def test_get_dictionaries(self):
df = pd.DataFrame([['a', 'R1', 'b'], ['c', 'R2', 'd']],
columns=['from', 'rel', 'to'])
assert get_dictionaries(df, ent=True) == self.d1
assert get_dictionaries(df, ent=False) == self.d2
def __init__(
self,
df=None,
kg=None,
ent2ix=None,
rel2ix=None,
dict_of_heads=None,
dict_of_tails=None,
):
if df is None:
if kg is None:
raise WrongArgumentsError(
"Please provide at least one " "argument of `df` and kg`"
)
else:
try:
assert (
(type(kg) == dict)
& ("heads" in kg.keys())
& ("tails" in kg.keys())
& ("relations" in kg.keys())
)
except AssertionError:
raise WrongArgumentsError(
"Keys in the `kg` dict should "
"contain `heads`, `tails`, "
"`relations`."
)
try:
assert (rel2ix is not None) & (ent2ix is not None)
except AssertionError:
raise WrongArgumentsError(
"Please provide the two "
"dictionaries ent2ix and rel2ix "
"if building from `kg`."
)
else:
if kg is not None:
raise WrongArgumentsError(
"`df` and kg` arguments should not " "both be provided."
)
if ent2ix is None:
self.ent2ix = get_dictionaries(df, ent=True)
else:
self.ent2ix = ent2ix
if rel2ix is None:
self.rel2ix = get_dictionaries(df, ent=False)
else:
self.rel2ix = rel2ix
self.n_ent = max(self.ent2ix.values()) + 1
self.n_rel = max(self.rel2ix.values()) + 1
if df is not None:
# build kg from a pandas dataframe
self.n_facts = len(df)
self.head_idx = tensor(df["from"].map(self.ent2ix).values).long()
self.tail_idx = tensor(df["to"].map(self.ent2ix).values).long()
self.relations = tensor(df["rel"].map(self.rel2ix).values).long()
self.magnitudes = tensor(df["how-much"], dtype=float64)
else:
# build kg from another kg
self.n_facts = kg["heads"].shape[0]
self.head_idx = kg["heads"]
self.tail_idx = kg["tails"]
self.relations = kg["relations"]
self.magnitudes = kg["magnitudes"]
if dict_of_heads is None or dict_of_tails is None:
self.dict_of_heads = defaultdict(set)
self.dict_of_tails = defaultdict(set)
self.evaluate_dicts()
else:
self.dict_of_heads = dict_of_heads
self.dict_of_tails = dict_of_tails
try:
self.sanity_check()
except AssertionError:
raise SanityError("Please check the sanity of arguments.")
def __init__(self,
df=None,
kg=None,
ent2ix=None,
rel2ix=None,
dict_of_heads=None,
dict_of_tails=None,
dict_of_rel=None,
id2point=None,
geo=None):
if df is None:
if kg is None:
raise WrongArgumentsError("Please provide at least one "
"argument of `df` and kg`")
else:
try:
assert (type(kg) == dict) & ('heads' in kg.keys()) & \
('tails' in kg.keys()) & \
('relations' in kg.keys())
except AssertionError:
raise WrongArgumentsError("Keys in the `kg` dict should "
"contain `heads`, `tails`, "
"`relations`.")
try:
assert (rel2ix is not None) & (ent2ix is not None)
except AssertionError:
raise WrongArgumentsError("Please provide the two "
"dictionaries ent2ix and rel2ix "
"if building from `kg`.")
else:
if kg is not None:
raise WrongArgumentsError("`df` and kg` arguments should not "
"both be provided.")
if ent2ix is None:
self.ent2ix = get_dictionaries(df, ent=True)
else:
self.ent2ix = ent2ix
if rel2ix is None:
self.rel2ix = get_dictionaries(df, ent=False)
else:
self.rel2ix = rel2ix
if id2point is not None:
self.id2point = id2point
self.n_ent = max(self.ent2ix.values()) + 1
self.n_rel = max(self.rel2ix.values()) + 1
self.geo = geo
if df is not None:
# build kg from a pandas dataframe
self.n_facts = len(df)
self.head_idx = tensor(df['from'].map(self.ent2ix).values).long()
self.tail_idx = tensor(df['to'].map(self.ent2ix).values).long()
self.relations = tensor(df['rel'].map(self.rel2ix).values).long()
else:
# build kg from another kg
self.n_facts = kg['heads'].shape[0]
self.head_idx = kg['heads']
self.tail_idx = kg['tails']
self.relations = kg['relations']
try:
self.point = kg['point']
except:
pass
if (geo is not None) and (df is not None): # Geo
self.entity2point, self.id2point = self.load_point(geo)
self.point = np.array([[
self.entity2point[triplet[0]], self.entity2point[triplet[2]]
] for triplet in df.values])
if dict_of_heads is None or dict_of_tails is None or dict_of_rel is None:
self.dict_of_heads = defaultdict(set)
self.dict_of_tails = defaultdict(set)
self.dict_of_rel = defaultdict(set)
self.evaluate_dicts()
else:
self.dict_of_heads = dict_of_heads
self.dict_of_tails = dict_of_tails
self.dict_of_rel = dict_of_rel
try:
self.sanity_check()
except AssertionError:
raise SanityError("Please check the sanity of arguments.")
def __init__(self,
df=None,
kg=None,
ent2ix=None,
rel2ix=None,
dict_of_heads=None,
dict_of_tails=None):
if df is None:
if kg is None:
raise WrongArgumentsError("Please provide at least one "
"argument of `df` and kg`")
else:
try:
assert (type(kg) == dict) & ('heads' in kg.keys()) & \
('tails' in kg.keys()) & \
('relations' in kg.keys())
except AssertionError:
raise WrongArgumentsError("Keys in the `kg` dict should "
"contain `heads`, `tails`, "
"`relations`.")
try:
assert (rel2ix is not None) & (ent2ix is not None)
except AssertionError:
raise WrongArgumentsError("Please provide the two "
"dictionaries ent2ix and rel2ix "
"if building from `kg`.")
else:
if kg is not None:
raise WrongArgumentsError("`df` and kg` arguments should not "
"both be provided.")
if ent2ix is None:
self.ent2ix = get_dictionaries(df, ent=True)
else:
self.ent2ix = ent2ix
self.ix2ent = {v: k for k, v in self.ent2ix.items()}
if rel2ix is None:
self.rel2ix = get_dictionaries(df, ent=False)
else:
self.rel2ix = rel2ix
self.ix2rel = {v: k for k, v in self.rel2ix.items()}
self.n_ent = max(self.ent2ix.values()) + 1
self.n_rel = max(self.rel2ix.values()) + 1
if df is not None:
# build kg from a pandas dataframe
self.n_facts = len(df)
self.head_idx = tensor(df['from'].map(self.ent2ix).values).long()
self.tail_idx = tensor(df['to'].map(self.ent2ix).values).long()
self.relations = tensor(df['rel'].map(self.rel2ix).values).long()
else:
# build kg from another kg
self.n_facts = kg['heads'].shape[0]
self.head_idx = kg['heads']
self.tail_idx = kg['tails']
self.relations = kg['relations']
if dict_of_heads is None or dict_of_tails is None:
self.dict_of_heads = defaultdict(set)
self.dict_of_tails = defaultdict(set)
self.evaluate_dicts()
else:
self.dict_of_heads = dict_of_heads
self.dict_of_tails = dict_of_tails
try:
self.sanity_check()
except AssertionError:
raise SanityError("Please check the sanity of arguments.")