NeuralNetwork.py

#!/usr/bin/python
# -*- coding: utf-8 -*-

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( 'C:/Users/tuchao1996/Desktop/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

def construct_feature_columns(input_features):
    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):    
    # 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

def train_nn_regression_model(
    learning_rate,
    steps,
    batch_size,
    hidden_units,
    training_examples,
    training_targets,
    validation_examples,
    validation_targets):

  periods = 10
  steps_per_period = steps / periods
  
  # Create a linear regressor object.
  dnn_regressor = tf.estimator.DNNRegressor(
      feature_columns=construct_feature_columns(training_examples),
      hidden_units=hidden_units
  )
  
  # Create input functions
  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.
  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.
    dnn_regressor.train(
        input_fn=training_input_fn,
        steps=steps_per_period
    )
    # Take a break and compute predictions.
    training_predictions = dnn_regressor.predict(input_fn=predict_training_input_fn)
    training_predictions = np.array([item['predictions'][0] for item in training_predictions])
    
    validation_predictions = dnn_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 dnn_regressor

if __name__ == '__main__' :
    # 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())

    dnn_regressor = train_nn_regression_model(
    learning_rate=0.01,
    steps=500,
    batch_size=10,
    hidden_units=[10, 2],
    training_examples=training_examples,
    training_targets=training_targets,
    validation_examples=validation_examples,
    validation_targets=validation_targets)