How to plot linear regression with multiple intercepts

Asked Jul 25 '16 at 09:47

Active Jul 25 '16 at 11:51

Viewed 558 times

I am trying to plot my data that includes certain days as my x value, and there are like 20+ different y values for each x value. I don't know if that is the reason why I am getting so many intercept values, but regardless it is not letting me run a regular linear regression test for my data. Can someone help me fix my code?`

from scipy import stats
import numpy as np
import pandas as pd
import statsmodels.formula.api as sm
df=pd.read_csv('F:/Data.csv',parse_dates=['Date'])
df2=pd.DataFrame(df, columns=['Date','CO2-Rh'])
x=df2['Date']
y=df2['CO2-Rh']
result = sm.ols(formula="x ~ y", data=df2).fit()

This is the part that gives me 39 different intercepts, what I am trying to do is print result.summary() here is how my dataframe looks like:

edited Jul 25 '16 at 10:04

asked Jul 25 '16 at 09:47

Sergio Espejo

perhaps you could show how `df2` looks like? – M.T Jul 25 '16 at 09:54
i'll do it right now @M.T – Sergio Espejo Jul 25 '16 at 10:00
I assume that all values of CO2-Rh have been measured succesively on one day. Further, assuming (hoping) that the time intervals of measurement have been equidistant, you could simply do regression of CO2-Rh with the index (0,1,2,3,...). – Nikolas Rieble Jul 25 '16 at 10:28
Maybe this will help? http://stackoverflow.com/questions/19991445/run-an-ols-regression-with-pandas-data-frame – Newyork167 Jul 25 '16 at 12:23

How to plot linear regression with multiple intercepts

0 Answers0