear_regressor.get_variable_value('linear/linear_model/bias_weights')

    x_extents = (y_extents - bias) / weight
    x_extents = np.maximum(np.minimum(x_extents,
                                      sample[my_feature].max()),
                           sample[my_feature].min())
    y_extents = weight * x_extents + bias
    plt.plot(x_extents, y_extents, color=colors[period]) 
  print "Model training finished."

  # Output a graph of loss metrics over periods.
  plt.subplot(1, 2, 2)
  plt.ylabel('RMSE')
  plt.xlabel('Periods')
  plt.title("Root Mean Squared Error vs. Periods")
  plt.tight_layout()
  plt.plot(root_mean_squared_errors)

  # Output a table with calibration data.
  calibration_data = pd.DataFrame()
  calibration_data["predictions"] = pd.Series(predictions)
  calibration_data["targets"] = pd.Series(targets)
  display.display(calibration_data.describe())

  print "Final RMSE (on training data): %0.2f" % root_mean_squared_error
  
train_model(
    learning_rate=0.00002,
    steps=1000,
    batch_size=5,
    input_feature="population"
)