from sklearn.preprocessing import LabelEncoder
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, confusion_matrix
if __name__ == "__main__":
here = os.path.dirname(os.path.abspath(__file__))
from d3mds import D3MDataset, D3MProblem, D3MDS
dspath = os.path.join(here, '..', '..', 'LL0_acled_dataset')
prpath = os.path.join(here, '..', '..', 'LL0_acled_problem')
assert os.path.exists(dspath)
assert os.path.exists(prpath)
d3mds = D3MDS(
dspath, prpath) # this checks that the problem and dataset correspond
print('\nLoading train and test data')
X_train = d3mds.get_train_data()
y_train = d3mds.get_train_targets().ravel()
print('X_train shape:', X_train.shape)
print('y_train shape:', y_train.shape)
X_test = d3mds.get_test_data()
y_test = d3mds.get_test_targets().ravel()
print('X_test shape:', X_test.shape)
print('y_test shape:', y_test.shape)
X_train = X_train[['notes']]
X_test = X_test[['notes']]
here = os.path.dirname(os.path.abspath(__file__))
from d3mds import D3MDataset, D3MProblem, D3MDS
from feat import AnnotatedTabularExtractor
from estimation import SGDClassifierEstimator, SGDRegressorEstimator, RBFSamplerSGDClassifierEstimator, RBFSamplerSGDRegressorEstimator
dspath = os.path.join(here, '..', '..', 'LL0_uci_las_vegas_strip_dataset')
prpath = os.path.join(here, '..', '..', 'LL0_uci_las_vegas_strip_problem')
solpath = os.path.join(here, '..')
assert os.path.exists(dspath)
assert os.path.exists(prpath)
N_ITER = 100 # Number of parameter settings that are sampled in RandomizedSearchCV. n_iter trades off runtime vs quality of the solution.
d3mds = D3MDS(
dspath,
prpath) # create the D3MDS object from the dataset and problem paths
class Spinner:
busy = False
delay = 0.1
@staticmethod
def spinning_cursor():
while 1:
for cursor in '|/-\\':
yield cursor
def __init__(self, delay=None):
self.spinner_generator = self.spinning_cursor()