def measure_bias(frame):
"""
Return a DataFrame that measures biases in a semantic space, on four
data sets:
- Gender
- Fine-grained ethnicity
- Coarse-grained ethnicity
- Religious beliefs
"""
vsw = VectorSpaceWrapper(frame=frame)
vsw.load()
gender_binary_axis = normalize_vec(
get_category_axis(frame, FEMALE_WORDS) -
get_category_axis(frame, MALE_WORDS))
gender_bias_numbers = []
for female_biased_word, male_biased_word in GENDER_BIAS_PAIRS:
female_biased_uri = standardized_uri('en', female_biased_word)
male_biased_uri = standardized_uri('en', male_biased_word)
diff = normalize_vec(
vsw.get_vector(female_biased_uri) -
vsw.get_vector(male_biased_uri)).dot(gender_binary_axis)
gender_bias_numbers.append(diff)
mean = np.mean(gender_bias_numbers)
sem = scipy.stats.sem(gender_bias_numbers)
gender_bias = pd.Series([mean, mean - sem * 2, mean + sem * 2],
index=['bias', 'low', 'high'])
stereotype_vecs_1 = get_vocabulary_vectors(frame, PEOPLE_BY_ETHNICITY)
stereotype_vecs_2 = get_vocabulary_vectors(frame, ETHNIC_STEREOTYPE_TERMS)
fine_ethnic_bias = correlation_bias(stereotype_vecs_1, stereotype_vecs_2)
stereotype_vecs_1 = get_vocabulary_vectors(frame, COARSE_ETHNICITY_TERMS)
stereotype_vecs_2 = get_vocabulary_vectors(frame, ETHNIC_STEREOTYPE_TERMS)
coarse_ethnic_bias = correlation_bias(stereotype_vecs_1, stereotype_vecs_2)
stereotype_vecs_1 = pd.DataFrame(
np.vstack(
[get_category_axis(frame, names) for names in ETHNIC_NAME_SETS]))
stereotype_vecs_2 = get_vocabulary_vectors(frame, ETHNIC_STEREOTYPE_TERMS)
name_ethnic_bias = correlation_bias(stereotype_vecs_1, stereotype_vecs_2)
stereotype_vecs_1 = get_vocabulary_vectors(frame, PEOPLE_BY_BELIEF)
stereotype_vecs_2 = get_vocabulary_vectors(frame, BELIEF_STEREOTYPE_TERMS)
belief_bias = correlation_bias(stereotype_vecs_1, stereotype_vecs_2)
return pd.DataFrame({
'gender': gender_bias,
'ethnicity-fine': fine_ethnic_bias,
'ethnicity-coarse': coarse_ethnic_bias,
'ethnicity-names': name_ethnic_bias,
'beliefs': belief_bias
}).T
def get_vector(self, query, oov_vector=True):
"""
Given one of the possible types of queries (see `similar_terms`), make
a vector to look up from it.
If there are 5 or fewer terms involved and `oov_vector=True`, this
will allow expanded_vector to use an out-of-vocab strategy to find missing
terms.
"""
self.load()
if isinstance(query, np.ndarray):
return query
elif isinstance(query, pd.Series) or isinstance(query, dict):
terms = list(query.items())
elif isinstance(query, pd.DataFrame):
terms = list(query.to_records())
elif isinstance(query, str):
terms = [(query, 1.)]
elif isinstance(query, list):
terms = query
else:
raise ValueError("Can't make a query out of type %s" % type(query))
cache_key = tuple(terms + [oov_vector])
if cache_key in self.cache:
return self.cache[cache_key]
oov_vector = oov_vector and (len(terms) <= 5)
vec = self.expanded_vector(terms, oov_vector=oov_vector)
self.cache[cache_key] = normalize_vec(vec)
return self.cache[cache_key]
def get_vector(self, query, include_neighbors=True):
"""
Given one of the possible types of queries (see `similar_terms`), make
a vector to look up from it.
If there are 5 or fewer terms involved and `include_neighbors=True`, this
will allow expanded_vector to look up neighboring terms in ConceptNet.
"""
self.load()
if isinstance(query, np.ndarray):
return query
elif isinstance(query, pd.Series) or isinstance(query, dict):
terms = list(query.items())
elif isinstance(query, pd.DataFrame):
terms = list(query.to_records())
elif isinstance(query, str):
terms = [(query, 1.)]
elif isinstance(query, list):
terms = query
else:
raise ValueError("Can't make a query out of type %s" % type(query))
cache_key = tuple(terms + [include_neighbors])
if cache_key in self.cache:
return self.cache[cache_key]
include_neighbors = include_neighbors and (len(terms) <= 5)
vec = self.expanded_vector(terms, include_neighbors=include_neighbors)
self.cache[cache_key] = normalize_vec(vec)
return self.cache[cache_key]
def get_vector(self, query, oov_vector=True):
"""
Given one of the possible types of queries (see `similar_terms`), make
a vector to look up from it.
