pandas - linear regression of dataframe columns values

Question

I have a pandas dataframe df like:

A,B,C
1,1,1
0.8,0.6,0.9
0.7,0.5,0.8
0.2,0.4,0.1
0.1,0,0

where the three columns have sorted values [0,1]. I'm trying to plot a linear regression over the three series. So far I was able to use scipy.stats as following:

from scipy import stats

xi = np.arange(len(df))

slope, intercept, r_value, p_value, std_err = stats.linregress(xi,df['A'])
line1 = intercept + slope*xi
slope, intercept, r_value, p_value, std_err = stats.linregress(xi,df['B'])
line2 = intercept + slope*xi
slope, intercept, r_value, p_value, std_err = stats.linregress(xi,df['C'])
line3 = intercept + slope*xi

plt.plot(line1,'r-')
plt.plot(line2,'b-')
plt.plot(line3,'g-')

plt.plot(xi,df['A'],'ro')
plt.plot(xi,df['B'],'bo')
plt.plot(xi,df['C'],'go')

obtaining the following plot:

Is it possible to obtain a single linear regression that summarize the three single linear regressions within scipy.stats?

If you want a regression that summarizes the three regressions, why not combine all the data and do linear regression on that data? — Daniel Underwood
– Daniel Underwood, Commented Jan 19, 2016 at 17:36

Primer · Accepted Answer · 2016-01-19 17:52:26Z

2

Perhaps something like this:

x = pd.np.tile(xi, 3)
y = pd.np.r_[df['A'], df['B'], df['C']]

slope, intercept, r_value, p_value, std_err = stats.linregress(x, y)
line4 = intercept + slope * xi

plt.plot(line4,'k-')

answered Jan 19, 2016 at 17:52

Primer

10.4k5 gold badges48 silver badges55 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

pandas - linear regression of dataframe columns values

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related