Google TensorFlow课程 编程笔记（5）———特征组合

特征组合

学习目标：学习FTRL优化算法的使用，理解独热编码，风箱和特征组合，并用之创建新的特征组合。

第1步：设置：加载必要的库+加载数据+数据预处理

from __future__ import print_function

import math

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

california_housing_dataframe = pd.read_csv("https://storage.googleapis.com/mledu-datasets/california_housing_train.csv", sep=",")

california_housing_dataframe = california_housing_dataframe.reindex(

    np.random.permutation(california_housing_dataframe.index))
def preprocess_features(california_housing_dataframe):
  """Prepares input features from California housing data set.

  Args:
    california_housing_dataframe: A Pandas DataFrame expected to contain data
      from the California housing data set.
  Returns:
    A DataFrame that contains the features to be used for the model, including
    synthetic features.
  """
  selected_features = california_housing_dataframe[
    ["latitude",
     "longitude",
     "housing_median_age",
     "total_rooms",
     "total_bedrooms",
     "population",
     "households",
     "median_income"]]
  processed_features = selected_features.copy()
  # Create a synthetic feature.
  processed_features["rooms_per_person"] = (
    california_housing_dataframe["total_rooms"] /
    california_housing_dataframe["population"])
  return processed_features

def preprocess_targets(california_housing_dataframe):
  """Prepares target features (i.e., labels) from California housing data set.

  Args:
    california_housing_dataframe: A Pandas DataFrame expected to contain data
      from the California housing data set.
  Returns:
    A DataFrame that contains the target feature.
  """
  output_targets = pd.DataFrame()
  # Scale the target to be in units of thousands of dollars.
  output_targets["median_house_value"] = (
    california_housing_dataframe["median_house_value"] / 1000.0)
  return output_targets

第2步：预览检查数据

# Choose the first 12000 (out of 17000) examples for training.
training_examples = preprocess_features(california_housing_dataframe.head(12000))
training_targets = preprocess_targets(california_housing_dataframe.head(12000))

# Choose the last 5000 (out of 17000) examples for validation.
validation_examples = preprocess_features(california_housing_dataframe.tail(5000))
validation_targets = preprocess_targets(california_housing_dataframe.tail(5000))

# Double-check that we've done the right thing.
print("Training examples summary:")
display.display(training_examples.describe())
print("Validation examples summary:")
display.display(validation_examples.describe())

print("Training targets summary:")
display.display(training_targets.describe())
print("Validation targets summary:")
display.display(validation_targets.describe())

第3步：创建特征列和回归模型

def construct_feature_columns(input_features):
  #创建特征列
  return set([tf.feature_column.numeric_column(my_feature)
              for my_feature in input_features])

def my_input_fn(features, targets, batch_size=1, shuffle=True, num_epochs=None):
    #创建回归训练的模型
    """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)
    
    # Shuffle the data, if specified
    if shuffle:
      ds = ds.shuffle(10000)
    
    # Return the next batch of data
    features, labels = ds.make_one_shot_iterator().get_next()
    return features, labels

第4步：创建训练模型
这次训练模型用的优化算法为FTRL优化算法

def train_model(
    learning_rate,
    steps,
    batch_size,
    feature_columns,
    training_examples,
    training_targets,
    validation_examples,
    validation_targets):
  #训练线性回归模型
  #Trains a linear regression model.
  
  periods = 10
  steps_per_period = steps / periods

  # Create a linear regressor object.
  #优化迭代器选择FTRL算法，性能比之前使用的SGD更好一些
  my_optimizer = tf.train.FtrlOptimizer(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
  )
  
  training_input_fn = lambda: my_input_fn(training_examples,
                                          training_targets["median_house_value"],
                                          batch_size=batch_size)
  predict_training_input_fn = lambda: my_input_fn(training_examples,
                                                  training_targets["median_house_value"],
                                                  num_epochs=1,
                                                  shuffle=False)
  predict_validation_input_fn = lambda: my_input_fn(validation_examples,
                                                    validation_targets["median_house_value"],
                                                    num_epochs=1,
                                                    shuffle=False)

  # Train the model, but do so inside a loop so that we can periodically assess
  # loss metrics.
  #计算预测值和RMSE损失值，并输出损失值
  print("Training model...")
  print("RMSE (on training data):")
  training_rmse = []
  validation_rmse = []
  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.
    training_predictions = linear_regressor.predict(input_fn=predict_training_input_fn)
    training_predictions = np.array([item['predictions'][0] for item in training_predictions])
    validation_predictions = linear_regressor.predict(input_fn=predict_validation_input_fn)
    validation_predictions = np.array([item['predictions'][0] for item in validation_predictions])
    
