def transform_one(self, obs, target, id):
df = self.dfTrain[self.dfTrain["search_term"] == obs].copy()
val_list = [config.MISSING_VALUE_NUMERIC]
if df is not None:
df = df[df["id"] != id].copy()
df = df[df["relevance"] == self.relevance].copy()
if df is not None and df.shape[0] > 0:
target_tokens = nlp_utils._tokenize(target, token_pattern)
target_ngrams = ngram_utils._ngrams(target_tokens, self.ngram)
val_list = []
for x in df[self.target_field]:
x_tokens = nlp_utils._tokenize(x, token_pattern)
x_ngrams = ngram_utils._ngrams(x_tokens, self.ngram)
val_list.append(dist_utils._jaccard_coef(x_ngrams, target_ngrams))
return val_list
def transform_one(self, obs, target, id):
df = self.dfTrain[self.dfTrain["search_term"] == obs].copy()
val_list = [config.MISSING_VALUE_NUMERIC]
if df is not None:
df = df[df["id"] != id].copy()
df = df[df["relevance"] == self.relevance].copy()
if df is not None and df.shape[0] > 0:
target_tokens = nlp_utils._tokenize(target, token_pattern)
target_ngrams = ngram_utils._ngrams(target_tokens, self.ngram)
val_list = []
for x in df[self.target_field]:
x_tokens = nlp_utils._tokenize(x, token_pattern)
x_ngrams = ngram_utils._ngrams(x_tokens, self.ngram)
val_list.append(
dist_utils._jaccard_coef(x_ngrams, target_ngrams))
return val_list
def transform_one(self, obs, target, id):
obs_tokens = nlp_utils._tokenize(obs, token_pattern)
target_tokens = nlp_utils._tokenize(target, token_pattern)
obs_ngrams = ngram_utils._ngrams(obs_tokens, self.ngram)
target_ngrams = ngram_utils._ngrams(target_tokens, self.ngram)
return dist_utils._jaccard_coef(obs_ngrams, target_ngrams)
def transform_one(self, obs, target, id):
obs_tokens = nlp_utils._tokenize(obs, token_pattern)
target_tokens = nlp_utils._tokenize(target, token_pattern)
obs_ngrams = ngram_utils._ngrams(obs_tokens, self.ngram)
target_ngrams = ngram_utils._ngrams(target_tokens, self.ngram)
return dist_utils._jaccard_coef(obs_ngrams, target_ngrams)
def distance(self, obs_ngrams, target_ngrams):
return dist_utils._jaccard_coef(obs_ngrams, target_ngrams)
