Build the first working 3×3 plus-sign image classifier

Now implement the shortest complete path for the artifact. The working mechanism is: flatten nine pixels, sum the center and four middle-edge positions, and compare that plus score with an explicit threshold. Keep every intermediate value available for inspection; hiding it behind a framework would make this lesson harder to reason about. The output should be deterministic for this fixture. Only after this path works should you generalize the data source or user interface.

The artifact's user-facing goal is specific: classify a tiny pixel grid as plus or other while keeping the pixels, score, threshold, and prediction visible. Its accepted input is exactly three rows of three binary brightness values. Those statements are intentionally narrower than “build an AI system.” Narrow scope lets us inspect every input and expected result, and it prevents a toy result from being presented as a production claim. This is the chapter's first end-to-end implementation. Run it twice and verify identical output.

Save this as lesson.py and run python3 lesson.py. It uses only the language standard library, so the example is reproducible offline.

def classify(img):
 flat=[p for row in img for p in row]; score=sum(flat[i] for i in [1,3,4,5,7])
 return ('plus' if score>=4 else 'other',score)
print(classify([[0,1,0],[1,1,1],[0,1,0]]))

Expected output: plus 5. Exact floating-point formatting may vary slightly, but the asserted behavior must not. Read the output as evidence about this stage, not merely proof that the interpreter started.

Print the 3×3 grid, flattened indices, five selected pixels, score, threshold, and label. If a rotated or shifted plus fails, that is an invariance limitation rather than a Python bug. Enumerate all nine single-pixel flips instead of trying one convenient corruption. Shape and binary-value errors should stop before scoring so malformed images cannot masquerade as confident predictions.

At the implementation stage, save the smallest failing fixture beside the expected result. Change one cause at a time and rerun the exact command printed above; that makes the repair reviewable and keeps this chapter's progressive artifact reproducible.

Use named positive and negative grids to compute confusion counts, then report every single-pixel-flip result. Accuracy alone hides whether the toy misses pluses or calls unrelated lines pluses, so include recall and false-positive count. Keep the threshold in the report and test a rotated plus separately. This evaluates a handcrafted detector, not a camera-ready vision model.

For this implementation page, preserve the fixture and result as evidence for the next page. Label observations separately from conclusions: a passing assertion establishes the behavior it names, while broader usefulness requires the chapter's full evaluation set and stated operating limits.