Add more arguments to the regression tools

Author: briling

qstack/regression/final_error.py

@@ -5,22 +5,34 @@
 from qstack.regression.kernel_utils import get_kernel, defaults
 from qstack.tools import correct_num_threads
 
-def final_error(X, y, sigma=defaults.sigma, eta=defaults.eta, akernel=defaults.kernel, test_size=defaults.test_size, save_alpha=None):
+def final_error(X, y, read_kernel=False, sigma=defaults.sigma, eta=defaults.eta, akernel=defaults.kernel,
+                test_size=defaults.test_size,
+                random_state=defaults.random_state,
+                return_pred=False, save_alpha=None):
     """
 
     .. todo::
         Write the docstring
     """
-    kernel = get_kernel(akernel)
-    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=0)
-    K_all  = kernel(X_train, X_train, 1.0/sigma)
-    Ks_all = kernel(X_test,  X_train, 1.0/sigma)
+    if read_kernel is False:
+        kernel = get_kernel(akernel)
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=random_state)
+        K_all  = kernel(X_train, X_train, 1.0/sigma)
+        Ks_all = kernel(X_test,  X_train, 1.0/sigma)
+    else:
+        idx_train, idx_test, y_train, y_test = train_test_split(np.arange(len(y)), y, test_size=test_size, random_state=random_state)
+        K_all  = X[np.ix_(idx_train,idx_train)]
+        Ks_all = X[np.ix_(idx_test, idx_train)]
     K_all[np.diag_indices_from(K_all)] += eta
     alpha = scipy.linalg.solve(K_all, y_train, assume_a='pos')
     y_kf_predict = np.dot(Ks_all, alpha)
     aes = np.abs(y_test-y_kf_predict)
-    if save_alpha: np.save(save_alpha, alpha)
-    return aes
+    if save_alpha:
+        np.save(save_alpha, alpha)
+    if return_pred:
+        return aes, y_kf_predict
+    else:
+        return aes
 
 def main():
     import sys
@@ -34,12 +46,13 @@ def main():
     parser.add_argument('--kernel',     type=str,   dest='kernel',      default=defaults.kernel,    help='kernel type (G for Gaussian, L for Laplacian, myL for Laplacian for open-shell systems) (default '+defaults.kernel+')')
     parser.add_argument('--save-alpha', type=str,   dest='save_alpha',  default=None,               help='file to write the regression coefficients to (default None)')
     parser.add_argument('--ll',     action='store_true', dest='ll',     default=False,              help='if correct for the numper of threads')
+    parser.add_argument('--random_state',  type=int, dest='random_state', default=defaults.random_state,  help='random state for test / train splitting')
     args = parser.parse_args()
     print(vars(args))
     if(args.ll): correct_num_threads()
     X = np.load(args.repr)
     y = np.loadtxt(args.prop)
-    aes = final_error(X, y, sigma=args.sigma, eta=args.eta, akernel=args.kernel, test_size=args.test_size, save_alpha=args.save_alpha)
+    aes = final_error(X, y, sigma=args.sigma, eta=args.eta, akernel=args.kernel, test_size=args.test_size, save_alpha=args.save_alpha, random_state=random_state)
     np.savetxt(sys.stdout, aes, fmt='%e')
 
 if __name__ == "__main__":

qstack/regression/kernel_utils.py

@@ -30,7 +30,8 @@ def __call__(self, parser, namespace, values, option_string=None):
   train_size=[0.125, 0.25, 0.5, 0.75, 1.0],
   etaarr=list(numpy.logspace(-10, 0, 5)),
   sigmaarr=list(numpy.logspace(0,6, 13)),
-  sigmaarr_mult=list(numpy.logspace(0,2, 5))
+  sigmaarr_mult=list(numpy.logspace(0,2, 5)),
+  random_state=0,
   )
 
 

qstack/regression/regression.py

@@ -11,6 +11,7 @@
 def regression(X, y, read_kernel=False, sigma=defaults.sigma, eta=defaults.eta,
                akernel=defaults.kernel, gkernel=defaults.gkernel, gdict=defaults.gdict,
                test_size=defaults.test_size, train_size=defaults.train_size, n_rep=defaults.n_rep,
+               random_state=defaults.random_state,
                sparse=None, debug=False):
     """
 
@@ -19,11 +20,11 @@ def regression(X, y, read_kernel=False, sigma=defaults.sigma, eta=defaults.eta,
     """
     if read_kernel is False:
         kernel = get_kernel(akernel, [gkernel, gdict])
-        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=0)
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=random_state)
         K_all  = kernel(X_train, X_train, 1.0/sigma)
         Ks_all = kernel(X_test,  X_train, 1.0/sigma)
     else:
-        idx_train, idx_test, y_train, y_test = train_test_split(np.arange(len(y)), y, test_size=test_size, random_state=0)
+        idx_train, idx_test, y_train, y_test = train_test_split(np.arange(len(y)), y, test_size=test_size, random_state=random_state)
         K_all  = X[np.ix_(idx_train,idx_train)]
         Ks_all = X[np.ix_(idx_test, idx_train)]
 
