def __init__(self, model_path):
# Load model
with open(model_path + '.model', 'rb') as fid:
self.clf = pickle.load(fid)
with open(model_path + '.dict', 'rb') as fid:
self.vec = pickle.load(fid)
self.feat_obj = FeaturesWrapper()
def predict(X, clf, vec, feat_obj=None, prob=False):
# Data -> features
if feat_obj == None:
feat_obj = FeaturesWrapper()
feats = feat_obj.extract_features(X)
if prob:
return predict_probs_vectorized(feats, clf, vec)
else:
return predict_vectorized(feats, clf, vec)
def main():
parser = argparse.ArgumentParser()
parser.add_argument("-t",
dest="txt",
help="The files that contain the training examples",
default=os.path.join(BASE_DIR, 'data/annotated.txt'))
parser.add_argument("-n",
dest="length",
help="Number of data points to use",
default=-1)
parser.add_argument("-f",
dest="folds",
help="Number of folds to partition data into",
default=10)
parser.add_argument("-r",
dest="random",
help="Random shuffling of input data.",
action='store_true',
default=False)
# Parse the command line arguments
args = parser.parse_args()
# Decode arguments
txt_files = glob.glob(args.txt)
length = int(args.length)
num_folds = int(args.folds)
# Get data from files
if not txt_files:
print 'no training files :('
sys.exit(1)
notes = []
for txt in txt_files:
note_tmp = Note()
note_tmp.read(txt)
notes.append(note_tmp)
# List of all data
X = []
Y = []
for n in notes:
# Data points
x = [it for it in zip(n.sid_list(), n.text_list())]
X += x
# Labels
y = [it for it in n.label_list()]
Y += y
# Limit length
X = X[:length]
Y = Y[:length]
# Build confusion matrix
confusion = [[0 for i in labels_map] for j in labels_map]
# Instantiate feat obj once (it'd really slow down CV to rebuild every time)
feat_obj = FeaturesWrapper()
# Extract features once
feats = train.extract_features(X, feat_obj)
data = zip(feats, Y)
# For each held-out test set
i = 1
for training, testing in cv_partitions(data[:length],
num_folds=num_folds,
shuffle=args.random):
# Users like to see progress
print 'Fold: %d of %d' % (i, num_folds)
i += 1
# Train on non-heldout data
X_train = [d[0] for d in training]
Y_train = [d[1] for d in training]
vec, clf = train.train_vectorized(X_train,
Y_train,
model_path=None,
grid=False)
# Predict on held out
X_test = [d[0] for d in testing]
Y_test = [d[1] for d in testing]
labels = predict.predict_vectorized(X_test, clf, vec)
# Compute confusion matrix for held_out data
testing_confusion = evaluate.create_confusion(labels, Y_test)
confusion = add_matrix(confusion, testing_confusion)
# Evaluate
evaluate.display_confusion(confusion)
def extract_features(X, feat_obj=None):
# Data -> features
if feat_obj == None:
feat_obj = FeaturesWrapper()
feats = feat_obj.extract_features(X)
return feats
