多元线性回归
- 之前复现了单特征预测幸福指数的线性回归模型,
- 现在使用多向量特征回归看看是否会减小误差
导库与查看数据
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 homemade.linear_regression import LinearRegression
data = pd.read_csv('F:/MLdata/data/world-happiness-report-2017.csv')
data.head(10)
查看变量与预测变量之间的分布关系
histohrams = data.hist(grid=False, figsize=(10, 10))
拆分训练集测试集
input_param_name_1 = 'Economy..GDP.per.Capita.'
input_param_name_2 = 'Freedom'
output_param_name = 'Happiness.Score'
# Split training set input and output.
x_train = train_data[[input_param_name_1, input_param_name_2]].values
y_train = train_data[[output_param_name]].values
# Split test set input and output.
x_test = test_data[[input_param_name_1, input_param_name_2]].values
y_test = test_data[[output_param_name]].values
- **在这里和之前发生了变化,输入变量变成了多维向量以GDP和FreeDom为例,绘制三维分布图
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.iplot(plot_figure)
绘制结果如下图所示,由于图片格式的限制,这里就只截图了,可以运行以后对每个点进行分析
模型训练
num_iterations = 500
regularization_param = 0
learning_rate = 0.01
polynomial_degree = 0
sinusoid_degree = 0 multipliers of additional features.
# Init linear regression instance.
linear_regression = LinearRegression(x_train, y_train, polynomial_degree, sinusoid_degree)
# Train linear regression.
(theta, cost_history) = linear_regression.train(
learning_rate,
regularization_param,
num_iterations
)
print('Initial cost: {:.2f}'.format(cost_history[0]))
print('Optimized cost: {:.2f}'.format(cost_history[-1]))
theta_table = pd.DataFrame({'Model Parameters': theta.flatten()})
theta_table.head()
结果分析
梯度下降图
plt.plot(range(num_iterations), cost_history)
plt.xlabel('Iterations')
plt.ylabel('Cost')
plt.title('Gradient Descent Progress')
plt.show()
绘制预测结果平面,可以很容易理解多元线性回归的原理,和单变量是类似的
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.iplot(plot_figure)
可以很明显的看出预测的平面分布
将测试集和训练集进行对比,看看预测损失有多少
test_predictions = linear_regression.predict(x_test)
test_predictions_table = pd.DataFrame({
'Economy GDP per Capita': x_test[:, 0].flatten(),
'Freedom': x_test[:, 1].flatten(),
'Test Happiness Score': y_test.flatten(),
'Predicted Happiness Score': test_predictions.flatten(),
'Prediction Diff': (y_test - test_predictions).flatten()
})
test_predictions_table.head(10)
相比单变量回归,明显变得更加优良了