逻辑上，前一段时间比较忙，这一段时间比较有空，刚好回归学习TensorFlow，哈哈。
开始开始：
第1步：设置：加载必要的库+加载数据+数据预处理
"""和之前一样添加必要的库和工具"""
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=",")
"""对特征数据进行预处理"""
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
"""对目标数据进行预处理"""
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()
# Create a boolean categorical feature representing whether the
# medianHouseValue is above a set threshold.
"""这里使用布尔分类，目标不再是具体的价格，而是房价是否过高"""
output_targets["median_house_value_is_high"] = (
california_housing_dataframe["median_house_value"] > 265000).astype(float)
return output_targets
california_housing_dataframe = california_housing_dataframe.reindex(
np.random.permutation(california_housing_dataframe.index))t)的功能是什么
"""对数据进行预览和检查"""
# 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2步：创建特征列和回归模型
"""把输入的特征转化成统一的特征列格式，方便统一运算和和使用"""
def construct_feature_columns(input_features):
"""Construct the TensorFlow Feature Columns.
Args:
input_features: The names of the numerical input features to use.
Returns:
A set of feature columns
"""
return set([tf.feature_column.numeric_column(my_feature)
for my_feature in input_features])
"""定义输入方程"""
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)
# 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错误示范第三步：这里尝试用线性回归方程看看情况
def train_linear_regressor_model(
learning_rate,
steps,
batch_size,
training_examples,
training_targets,
validation_examples,
validation_targets):
periods = 10
steps_per_period = steps / periods
# Create a linear regressor object.
"""这里选择了线性回归模型"""
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=construct_feature_columns(training_examples),
optimizer=my_optimizer
)
# Create input functions
training_input_fn = lambda: my_input_fn(training_examples,
training_targets["median_house_value_is_high"],
batch_size=batch_size)
predict_training_input_fn = lambda: my_input_fn(training_examples,
training_targets["median_house_value_is_high"],
num_epochs=1,
shuffle=False)
predict_validation_input_fn = lambda: my_input_fn(validation_examples,
validation_targets["median_house_value_is_high"],
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.
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错误示范第4步：调整训练模型参数并输出RMSE
linear_regressor = train_linear_regressor_model(
learning_rate=0.000001,
steps=200,
batch_size=20,
training_examples=training_examples,
training_targets=training_targets,
validation_examples=validation_examples,
validation_targets=validation_targets)
这个结果看起来好像还不错，不过这里当我们的损失方程用的是：linenarRegressor，然而在解读概率时，并不能起到很好的效果，例如： 0.9和0.99999之间的差异会很小。
关于logloss：
所以我们使用logloss会更好一点，由于“ y' ”是对于特征集“x”的测试值，所以先计算出预测值。
第3步：计算预测值y‘
"""计算预测值"""
predict_validation_input_fn = lambda: my_input_fn(validation_examples,
validation_targets["median_house_value_is_high"],
num_epochs=1,
shuffle=False)
validation_predictions = linear_regressor.predict(input_fn=predict_validation_input_fn)
validation_predictions = np.array([item['predictions'][0] for item in validation_predictions])
_ = plt.hist(validation_predictions)第4步：创建逻辑回归模型
def train_linear_classifier_model(
learning_rate,
steps,
batch_size,
training_examples,
training_targets,
validation_examples,
validation_targets):
periods = 10
steps_per_period = steps / periods
# Create a linear classifier object.
my_optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
my_optimizer = tf.contrib.estimator.clip_gradients_by_norm(my_optimizer, 5.0)
linear_classifier = tf.estimator.LinearClassifier(
feature_columns=construct_feature_columns(training_examples),
optimizer=my_optimizer
)
# Create input functions
training_input_fn = lambda: my_input_fn(training_examples,
training_targets["median_house_value_is_high"],
batch_size=batch_size)
predict_training_input_fn = lambda: my_input_fn(training_examples,
training_targets["median_house_value_is_high"],
num_epochs=1,
shuffle=False)
predict_validation_input_fn = lambda: my_input_fn(validation_examples,
validation_targets["median_house_value_is_high"],
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("LogLoss (on training data):")
training_log_losses = []
validation_log_losses = []
for period in range (0, periods):
# Train the model, starting from the prior state.
linear_classifier.train(
input_fn=training_input_fn,
steps=steps_per_period
)
# Take a break and compute predictions.
training_probabilities = linear_classifier.predict(input_fn=predict_training_input_fn)
training_probabilities = np.array([item['probabilities'] for item in training_probabilities])
validation_probabilities = linear_classifier.predict(input_fn=predict_validation_input_fn)
validation_probabilities = np.array([item['probabilities'] for item in validation_probabilities])
training_log_loss = metrics.log_loss(training_targets, training_probabilities)
validation_log_loss = metrics.log_loss(validation_targets, validation_probabilities)
# Occasionally print the current loss.
print(" period %02d : %0.2f" % (period, training_log_loss))
# Add the loss metrics from this period to our list.
training_log_losses.append(training_log_loss)
validation_log_losses.append(validation_log_loss)
print("Model training finished.")
# Output a graph of loss metrics over periods.
plt.ylabel("LogLoss")
plt.xlabel("Periods")
plt.title("LogLoss vs. Periods")
plt.tight_layout()
plt.plot(training_log_losses, label="training")
plt.plot(validation_log_losses, label="validation")
plt.legend()
return linear_classifier第5步：调整模型参数并输出logloss
"""执行训练模型"""
linear_classifier = train_linear_classifier_model(
learning_rate=0.000005,
steps=500,
batch_size=20,
training_examples=training_examples,
training_targets=training_targets,
validation_examples=validation_examples,
validation_targets=validation_targets)
第6步：计算准确率并为验证集绘制ROC曲线
"""计算准确率"""
evaluation_metrics = linear_classifier.evaluate(input_fn=predict_validation_input_fn)
print("AUC on the validation set: %0.2f" % evaluation_metrics['auc'])
print("Accuracy on the validation set: %0.2f" % evaluation_metrics['accuracy'])
predict_validation_input_fn = lambda: my_input_fn(validation_examples,
validation_targets["median_house_value_is_high"],
num_epochs=1,
shuffle=False)
validation_predictions = linear_regressor.predict(input_fn=predict_validation_input_fn)
validation_predictions = np.array([item['predictions'][0] for item in validation_predictions])
_ = plt.hist(validation_predictions)
第7步：调整训练模型参数提升准确率
linear_classifier = train_linear_classifier_model(
learning_rate=0.000003,
steps=20000,
batch_size=500,
training_examples=training_examples,
training_targets=training_targets,
validation_examples=validation_examples,
validation_targets=validation_targets)
evaluation_metrics = linear_classifier.evaluate(input_fn=predict_validation_input_fn)
print("AUC on the validation set: %0.2f" % evaluation_metrics['auc'])
print("Accuracy on the validation set: %0.2f" % evaluation_metrics['accuracy'])
完成！~
本次练习总结：当做概率预测时，逻辑回归模型比线性回归模型更加合理，可以避免在某些情况下出现超过100%的概率，
而损失方程（Loss Function）方面，logloss方程要比LM方程更加合理。
本文仅为个人学习笔记记录，若有不详尽和错误的地方，还请谅解。请结合Google 机器学习，编程练习：逻辑回归一起阅读
编程练习地址：https://colab.research.google.com/notebooks/mlcc/logistic_regression.ipynb?hl=zh-cn