Y_val_pred = self.clf.predict(X_features_val)
self.evaluatorInstance = Evaluator()
a = self.evaluatorInstance.getAccuracy(Y_val_true, Y_val_pred)
p, r, f = self.evaluatorInstance.getPRF(Y_val_true, Y_val_pred)
print("Accuracy: " + str(a))
print("Precision: " + str(p))
print("Recall: " + str(r))
print("F-measure: " + str(f))
if __name__ == '__main__':
trainFilePath = sys.argv[
1] #please give the path to your reformatted quasar-s json train file
valFilePath = sys.argv[2] # provide the path to val file
retrievalInstance = Retrieval()
featurizerInstance = [
TfIdfFeaturizer(),
CountFeaturizer(),
HashVectorizer()
]
classifierInstance = [
NNClassifier(),
SVMClassifier(),
MultinomialNaiveBayes()
]
for feature in featurizerInstance:
for classifier in classifierInstance:
trainInstance = Pipeline(trainFilePath, valFilePath,
retrievalInstance, feature, classifier)
def get(self, query_string):
retrival = Retrieval()
return retrival.query(query_string)
#if __name__ == '__main__':
# from quasar_pipeline import *
#trainFilePath = sys.argv[1] #please give the path to your reformatted quasar-s json train file
#valFilePath = sys.argv[2] # provide the path to val file
#a = json.load(open('data/msmarco_train_formatted.json'))
#a['questions'][0].keys()
train_path = 'data/quasar-s_train_formatted.json'
val_path = 'data/quasar-s_dev_formatted.json'
for N in [5000, 7000, 10000]:
print ('N = ' + str(N))
print()
p = Pipeline(train_path, val_path, Retrieval(), CountFeaturizer(), MultinomialNaiveBayes())
print('Count MNB')
p.qa()
p.classifierInstance = SVM()
print()
print('Count SVM')
p.qa()
p.classifierInstance = Perceptron()
print()
print('Count perceptron')
p.qa()
p.classifierInstance = MultinomialNaiveBayes()