[英]Multiple Linear Regression using ScikitLearn, different approaches give different answers
這可能與此處的統計信息交換同樣有效(可能是我不確定的統計信息或python。
假設我有兩個自變量X,Y
來解釋Z
一些方差。
from sklearn.linear_model import LinearRegression
import numpy as np
from scipy.stats import pearsonr,linregress
Z = np.array([1,3,5,6,7,8,9,7,10,9])
X = np.array([2,5,3,1,6,4,7,8,6,7])
Y = np.array([3,2,6,4,6,1,2,5,6,10])
我想從Z回歸X和Y的可變性。我知道兩種方法:
首先從Z回歸X(形成X,Z的線性回歸,找到殘差,然后對Y重復)。 這樣:
regr = linregress(X,Z)
resi_1 = NAO - (X*regr[0])+regr[1] #residual = y-mx+c
regr = linregress(Y,resi_1)
resi_2 = resi_1 - (Y*regr[0])+regr[1] #residual = y-mx+c
其中regr_2
是Z的其余部分,其中X和Y依次回歸。
另一種方法是為X和Y創建一個預測Z的多元線性回歸模型:
regr = LinearRegression()
Model = regr.fit(np.array((X,Y)).swapaxes(0,1),Z)
pred = Model.predict(np.array((X,Y)).swapaxes(0,1))
resi_3 = Z - pred
第一個順序方法resi_2
和多元線性回歸resi_3
非常相似(相關性= 0.97),但不相等。 這兩個殘差如下圖所示:
任何偉大的想法(不是統計學家,所以我的理解可能是python問題!)。 請注意,如果在第一部分中我先回歸Y,然后再回歸X,則得到不同的殘差。
這是使用數據和scipy的curve_fit()例程以及散點圖,曲面圖和輪廓圖的示例3D圖形曲面擬合器。 您應該能夠單擊並拖動3D圖以在3維空間中旋轉它們,並看到數據似乎不位於任何類型的光滑表面上,因此此處使用的平面模型“ z =(a * x) +(b * y)+ c”對於此數據而言,幾乎沒有任何其他模型更好或更差。
fitted prameters [ 0.65963199 0.18537117 2.43363301]
RMSE: 2.11487214206
R-squared: 0.383078044516
import numpy, scipy, scipy.optimize
import matplotlib
from mpl_toolkits.mplot3d import Axes3D
from matplotlib import cm # to colormap 3D surfaces from blue to red
import matplotlib.pyplot as plt
graphWidth = 800 # units are pixels
graphHeight = 600 # units are pixels
# 3D contour plot lines
numberOfContourLines = 16
def SurfacePlot(func, data, fittedParameters):
f = plt.figure(figsize=(graphWidth/100.0, graphHeight/100.0), dpi=100)
matplotlib.pyplot.grid(True)
axes = Axes3D(f)
x_data = data[0]
y_data = data[1]
z_data = data[2]
xModel = numpy.linspace(min(x_data), max(x_data), 20)
yModel = numpy.linspace(min(y_data), max(y_data), 20)
X, Y = numpy.meshgrid(xModel, yModel)
Z = func(numpy.array([X, Y]), *fittedParameters)
axes.plot_surface(X, Y, Z, rstride=1, cstride=1, cmap=cm.coolwarm, linewidth=1, antialiased=True)
axes.scatter(x_data, y_data, z_data) # show data along with plotted surface
axes.set_title('Surface Plot (click-drag with mouse)') # add a title for surface plot
axes.set_xlabel('X Data') # X axis data label
axes.set_ylabel('Y Data') # Y axis data label
axes.set_zlabel('Z Data') # Z axis data label
plt.show()
plt.close('all') # clean up after using pyplot or else there can be memory and process problems
def ContourPlot(func, data, fittedParameters):
f = plt.figure(figsize=(graphWidth/100.0, graphHeight/100.0), dpi=100)
axes = f.add_subplot(111)
x_data = data[0]
y_data = data[1]
z_data = data[2]
xModel = numpy.linspace(min(x_data), max(x_data), 20)
yModel = numpy.linspace(min(y_data), max(y_data), 20)
X, Y = numpy.meshgrid(xModel, yModel)
Z = func(numpy.array([X, Y]), *fittedParameters)
axes.plot(x_data, y_data, 'o')
axes.set_title('Contour Plot') # add a title for contour plot
axes.set_xlabel('X Data') # X axis data label
axes.set_ylabel('Y Data') # Y axis data label
CS = matplotlib.pyplot.contour(X, Y, Z, numberOfContourLines, colors='k')
matplotlib.pyplot.clabel(CS, inline=1, fontsize=10) # labels for contours
plt.show()
plt.close('all') # clean up after using pyplot or else there can be memory and process problems
def ScatterPlot(data):
f = plt.figure(figsize=(graphWidth/100.0, graphHeight/100.0), dpi=100)
matplotlib.pyplot.grid(True)
axes = Axes3D(f)
x_data = data[0]
y_data = data[1]
z_data = data[2]
axes.scatter(x_data, y_data, z_data)
axes.set_title('Scatter Plot (click-drag with mouse)')
axes.set_xlabel('X Data')
axes.set_ylabel('Y Data')
axes.set_zlabel('Z Data')
plt.show()
plt.close('all') # clean up after using pyplot or else there can be memory and process problems
def func(data, a, b, c): # example flat surface
x = data[0]
y = data[1]
return (a * x) + (b * y) + c
if __name__ == "__main__":
xData = numpy.array([2.0, 5.0, 3.0, 1.0, 6.0, 4.0, 7.0, 8.0, 6.0, 7.0])
yData = numpy.array([3.0, 2.0, 6.0, 4.0, 6.0, 1.0, 2.0, 5.0, 6.0, 10.0])
zData = numpy.array([1.0, 3.0, 5.0, 6.0, 7.0, 8.0, 9.0, 7.0, 10.0, 9.0])
data = [xData, yData, zData]
initialParameters = [1.0, 1.0, 1.0] # these are the same as scipy default values in this example
# here a non-linear surface fit is made with scipy's curve_fit()
fittedParameters, pcov = scipy.optimize.curve_fit(func, [xData, yData], zData, p0 = initialParameters)
ScatterPlot(data)
SurfacePlot(func, data, fittedParameters)
ContourPlot(func, data, fittedParameters)
print('fitted prameters', fittedParameters)
modelPredictions = func(data, *fittedParameters)
absError = modelPredictions - zData
SE = numpy.square(absError) # squared errors
MSE = numpy.mean(SE) # mean squared errors
RMSE = numpy.sqrt(MSE) # Root Mean Squared Error, RMSE
Rsquared = 1.0 - (numpy.var(absError) / numpy.var(zData))
print('RMSE:', RMSE)
print('R-squared:', Rsquared)
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.