def matrix_regression(input_vals, output_vals, funcs, categorical = False):
'''Linear regression on a matrix of input properties and input values.
Produces a linear model for factors influencing output values.
Functions must be tuples (title, func).
Input_vals and output_vals must be the same size
'''
assert(len(input_vals) == len(output_vals))
#Add a constant function for the intercept
if 'Intercept' not in map(lambda x: x[0], funcs): funcs.append(('Intercept', lambda x: 1))
#Build up a matrix of each input function on each input val
m = r.matrix(1.0, nrow=len(input_vals), ncol=len(funcs))
for i in xrange(len(input_vals)):
for j in xrange(len(funcs)):
m[i][j] = funcs[j][1](i)
if categorical and m[i][j]: m[i][j] = 1
#Regression, done in R
fit = r.lsfit(m,output_vals, intercept = False, )
#Extract values
coefficients = map(lambda x: x[1], sorted(fit['coefficients'].items(), key = lambda x: int(x[0][1:])))
regression_func = lambda x,c=coefficients: sum([c[j] * funcs[j][1](x) for j in xrange(len(funcs))])
model_vals = map(regression_func, input_vals)
least_squares_quality = least_squares_error(model_vals,output_vals)
linear_quality = linear_error(model_vals,output_vals)
return coefficients, regression_func, model_vals, least_squares_quality, linear_quality
def fit_line(x1, y1):
myline = None
if (len(x1) == 2):
tmp_line = line(0, 0)
myline = tmp_line.get_line_from_points(point(x1[0], y1[0], 0),
point(x1[1], y1[1], 0))
elif (len(x1) > 2):
retHash = r.lsfit(x1, y1)['coefficients']
slope1 = retHash['X']
intercept1 = retHash['Intercept']
#slope1, intercept1, = stats.linregress(x1,y1)[0:2]
myline = line(slope1, intercept1)
return myline
from rpy import r
my_x = [5.05, 6.75, 3.21, 2.66]
my_y = [1.65, 26.5, -5.93, 7.96]
ls_fit = r.lsfit(my_x,my_y)
gradient = ls_fit['coefficients']['X']
yintercept= ls_fit['coefficients']['Intercept']
r.png("scatter_regression.png", width=400, height=350)
r.plot(x=my_x, y=my_y, xlab="x", ylab="y", xlim=(0,7), ylim=(-16,27),
main="Example Scatter with regression")
r.abline(a=yintercept, b=gradient, col="red")
r.dev_off()
income = [125000,100000,40000, 35000, 41000, 29000, 35000, 24000, 50000, 60000];
# do the scatter plot
# Specify the output picture size and format.
print "Writing output graph to file: scatterplot.png"
print "To view it in Linux, you can use the File Browser and double-click."
print "For command-line viewing, use the gthumb image viewer as follows:"
print "% gthumb scatterplot.png"
r.png("scatterplot.png", width=400, height=350);
# Draw the plot. xlim and ylim specify the range for the axis. We
# prefer to keep the graph origin at 0,0.
r.plot(x=education_years, y=income, xlab="Education Years", ylab = "Income",
main = "Scatter Plot with Least Squares Fit");
# Compute the least-square fit object between education_years and income.
leastsquarefit = r.lsfit(education_years, income);
#print "leastsquarefit = ", leastsquarefit; # for debugging.
# Compute the slope of the line and the y-intercept from the least-square
# fit object.
gradient = leastsquarefit['coefficients']['X'];
yintercept = leastsquarefit['coefficients']['Intercept'];
# Now plot the least square fit line.
r.abline(a=yintercept, b=gradient, col="red");
# Now turn off the graphics device. This is a R operation to "close"
# the graph.
r.dev_off();