notebook.community

Edit and run



In [1]:

    
import pandas as pd
import numpy as np
import sklearn.linear_model as sl



In [31]:

    
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 [33]:

    
def lasso_fit(x, y):
    
    #Define the alpha values to test
    alpha_lasso = [1e-15, 1e-10, 1e-8, 1e-5,1e-4, 1e-3,1e-2, 1, 5, 10]
    
    #Initialize the dataframe to store coefficients
    col = ['rss','intercept'] + ['coef_x_%d'%i for i in range(1,x.shape[1]+1)]
    ind = [str(alpha_lasso[i]) for i in range(0,10)]
    coef_matrix_lasso = pd.DataFrame(index=ind, columns=col)
    
    for i in range(10):
        ls = sl.Lasso(alpha=alpha_lasso[i],normalize=True, max_iter=1e5)
        ls.fit(x,y)
        y_pred = ls.predict(x)
        #Return the result in pre-defined format
        rss = sum((y_pred-y)**2)
        ret = [rss]
        ret.extend([ls.intercept_])
        ret.extend(ls.coef_)
        coef_matrix_lasso.iloc[i,] = ret
    
    exist = np.sum(coef_matrix_lasso.ix[:,2:]==0, axis = 1)!=x.shape[1]
    if(sum(exist)==0):
        size = 0
        lm = sl.LinearRegression()
        intercept = pd.DataFrame(np.ones(x.shape[0]))
        lm.fit(intercept, y)
        fitted = lm.predict(intercept)
    else:
        alpha = pd.to_numeric(coef_matrix_lasso.index[exist][-1])
        ls = sl.Lasso(alpha=alpha,normalize=True, max_iter=1e5)
        ls.fit(x,y)
        fitted = ls.predict(x)
        index = np.array(range(len(ls.coef_)))[ls.coef_!=0]
        size = len(index)
        
    # get residuals
    residual = sum((y-fitted)**2)
    df_residual = x.shape[0] - size - 1
    
    return {'fitted':fitted, 'residual':residual, 'df_residual':df_residual, 
            'size':size, 'index': index}



In [34]:

    
lasso_fit(x,y)









    Out[34]:





{'df_residual': 92,
 'fitted': array([ 52.92355824,  57.0009211 ,  57.0009211 ,  58.36004205,
         57.0009211 ,  54.28267919,  58.36004205,  66.51476775,
         55.64180014,  63.79652585,  55.64180014,  59.719163  ,
         61.07828395,  59.719163  ,  69.23300966,  55.64180014,
         54.28267919,  62.4374049 ,  58.36004205,  51.56443729,
         62.4374049 ,  62.4374049 ,  57.0009211 ,  54.28267919,
         63.79652585,  58.36004205,  59.719163  ,  59.719163  ,
         58.36004205,  57.0009211 ,  55.64180014,  59.719163  ,
         54.28267919,  58.36004205,  52.92355824,  61.07828395,
         55.64180014,  59.719163  ,  62.4374049 ,  63.79652585,
         58.36004205,  59.719163  ,  57.0009211 ,  57.0009211 ,
         62.4374049 ,  57.0009211 ,  58.36004205,  58.36004205,
         55.64180014,  62.4374049 ,  67.87388871,  59.719163  ,
         58.36004205,  58.36004205,  59.719163  ,  55.64180014,
         57.0009211 ,  61.07828395,  59.719163  ,  59.719163  ,
         67.87388871,  62.4374049 ,  55.64180014,  52.92355824,
         51.56443729,  58.36004205,  55.64180014,  67.87388871,
         62.4374049 ,  59.719163  ,  59.719163  ,  58.36004205,
         51.56443729,  59.719163  ,  61.07828395,  57.0009211 ,
         54.28267919,  61.07828395,  61.07828395,  65.1556468 ,
         62.4374049 ,  62.4374049 ,  55.64180014,  57.0009211 ,
         65.1556468 ,  65.1556468 ,  59.719163  ,  57.0009211 ,
         65.1556468 ,  59.719163  ,  58.36004205,  55.64180014,
         61.07828395,  57.0009211 ]),
 'index': array([1]),
 'residual': 15913.861386451388,
 'size': 1}



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