Fix loc/iloc and groupby column selection to preserve weights

[MaxGhenis]

Summary

• Fix MicroDataFrame.loc[] and .iloc[] to return MicroDataFrame with properly filtered weights instead of plain pandas.DataFrame (fixes MicroDataFrame.loc[] returns plain DataFrame, losing weights #265)
• Fix MicroDataFrame.groupby(col)["y"].sum() and groupby(col)[["y"]].sum() to use weighted aggregation (fixes MicroDataFrame.groupby(col)[[cols]].aggfunc doesn't consider weights #193)

Changes

Issue #265 Fix

Added custom _MicroLocIndexer and _MicroILocIndexer classes that wrap pandas' indexers. These ensure that when filtering rows, the result is a MicroDataFrame with properly filtered weights:

df = MicroDataFrame({'x': [1, 2, 3]}, weights=[10, 20, 30])
subset = df.loc[df.x > 1]  # Now returns MicroDataFrame with weights [20, 30]
subset.x.sum()  # Returns 130 (weighted), not 5 (unweighted)

Issue #193 Fix

Added __getitem__ method to MicroDataFrameGroupBy class. When selecting columns after groupby, it now returns properly configured groupby objects with weights:

d = MicroDataFrame(dict(g=["a", "a", "b"], y=[1, 2, 3]), weights=[4, 5, 6])
d.groupby("g")["y"].sum()     # Now returns a=14, b=18 (weighted)
d.groupby("g")[["y"]].sum()   # Now returns a=14, b=18 (weighted)

Test plan

• Added test_loc_preserves_weights() - tests .loc[] filtering
• Added test_iloc_preserves_weights() - tests .iloc[] filtering
• Added test_groupby_column_selection() - tests groupby column selection
• All 26 tests pass
• Code passes linting

🤖 Generated with Claude Code

[baogorek]

Hi @MaxGhenis , documentation was also broken in -us-data. I have a branch out if you want me to try to bring anything over.

For the fix, the values are looking good but I'm seeing NaN weights in certain circumstances:

from microdf import MicroDataFrame
In [8]: df = MicroDataFrame({'group': ['A', 'A', 'B', 'B'], 'value': [10, 20, 30, 40]}, weights=[1, 2, 3, 4])

In [9]: df.groupby("group").value.sum()
Out[9]: 
group
A     50.0
B    250.0
dtype: float64

In [10]: df.groupby("group")['value'].sum()
Out[10]: 
group
A     50.0
B    250.0
dtype: float64

In [11]: df.groupby("group").sum()
Out[11]: 
       weight  value
group               
A         NaN   50.0
B         NaN  250.0

In [13]: df.groupby("group")[["value"]].sum()
Out[13]: 
       weight  value
group               
A         NaN   50.0
B         NaN  250.0

I think we'd want to sum the weights, right?

[MaxGhenis]

@baogorek Thanks for the review! I've fixed the NaN weights issue.

The problem was that groupby aggregation results were being returned as MicroDataFrame, which automatically adds a weights column. Since weights have already been applied during aggregation, the result should be a plain pd.DataFrame instead.

Now the output is clean:

from microdf import MicroDataFrame
df = MicroDataFrame({'group': ['A', 'A', 'B', 'B'], 'value': [10, 20, 30, 40]}, weights=[1, 2, 3, 4])

df.groupby("group").sum()
#        value
# group       
# A       50.0
# B      250.0

df.groupby("group")[["value"]].sum()
#        value
# group       
# A       50.0
# B      250.0

I've also added a test to verify aggregated results don't have a spurious weight column.

[MaxGhenis]

I've also fixed the documentation build by migrating to Jupyter Book 2.0 / MyST:

• Added docs/myst.yml configuration
• Updated CI workflow to install mystmd via npm and use myst build --html
• Added Node.js setup step (required by MyST)

All CI checks are now passing! ✅

[baogorek]

LGTM!!