    # Compute training and validation loss.
    training_root_mean_squared_error = math.sqrt(
        metrics.mean_squared_error(training_predictions, training_targets))
    validation_root_mean_squared_error = math.sqrt(
        metrics.mean_squared_error(validation_predictions, validation_targets))
    # Occasionally print the current loss.
    print("  period %02d : %0.2f" % (period, training_root_mean_squared_error))
    # Add the loss metrics from this period to our list.
    training_rmse.append(training_root_mean_squared_error)
    validation_rmse.append(validation_root_mean_squared_error)
  print("Model training finished.")

  
  # Output a graph of loss metrics over periods.
  plt.ylabel("RMSE")
  plt.xlabel("Periods")
  plt.title("Root Mean Squared Error vs. Periods")
  plt.tight_layout()
  plt.plot(training_rmse, label="training")
  plt.plot(validation_rmse, label="validation")
  plt.legend()

  return linear_regressor

第5步：调整训练模型参数并输出RMSE

_ = train_model(
    learning_rate=1.0,
    steps=500,
    batch_size=100,
    feature_columns=construct_feature_columns(training_examples),
    training_examples=training_examples,
    training_targets=training_targets,
    validation_examples=validation_examples,
    validation_targets=validation_targets)

由于经度对房价的影响并不是连续的，所以我们对经度特征进行分箱，以得到更好的结果

第6步：对特征值进行分箱操作

def get_quantile_based_boundaries(feature_values, num_buckets):
  #输出参数为特征值和分箱数
  boundaries = np.arange(1.0, num_buckets) / num_buckets
  quantiles = feature_values.quantile(boundaries)
  return [quantiles[q] for q in quantiles.keys()]
  #返回分箱编号到对应字典的键中

# Divide households into 7 buckets.
#把家庭数分为7个箱
households = tf.feature_column.numeric_column("households")
bucketized_households = tf.feature_column.bucketized_column(
  households, boundaries=get_quantile_based_boundaries(
    california_housing_dataframe["households"], 7))

# Divide longitude into 10 buckets.
#把经度分成10个分箱
longitude = tf.feature_column.numeric_column("longitude")
bucketized_longitude = tf.feature_column.bucketized_column(
  longitude, boundaries=get_quantile_based_boundaries(
    california_housing_dataframe["longitude"], 10))

第7步：使用分箱特征训练模型

def construct_feature_columns():
  """Construct the TensorFlow Feature Columns.

  Returns:
    A set of feature columns
  """
  #对各个特征值都进行分箱操作
  households = tf.feature_column.numeric_column("households")
  longitude = tf.feature_column.numeric_column("longitude")
  latitude = tf.feature_column.numeric_column("latitude")
  housing_median_age = tf.feature_column.numeric_column("housing_median_age")
  median_income = tf.feature_column.numeric_column("median_income")
  rooms_per_person = tf.feature_column.numeric_column("rooms_per_person")
  
  # Divide households into 7 buckets.
  bucketized_households = tf.feature_column.bucketized_column(
    households, boundaries=get_quantile_based_boundaries(
      training_examples["households"], 7))

  # Divide longitude into 10 buckets.
  bucketized_longitude = tf.feature_column.bucketized_column(
    longitude, boundaries=get_quantile_based_boundaries(
      training_examples["longitude"], 10))
  
  # Divide latitude into 10 buckets.
  bucketized_latitude = tf.feature_column.bucketized_column(
    latitude, boundaries=get_quantile_based_boundaries(
      training_examples["latitude"], 10))

  # Divide housing_median_age into 7 buckets.
  bucketized_housing_median_age = tf.feature_column.bucketized_column(
    housing_median_age, boundaries=get_quantile_based_boundaries(
      training_examples["housing_median_age"], 7))
  
  # Divide median_income into 7 buckets.
  bucketized_median_income = tf.feature_column.bucketized_column(
    median_income, boundaries=get_quantile_based_boundaries(
      training_examples["median_income"], 7))
  
  # Divide rooms_per_person into 7 buckets.
  bucketized_rooms_per_person = tf.feature_column.bucketized_column(
    rooms_per_person, boundaries=get_quantile_based_boundaries(
      training_examples["rooms_per_person"], 7))
  
