def setup_module():
global x_tr, y_tr, x_dv, y_dv, counts_tr, counts_dv, counts_bl, x_dv_pruned, x_tr_pruned
global vocab
y_tr, x_tr = preproc.read_data('../lyrics-train.csv', preprocessor=preproc.bag_of_words)
y_dv, x_dv = preproc.read_data('../lyrics-dev.csv', preprocessor=preproc.bag_of_words)
counts_tr = preproc.aggregate_counts(x_tr)
counts_dv = preproc.aggregate_counts(x_dv)
def setup_module():
global x_tr, y_tr, x_dv, y_dv, counts_tr, counts_dv, counts_bl, x_dv_pruned, x_tr_pruned
global vocab
y_tr,x_tr = preproc.read_data('lyrics-train.csv',preprocessor=preproc.bag_of_words)
y_dv,x_dv = preproc.read_data('lyrics-dev.csv',preprocessor=preproc.bag_of_words)
counts_tr = preproc.aggregate_counts(x_tr)
counts_dv = preproc.aggregate_counts(x_dv)
def setup_module():
global x_tr, y_tr, x_dv, y_dv, counts_tr, x_dv_pruned, x_tr_pruned
global labels
global vocab
global X_tr, X_tr_var, X_dv_var, Y_tr, Y_dv, Y_tr_var, Y_dv_var, Y_test_var
y_tr, x_tr = preproc.read_data('../lyrics-train.csv', preprocessor=preproc.bag_of_words)
labels = set(y_tr)
counts_tr = preproc.aggregate_counts(x_tr)
x_tr_pruned, vocab = preproc.prune_vocabulary(counts_tr, x_tr, 10)
X_tr = preproc.make_numpy(x_tr_pruned, vocab)
label_set = sorted(list(set(y_tr)))
Y_tr = np.array([label_set.index(y_i) for y_i in y_tr])
X_tr_var = Variable(torch.from_numpy(X_tr.astype(np.float32)))
Y_tr_var = Variable(torch.from_numpy(Y_tr))
y_dv, x_dv = preproc.read_data('../lyrics-dev.csv', preprocessor=preproc.bag_of_words)
x_dv_pruned, _ = preproc.prune_vocabulary(counts_tr, x_dv, 10)
# remove this, so people can run earlier tests
X_dv = preproc.make_numpy(x_dv_pruned, vocab)
Y_dv = np.array([label_set.index(y_i) for y_i in y_dv])
X_dv_var = Variable(torch.from_numpy(X_dv.astype(np.float32)))
Y_dv_var = Variable(torch.from_numpy(Y_dv))
def setup_module():
global x_tr, y_tr, x_dv, y_dv, counts_tr, x_dv_pruned, x_tr_pruned
global labels
global vocab
global X_tr, X_tr_var, X_dv_var, Y_tr, Y_dv, Y_tr_var, Y_dv_var
y_tr,x_tr = preproc.read_data('lyrics-train.csv',preprocessor=preproc.bag_of_words)
labels = set(y_tr)
counts_tr = preproc.aggregate_counts(x_tr)
y_dv,x_dv = preproc.read_data('lyrics-dev.csv',preprocessor=preproc.bag_of_words)
x_tr_pruned, vocab = preproc.prune_vocabulary(counts_tr, x_tr, 10)
x_dv_pruned, _ = preproc.prune_vocabulary(counts_tr, x_dv, 10)
## remove this, so people can run earlier tests
X_tr = preproc.make_numpy(x_tr_pruned,vocab)
X_dv = preproc.make_numpy(x_dv_pruned,vocab)
label_set = sorted(list(set(y_tr)))
Y_tr = np.array([label_set.index(y_i) for y_i in y_tr])
Y_dv = np.array([label_set.index(y_i) for y_i in y_dv])
X_tr_var = Variable(torch.from_numpy(X_tr.astype(np.float32)))
X_dv_var = Variable(torch.from_numpy(X_dv.astype(np.float32)))
Y_tr_var = Variable(torch.from_numpy(Y_tr))
Y_dv_var = Variable(torch.from_numpy(Y_dv))
def estimate_nb(x, y, smoothing):
"""estimate a naive bayes model
:param x: list of dictionaries of base feature counts
:param y: list of labels
:param smoothing: smoothing constant
:returns: a defaultdict of features and weights. features are tuples (label,base_feature).
