Apply function to every row in a Pandas DataFrame

Python is a great language for performing data analysis tasks. It provides with a huge amount of Classes and function which help in analyzing and manipulating data in an easier way.

One can use apply() function in order to apply function to every row in given dataframe. Let’s see the ways we can do this task.

Example #1:

# Import pandas package  
import pandas as pd 
  
# Function to add 
def add(a, b, c): 
    return a + b + c 
  
def main(): 
      
    # create a dictionary with 
    # three fields each 
    data = { 
            'A':[1, 2, 3],  
            'B':[4, 5, 6],  
            'C':[7, 8, 9] } 
      
    # Convert the dictionary into DataFrame  
    df = pd.DataFrame(data) 
    print("Original DataFrame:\n", df) 
      
    df['add'] = df.apply(lambda row : add(row['A'], 
                     row['B'], row['C']), axis = 1) 
   
    print('\nAfter Applying Function: ') 
    # printing the new dataframe 
    print(df) 
   
if __name__ == '__main__': 
    main() 

Output:

Example #2:

You can use the numpy function as the parameters to the dataframe as well.

import pandas as pd 
import numpy as np 
   
def main(): 
      
    # create a dictionary with 
    # five fields each 
    data = { 
            'A':[1, 2, 3],  
            'B':[4, 5, 6],  
            'C':[7, 8, 9] } 
      
    # Convert the dictionary into DataFrame  
    df = pd.DataFrame(data) 
    print("Original DataFrame:\n", df) 
      
    # applying function to each row in the dataframe 
    # and storing result in a new coloumn 
    df['add'] = df.apply(np.sum, axis = 1) 
   
    print('\nAfter Applying Function: ') 
    # printing the new dataframe 
    print(df) 
   
if __name__ == '__main__': 
    main() 

Output:

Example #3: Normalising Data

# Import pandas package  
import pandas as pd 
  
def normalize(x, y): 
    x_new = ((x - np.mean([x, y])) /
             (max(x, y) - min(x, y))) 
      
    # print(x_new) 
    return x_new 
  
def main(): 
      
    # create a dictionary with three fields each 
    data = { 
        'X':[1, 2, 3],  
        'Y':[45, 65, 89] } 
      
    # Convert the dictionary into DataFrame  
    df = pd.DataFrame(data) 
    print("Original DataFrame:\n", df) 
      
    df['X'] = df.apply(lambda row : normalize(row['X'], 
                                  row['Y']), axis = 1) 
   
    print('\nNormalized:') 
    print(df) 
   
if __name__ == '__main__': 
    main() 

Output:

Example #4: Generate range

import pandas as pd 
import numpy as np 
   
pd.options.mode.chained_assignment = None
  
# Function to generate range 
def generate_range(n): 
      
    # printing the range for eg: 
    # input is 67 output is 60-70 
    n = int(n) 
      
    lower_limit = n//10 * 10
    upper_limit = lower_limit + 10
      
    return str(str(lower_limit) + '-' + str(upper_limit)) 
       
def replace(row): 
    for i, item in enumerate(row): 
          
        # updating the value of the row 
        row[i] = generate_range(item) 
    return row 
           
   
def main(): 
    # create a dictionary with 
    # three fields each 
    data = { 
            'A':[0, 2, 3],  
            'B':[4, 15, 6],  
            'C':[47, 8, 19] } 
      
    # Convert the dictionary into DataFrame  
    df = pd.DataFrame(data) 
   
    print('Before applying function: ') 
    print(df) 
       
    # applying function to each row in 
    # dataframe and storing result in a new coloumn 
    df = df.apply(lambda row : replace(row)) 
       
   
    print('After Applying Function: ') 
    # printing the new dataframe 
    print(df) 
   
if __name__ == '__main__': 
    main() 

Output:

My Personal Notes

Recommended Posts: