Replace Boston housing analysis with Ames housing #598
Conversation
fverac
force-pushed
the
fverac/replaceBostonHousing
branch
from
999208a to
4171a4b
Compare
| " feature_inds= [\n", | ||
| " 'HasFireplace',\n", | ||
| " 'HasPorch',\n", | ||
| " 'HasDeck',\n", | ||
| " ],\n", |
There was a problem hiding this comment.
Why these three features? Overall, this new notebook is good, but one thing that's missing compared to the old one is any finding that one of top predictive features may not be causally important.
Maybe the dataset doesn't support such a finding, and that would be fine to point out too (something like "We find that not only are features X, Y, and Z predictive of high prices, but that even when accounting for other features they appear to be causally linked.") But right now there doesn't seem to be a connection between the predictive and causal analysis.
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "We've seen which features are good predictors of home value, but are these features also causally signficiant? Below we use the CausalAnalysis class to assess the causal effects of certain house characteristics on home value." |
There was a problem hiding this comment.
This is good, but it would be nice to have a parallel statement after calling CausalAnalysis which summarizes whether it agrees or disagrees with the predictive analysis.
fverac
force-pushed
the
fverac/replaceBostonHousing
branch
from
a5d1e49 to
03147bf
Compare
No description provided.