Build the first working threshold prediction game

Build only what the claim requires: for a chosen threshold, accuracy and confusion counts are exact on the fixture. Prefer boring, deterministic code over frameworks you cannot yet explain. Run the path twice; identical output on this fixture is a feature, not a lack of creativity.

data=[(1,0.9),(1,0.6),(0,0.4),(0,0.2),(1,0.55)]; thr=0.5
pred=[int(s>=thr) for y,s in data]
tp=sum(y==1 and p==1 for (y,_),p in zip(data,pred))
fp=sum(y==0 and p==1 for (y,_),p in zip(data,pred))
tn=sum(y==0 and p==0 for (y,_),p in zip(data,pred))
fn=sum(y==1 and p==0 for (y,_),p in zip(data,pred))
acc=sum(y==p for (y,_),p in zip(data,pred))/len(data)
print({'acc':acc,'tp':tp,'fp':fp,'tn':tn,'fn':fn})

Expected evidence: acc and confusion counts. Read each printed intermediate as part of the argument that the path works—not as decoration.

Narrate the journey from raw input to result for a single example from 5 (truth, score) pairs. If you cannot name an intermediate, the implementation is still too opaque for this lab. Only after this path is solid should you generalize data sources or UI.

While implementing the threshold prediction game, print or log at least three intermediates that map to the claim (for a chosen threshold, accuracy and confusion counts are exact on the fixture). Good intermediates are values a teammate could recompute with a calculator or diff. Bad intermediates are framework traces you cannot explain.

Re-run with 5 (truth, score) pairs twice. If the second run differs, either the path is nondeterministic (document the seed) or you have hidden global state—both are lab bugs until named.

Stop adding features once the path supports choose a cutoff that balances errors without claiming generalization from five rows. Extra UI, extra tools, or extra models belong in later chapters. The mastery bar for this page is simply: a deterministic end-to-end path with intermediates.

At the implementation stage for prediction-game, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about 5 (truth, score) pairs that later pages inherit without redefining success. Keep that fixture small enough to inspect by hand, keep outputs copy-pasteable as text, and refuse to narrate this baseline as if it were a production SLA: confusion counts computed by hand at threshold 0.5.

For this page specifically, success looks like a deterministic path with printed intermediates while still centering the user decision to choose a cutoff that balances errors without claiming generalization from five rows. If you cannot point to a file, command, or assertion that proves that for the threshold prediction game, stay on this page instead of advancing.

Confusion matrix glossary

Previous · Next