I'm getting " ValueError: 111816 is not in range" error when trying to use FuzzyWuzzy between two other dataframe column - fuzzywuzzy

Question

I am getting error when trying to use FuzzyWuzzy between two other dataframe column.
I want to match df_1['name_new'] to df['term'].
below is the site where I got my code
https://towardsdatascience.com/fuzzy-string-match-with-python-on-large-dataset-and-why-you-should-not-use-fuzzywuzzy-4ec9f0defcd
#Transform text to vectors with TF-IDF:
from sklearn.feature_extraction.text import TfidfVectorizer
tfidf_vectorizer = TfidfVectorizer(ngram_range=(1,2), max_df=0.9, min_df=5, token_pattern='(\S+)')
tf_idf_matrix_1 = tfidf_vectorizer.fit_transform(df_1['name_new'])
tf_idf_matrix_2 = tfidf_vectorizer.fit_transform(df['term'])
I careated "tf_idf_matrix_2 " to match other df's 'term' column
from scipy.sparse import csr_matrix
!pip install sparse_dot_topn
import sparse_dot_topn.sparse_dot_topn as ct
def awesome_cossim_top(A, B, ntop, lower_bound=0):
# force A and B as a CSR matrix.
# If they have already been CSR, there is no overhead
A = A.tocsr()
B = B.tocsr()
M, _ = A.shape
_, N = B.shape
idx_dtype = np.int32
nnz_max = M*ntop
indptr = np.zeros(M+1, dtype=idx_dtype)
indices = np.zeros(nnz_max, dtype=idx_dtype)
data = np.zeros(nnz_max, dtype=A.dtype)
ct.sparse_dot_topn(
M, N, np.asarray(A.indptr, dtype=idx_dtype),
np.asarray(A.indices, dtype=idx_dtype),
A.data,
np.asarray(B.indptr, dtype=idx_dtype),
np.asarray(B.indices, dtype=idx_dtype),
B.data,
ntop,
lower_bound,
indptr, indices, data)
return csr_matrix((data,indices,indptr),shape=(M,N))
import time
t1 = time.time()
# adjust lower bound: 0.8
# keep top 10 similar results
matches = awesome_cossim_top(tf_idf_matrix_1, tf_idf_matrix_2.transpose(), 10, 0.8)
t = time.time()-t1
print("finished in:", t)
def get_matches_df(sparse_matrix, name_vector, top=10000):
non_zeros = sparse_matrix.nonzero()
sparserows = non_zeros[0]
sparsecols = non_zeros[1]
if top:
nr_matches = top
else:
nr_matches = sparsecols.size
left_side = np.empty([nr_matches], dtype=object)
right_side = np.empty([nr_matches], dtype=object)
similairity = np.zeros(nr_matches)
for index in range(0, nr_matches):
left_side[index] = name_vector[sparserows[index]]
right_side[index] = name_vector[sparsecols[index]]
similairity[index] = sparse_matrix.data[index]
return pd.DataFrame({'name_new_1': left_side,
'term_1': right_side,
'similairity_score': similairity})
matches_df = pd.DataFrame()
matches_df = get_matches_df(matches, df_1['name_new'], top=10000)
# Remove all exact matches
I get my error like this=>
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/pandas/core/indexes/range.py in get_loc(self, key, method, tolerance)
384 try:
--> 385 return self._range.index(new_key)
386 except ValueError as err:
ValueError: 111816 is not in range
The above exception was the direct cause of the following exception:
KeyError Traceback (most recent call last)
4 frames
/usr/local/lib/python3.7/dist-packages/pandas/core/indexes/range.py in get_loc(self, key, method, tolerance)
385 return self._range.index(new_key)
386 except ValueError as err:
--> 387 raise KeyError(key) from err
388 raise KeyError(key)
389 return super().get_loc(key, method=method, tolerance=tolerance)
KeyError: 111816
Please help... what is wrong with my code?