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 Datasetdef 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/repeatingds = Dataset.from_tensor_slices((features,targets)) # warning: 2GB limitds = ds.batch(batch_size).repeat(num_epochs)# Shuffle the data, if specifiedif shuffle:ds = ds.shuffle(buffer_size=10000)# Return the next batch of datafeatures, labels = ds.make_one_shot_iterator().get_next()return features, labelsdef train_model(learning_rate, steps, batch_size, input_feature="total_rooms"):periods = 10steps_per_period = steps / periods# 第 1 步：定义特征并配置特征列my_feature = input_featuremy_feature_data = california_housing_dataframe[[my_feature]]# Create feature columnsfeature_columns = [tf.feature_column.numeric_column(my_feature)]# 第 2 步：定义目标my_label = "median_house_value"targets = california_housing_dataframe[my_label]# 第 4 步：定义输入函数# Create input functionstraining_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)# 第 3 步：配置 LinearRegressor 线性回归器# 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):# 第 5 步：训练模型# Train the model, starting from the prior state.
            linear_regressor.train(input_fn=training_input_fn,steps=steps_per_period)# 第 6 步：评估模型# 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) / weightx_extents = np.maximum(np.minimum(x_extents,sample[my_feature].max()),sample[my_feature].min())y_extents = weight * x_extents + biasplt.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)plt.show()# 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)tf.logging.set_verbosity(tf.logging.ERROR)
pd.options.display.max_rows = 10
pd.options.display.float_format = '{:.1f}'.formatcalifornia_housing_dataframe = pd.read_csv("E://woodsfile//machine learning//Tensorflow实战代码//tensorflow使用步骤//california_housing_train.csv",sep=",")## 对数据进行随机化处理
california_housing_dataframe = california_housing_dataframe.reindex(np.random.permutation(california_housing_dataframe.index))california_housing_dataframe["median_house_value"] /= 1000.0# 输出关于各列的一些实用统计信息快速摘要：样本数、均值、标准偏差、最大值、最小值和各种分位数
california_housing_dataframe.describe()train_model(learning_rate=0.00002,steps=500,batch_size=5
)

1 # Define the input feature: total_rooms.
2 # 只提取一个特征值：total_rooms
3 my_feature = california_housing_dataframe[["total_rooms"]]
4
5 # 将total_rooms列中的数据转化为数值，为一维数组
6 feature_columns = [tf.feature_column.numeric_column("total_rooms")]

1 # Define the label.
2 targets = california_housing_dataframe["median_house_value"]

# Use gradient descent as the optimizer for training the model.
my_optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.0000001)#这一步使用了梯度裁剪，保证梯度大小在训练期间不会变得过大，梯度过大导致梯度下降法失败
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
)

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/repeatingds = Dataset.from_tensor_slices((features,targets)) # warning: 2GB limitds = ds.batch(batch_size).repeat(num_epochs)# Shuffle the data, if specifiedif shuffle:ds = ds.shuffle(buffer_size=10000)# Return the next batch of datafeatures, labels = ds.make_one_shot_iterator().get_next()return features, labels

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

# Create an input function for predictions.
# Note: Since we're making just one prediction for each example, we don't
# need to repeat or shuffle the data here.
prediction_input_fn =lambda: my_input_fn(my_feature, targets, num_epochs=1, shuffle=False)# Call predict() on the linear_regressor to make predictions.
predictions = linear_regressor.predict(input_fn=prediction_input_fn)# Format predictions as a NumPy array, so we can calculate error metrics.
predictions = np.array([item['predictions'][0] for item in predictions])# Print Mean Squared Error and Root Mean Squared Error.
mean_squared_error = metrics.mean_squared_error(predictions, targets)
root_mean_squared_error = math.sqrt(mean_squared_error)
print("Mean Squared Error (on training data): %0.3f" % mean_squared_error)
print("Root Mean Squared Error (on training data): %0.3f" % root_mean_squared_error) 

calibration_data = pd.DataFrame()
calibration_data["predictions"] = pd.Series(predictions)
calibration_data["targets"] = pd.Series(targets)
calibration_data.describe()
print(calibration_data.describe())