Re: [Matplotlib-users] regression coeffiecients

[Oz Nahum]

I'm answering to myself on the mailing list just in case it might help some
in the future.

As, someone pointed out the error is in the assignment operator:

I wrote in the code:
 sum1 =+ (i-mx)*(j-my)

which does not add the values but puts them.
Instead I should have wrote
 sum1 += (i-mx)*(j-my)

a little difference that does a lot... :-)

here is the correct function:


def slope(x,y):
sum1 = 0
sum2 = 0
mx = mean(x)
my = mean(y)
for i,j in zip(x,y):
sum1 += (i-mx)*(j-my)
print sum1
sum2 += (i-mx)**2
slope = sum1/sum2
return slope


-- 
 .''`.
: :' :  We are debian.org. Lower your prices,
`. `'   surrender your code.
  `-We will add your hardware and  software
distinctiveness to our own.
Resistance is futile.


   Imagine there's no countries
   It isn't hard to do
   Nothing to kill or die for
   And no religion too
   Imagine all the people
   Living life in peace

  You all must read 'The God Delusion'
  http://en.wikipedia.org/wiki/The_God_Delusion
---
when one person suffers from a delusion it is called insanity. When many
people suffer from a delusion it is called religion.
Robert Pirsig, Zen and the Art of Motorcycle Maintenance
-
This SF.Net email is sponsored by the Moblin Your Move Developer's challenge
Build the coolest Linux based applications with Moblin SDK  win great prizes
Grand prize is a trip for two to an Open Source event anywhere in the world
http://moblin-contest.org/redirect.php?banner_id=100url=/___
Matplotlib-users mailing list
Matplotlib-users@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/matplotlib-users

[Matplotlib-users] regression coeffiecients

[Oz Nahum]

Hello,
I'm having troubles understand something about regression coefficients.
If I have two vectors:

x = [1.38, 1.98, 3.18, 3.56, 4.9, 6.21, 6.44, 7.47, 8.36, 8.81]
y = [8.19, 17.77, 20.12, 14.55, 20.17 ,31.22 ,28.94, 34.79, 40.26, 38.99]

and I would like to find out the regression coefficient  I can use polyfit:

b1, b = polyfit(x,y,1)

my first question is can I get from polyfit the  corrlation coeficient (I
know about corrcoef, just looking for more opotions).

The second question is about a fuction I wrote: according to
http://en.wikipedia.org/wiki/Regression_analysis#Linear_regression
it's pretty easy to write a little python funcion to calculate the
regression coefficients. Here is mine:

def b1(x,y):
sum1 = 0
sum2 = 0
mx = mean(x)
my = mean(y)
for i,j in zip(x,y):
sum1 =+ (i-mx)*(j-my)
print sum1
sum2 =+ (i-mx)**2
b1 = sum1/sum2
return b1

both methods yeild two different b1 values. Can anyone please tell me what
wrong with my function ?

Thanks, Oz.




-- 
 .''`.
: :' :  We are debian.org. Lower your prices,
`. `'   surrender your code.
  `-We will add your hardware and  software
distinctiveness to our own.
Resistance is futile.


   Imagine there's no countries
   It isn't hard to do
   Nothing to kill or die for
   And no religion too
   Imagine all the people
   Living life in peace

  You all must read 'The God Delusion'
  http://en.wikipedia.org/wiki/The_God_Delusion
---
when one person suffers from a delusion it is called insanity. When many
people suffer from a delusion it is called religion.
Robert Pirsig, Zen and the Art of Motorcycle Maintenance
-
This SF.Net email is sponsored by the Moblin Your Move Developer's challenge
Build the coolest Linux based applications with Moblin SDK  win great prizes
Grand prize is a trip for two to an Open Source event anywhere in the world
http://moblin-contest.org/redirect.php?banner_id=100url=/___
Matplotlib-users mailing list
Matplotlib-users@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/matplotlib-users