Arithmetic Operators

Nerd Cafe

What Are Arithmetic Operators?

Arithmetic operators are used to perform mathematical operations in Python like:

• Addition

• Subtraction

• Multiplication

• Division

• etc.

These are fundamental in Python and especially important when working with data preprocessing, feature engineering, loss functions, and model evaluations in machine learning.

List of Arithmetic Operators in Python

Operator	Symbol	Description
Addition	+	Adds two values	a + b
Subtraction	-	Subtracts right from left	a - b
Multiplication	*	Multiplies two values	a * b
Division	/	Divides left by right (float result)	a / b
Floor Division	//	Divides and returns the integer part	a // b
Modulus	%	Returns remainder	a % b
Exponent	**	Raises a number to the power of another	a ** b

Let’s Explore Each One with Practical Notes

We'll define two variables and apply each operator.

a = 15
b = 4

Addition (+)

result = a + b
print("Addition:", result)

Use case in ML: Adding feature values, summing arrays, or updating weights in optimization.

Output:

Addition: 19

Subtraction (-)

result = a - b
print("Subtraction:", result)

Use case in ML: Calculating error (y_pred - y_actual), cost reduction, or feature differences.

Output:

Subtraction: 11

Multiplication (*)

result = a * b
print("Multiplication:", result)

Use case in ML: Element-wise product, scaling features, matrix dot product.

Output:

Multiplication: 60

Division (/)

result = a / b
print("Division:", result)

Returns float. Always remember in ML tasks, data normalization often uses floating-point division.

Output:

Division: 3.75

Floor Division (//)

result = a // b
print("Floor Division:", result)

Use case: Useful in splitting data or indexing (especially integer divisions like train/test split sizes).

Output:

Floor Division: 3

Modulus (%)

result = a % b
print("Modulus:", result)

Use case: Useful in batch processing (batch_index % batch_size) or finding remainder values in loop counters.

Output:

Modulus: 3

Exponentiation (**)

result = a ** b
print("Exponentiation:", result)

Use case: Common in ML when applying exponential decay (learning_rate ** epoch) or polynomial features.

Output:

Exponentiation: 50625

Practical ML Examples Using Arithmetic Operators

Example 1: Feature Normalization

x = 72
mean = 50
std = 10

# z-score normalization
z = (x - mean) / std
print("Normalized value:", z)

Uses subtraction and division.

Output:

Normalized value: 2.2

Example 2: Gradient Descent Step

weight = 0.5
learning_rate = 0.1
gradient = 0.6

# weight update
weight = weight - learning_rate * gradient
print("Updated weight:", weight)

Subtraction, multiplication.

Output:

Updated weight: 0.44

Example 3: Splitting Data into Batches

total_samples = 105
batch_size = 32

num_batches = total_samples // batch_size
remaining = total_samples % batch_size

print("Full batches:", num_batches)
print("Remaining samples:", remaining)

Floor division and modulus.

Output:

Full batches: 3
Remaining samples: 9

Notes and Tips

• Always be mindful of data types: int, float — especially in division.

• In Python:

  • 5 / 2 = 2.5 (float)

  • 5 // 2 = 2 (integer)

• When using NumPy for vector operations, all these operators work element-wise. We’ll cover that in the NumPy section.

Summary Table with Examples

Operation	Code	Output
a+b	15 + 4	19
a - b	15 - 4	11
a * b	15*4	60
a / b	15 / 4	3.75
a // b	15 // 4	3
a % b	15 % 4	3
a** b	15 ** 4	50625

Keywords

arithmetic, operators, python, addition, subtraction, multiplication, division, floor division, modulus, exponentiation, machine learning, normalization, feature scaling, gradient descent, batch processing, data science, z-score, loss function, data preprocessing, numpy, nerd cafe