

In [1]:

    
!pip install .









    



Processing /Users/Cecilia/Desktop/STA 663/project/STA-663-Final-Project/fastfsr
  Requirement already satisfied (use --upgrade to upgrade): fastfsr==0.1 from file:///Users/Cecilia/Desktop/STA%20663/project/STA-663-Final-Project/fastfsr in /Users/Cecilia/anaconda/lib/python3.5/site-packages



In [2]:

    
import fastfsr



In [3]:

    
%matplotlib inline
import seaborn as sns
import matplotlib.pyplot as plt

import pandas as pd
import numpy as np

The fsr_fast function performs Fast FSR (no phony var. generation). It returns uses reg_subset to calculate the p-values and feed into fsr_fast_pv to implement the Fast FSR algorithm. The plot from fsr_fast_pv is carried over and will be displayed if `printout = True'.

In addition, the residual degrees of freedom, fitted values



In [4]:

    
ncaa = pd.read_csv("http://www4.stat.ncsu.edu/~boos/var.select/ncaa.data2.txt", 
                   delim_whitespace = True)
x = ncaa.ix[:,:-1]
y = ncaa.ix[:,-1]
x.head()



In [6]:

    
fastfsr.fsr_fast(x, y, plot = True, printout = True)









    



            pval         pvmax     ghigh          glow
0   1.110223e-16  1.110223e-16 -0.000002  9.992007e-16
1   6.951095e-05  6.951095e-05  0.000625  3.938954e-04
2   1.158459e-02  1.158459e-02  0.065645  2.703071e-02
3   5.299074e-03  1.158459e-02  0.027030  2.703071e-02
4   2.483425e-03  1.158459e-02  0.027030  2.703071e-02
5   4.331519e-02  4.331519e-02  0.101069  8.044250e-02
6   5.273414e-02  5.273414e-02  0.097935  7.910121e-02
7   1.056315e-01  1.056315e-01  0.158447  8.642579e-02
8   8.262706e-02  1.056315e-01  0.086426  8.642579e-02
9   5.363568e-02  1.056315e-01  0.086426  8.642579e-02
10  2.349586e-01  2.349586e-01  0.192239  1.566390e-01
11  2.864403e-01  2.864403e-01  0.190960  1.542371e-01
12  3.163182e-01  3.163182e-01  0.170325  1.054394e-01
13  2.697263e-01  3.163182e-01  0.105439  1.054394e-01
14  4.953258e-01  4.953258e-01  0.165109  1.238314e-01
15  6.326487e-01  6.326487e-01  0.158162  1.116439e-01
16  7.056418e-01  7.056418e-01  0.124525  7.840464e-02
17  8.605404e-01  8.605404e-01  0.095616  4.529160e-02
18  9.031976e-01  9.031976e-01  0.047537  0.000000e+00    m1   m  gam0  size  alphamax  alpha_fast
0  19  19  0.05     5  0.234958    0.021429






    Out[6]:





{'df_residual': 88,
 'fitted': array([ 39.97319987,  52.64145288,  51.31626901,  49.45817916,
         52.76003971,  52.09365876,  62.21731499,  83.46777372,
         60.30117759,  68.25962825,  55.49774106,  64.22824537,
         56.80145361,  58.13377833,  95.81098975,  45.10069166,
         48.5023815 ,  61.75018487,  56.63641511,  30.30552519,
         69.63687727,  71.67508299,  47.44581449,  41.38009064,
         82.39555916,  60.89678086,  55.86806477,  60.40105953,
         52.97306638,  52.32248597,  54.58600284,  54.72958362,
         34.98385796,  51.99723444,  36.34890947,  64.92903678,
         36.76333365,  63.70743018,  72.27393023,  76.79752933,
         63.26698036,  58.23771906,  52.97228084,  50.04166835,
         71.06778164,  55.6504356 ,  60.55746898,  56.6493757 ,
         40.73802362,  66.17385709,  96.76532902,  63.74160655,
         60.50068658,  50.71602229,  52.28020596,  46.87603065,
         52.86288238,  72.38682421,  65.26057094,  65.25404745,
         84.40695335,  78.03422549,  44.63575344,  38.97775534,
         28.69637283,  59.63252913,  55.09716218,  95.952859  ,
         73.78844456,  66.64091251,  52.30527841,  59.77698098,
         28.13040121,  59.81486661,  73.55932889,  51.73408815,
         42.12665683,  66.11674205,  62.39400279,  79.87453995,
         66.64400901,  64.23340288,  38.08783758,  38.15882539,
         88.93618701,  78.43695163,  67.89315809,  48.27298631,
         82.76456973,  59.87605898,  62.13871824,  51.17954363,
         66.1725256 ,  49.94174404]),
 'index': array([1, 2, 4, 3, 6]),
 'residual': 4565.3324512695444,
 'size': 5}



In [ ]:

	x1	x2	x3	x4	x5	x6	x7	x8	x9	x10	x11	x12	x13	x14	x15	x16	x17	x18	x19
0	13	17	9	15	28.0	0	-1.14045	3.660	4.490	3409	65.8	18	81	42.2	660000	77	100	59	1
1	28	20	32	18	18.4	18	-0.13719	2.594	3.610	7258	66.3	17	82	40.5	150555	88	94	41	25
2	32	20	20	20	34.8	18	1.55358	2.060	4.930	6405	75.0	19	71	46.5	415400	94	81	25	36
3	32	21	24	21	14.5	20	2.05712	2.887	3.876	18294	66.0	16	84	42.2	211000	93	88	26	13
4	24	20	16	20	21.8	13	-0.77082	2.565	4.960	8259	63.5	16	91	41.2	44000	90	92	32	31