If there are 5 or fewer terms involved and `oov_vector=True`, this
will allow expanded_vector to look up neighboring terms in ConceptNet.
"""
self.load()
if isinstance(query, np.ndarray):
return query
elif isinstance(query, pd.Series) or isinstance(query, dict):
terms = list(query.items())
elif isinstance(query, pd.DataFrame):
terms = list(query.to_records())
elif isinstance(query, str):
terms = [(query, 1.)]
elif isinstance(query, list):
terms = query
else:
raise ValueError("Can't make a query out of type %s" % type(query))
cache_key = tuple(terms + [oov_vector])
if cache_key in self.cache:
return self.cache[cache_key]
oov_vector = oov_vector and (len(terms) <= 5)
vec = self.expanded_vector(terms, oov_vector=oov_vector)
self.cache[cache_key] = normalize_vec(vec)
return self.cache[cache_key]
def get_weighted_vector(frame, weighted_terms):
"""
Given a list of (term, weight) pairs, get a unit vector corresponding
to the weighted average of those term vectors.
A simplified version of VectorSpaceWrapper.get_vector().
"""
total = frame.iloc[0] * 0.
for term, weight in weighted_terms:
if term in frame.index:
vec = frame.loc[term]
total += vec * weight
return normalize_vec(total)
def reject_subspace(frame, vecs):
"""
Return a modification of the vector space `frame` where none of
its rows have any correlation with any rows of `vecs`, by subtracting
the outer product of `frame` with each normalized row of `vecs`.
"""
current_array = frame.copy()
for vec in vecs:
vec = normalize_vec(vec)
projection = current_array.dot(vec)
current_array -= np.outer(projection, vec)
return l2_normalize_rows(current_array, offset=1e-9)
def get_weighted_vector(frame, weighted_terms):
"""
Given a list of (term, weight) pairs, get a unit vector corresponding
to the weighted average of those term vectors.
A simplified version of VectorSpaceWrapper.get_vector().
"""
total = frame.iloc[0] * 0.
for term, weight in weighted_terms:
if term in frame.index:
vec = frame.loc[term]
total += vec * weight
return normalize_vec(total)
def reject_subspace(frame, vecs):
"""
Return a modification of the vector space `frame` where none of
its rows have any correlation with any rows of `vecs`, by subtracting
the outer product of `frame` with each normalized row of `vecs`.
"""
current_array = frame.copy().values
for vec in vecs:
vec = normalize_vec(vec)
projection = current_array.dot(vec)
np.subtract(current_array, np.outer(projection, vec), out=current_array)
normalize(current_array, norm='l2', copy=False)
current_array = pd.DataFrame(current_array, index=frame.index)
current_array.fillna(0, inplace=True)
return current_array
def reject_subspace(frame, vecs):
"""
Return a modification of the vector space `frame` where none of
its rows have any correlation with any rows of `vecs`, by subtracting
the outer product of `frame` with each normalized row of `vecs`.
"""
current_array = frame.copy().values
for vec in vecs:
vec = normalize_vec(vec)
projection = current_array.dot(vec)
np.subtract(current_array, np.outer(projection, vec), out=current_array)
normalize(current_array, norm='l2', copy=False)
current_array = pd.DataFrame(current_array, index=frame.index)
current_array.fillna(0, inplace=True)
return current_array
def get_vector(self, query, include_neighbors=True):
"""
Given one of the possible types of queries (see `similar_terms`), make
a vector to look up from it.
If there are 5 or fewer terms involved and `include_neighbors=True`, this
will allow expanded_vector to look up neighboring terms in ConceptNet.
"""
self.load()
if isinstance(query, pd.DataFrame) or isinstance(query, dict):
terms = list(query.items())
elif isinstance(query, str):
terms = [(query, 1.0)]
elif isinstance(query, list):
terms = query
else:
raise ValueError("Can't make a query out of type %s" % type(query))
include_neighbors = include_neighbors and (len(terms) <= 5)
vec = self.expanded_vector(terms, include_neighbors=include_neighbors)
return normalize_vec(vec)
def get_vector(self, query, include_neighbors=True):
"""
Given one of the possible types of queries (see `similar_terms`), make
a vector to look up from it.
If there are 5 or fewer terms involved and `include_neighbors=True`, this
will allow expanded_vector to look up neighboring terms in ConceptNet.
"""
self.load()
# FIXME: is pd.DataFrame supposed to be pd.Series here?
if isinstance(query, pd.DataFrame) or isinstance(query, dict):
terms = list(query.items())
elif isinstance(query, str):
terms = [(query, 1.)]
elif isinstance(query, list):
terms = query
else:
raise ValueError("Can't make a query out of type %s" % type(query))
include_neighbors = include_neighbors and (len(terms) <= 5)
vec = self.expanded_vector(terms, include_neighbors=include_neighbors)
return normalize_vec(vec)
