import sys import numpy as np from pandas import DataFrame from ast import literal_eval import statsmodels.formula.api as sm from sklearn.cross_validation import train_test_split from stupidlySimplePredictions import get_data_from_file command = sys.argv[1] f_string, num_years = command.split() num_years = int(num_years) X,y = get_data_from_file(f_string, num_years) X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=.3,random_state=123) X1_train = np.concatenate((np.ones((len(y_train),1)),X_train), axis=1) result = sm.OLS(y_train,X1_train).fit() print result.summary()
for i in range(np.size(residual,0)):
residual[i] = y[i][0] - prodsum[i]
return residual
def sum_sq_res(p, y, X):
'''Compute sum of squared residuals'''
prod = p*X
prodsum = prod.sum(axis=1)
residual = np.zeros([np.size(y,0)])
for i in range(np.size(residual,0)):
residual[i] = y[i][0] - prodsum[i]
J = (residual**2).sum()
return J
if __name__ == '__main__':
X,y = get_data_from_file('HRminAB50minSeasons5.txt',5)
#X = X[:,1:]
X = pad(X)
# unconstrained linear regression
plsq = leastsq(residuals, p0, args=(y,X))
# linear regression constrained to having coefficients sum
# to one, so that the result is the optimal weighted average
cons = ({'type': 'eq', 'fun': lambda x: np.sum(x) -1})
constrained = minimize(sum_sq_res, p0, args=(y,X), constraints=cons,
method='SLSQP', options={'disp':True})
# plot results
unc_y = (X*plsq[0]).sum(axis=1)
con_y = (X*constrained.x).sum(axis=1)
