[USER (data scientist)]: Alright, we've encoded the categorical variables, so let's tackle question three. Could you whip up some code to figure out if we need to normalize the credit_customers dataset? Just check if the value is over 1, and if it is, we should normalize it and generate the top 5 rows of normalized dataframe. By the way, Standard Scaling works well for this - it centers each feature around 0 with a standard deviation of 1, which is pretty popular and effective. Specifically, you can generate a dataframe showing the first few rows of the normalized 'credit_customers' dataset, after applying standard scaling to its numerical columns.
My template of code snippet is:

---BEGIN CODE TEMPLATE---

import pandas as pd  
import numpy as np
from sklearn.preprocessing import StandardScaler 
import pickle
  
# Load the dataset  
credit_customers = pd.read_csv("credit_customers.csv")  
  
# YOUR SOLUTION BEGIN:
<code1>
[COMPLETE YOUR CODE]  
</code1>
# YOUR SOLUTION END

print("Data after Standard Scaling:\n", credit_customers_normalized.head())  

# save data
pickle.dump(credit_customers_normalized.head(),open("./pred_result/credit_customers_normalized_head.pkl","wb"))

---END CODE TEMPLATE---

[YOU (AI assistant)]: Sure, I can help you:
'''
import pandas as pd  
import numpy as np
from sklearn.preprocessing import StandardScaler 
import pickle
  
# Load the dataset  
credit_customers = pd.read_csv("credit_customers.csv")  
  
# YOUR SOLUTION BEGIN:
