def read_vectors(infile):
_, word_vectors0, _ = load_saved_params(infile)
num_words = word_vectors0.shape[0] / 2
print "loaded vectors for %d words" % num_words
word_vectors = (word_vectors0[:num_words,:] + word_vectors0[num_words:,:])
#dim_vectors = word_vectors.shape[1]
return word_vectors
word_vectors, params, postprocessing=normalize_rows, use_saved=True, print_every=100, save_params_every=5000)
# sanity check: cost at convergence should be around or below 10
# sum the input and output word vectors
word_vectors = (word_vectors0[:num_words,:] + word_vectors0[num_words:,:])
print "\n=== For autograder ==="
check_words = ["the", "a", "an", "movie", "ordinary", "but", "and"]
check_idx = [tokens[word] for word in check_words]
check_vecs = word_vectors[check_idx, :]
print check_vecs
# Visualize the word vectors you trained
_, word_vectors0, _ = load_saved_params()
word_vectors = (word_vectors0[:num_words,:] + word_vectors0[num_words:,:])
visualize_words = ["the", "a", "an", "good", "great", "cool", "brilliant", "wonderful", "well", "amazing", "worth", "sweet", "enjoyable", "boring", "bad", "waste", "dumb", "annoying", "london", "england", "york", "yorker", "winter", "car", "automatically"]
visualize_idx = [tokens[word] for word in visualize_words]
visualize_vecs = word_vectors[visualize_idx, :]
temp = (visualize_vecs - np.mean(visualize_vecs, axis=0))
covariance = 1.0 / len(visualize_idx) * temp.T.dot(temp)
U, S, V = np.linalg.svd(covariance)
coord = temp.dot(U[:,0:2])
print "SVD coordinates"
for i in xrange(len(visualize_words)):
plt.text(coord[i,0], coord[i,1], visualize_words[i], bbox=dict(facecolor='green', alpha=0.1))
plt.xlim((np.min(coord[:,0]), np.max(coord[:,0])))
plt.ylim((np.min(coord[:,1]), np.max(coord[:,1])))
def main(args):
""" Train a model to do sentiment analyis"""
# Load the dataset
dataset = StanfordSentiment()
tokens = dataset.tokens()
nWords = len(tokens)
if args.yourvectors:
_, wordVectors, _ = load_saved_params()
wordVectors = np.concatenate(
(wordVectors[:nWords,:], wordVectors[nWords:,:]),
axis=1)
elif args.pretrained:
wordVectors = glove.loadWordVectors(tokens)
dimVectors = wordVectors.shape[1]
# Load the train set
trainset = dataset.getTrainSentences()
nTrain = len(trainset)
trainFeatures = np.zeros((nTrain, dimVectors))
trainLabels = np.zeros((nTrain,), dtype=np.int32)
for i in xrange(nTrain):
words, trainLabels[i] = trainset[i]
trainFeatures[i, :] = getSentenceFeatures(tokens, wordVectors, words)
# Prepare dev set features
devset = dataset.getDevSentences()
nDev = len(devset)
devFeatures = np.zeros((nDev, dimVectors))
devLabels = np.zeros((nDev,), dtype=np.int32)
for i in xrange(nDev):
words, devLabels[i] = devset[i]
devFeatures[i, :] = getSentenceFeatures(tokens, wordVectors, words)
# Prepare test set features
testset = dataset.getTestSentences()
nTest = len(testset)
testFeatures = np.zeros((nTest, dimVectors))
testLabels = np.zeros((nTest,), dtype=np.int32)
for i in xrange(nTest):
words, testLabels[i] = testset[i]
testFeatures[i, :] = getSentenceFeatures(tokens, wordVectors, words)
# We will save our results from each run
results = []
regValues = getRegularizationValues()
for reg in regValues:
print "Training for reg=%f" % reg
# Note: add a very small number to regularization to please the library
clf = LogisticRegression(C=1.0/(reg + 1e-12))
clf.fit(trainFeatures, trainLabels)
# Test on train set
pred = clf.predict(trainFeatures)
trainAccuracy = accuracy(trainLabels, pred)
print "Train accuracy (%%): %f" % trainAccuracy
# Test on dev set
pred = clf.predict(devFeatures)
devAccuracy = accuracy(devLabels, pred)
print "Dev accuracy (%%): %f" % devAccuracy
# Test on test set
# Note: always running on test is poor style. Typically, you should
# do this only after validation.
pred = clf.predict(testFeatures)
testAccuracy = accuracy(testLabels, pred)
print "Test accuracy (%%): %f" % testAccuracy
results.append({
"reg": reg,
"clf": clf,
"train": trainAccuracy,
"dev": devAccuracy,
"test": testAccuracy})
# Print the accuracies
print ""
print "=== Recap ==="
print "Reg\t\tTrain\tDev\tTest"
for result in results:
print "%.2E\t%.3f\t%.3f\t%.3f" % (
result["reg"],
result["train"],
result["dev"],
result["test"])
print ""
bestResult = chooseBestModel(results)
print "Best regularization value: %0.2E" % bestResult["reg"]
print "Test accuracy (%%): %f" % bestResult["test"]
# do some error analysis
if args.pretrained:
plotRegVsAccuracy(regValues, results, "q4_reg_v_acc.png")
outputConfusionMatrix(devFeatures, devLabels, bestResult["clf"],
"q4_dev_conf.png")
outputPredictions(devset, devFeatures, devLabels, bestResult["clf"],
"q4_dev_pred.txt")
