from pyutils.ensemble_selection.Ensemble import Ensemble
from scipy.spatial.distance import hamming
print
print 'Reading data...'
Id_test, X_test = extract_testing_data(args.kaggle_root +
'/data/kaggle_test_tf_idf.csv')
print
print 'Loading ensemble...'
ensemble = joblib.load(args.ensemble_dir + '/ensemble.pkl')
if args.hill_predict:
print
print 'Ensemble hill predicting...'
Id_train, X_train, y_train = extract_training_data(
args.kaggle_root + '/data/kaggle_train_tf_idf.csv')
err = hamming(ensemble.hill_predict(X_train), y_train)
print '\tHill climbing error: {0}'.format(err)
print
print 'Predicting...'
pred = ensemble.predict(X_test)
with open(args.submission_fname, 'w') as f:
f.write('Id,Prediction\n')
for i, j in zip(Id_test.astype(int).tolist(), pred.tolist()):
f.write('{0},{1}\n'.format(i, j))
print '\tOutput written to {0}.'.format(args.submission_fname)
print
print 'Done.\n'
parser = argparse.ArgumentParser()
parser.add_argument('penalty',
help='L1 or L2 penalization.')
parser.add_argument('C',
help='Regularization parameter.')
parser.add_argument('fit_intercept',
help='Whether to include a constant bias term in the loss function.')
parser.add_argument('n_components_pca',
help='n_components for PCA.')
parser.add_argument('model_fname',
help='Absolute path to pickle the fitted CvModel.')
args = parser.parse_args()
n_components_pca = None if args.n_components_pca == 'None' else int(args.n_components_pca)
Id, X, y = extract_training_data('/nfs/raid13/babar/dchao/KaggleCS155/data/kaggle_train_tf_idf.csv')
# trans/clf specs
n_folds = 5
scaler = StandardScaler()
pca = PCA(n_components=n_components_pca, whiten=True)
trans = Pipeline([('scale_center', scaler),('pca', pca)]).fit(X)
clf = LogisticRegression(
penalty = args.penalty,
C = float(args.C),
fit_intercept = bool(args.fit_intercept),
class_weight = 'auto'
)
cv_clf = CvModel(n_folds, trans, clf)
cv_clf.fit(X, y)
import os
import re
from operator import itemgetter
from pyutils.kaggle_io.extract_inputs import extract_training_data
from pyutils.ensemble_selection.CvModel import CvModel
from sklearn.externals import joblib
from scipy.spatial.distance import hamming
model_dirs = []
with open(args.model_dirlist_fname, 'r') as f:
for line in f:
model_dirs.append(line.strip())
print 'Reading training data.\n'
Id, X, y = extract_training_data(args.kaggle_root + '/data/kaggle_train_tf_idf.csv')
print 'Scoring models.'
hillclimb_errs = []
prog, model_rootdir = re.compile('.*\.pkl$'), args.kaggle_root + '/models'
for m_dir in model_dirs:
dir_contents = os.listdir(model_rootdir + '/' + m_dir)
for fname in dir_contents:
try:
model_name = m_dir + '/' + prog.match(fname).group(0)
print '\t{0}'.format(model_name)
model = joblib.load(model_rootdir + '/' + model_name)
err = hamming(model.hill_predict(X), y)
hillclimb_errs.append((model_name, err))
except AttributeError:
