Fuzzy String Matching

fuzzy_conventional.py

# Import module for data manipulation
import pandas as pd
# Import module for linear algebra
import numpy as np
# Import module for Fuzzy string matching
from fuzzywuzzy import fuzz, process
# Import module for binary search

def stringMatching(
    df: pd.DataFrame,
    column: str,
    clean: pd.Series,
    mapping_df: pd.DataFrame,
    col: str
    ):
    # Create vectorizer
    categoryClean = clean.drop_duplicates().reset_index(drop = True)
    categoryMessy = df[column].drop_duplicates().dropna().reset_index(drop = True).astype(str)

    categoryFuzzy = {}
    ratioFuzzy = {}
    for i in range(len(categoryMessy)):
        resultFuzzy = process.extractOne(categoryMessy[i].lower(), categoryClean)
        # Mapping
        catFuzzy = {categoryMessy[i]:resultFuzzy[0]}
        ratFuzzy = {categoryMessy[i]:resultFuzzy[1]}
        # Save result
        categoryFuzzy.update(catFuzzy)
        # Save the ratio
        ratioFuzzy.update(ratFuzzy)

    # Create column names
    catCol = col
    ratCol = 'Ratio'
    # Merge the result
    df[catCol] = df[column]
    df[ratCol] = df[column]
    # Mapping the result
    df[catCol] = df[catCol].map(categoryFuzzy)
    df[ratCol] = df[ratCol].map(ratioFuzzy)
    return df