def __init__(self):
self.similarity_function = [
sm.BagDistance(),
sm.Cosine(),
sm.Dice(),
sm.Editex(),
sm.GeneralizedJaccard(),
sm.Jaccard(),
sm.Jaro(),
sm.JaroWinkler(),
sm.Levenshtein(),
sm.OverlapCoefficient(),
sm.TverskyIndex()
]
self.alphanumeric_tokenizer = sm.AlphanumericTokenizer(return_set=True)
df['TfIdf'] = df.apply(
lambda x: tfidf.get_sim_score(x['aTokens'], x['bTokens']), axis=1)
df.head()
# # Sequence Based Similarities
# In[38]:
aff = sm.Affine()
df['Affine'] = df.apply(
lambda x: aff.get_raw_score(x['Sequence1'], x['Sequence2']), axis=1)
df.head()
# In[39]:
bd = sm.BagDistance()
df['Bag'] = df.apply(
lambda x: bd.get_sim_score(x['Sequence1'], x['Sequence2']), axis=1)
df.head()
# In[40]:
ed = sm.Editex()
df['Editex'] = df.apply(
lambda x: ed.get_sim_score(x['Sequence1'], x['Sequence2']), axis=1)
df.head()
# In[41]:
jaro = sm.Jaro()
df['Jaro'] = df.apply(