diff --git a/02_activities/assignments/a1_sampling_and_reproducibility.ipynb b/02_activities/assignments/a1_sampling_and_reproducibility.ipynb index 873f5985..bc5b13a1 100644 --- a/02_activities/assignments/a1_sampling_and_reproducibility.ipynb +++ b/02_activities/assignments/a1_sampling_and_reproducibility.ipynb @@ -16,7 +16,9 @@ "cell_type": "markdown", "id": "4ea73db3", "metadata": {}, - "source": [] + "source": [ + "Sampling occurs at two stages in the model. The first is infection sampling, performed by np.random.choice(ppl.index, size=int(len(ppl) * ATTACK_RATE), replace=False). The sampling frame is all 1,000 individuals in the DataFrame. The sample size is 100 (10% of 1,000, set by ATTACK_RATE = 0.10). This is simple random sampling without replacement, drawing uniformly from the index with no underlying probability distribution — every individual has an equal chance of being selected. The second is primary contact tracing, performed by np.random.rand(sum(ppl['infected'])) < TRACE_SUCCESS. The sampling frame is the 100 infected individuals. Each is independently assigned a traced status with probability 0.20 (TRACE_SUCCESS = 0.20), modelling a Bernoulli distribution with p = 0.20. The expected sample size is 20 traced individuals. Secondary contact tracing is not a sampling stage — it is a deterministic rule that upgrades all infected attendees of an event to traced if that event already has 2 or more traced cases (SECONDARY_TRACE_THRESHOLD = 2). It does not involve any random function." + ] }, { "cell_type": "markdown", @@ -30,7 +32,11 @@ "cell_type": "markdown", "id": "4cf5d993", "metadata": {}, - "source": [] + "source": [ + "With 10 repetitions, the results are highly irreproducible — each run produces a substantially different histogram, with the distributions shifting shape and position dramatically between executions. The small sample means a single simulation can skew the entire output.\n", + "With 100 repetitions, results are more stable but still noticeably inconsistent across runs — the general shape begins to emerge, but the exact distributions shift enough that different conclusions could be drawn depending on the run.\n", + "At 1000 repetitions, the histograms are much more consistent across runs, though still not identical. In all three cases the results are not fully reproducible because no random seed is set, meaning np.random.choice and np.random.rand draw fresh values on every execution. The fewer the repetitions, the more severely this affects the output." + ] }, { "cell_type": "markdown", @@ -40,10 +46,32 @@ "Alter the code so that it is reproducible. Describe the changes you made to the code and how they affected the reproducibility of the script. The script needs to produce the same output when run multiple times." ] }, + { + "cell_type": "code", + "execution_count": 2, + "id": "ed991755", + "metadata": {}, + "outputs": [], + "source": [ + "# Set random seed for reproducibility\n", + "np.random.seed(42)\n", + "\n", + "# Run the simulation 1000 times\n", + "results = [simulate_event(m) for m in range(1000)]" + ] + }, { "cell_type": "markdown", "id": "77613cc3", "metadata": {}, + "source": [ + "By fixing the seed with np.random.seed(42), we initialize NumPy's random number generator to a known state before any stochastic calls are made. Every subsequent call to np.random.choice and np.random.rand inside simulate_event() then draws from a deterministic sequence, so the same 1,000 simulations are reproduced exactly on every run. The choice of 42 is arbitrary — any integer works — but it must be set before the simulation loop, not inside simulate_event(), because placing it inside the function would reset the generator on every iteration, destroying the variation between simulations rather than preserving it across script runs." + ] + }, + { + "cell_type": "markdown", + "id": "fb85acf3", + "metadata": {}, "source": [] }, { @@ -59,7 +87,18 @@ "execution_count": null, "id": "ab8587a0", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "# Import necessary libraries\n", "import pandas as pd\n", @@ -193,7 +232,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "sampling-env", "language": "python", "name": "python3" }, @@ -207,7 +246,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.13.0" + "version": "3.11.2" } }, "nbformat": 4,