Linear Regression to fit 2D data in python - python

I have a function Polyfit which I want it to get the data here x and y and return a 2D line fitted to that data using linear regression. I get a good result but it's too good and I don't know if I am doing it correctly all the way to the end.
#creating the data and plotting them
np.random.seed(0)
N = 10 # number of data points
x = np.linspace(0,2*np.pi,N)
y = np.sin(x) + np.random.normal(0,.3,x.shape)
plt.figure()
plt.plot(x,y,'o')
plt.xlabel('x')
plt.ylabel('y')
plt.title('2D data (#data = %d)' % N)
plt.show()
def polyfit(x,y,degree,delta):
#x,y
X = np.vstack([np.ones(x.shape), x, y]).T
Y = np.vstack([y]).T
XtX = np.dot(X.T, X)
XtY = np.dot(X.T, Y)
theta = np.dot(np.linalg.inv(XtX), XtY)
degree = theta.shape[0]
delta = theta.T * theta
x_theta = X.T * theta
pred = np.sum([theta* x])
loss = np.dot((Y.T - x_theta).T, (Y.T - x_theta))
c = theta[0] + theta[1] * x[1] + theta[2] * math.pow(x[2],2)
return pred
result = polyfit(x,y,2,2)
fin = y - result
plt.plot(x, fin, 'go--')
Data image:
Result of the fitted line:

Here is a graphing example polynomial fitter using numpy's polyfit() for the fit and numpy's polyval() to calculate model predictions, along with RMSE and R-squared values.
import numpy, scipy, matplotlib
import matplotlib.pyplot as plt
xData = numpy.array([1.1, 2.2, 3.3, 4.4, 5.0, 6.6, 7.7, 0.0])
yData = numpy.array([1.1, 20.2, 30.3, 40.4, 50.0, 60.6, 70.7, 0.1])
polynomialOrder = 2 # example quadratic
# curve fit the test data
fittedParameters = numpy.polyfit(xData, yData, polynomialOrder)
print('Fitted Parameters:', fittedParameters)
modelPredictions = numpy.polyval(fittedParameters, xData)
absError = modelPredictions - yData
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(yData))
print('RMSE:', RMSE)
print('R-squared:', Rsquared)
print()
##########################################################
# graphics output section
def ModelAndScatterPlot(graphWidth, graphHeight):
f = plt.figure(figsize=(graphWidth/100.0, graphHeight/100.0), dpi=100)
axes = f.add_subplot(111)
# first the raw data as a scatter plot
axes.plot(xData, yData, 'D')
# create data for the fitted equation plot
xModel = numpy.linspace(min(xData), max(xData))
yModel = numpy.polyval(fittedParameters, xModel)
# now the model as a line plot
axes.plot(xModel, yModel)
axes.set_xlabel('X Data') # X axis data label
axes.set_ylabel('Y Data') # Y axis data label
plt.show()
plt.close('all') # clean up after using pyplot
graphWidth = 800
graphHeight = 600
ModelAndScatterPlot(graphWidth, graphHeight)

Related

opt.curve_fit with only one parameter

I'm having trouble fitting a curve with only one parameter using scipy.opt.curve_fit:
import scipy.optimize as opt
import numpy as np
def func(T):
return 76.881324*np.exp((-L)/(8.314*T))
best_params, cov_matrix = opt.curve_fit(func, xdata = x, ydata = y, p0=[])
I have arrays of values, x (T in the below eq) and y (P) that I'm trying to fit to the equation
but it seems it wants func() to have more than one argument. How do I fix this?
Here is a graphical Python fitter using your equation with some test data. Replace the example data with your own and you should be done.
import numpy, scipy, matplotlib
import matplotlib.pyplot as plt
from scipy.optimize import curve_fit
xData = numpy.array([1.1, 2.2, 3.3, 4.4, 5.0, 6.6, 7.7])
yData = numpy.array([1.1, 20.2, 30.3, 60.4, 50.0, 60.6, 70.7])
def func(T, L):
return 76.881324*numpy.exp((-L)/(8.314*T))
# all "1.0" is the same as the scipy defaults
initialParameters = numpy.array([1.0])
# curve fit the test data
fittedParameters, pcov = curve_fit(func, xData, yData, initialParameters)
modelPredictions = func(xData, *fittedParameters)
absError = modelPredictions - yData
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(yData))
print('Parameters:', fittedParameters)
print('RMSE:', RMSE)
print('R-squared:', Rsquared)
print()
##########################################################
# graphics output section
def ModelAndScatterPlot(graphWidth, graphHeight):
f = plt.figure(figsize=(graphWidth/100.0, graphHeight/100.0), dpi=100)
axes = f.add_subplot(111)
# first the raw data as a scatter plot
axes.plot(xData, yData, 'D')
# create data for the fitted equation plot
xModel = numpy.linspace(min(xData), max(xData))
yModel = func(xModel, *fittedParameters)
# now the model as a line plot
axes.plot(xModel, yModel)
axes.set_xlabel('X Data') # X axis data label
axes.set_ylabel('Y Data') # Y axis data label
plt.show()
plt.close('all') # clean up after using pyplot
graphWidth = 800
graphHeight = 600
ModelAndScatterPlot(graphWidth, graphHeight)

