def log(info):
f = file('submission.txt', 'w+')
f.write(str(info))
f.close()
def submission(preds):
out = ""
for p in preds:
out += str(p) + "\n"
log(out)
data, targets = Data.data()
print "training data: ", len(data)
test = Data.test()
print "test data: ", len(test)
data = data + test
print "all data: ", len(data)
# preprocessing
start = time()
matrix = BlackboxPreprocess.to_matrix(data)
print matrix.shape
matrix = BlackboxPreprocess.scale(matrix)
#matrix = BlackboxPreprocess.polynomial(matrix, 2)
matrix = preprocessing.normalize(matrix, norm='l2')
min_max_scaler = preprocessing.MinMaxScaler(feature_range=(-1.,1.))
matrix = min_max_scaler.fit_transform(matrix)
#matrix = BlackboxPreprocess.norm(matrix)
print matrix.shape
from preprocess import Polynomial from abstract_model import ClassifierEnsemble from sklearn_wrapper import LinearRegressionModel, LogisticRegressionModel, SVCModel from score import score import logging """ This is supposed to be a sample interface for me to develop to support. """ objective = Objective.MAXIMIZE # data train_data, train_targets = Data.train() test_data, test_targets = Data.test() # feature engineering extra_data = test_data pipe = Pipeline(Polynomial, LogisticRegressionModel, objective, logging.WARN) pipe.fit(train_data, train_targets, extra_data) print pipe.hyperparams # train model train_data = pipe.transform(train_data) voter1 = LogisticRegressionModel(objective, logging.INFO) models = [m(objective, logging.INFO) for m in [SVCModel, LogisticRegressionModel]] ensemble = ClassifierEnsemble(models, voter1, objective, logging.INFO) voter2 = LogisticRegressionModel(objective, logging.INFO)
from data import Data
from blackbox_preprocess import BlackboxPreprocess
from sklearn.linear_model import LogisticRegression
data, targets = Data.data()
extra = Data.test()
data = data + extra
originals = data
# preprocessing
matrix = BlackboxPreprocess.to_matrix(data)
print "(examples, dimensions): ", matrix.shape
matrix = BlackboxPreprocess.scale(matrix)
matrix = BlackboxPreprocess.polynomial(matrix, 2)
print "(examples, dimensions): ", matrix.shape
data = matrix.tolist()
# split training and CV data
tr_data = data[:1000]
unlabeled = data[1000:]
# create psuedo labels
model = LogisticRegression(C=1.3, penalty='l1', tol=0.05)
print len(targets)
print targets[:10]
model.fit(tr_data, targets)
labeled = []
for i,u in enumerate(unlabeled):
orig = originals[i]