def load_caches():
polarity.load_cached_polarity()
Sentence.load_cached_parses()
Sentence.load_cached_concepts()
def main():
polarity.load_cached_polarity()
original_read_input()
results = load_results(SAMPlE_DATA_PATH)
gold_samples = filter(lambda x: x["type"] == "manual_label" and x["food"] == foodName, results)
positve_examples = filter(lambda x: x["rating"] in (1, 2) , gold_samples)
negative_examples = filter(lambda x: x["rating"] in (-1, -2), gold_samples)
neutral_examples = filter(lambda x: x["rating"] == 0, gold_samples)
# for now, let's do the first 10 sentences
gold_samples = gold_samples[0:280]
for i in range(len(gold_samples)):
print str(i) + '/' + str(len(gold_samples))
gold_sample = gold_samples[i]
setup(gold_sample, i)
cArray = []
for i in range(-15,15):
cArray.append(math.pow(2,i))
gammaArray = []
for i in range(-5,0):
gammaArray.append(math.pow(10,i))
coeffArray = []
for i in range(-5,0):
coeffArray.append(math.pow(10,i))
# Set the parameters by cross-validation
tuned_parameters = [{'kernel': ['rbf'], 'gamma': gammaArray,
'C': cArray},
{'kernel': ['poly'], 'gamma' : gammaArray,
'C': cArray, 'coef0': coeffArray},
{'kernel': ['linear'], 'C': cArray}]
global x
#x = preprocessing.scale(x)
x[:,0] = 1
# negativeWeight = len(y) / float(len(filter(lambda x : x == -1, y)))
# zeroWeight = len(y) / float(len(filter(lambda x : x == 0, y)))
# positiveWeight = len(y) / float(len(filter(lambda x : x == 1, y)))
negativeWeight = 1
zeroWeight = 1
positiveWeight = 1
X_train, X_test, y_train, y_test = cross_validation.train_test_split(x, y, test_size=0.5, random_state=0)
clf = GridSearchCV(SVC(class_weight={-1: negativeWeight, 0: zeroWeight, 1:
positiveWeight}), tuned_parameters,
cv=5, scoring='f1',
n_jobs=16 )
clf.fit(X_train, y_train)
print("Best parameters set found on development set:")
print()
print(clf.best_estimator_)
print()
# print("Grid scores on development set:")
# print()
# for params, mean_score, scores in clf.grid_scores_:
# print("%0.3f (+/-%0.03f) for %r"
# % (mean_score, scores.std() / 2, params))
# print()
print("Detailed classification report:")
print()
print("The model is trained on the full development set.")
print("The scores are computed on the full evaluation set.")
print()
y_true, y_pred = y_test, clf.predict(X_test)
print(classification_report(y_true, y_pred))
print()