Multiple Linear Regression using ScikitLearn, different approaches give different answers

This is probably as equally valid on stats exchange as here (could be the stats or python that i'm not sure about.
Suppose I have two independent variables X,Y that explain some of the variance of Z.
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])
I want to regress out the variability in X and Y from Z. There's two approaches that I know of:
Regress out X from Z first (form a linear regression of X,Z, find the residual, then repeat for Y). Such that:
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
Where regr_2 is the remainder of Z where X and Y have been sequentially regressed out.
The alternative is to create a multiple linear regression model for X and Y predicting Z:
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
The residual from the first sequential approach resi_2 and the multiple linear regression resi_3 are very similar (correlation=0.97) but not equivalent. The two residuals are plotted below:
Any thoughts great (not a statistician so could be my understanding vs a python problem!). Note if for the first part I regress out Y first, then X, I get different residuals.
Here is an example 3D graphical surface fitter using your data and scipy's curve_fit() routine with scatter, surface, and contour plots. You should be able to click-drag the 3D plots to rotate them in 3-space and see that the data does not appear to lie on any sort of smooth surface, so the flat plane model used here "z = (a *x) + (b * y) + c" is pretty much no better or worse than any other model for this data.
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)

How to use curvefit in python

I am studying nonlinear curvefit with python.
I made example like below.
But the optimized plot is not drawn well
plt.plot(basketCont, fittedData)
I guess the optimized parametes are not good also.
Could you give some recommends? Thank you.
import matplotlib
matplotlib.use('Qt4Agg')
import matplotlib.pyplot as plt
from matplotlib.pyplot import cm
import numpy as np
from scipy.optimize import curve_fit
def func(x, a, b, c):
return a - b* np.exp(c * x)
baskets = np.array([475, 108, 2, 38, 320])
scaling_factor = np.array([95.5, 57.7, 1.4, 21.9, 88.8])
popt,pcov = curve_fit(func, baskets, scaling_factor)
print (popt)
print (pcov)
basketCont=np.linspace(min(baskets),max(baskets),50)
fittedData=[func(x, *popt) for x in basketCont]
fig1 = plt.figure(1)
plt.scatter(baskets, scaling_factor, s=5)
plt.plot(basketCont, fittedData)
plt.grid()
plt.show()
I personally could not get a good fit to your data using the equation you posted, however the Hill sigmoidal equation gave a good fit. Here is the Python code for the graphical fitter I used.
import numpy, scipy, matplotlib
import matplotlib.pyplot as plt
from scipy.optimize import curve_fit
import warnings
baskets = numpy.array([475.0, 108.0, 2.0, 38.0, 320.0])
scaling_factor = numpy.array([95.5, 57.7, 1.4, 21.9, 88.8])
# rename data for simpler code re-use later
xData = baskets
yData = scaling_factor
def func(x, a, b, c): # Hill sigmoidal equation from zunzun.com
return a * numpy.power(x, b) / (numpy.power(c, b) + numpy.power(x, b))
# these are the same as the scipy defaults
initialParameters = numpy.array([1.0, 1.0, 1.0])
# do not print unnecessary warnings during curve_fit()
warnings.filterwarnings("ignore")
# curve fit the test data
fittedParameters, pcov = curve_fit(func, xData, yData, initialParameters)
modelPredictions = func(xData, *fittedParameters)
absError = modelPredictions - yData
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(yData))
print('Parameters:', fittedParameters)
print('RMSE:', RMSE)
print('R-squared:', Rsquared)
print()
##########################################################
# graphics output section
def ModelAndScatterPlot(graphWidth, graphHeight):
f = plt.figure(figsize=(graphWidth/100.0, graphHeight/100.0), dpi=100)
axes = f.add_subplot(111)
# first the raw data as a scatter plot
axes.plot(xData, yData, 'D')
# create data for the fitted equation plot
xModel = numpy.linspace(min(xData), max(xData))
yModel = func(xModel, *fittedParameters)
# now the model as a line plot
axes.plot(xModel, yModel)
axes.set_xlabel('X Data') # X axis data label
axes.set_ylabel('Y Data') # Y axis data label
plt.show()
plt.close('all') # clean up after using pyplot
graphWidth = 800
graphHeight = 600
ModelAndScatterPlot(graphWidth, graphHeight)