:rtype: defaultdict
Hint: See clf_base.predict() for the exact return type information.
"""
new_x = []
for i in x:
new_x.append(Counter(i))
counts_tr = preproc.aggregate_counts(new_x)
vocab = [w for w, c in counts_tr.items()
if c >= 10] #calculating vocabulary again
len_v = len(vocab)
features = defaultdict(float)
y_lable = set(y)
for label in y_lable:
allcounts_label = get_corpus_counts(x, y, label)
for word in vocab:
features[(label, word)] = np.log(
(allcounts_label[word] + smoothing) /
(sum(list(allcounts_label.values())) + (smoothing * len_v)))
features[(label, OFFSET)] = np.log(len(list(y[label == y])) / len(y))
return features
def setup_module():
global vocab, label_set, x_tr_pruned, X_tr
y_tr,x_tr = preproc.read_data('lyrics-train.csv',preprocessor=preproc.bag_of_words)
labels = set(y_tr)
counts_tr = preproc.aggregate_counts(x_tr)
x_tr_pruned, vocab = preproc.prune_vocabulary(counts_tr, x_tr, 10)
X_tr = preproc.make_numpy(x_tr_pruned,vocab)
label_set = sorted(list(set(y_tr)))
def setup_module():
global vocab, label_set, x_tr_pruned, X_tr
y_tr, x_tr = preproc.read_data('lyrics-train.csv',
preprocessor=preproc.bag_of_words)
labels = set(y_tr)
counts_tr = preproc.aggregate_counts(x_tr)
x_tr_pruned, vocab = preproc.prune_vocabulary(counts_tr, x_tr, 10)
X_tr = preproc.make_numpy(x_tr_pruned, vocab)
label_set = sorted(list(set(y_tr)))
def setup_module():
#global y_tr, x_tr, corpus_counts, labels, vocab
#corpus_counts = get_corpus_counts(x_tr)
global x_tr, y_tr, x_dv, y_dv, counts_tr, x_dv_pruned, x_tr_pruned, x_bl_pruned
global labels
global vocab
y_tr,x_tr = preproc.read_data('lyrics-train.csv',preprocessor=preproc.bag_of_words)
labels = set(y_tr)
counts_tr = preproc.aggregate_counts(x_tr)
y_dv,x_dv = preproc.read_data('lyrics-dev.csv',preprocessor=preproc.bag_of_words)
x_tr_pruned, vocab = preproc.prune_vocabulary(counts_tr, x_tr, 10)
x_dv_pruned, _ = preproc.prune_vocabulary(counts_tr, x_dv, 10)
def setup_module():
#global y_tr, x_tr, corpus_counts, labels, vocab
#corpus_counts = get_corpus_counts(x_tr)
global x_tr, y_tr, x_dv, y_dv, counts_tr, x_dv_pruned, x_tr_pruned, x_bl_pruned
global labels
global vocab
y_tr,x_tr = preproc.read_data('lyrics-train.csv',preprocessor=preproc.bag_of_words)
labels = set(y_tr)
counts_tr = preproc.aggregate_counts(x_tr)
y_dv,x_dv = preproc.read_data('lyrics-dev.csv',preprocessor=preproc.bag_of_words)
x_tr_pruned, vocab = preproc.prune_vocabulary(counts_tr, x_tr, 10)
x_dv_pruned, _ = preproc.prune_vocabulary(counts_tr, x_dv, 10)
