Fuzzywazzy in data science

 import numpy as np

import pandas as pd


from fuzzywuzzy import process

import fuzzywuzzy


df = pd.DataFrame({"name":["alice_sahu","alice sahu","banika_pradhan","banika pradhan,","banika pradhan","swapita_maheswari"],"age":[20,22,35,21,19,30]})

name = df['name']

unique_array = df['name'].unique()

#print(unique_array)

match_value = fuzzywuzzy.process.extract("alice_sahu",name,limit=10,scorer=fuzzywuzzy.fuzz.token_sort_ratio)

#print(match_value)

df['name'] = df['name'].str.strip(',')

#print(df)



close_matches = []

for match in match_value:

  

  #for matches in match:

  if match[1]==90:

    

        close_matches.append(match[0])



print(close_matches)

row_matches = df['name'].isin(close_matches)

#name = df['name']


df.loc[row_matches,'name']=["alice_sahu"]

print(df)





  


Comments

Post a Comment

Popular posts from this blog

card slot machine

import random dict = {'A':4,'KING':4,'QUEEN':4, 'J':4, '10':4, '9':4, '8':4,'7':4,'6':4,'5':4,'4':4,'3':4,'2':4} ROWS = 3 COLS = 3 NUM_TIMES = 5 MAX_BET = 500  def sequence_game(alhp):     all_cards = []     for i, dict in alhp.items():         for _ in range(dict):             all_cards.append(i)     return all_cards         def deposit():   while True:     amount_input = input("how much amount you want to deposit? $ ")     amount = 0     if amount_input.isdigit():       amount = int(amount_input)       if amount > 0:         break       else:         print("amount must be greater than 0")   return amount def get_bet_amount():     while True:      bet_amount_input = (input("how much amount you want to bet ? $ "))     ...
Read more

Programming

 import pandas as pd # Load the Excel file into a DataFrame df = pd.read_excel("your_file.xlsx") # Split the header into multiple columns based on ';' header_split = df.columns[0].split(';') # Create a new DataFrame to store the split values split_values = pd.DataFrame(columns=header_split) # Iterate through each row and split the values after ';' for index, row in df.iterrows():     values = row[df.columns[0]].split(';')     # Pad the split values if there are fewer values than columns     if len(values) < len(header_split):         values += [''] * (len(header_split) - len(values))     split_values.loc[index] = values # Concatenate the split_values DataFrame with the original DataFrame df = pd.concat([df, split_values], axis=1) # Drop the original column containing the combined header and values df.drop(columns=[df.columns[0]], inplace=True) # Display the DataFrame print(df)
Read more

Card Game In Python

 import random dict = {'A':4,'KING':4,'QUEEN':4, 'J':4} ROWS = 3 COLS = 3 def sequence_game(alhp,rows,cols):     all_cards = []     for i, dict in alhp.items():         for _ in range(dict):             all_cards.append(i)     user_input = input("do you want to play ? ")     if user_input == 'y':         print(f"all_cards : {all_cards}")     random_choice = []          for col in range(cols):      value = random.choice(all_cards)      all_cards.remove(value)      random_choice.append(value)                        lets_distribute_all_cards = input(" ready to distribute ? ")     if lets_distribute_all_cards == 'y':                           print(random_c...
Read more