Skip to content
This repository was archived by the owner on May 7, 2026. It is now read-only.

docs: add examples for ml PCA and SimpleImputer #1236

Merged
GarrettWu merged 3 commits into from
Dec 21, 2024
Merged

docs: add examples for ml PCA and SimpleImputer #1236

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
cc2ca46
docs: add examples for ml PCA and SimpleImputer
GarrettWu Dec 20, 2024
e5f9453
fix
GarrettWu Dec 20, 2024
5872a04
fix
GarrettWu Dec 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 24 additions & 0 deletions third_party/bigframes_vendored/sklearn/decomposition/_pca.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,30 @@
class PCA(BaseEstimator, metaclass=ABCMeta):
"""Principal component analysis (PCA).

**Examples:**

>>> import bigframes.pandas as bpd
>>> from bigframes.ml.decomposition import PCA
>>> bpd.options.display.progress_bar = None
>>> X = bpd.DataFrame({"feat0": [-1, -2, -3, 1, 2, 3], "feat1": [-1, -1, -2, 1, 1, 2]})
>>> pca = PCA(n_components=2).fit(X)
>>> pca.predict(X) # doctest:+SKIP
principal_component_1 principal_component_2
0 -0.755243 0.157628
1 -1.05405 -0.141179
2 -1.809292 0.016449
3 0.755243 -0.157628
4 1.05405 0.141179
5 1.809292 -0.016449
<BLANKLINE>
[6 rows x 2 columns]
>>> pca.explained_variance_ratio_ # doctest:+SKIP
principal_component_id explained_variance_ratio
0 1 0.00901
1 0 0.99099
<BLANKLINE>
[2 rows x 2 columns]

Args:
n_components (int, float or None, default None):
Number of components to keep. If n_components is not set, all
Expand Down
16 changes: 16 additions & 0 deletions third_party/bigframes_vendored/sklearn/impute/_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,22 @@ class SimpleImputer(_BaseImputer):
Replace missing values using a descriptive statistic (e.g. mean, median, or
most frequent) along each column.

**Examples:**

>>> import bigframes.pandas as bpd
>>> from bigframes.ml.impute import SimpleImputer
>>> bpd.options.display.progress_bar = None
>>> X_train = bpd.DataFrame({"feat0": [7.0, 4.0, 10.0], "feat1": [2.0, None, 5.0], "feat2": [3.0, 6.0, 9.0]})
>>> imp_mean = SimpleImputer().fit(X_train)
>>> X_test = bpd.DataFrame({"feat0": [None, 4.0, 10.0], "feat1": [2.0, None, None], "feat2": [3.0, 6.0, 9.0]})
>>> imp_mean.transform(X_test)
imputer_feat0 imputer_feat1 imputer_feat2
0 7.0 2.0 3.0
1 4.0 3.5 6.0
2 10.0 3.5 9.0
<BLANKLINE>
[3 rows x 3 columns]

Args:
strategy ({'mean', 'median', 'most_frequent'}, default='mean'):
The imputation strategy. 'mean': replace missing values using the mean along
Expand Down