问fit_transform、transform和TfidfVectorizer如何工作

EN

import pandas as pd
import sqlite3 as sql
from sklearn.feature_extraction.text import TfidfVectorizer
import numpy as np
from scipy.sparse import csr_matrix
import sparse_dot_topn.sparse_dot_topn as ct
import re

def ngrams(string, n=3):
    string = re.sub(r'[,-./]|\sBD',r'', re.sub(' +', ' ',str(string)))
    ngrams = zip(*[string[i:] for i in range(n)])
    return [''.join(ngram) for ngram in ngrams]

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)

    print('ct.sparse_dot_topn: ', ct.sparse_dot_topn)
    return csr_matrix((data,indices,indptr),shape=(M,N))

    def get_matches_df(sparse_matrix, A, B, top=100):
        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] = A[sparserows[index]]
            right_side[index] = B[sparsecols[index]]
            similairity[index] = sparse_matrix.data[index]

        return pd.DataFrame({'left_side': left_side,
                             'right_side': right_side,
                             'similairity': similairity})

Col_clean = 'fruits_normalized'
Col_dirty = 'fruits'

#read table
data_dirty={f'{Col_dirty}':['I am an apple', 'You are an apple', 'Aple', 'Appls', 'Apples']}
data_clean= {f'{Col_clean}':['apple', 'pear', 'banana', 'apricot', 'pineapple']}

df_clean = pd.DataFrame(data_clean)
df_dirty = pd.DataFrame(data_dirty)

Name_clean = df_clean[f'{Col_clean}'].unique()
Name_dirty= df_dirty[f'{Col_dirty}'].unique()

vectorizer = TfidfVectorizer(min_df=1, analyzer=ngrams)
clean_idf_matrix = vectorizer.fit_transform(Name_clean)
dirty_idf_matrix = vectorizer.transform(Name_dirty)

matches = awesome_cossim_top(dirty_idf_matrix, clean_idf_matrix.transpose(),1,0)
matches_df = get_matches_df(matches, Name_dirty, Name_clean, top = 0)

with pd.option_context('display.max_rows', None, 'display.max_columns', None):
    matches_df.to_excel("output_apple.xlsx")

print('done')