回归逻辑（三）

对于一个样本（x,y):如果它属于类别y = 1，那么他出现的概率是 P（y = 1 | x)；如果它属于类别 y = 0,那么它出现的概率是P(y = 0 | x)。不管是y = 1还是y = 0,(x,y)出现的概率可统一表示为P(y = 1|x)^y P(y = 0 | x)^(1 - y) 或者 fw(x)^y(1 - fw(x))^(1 - y)。因此，m个样本同时出现的概率如下：

                  只有使这个概率最大的w，才能使这m个样本以最大的概率出现。逻辑回归需要求出使概率最大的w。因为乘法计算会使数值迅速变成无穷大或趋近于0，所以，为了使算法具有数值稳定性并方便导数计算，通常将这个概率的·1负对数的平均值作为代价函数，即 称为该样本的交叉熵损失，通常用符号L(i)表示。所有的样本的交叉熵损失可表示为          

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import plotly
import plotly.graph_objs as go

plotly.offline.init_notebook_mode()
from linear_regression import LinearRegression

data = pd.read_csv('../data/world-happiness-report-2017.csv')

train_data = data.sample(frac=0.8)
test_data = data.drop(train_data.index)

input_param_name_1 = 'Economy..GDP.per.Capita.'
input_param_name_2 = 'Freedom'
output_param_name = 'Happiness.Score'


x_train = train_data[[input_param_name_1, input_param_name_2]].values
y_train = train_data[[output_param_name]].values

x_test = test_data[[input_param_name_1, input_param_name_2]].values
y_test = test_data[[output_param_name]].values

# Configure the plot with training dataset.
plot_training_trace = go.Scatter3d(
    x=x_train[:, 0].flatten(),
    y=x_train[:, 1].flatten(),
    z=y_train.flatten(),
    name='Training Set',
    mode='markers',
    marker={
        'size': 10,
        'opacity': 1,
        'line': {
            'color': 'rgb(255, 255, 255)',
            'width': 1
        },
    }
)


plot_test_trace = go.Scatter3d(
    x=x_test[:, 0].flatten(),
    y=x_test[:, 1].flatten(),
    z=y_test.flatten(),
    name='Test Set',
    mode='markers',
    marker={
        'size': 10,
        'opacity': 1,
        'line': {
            'color': 'rgb(255, 255, 255)',
            'width': 1
        },
    }
)


plot_layout = go.Layout(
    title='Date Sets',
    scene={
        'xaxis': {'title': input_param_name_1},
        'yaxis': {'title': input_param_name_2},
        'zaxis': {'title': output_param_name} 
    },
    margin={'l': 0, 'r': 0, 'b': 0, 't': 0}
)

plot_data = [plot_training_trace, plot_test_trace]

plot_figure = go.Figure(data=plot_data, layout=plot_layout)

plotly.offline.plot(plot_figure)

num_iterations = 500  
learning_rate = 0.01  
polynomial_degree = 0  
sinusoid_degree = 0  

linear_regression = LinearRegression(x_train, y_train, polynomial_degree, sinusoid_degree)

(theta, cost_history) = linear_regression.train(
    learning_rate,
    num_iterations
)

print('开始损失',cost_history[0])
print('结束损失',cost_history[-1])

plt.plot(range(num_iterations), cost_history)
plt.xlabel('Iterations')
plt.ylabel('Cost')
plt.title('Gradient Descent Progress')
plt.show()

predictions_num = 10

x_min = x_train[:, 0].min();
x_max = x_train[:, 0].max();

y_min = x_train[:, 1].min();
y_max = x_train[:, 1].max();


x_axis = np.linspace(x_min, x_max, predictions_num)
y_axis = np.linspace(y_min, y_max, predictions_num)


x_predictions = np.zeros((predictions_num * predictions_num, 1))
y_predictions = np.zeros((predictions_num * predictions_num, 1))

x_y_index = 0
for x_index, x_value in enumerate(x_axis):
    for y_index, y_value in enumerate(y_axis):
        x_predictions[x_y_index] = x_value
        y_predictions[x_y_index] = y_value
        x_y_index += 1

z_predictions = linear_regression.predict(np.hstack((x_predictions, y_predictions)))

plot_predictions_trace = go.Scatter3d(
    x=x_predictions.flatten(),
    y=y_predictions.flatten(),
    z=z_predictions.flatten(),
    name='Prediction Plane',
    mode='markers',
    marker={
        'size': 1,
    },
    opacity=0.8,
    surfaceaxis=2, 
)

plot_data = [plot_training_trace, plot_test_trace, plot_predictions_trace]
plot_figure = go.Figure(data=plot_data, layout=plot_layout)
plotly.offline.plot(plot_figure)