Last active
August 29, 2018 01:16
-
-
Save rileypeterson/2e1fe30b5508557bb4a8f1c8035a4eb3 to your computer and use it in GitHub Desktop.
Expanding Linear Regression
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# UPDATE: He re-added the question here: https://stackoverflow.com/questions/52048919/how-to-incrementally-add-linear-regression-column-to-pandas-dataframe/52068085#52068085 | |
# Some guy had this weird question on Stack Overflow about cummulatively applying linear regression to a dataframe | |
# He deleted the question (I don't think this operation is very useful), but I figured out a way to do it here: | |
# Pretty wacky | |
from io import StringIO | |
import pandas as pd | |
import numpy as np | |
df = pd.read_table(StringIO(""" a b | |
0 6.0 0.6 | |
1 1.0 0.3 | |
2 3.0 0.8 | |
3 5.0 0.1 | |
4 7.0 0.4 | |
5 2.0 0.2 | |
6 0.0 0.9 | |
7 4.0 0.7 | |
8 8.0 0.0 | |
9 9.0 0.5 | |
10 10.0 0.4 | |
11 11.0 0.35 | |
12 12.0 0.3 | |
13 13.0 0.28 | |
14 14.0 0.27 | |
15 15.0 0.22"""), sep='\s+') | |
df = df.sort_values(by='a') | |
ax = df.plot(x='a',y='b',kind='scatter') | |
m, b = np.polyfit(df['a'],df['b'],1) | |
lin_reg = lambda x, m, b : m*x + b | |
df['lin'] = lin_reg(df['a'], m, b) | |
def make_m(x): | |
y = df['b'].iloc[0:len(x)] | |
return np.polyfit(x, y, 1)[0] | |
def make_b(x): | |
y = df['b'].iloc[0:len(x)] | |
return np.polyfit(x, y, 1)[1] | |
df['new'] = df['a'].expanding().apply(make_m, raw=True)*df['a'] + df['a'].expanding().apply(make_b, raw=True) | |
# df = df.sort_values(by='a') | |
ax.plot(df.a,df.lin) | |
ax.plot(df.a,df.new) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment