Monte Carlo simulation basics in NumPy - Step-by-Step Execution

Concept Flow - Monte Carlo simulation basics

Define problem and model

↓

Generate random samples

↓

Run simulation for each sample

↓

Collect results

↓

Analyze output statistics

↓

Make decisions

Monte Carlo simulation repeats random sampling to estimate results and analyze outcomes.

Execution Sample

NumPy

import numpy as np
np.random.seed(0)
samples = np.random.rand(5)
mean_estimate = np.mean(samples)
print(mean_estimate)

This code generates 5 random numbers between 0 and 1 and calculates their average.

Execution Table

Step	Action	Random Samples Generated	Mean Calculation	Output
1	Set random seed for reproducibility	-	-	-
2	Generate 5 random samples	[0.5488135, 0.71518937, 0.60276338, 0.54488318, 0.4236548]	-	-
3	Calculate mean of samples	-	Mean = (0.5488 + 0.7152 + 0.6028 + 0.5449 + 0.4237) / 5 = 0.5671	-
4	Print mean estimate	-	-	0.5671

💡 All 5 samples processed, mean calculated and printed.

Variable Tracker

Variable	Start	After Step 2	After Step 3	Final
samples	None	[0.5488135, 0.71518937, 0.60276338, 0.54488318, 0.4236548]	[0.5488135, 0.71518937, 0.60276338, 0.54488318, 0.4236548]	[0.5488135, 0.71518937, 0.60276338, 0.54488318, 0.4236548]
mean_estimate	None	None	0.5671	0.5671

Key Moments - 3 Insights

Why do we set a random seed before generating samples?

Setting a random seed makes the random numbers the same every time we run the code, so results are repeatable. See Step 1 in execution_table.

How is the mean estimate calculated from the samples?

The mean is the sum of all sample values divided by the number of samples, shown in Step 3 of execution_table.

What does the output number represent in Monte Carlo simulation?

It represents an estimate based on random samples, here the average of 5 random values, as shown in Step 4.

Visual Quiz - 3 Questions

Look at the execution_table, what is the value of 'samples' after Step 2?

A [0.5488135, 0.71518937, 0.60276338, 0.54488318, 0.4236548]

B [0.1, 0.2, 0.3, 0.4, 0.5]

C None

D [1, 2, 3, 4, 5]

💡 Hint

Check the 'Random Samples Generated' column in Step 2 of execution_table.

At which step is the mean of the samples calculated?

A Step 1

B Step 2

C Step 3

D Step 4

💡 Hint

Look at the 'Mean Calculation' column in execution_table.

If we increase the number of samples from 5 to 10, what changes in the execution_table?

A The random seed will change

B More random samples will be generated in Step 2

C The mean calculation will be skipped

D Output will be a fixed number 0.5

💡 Hint

More samples means Step 2's 'Random Samples Generated' list will be longer.

Concept Snapshot

Monte Carlo simulation:
- Use random samples to estimate results
- Set random seed for repeatability
- Generate samples with numpy.random.rand
- Calculate statistics (mean, etc.) on samples
- Repeat many times for better estimates

Full Transcript

Monte Carlo simulation uses random sampling to estimate answers. First, we set a random seed to get the same random numbers each time. Then, we generate random samples using numpy's random functions. Next, we calculate statistics like the mean from these samples. Finally, we use these results to understand or predict outcomes. This example generated 5 random numbers and found their average, showing the basic steps of Monte Carlo simulation.