  #把分箱后的结果传入特征列
  feature_columns = set([
    bucketized_longitude,
    bucketized_latitude,
    bucketized_housing_median_age,
    bucketized_households,
    bucketized_median_income,
    bucketized_rooms_per_person])
  
  return feature_columns

_ = train_model(
    learning_rate=1.0,
    steps=500,
    batch_size=100,
    feature_columns=construct_feature_columns(),
    training_examples=training_examples,
    training_targets=training_targets,
    validation_examples=validation_examples,
    validation_targets=validation_targets)

第8步：使用特征组合训练特征

def construct_feature_columns():
  """Construct the TensorFlow Feature Columns.

  Returns:
    A set of feature columns
  """
  households = tf.feature_column.numeric_column("households")
  longitude = tf.feature_column.numeric_column("longitude")
  latitude = tf.feature_column.numeric_column("latitude")
  housing_median_age = tf.feature_column.numeric_column("housing_median_age")
  median_income = tf.feature_column.numeric_column("median_income")
  rooms_per_person = tf.feature_column.numeric_column("rooms_per_person")
  
  # Divide households into 7 buckets.
  bucketized_households = tf.feature_column.bucketized_column(
    households, boundaries=get_quantile_based_boundaries(
      training_examples["households"], 7))

  # Divide longitude into 10 buckets.
  bucketized_longitude = tf.feature_column.bucketized_column(
    longitude, boundaries=get_quantile_based_boundaries(
      training_examples["longitude"], 10))
  
  # Divide latitude into 10 buckets.
  bucketized_latitude = tf.feature_column.bucketized_column(
    latitude, boundaries=get_quantile_based_boundaries(
      training_examples["latitude"], 10))

  # Divide housing_median_age into 7 buckets.
  bucketized_housing_median_age = tf.feature_column.bucketized_column(
    housing_median_age, boundaries=get_quantile_based_boundaries(
      training_examples["housing_median_age"], 7))
  
  # Divide median_income into 7 buckets.
  bucketized_median_income = tf.feature_column.bucketized_column(
    median_income, boundaries=get_quantile_based_boundaries(
      training_examples["median_income"], 7))
  
  # Divide rooms_per_person into 7 buckets.
  bucketized_rooms_per_person = tf.feature_column.bucketized_column(
    rooms_per_person, boundaries=get_quantile_based_boundaries(
      training_examples["rooms_per_person"], 7))
  
  # Make a feature column for the long_x_lat feature cross
  #创建一个由经度和纬度合成的组合的特征
  long_x_lat = tf.feature_column.crossed_column(
  set([bucketized_longitude, bucketized_latitude]), hash_bucket_size=1000)
  
  feature_columns = set([
    bucketized_longitude,
    bucketized_latitude,
    bucketized_housing_median_age,
    bucketized_households,
    bucketized_median_income,
    bucketized_rooms_per_person,
    long_x_lat])
  
  return feature_columns

_ = train_model(
    learning_rate=1.0,
    steps=500,
    batch_size=100,
    feature_columns=construct_feature_columns(),
    training_examples=training_examples,
    training_targets=training_targets,
    validation_examples=validation_examples,
    validation_targets=validation_targets)

本次练习要点：

FTRL优化算法：总的来说就是比原先用的SGD好一点。具体参考参考资料。

分箱（分桶）：当分析的输入特征值并没有很强的连续性变化时，使用分箱可以获得更好的预测效果以及更快的运行速度。

特征组合：组合多个特征以便学习非线性关系，但目前特征列API仅支持组合离散特征。

独热编码：当分析一些离散的特征或者文字等无法用数字表达的特征时用独热编码，独热编码的大意为，创建一个矢量，矢量中的每一个数对应一个特征量（数字或文字等），表示一个特征时，矢量上对应的位为1，其他位全为0。

分箱和组合特征的参考资料：http://developers.googleblog.cn/2017/12/tensorflow.html

FTRL优化算法参考资料：

http://vividfree.github.io/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0/2015/12/05/understanding-FTRL-algorithm

本文仅为个人学习笔记记录，请结合Google 机器学习，编程练习：特征组合一起阅读

编程练习地址：

https://colab.research.google.com/notebooks/mlcc/feature_crosses.ipynb?hl=zh-cn#scrollTo=1Cdr02tLIK_Q