words, valence = np.array(words), np.array(valence)
words_pos, valence_pos = words[valence > np.average(valence)], valence[
valence > np.average(valence)] # avg = 5.1511713456
words_neg, valence_neg = words[valence < np.average(valence)], valence[
valence < np.average(valence)] # avg = 5.1511713456
pos = avg_valence(texts, words_pos, valence_pos)
neg = avg_valence(texts, words_neg, valence_neg)
from visualization import draw_scatter_with_color
draw_scatter_with_color(pos, neg, labels, 'pos', 'neg')
# classify
polarity = []
for pos_score, neg_score in zip(pos, neg):
if pos_score == -1:
polarity.append(0)
elif neg_score == -1:
polarity.append(1)
else:
if pos_score > neg_score:
polarity.append(1)
else:
polarity.append(0)
from analysis import analysis_result
print(labels)
print(polarity)
analysis_result(labels, polarity)
__author__ = "hs"
__author__ = "hs"
__author__ = "NLP-PC"
import feature_generating
import classifiers
import analysis
from load_data import load_train_data, load_processed_data
from load_data import load_test_data
from save_data import dump_picle
from vectorizers import TFIDF_estimator, anew_estimator
from analysis import analysis_result
from classifiers import mNB
from load_data import load_selected_data
print("Start")
vectorizer = TFIDF_estimator()
texts, train_labels = load_selected_data(data_type="train")
transformed_train = vectorizer.fit_transform(texts)
testdata, true_labels = load_selected_data(data_type="test")
transformed_test = vectorizer.transform(testdata)
predict = mNB(transformed_train, train_labels, transformed_test)
analysis_result(predict, true_labels)
words, valence = np.array(words), np.array(valence)
words_pos, valence_pos = words[valence > np.average(valence)], valence[
valence > np.average(valence)] # avg = 5.1511713456
words_neg, valence_neg = words[valence < np.average(valence)], valence[
valence < np.average(valence)] # avg = 5.1511713456
pos = avg_valence(texts, words_pos, valence_pos)
neg = avg_valence(texts, words_neg, valence_neg)
from visualization import draw_scatter_with_color
draw_scatter_with_color(pos, neg, labels, 'pos', 'neg')
# classify
polarity = []
for pos_score, neg_score in zip(pos, neg):
if pos_score == -1:
polarity.append(0)
elif neg_score == -1:
polarity.append(1)
else:
if pos_score > neg_score:
polarity.append(1)
else:
polarity.append(0)
from analysis import analysis_result
print(labels)
print(polarity)
analysis_result(labels, polarity)
if count != 0:
vec /= count
return vec
from sklearn.preprocessing import scale
train_vecs = np.concatenate([buildWordVector(z, n_dim) for z in x_train])
if scaling == True:
train_vecs = scale(train_vecs)
# Train word2vec on test tweets
# imdb_w2v.train(x_test)
# Build test tweet vectors then scale
test_vecs = np.concatenate([buildWordVector(z, n_dim) for z in x_test])
if scaling == True:
test_vecs = scale(test_vecs)
# scaling to [0, 1] interval
min_max_scaler = MinMaxScaler()
train_vecs = min_max_scaler.fit_transform(train_vecs)
test_vecs = min_max_scaler.fit_transform(test_vecs)
# Use classification algorithm (i.e. Stochastic Logistic Regression) on training set, then assess model performance on test set
from classifiers import gNB, mNB
from analysis import analysis_result
pre = mNB(train_vecs, y_train, test_vecs)
analysis_result(pre, y_test)
if count != 0:
vec /= count
return vec
from sklearn.preprocessing import scale
train_vecs = np.concatenate([buildWordVector(z, n_dim) for z in x_train])
if scaling == True:
train_vecs = scale(train_vecs)
# Train word2vec on test tweets
# imdb_w2v.train(x_test)
# Build test tweet vectors then scale
test_vecs = np.concatenate([buildWordVector(z, n_dim) for z in x_test])
if scaling == True:
test_vecs = scale(test_vecs)
# scaling to [0, 1] interval
min_max_scaler = MinMaxScaler()
train_vecs = min_max_scaler.fit_transform(train_vecs)
test_vecs = min_max_scaler.fit_transform(test_vecs)
# Use classification algorithm (i.e. Stochastic Logistic Regression) on training set, then assess model performance on test set
from classifiers import gNB, mNB
from analysis import analysis_result
pre = mNB(train_vecs, y_train, test_vecs)
analysis_result(pre, y_test)
test_predict, outputs_, test_loss = sess.run([pred, outputs, loss],
feed_dict={
x_: test_xs,
y_: test_ys
})
loss_val = sess.run(loss, feed_dict={y_: test_ys, pred: test_predict})
print outputs_, 'outputs shape', np.shape(outputs_)
print("RMSE: {}".format(loss_val))
# print test_predict
raise KeyboardInterrupt
except KeyboardInterrupt as kbi:
print '#### result ###'
pred = test_predict * normalize_factor
test_ys = test_ys * normalize_factor
analysis.analysis_result(true=test_ys,
pred=pred,
error_range_percent=5)
test_ys = test_ys * (max_ - min_) + min_
utils.plot_xy(test_predict=test_predict,
test_ys=test_ys,
savename='./dynalog_result_last_' +
args.save_folder_name + '.png')
print '########'
print test_ys[:10]
print test_predict[:10]
sess.close()
print 'start evaluation'
eval.eval(x=test_xs,
y=test_ys,
error_range_percent=5,
model_path=os.path.join(
__author__ = 'hs'
__author__ = 'hs'
__author__ = 'NLP-PC'
import feature_generating
import classifiers
import analysis
from load_data import load_train_data, load_processed_data
from load_data import load_test_data
from save_data import dump_picle
from vectorizers import TFIDF_estimator, anew_estimator
from analysis import analysis_result
from classifiers import mNB
from load_data import load_selected_data
print('Start')
vectorizer = TFIDF_estimator()
texts, train_labels = load_selected_data(data_type='train')
transformed_train = vectorizer.fit_transform(texts)
testdata, true_labels = load_selected_data(data_type='test')
transformed_test = vectorizer.transform(testdata)
predict = mNB(transformed_train, train_labels, transformed_test)
analysis_result(predict, true_labels)
