def from_db_format(key: str, val: list) -> 'MarkovNeighbor':
key = key
text = val[NeighborIdx.TEXT.value]
pos = Pos(val[NeighborIdx.POS.value])
compound = val[NeighborIdx.COMPOUND.value]
values = val[NeighborIdx.VALUE_MATRIX.value]
dist = val[NeighborIdx.DISTANCE_MATRIX.value]
return MarkovNeighbor(key, text, pos, compound, values, dist)
def from_token(token: Token) -> 'MarkovWord':
if CapitalizationMode.from_token(
token,
CAPITALIZATION_COMPOUND_RULES) == CapitalizationMode.COMPOUND:
compound = True
else:
compound = False
return MarkovWord(token.text,
Pos.from_token(token),
compound=compound,
neighbors={})
def from_token(token: Token) -> 'MarkovNeighbor':
key = token.text.lower()
text = token.text
if CapitalizationMode.from_token(token, CAPITALIZATION_COMPOUND_RULES) == CapitalizationMode.COMPOUND:
compound = True
else:
compound = False
pos = Pos.from_token(token)
values = [0, 0]
dist = [0] * (MARKOV_WINDOW_SIZE * 2 + 1)
return MarkovNeighbor(key, text, pos, compound, values, dist)
def from_token(token: Token) -> 'MarkovNeighbor':
key = token.text.lower()
text = token.text
if CapitalizationMode.from_token(token, CAPITALIZATION_COMPOUND_RULES) == CapitalizationMode.COMPOUND:
compound = True
else:
compound = False
pos = Pos.from_token(token)
values = [0, 0]
dist = [0] * (MARKOV_WINDOW_SIZE * 2 + 1)
return MarkovNeighbor(key, text, pos, compound, values, dist)
def from_db_format(row: dict) -> 'MarkovWord':
word = MarkovWord(row[MarkovTrieDb.WORD_KEY][WordKey.TEXT],
Pos(row[MarkovTrieDb.WORD_KEY][WordKey.POS]),
row[MarkovTrieDb.WORD_KEY][WordKey.COMPOUND],
row[MarkovTrieDb.NEIGHBORS_KEY])
return word
def from_token(token: Token) -> 'MarkovWord':
if CapitalizationMode.from_token(token, CAPITALIZATION_COMPOUND_RULES) == CapitalizationMode.COMPOUND:
compound = True
else:
compound = False
return MarkovWord(token.text, Pos.from_token(token), compound=compound, neighbors={})
def analyze(token: Token, mode: CapitalizationMode):
pos = Pos.from_token(token)
mode = PoSCapitalizationMode(pos, mode)
return mode.to_embedding()
def from_embedding(embedding: int):
pos_part = int(embedding / len(CapitalizationMode))
mode_part = int(embedding % len(CapitalizationMode))
return PoSCapitalizationMode(Pos(pos_part), CapitalizationMode(mode_part))
def analyze(token: Token, mode: CapitalizationMode):
pos = Pos.from_token(token)
mode = PoSCapitalizationMode(pos, mode)
return mode.to_embedding()