Fitting a power law with known exponent and extracting the coefficient in Python

I have a data set that I know fits to a curve of the form:
y = a x²
and I want to extract the value of a.
What's the best way to go about this in Python (with scipy etc.) ?
Here is a graphical fitter example using scipy's curve_fit():
import numpy, scipy, matplotlib
import matplotlib.pyplot as plt
from scipy.optimize import curve_fit
xData = numpy.array([1.1, 2.2, 3.3, 4.4, 5.0, 6.6, 7.7])
yData = numpy.array([1.1, 20.2, 30.3, 60.4, 50.0, 60.6, 70.7])
def func(x, a):
return (a * numpy.square(x))
# same as the scipy default
initialParameters = numpy.array([1.0])
# curve fit the test data
fittedParameters, pcov = curve_fit(func, xData, yData, initialParameters)
modelPredictions = func(xData, *fittedParameters)
absError = modelPredictions - yData
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(yData))
print('Parameters:', fittedParameters)
print('RMSE:', RMSE)
print('R-squared:', Rsquared)
print()
##########################################################
# graphics output section
def ModelAndScatterPlot(graphWidth, graphHeight):
f = plt.figure(figsize=(graphWidth/100.0, graphHeight/100.0), dpi=100)
axes = f.add_subplot(111)
# first the raw data as a scatter plot
axes.plot(xData, yData, 'D')
# create data for the fitted equation plot
xModel = numpy.linspace(min(xData), max(xData))
yModel = func(xModel, *fittedParameters)
# now the model as a line plot
axes.plot(xModel, yModel)
axes.set_xlabel('X Data') # X axis data label
axes.set_ylabel('Y Data') # Y axis data label
plt.show()
plt.close('all') # clean up after using pyplot
graphWidth = 800
graphHeight = 600
ModelAndScatterPlot(graphWidth, graphHeight)

Polynomial regression

I wanted to know if someone could help me in order to understand how to change this code ( linear regression ) into polynomial regression. I am trying to not use to much of pre-made function to make sure that I am understanding what I am doing.
# Importing Necessary Libraries
%matplotlib inline
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = (20.0, 10.0)
# Reading Data
data = pd.read_csv('test.csv')
print(data.shape)
data.head()
# Collecting X and Y
X = data['a'].values
Y = data['b'].values
# Mean X and Y
mean_x = np.mean(X)
mean_y = np.mean(Y)
# Total number of values
m = len(X)
# Using the formula to calculate b1 and b2
numer = 0
denom = 0
for i in range(m):
numer += (X[i] - mean_x) * (Y[i] - mean_y)
denom += (X[i] - mean_x) ** 2
b1 = numer / denom
b0 = mean_y - (b1 * mean_x)
# Print coefficients
print(b1, b0)
max_x = np.max(X) + 100
min_x = np.min(X) - 100
# Calculating line values x and y
x = np.linspace(min_x, max_x, 1000)
y = b0 + b1 * x
# Ploting Line
plt.plot(x, y, color='#58b970', label='Regression Line')
# Ploting Scatter Points
plt.scatter(X, Y, c='#ef5423', label='Scatter Plot')
plt.xlabel('a')
plt.ylabel('b')
plt.legend()
plt.show()
And now I want from this code to "upgrade" it to make it work as a polynomial regression, degree 3 ( ax^3 + bx² ... ). Someone could help me ? Thanks in advance.
Here is an example graphing polynomial fitter:
import numpy, matplotlib
import matplotlib.pyplot as plt
xData = numpy.array([1.1, 2.2, 3.3, 4.4, 5.0, 6.6, 7.7, 0.0])
yData = numpy.array([1.1, 20.2, 30.3, 40.4, 50.0, 60.6, 70.7, 0.1])
polynomialOrder = 2 # example quadratic
# curve fit the test data
fittedParameters = numpy.polyfit(xData, yData, polynomialOrder)
print('Fitted Parameters:', fittedParameters)
modelPredictions = numpy.polyval(fittedParameters, xData)
absError = modelPredictions - yData
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(yData))
print('RMSE:', RMSE)
print('R-squared:', Rsquared)
print()
##########################################################
# graphics output section
def ModelAndScatterPlot(graphWidth, graphHeight):
f = plt.figure(figsize=(graphWidth/100.0, graphHeight/100.0), dpi=100)
axes = f.add_subplot(111)
# first the raw data as a scatter plot
axes.plot(xData, yData, 'D')
# create data for the fitted equation plot
xModel = numpy.linspace(min(xData), max(xData))
yModel = numpy.polyval(fittedParameters, xModel)
# now the model as a line plot
axes.plot(xModel, yModel)
axes.set_xlabel('X Data') # X axis data label
axes.set_ylabel('Y Data') # Y axis data label
plt.show()
plt.close('all') # clean up after using pyplot
graphWidth = 800
graphHeight = 600
ModelAndScatterPlot(graphWidth, graphHeight)

Categories