@@ -68,20 +69,21 @@ def regression(X, y, read_kernel=False, sigma=defaults.sigma, eta=defaults.eta,
 def main():
     import argparse
     parser = argparse.ArgumentParser(description='This program computes the learning curve.')
-    parser.add_argument('--x',          type=str,   dest='repr',       required=True, help='path to the representations file')
-    parser.add_argument('--y',          type=str,   dest='prop',       required=True, help='path to the properties file')
-    parser.add_argument('--test',       type=float, dest='test_size',  default=defaults.test_size, help='test set fraction (default='+str(defaults.test_size)+')')
-    parser.add_argument('--eta',        type=float, dest='eta',        default=defaults.eta,       help='eta hyperparameter (default='+str(defaults.eta)+')')
-    parser.add_argument('--sigma',      type=float, dest='sigma',      default=defaults.sigma,     help='sigma hyperparameter (default='+str(defaults.sigma)+')')
-    parser.add_argument('--akernel',     type=str,   dest='akernel',     default=defaults.kernel,    help='local kernel type (G for Gaussian, L for Laplacian, myL for Laplacian for open-shell systems) (default '+defaults.kernel+')')
-    parser.add_argument('--gkernel',     type=str,   dest='gkernel',     default=defaults.gkernel,    help='global kernel type (avg for average kernel, rem for REMatch kernel) (default '+str(defaults.gkernel)+')')
-    parser.add_argument('--gdict',     nargs='*',   action=ParseKwargs, dest='gdict',     default=defaults.gdict,    help='dictionary like input string to initialize global kernel parameters')
-    parser.add_argument('--splits',     type=int,   dest='splits',     default=defaults.n_rep,     help='number of splits (default='+str(defaults.n_rep)+')')
-    parser.add_argument('--train',      type=float, dest='train_size', default=defaults.train_size, nargs='+', help='training set fractions')
-    parser.add_argument('--debug',      action='store_true', dest='debug', default=False,  help='enable debug')
-    parser.add_argument('--ll',         action='store_true', dest='ll',    default=False,  help='if correct for the numper of threads')
-    parser.add_argument('--readkernel', action='store_true', dest='readk', default=False,  help='if X is kernel')
-    parser.add_argument('--sparse',     type=int, dest='sparse', default=None,  help='regression basis size for sparse learning')
+    parser.add_argument('--x',             type=str,   dest='repr',       required=True, help='path to the representations file')
+    parser.add_argument('--y',             type=str,   dest='prop',       required=True, help='path to the properties file')
+    parser.add_argument('--test',          type=float, dest='test_size',  default=defaults.test_size, help='test set fraction (default='+str(defaults.test_size)+')')
+    parser.add_argument('--eta',           type=float, dest='eta',        default=defaults.eta,       help='eta hyperparameter (default='+str(defaults.eta)+')')
+    parser.add_argument('--sigma',         type=float, dest='sigma',      default=defaults.sigma,     help='sigma hyperparameter (default='+str(defaults.sigma)+')')
+    parser.add_argument('--akernel',       type=str,   dest='akernel',     default=defaults.kernel,    help='local kernel type (G for Gaussian, L for Laplacian, myL for Laplacian for open-shell systems) (default '+defaults.kernel+')')
+    parser.add_argument('--gkernel',       type=str,   dest='gkernel',     default=defaults.gkernel,    help='global kernel type (avg for average kernel, rem for REMatch kernel) (default '+str(defaults.gkernel)+')')
+    parser.add_argument('--gdict',         nargs='*',   action=ParseKwargs, dest='gdict',     default=defaults.gdict,    help='dictionary like input string to initialize global kernel parameters')
+    parser.add_argument('--splits',        type=int,   dest='splits',     default=defaults.n_rep,     help='number of splits (default='+str(defaults.n_rep)+')')
+    parser.add_argument('--train',         type=float, dest='train_size', default=defaults.train_size, nargs='+', help='training set fractions')
+    parser.add_argument('--debug',         action='store_true', dest='debug', default=False,  help='enable debug')
+    parser.add_argument('--ll',            action='store_true', dest='ll',    default=False,  help='if correct for the numper of threads')
+    parser.add_argument('--readkernel',    action='store_true', dest='readk', default=False,  help='if X is kernel')
+    parser.add_argument('--sparse',        type=int, dest='sparse', default=None,  help='regression basis size for sparse learning')
+    parser.add_argument('--random_state',  type=int, dest='random_state', default=defaults.random_state,  help='random state for test / train splitting')
     args = parser.parse_args()
     print(vars(args))
     if(args.ll): correct_num_threads()