def test_should_append_zero_if_unigram_is_not_present_in_text():
test_text = "Responsible for developing and implementing high level security features successfully. Led a team of 10 people and pushed a new enhancement in 4 weeks without any bugs"
unigram_list = ["responsible", "developed", "monitored", "solution", "java", "c++", "strong"]
unigram_feature = unigram_features(test_text, unigram_list)
eq_(0, unigram_feature[3])
eq_(0, unigram_feature[4])
eq_(0, unigram_feature[5])
eq_(0, unigram_feature[6])
def test_should_stem_words_and_create_feature_set():
test_text = "Responsible for developing and implementing high level security features successfully"
unigram_list = ["responsible", "develop", "implement", "success"]
unigram_feature = unigram_features(test_text, unigram_list)
expected_value = 1
eq_(expected_value, unigram_feature[0])
eq_(expected_value, unigram_feature[1])
eq_(expected_value, unigram_feature[2])
eq_(expected_value, unigram_feature[3])
def test_should_stem_words_and_create_feature_set():
test_text = "Responsible for developing and implementing high level security features successfully"
unigram_list = ['responsible', 'develop', 'implement', 'success']
unigram_feature = unigram_features(test_text, unigram_list)
expected_value = 1
eq_(expected_value, unigram_feature[0])
eq_(expected_value, unigram_feature[1])
eq_(expected_value, unigram_feature[2])
eq_(expected_value, unigram_feature[3])
def test_should_append_zero_if_unigram_is_not_present_in_text():
test_text = "Responsible for developing and implementing high level security features successfully. Led a team of 10 people and pushed a new enhancement in 4 weeks without any bugs"
unigram_list = [
'responsible', 'developed', 'monitored', 'solution', 'java', 'c++',
'strong'
]
unigram_feature = unigram_features(test_text, unigram_list)
eq_(0, unigram_feature[3])
eq_(0, unigram_feature[4])
eq_(0, unigram_feature[5])
eq_(0, unigram_feature[6])
def feature_consolidation(resume_text, top_unigram_list, top_bigram_list):
"""
Function to consolidate all the featuresets for the training data
Args:
top_unigram_list -- list of top unigrams from the training dataset
top_bigram_list -- list of top bigrams from the training dataset
Returns:
consolidated_features -- list of consolidated features
"""
uni_feats = [unigram_features(resume_text, top_unigram_list)]
bi_feats = [bigram_features(resume_text, top_bigram_list)]
consolidated_features = []
ind = 0
while ind < len(uni_feats):
consolidated_features.append(uni_feats[ind] + bi_feats[ind])
ind += 1
return consolidated_features
def feature_consolidation(resume_text, top_unigram_list, top_bigram_list):
"""
Function to consolidate all the featuresets for the training data
Args:
top_unigram_list -- list of top unigrams from the training dataset
top_bigram_list -- list of top bigrams from the training dataset
Returns:
consolidated_features -- list of consolidated features
"""
uni_feats = [unigram_features(resume_text, top_unigram_list)]
bi_feats = [bigram_features(resume_text, top_bigram_list)]
consolidated_features = []
ind = 0
while ind < len(uni_feats):
consolidated_features.append(uni_feats[ind] + bi_feats[ind])
ind += 1
return consolidated_features
def feature_consolidation(resumes, top_unigram_list, top_bigram_list, add_true_score=False):
"""
Function to consolidate all the featuresets for the training data
Args:
resumes -- list of tuples [(resume_text, tag, filename), (resume_text, tag, filename)...]
top_unigram_list -- list of top unigrams from the training dataset
top_bigram_list -- list of top bigrams from the training dataset
add_true_score -- boolean (default: False)
Returns:
consolidated_features -- list of consolidated features
"""
uni_feats = [unigram_features(resume_text, top_unigram_list) for (resume_text, label, fname) in resumes]
bi_feats = [bigram_features(resume_text, top_bigram_list) for (resume_text, label, fname) in resumes]
consolidated_features = []
ind = 0
while ind < len(uni_feats):
consolidated_features.append(uni_feats[ind] + bi_feats[ind])
ind += 1
return consolidated_features
def test_should_generate_unigrams_from_text_and_create_feature_set():
test_text = "Responsible for implementing high level security features successfully"
unigram_list = ["responsible", "developed", "monitored", "solution"]
unigram_feature = unigram_features(test_text, unigram_list)
expected_value = 4
eq_(expected_value, len(unigram_feature))
def test_should_generate_unigrams_from_text_and_create_feature_set():
test_text = "Responsible for implementing high level security features successfully"
unigram_list = ['responsible', 'developed', 'monitored', 'solution']
unigram_feature = unigram_features(test_text, unigram_list)
expected_value = 4
eq_(expected_value, len(unigram_feature))
