Skip to content

Commit

Permalink
Add doctest (rapidsai#4618)
Browse files Browse the repository at this point in the history 
Continuation of rapidsai#2975 to change docstring to a doctest format.
I'm also adding a pytest file to execute doctest, similar to what's being done in [cudf](https://github.com/rapidsai/cudf/blob/branch-22.04/python/cudf/cudf/tests/test_doctests.py)

Authors:
  - Micka (https://github.com/lowener)
  - Yuqiong Li (https://github.com/yuqli)
  - Dante Gama Dessavre (https://github.com/dantegd)
  - Michael Demoret (https://github.com/mdemoret-nv)

Approvers:
  - Dante Gama Dessavre (https://github.com/dantegd)

URL: rapidsai#4618
  • Loading branch information
@lowener
lowener authored Mar 29, 2022
1 parent 8f30123 commit f7570fb
Show file tree
Hide file tree
Showing 91 changed files with 2,157 additions and 1,969 deletions.
59 changes: 59 additions & 0 deletions python/cuml/__init__.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -111,3 +111,62 @@ def __getattr__(name):
return _global_settings_data.settings

raise AttributeError(f"module {__name__} has no attribute {name}")


__all__ = [
# Modules
"common",
"metrics",
"multiclass",
"naive_bayes",
"preprocessing",
# Classes
"AgglomerativeClustering",
"ARIMA",
"AutoARIMA",
"Base",
"CD",
"cuda",
"DBSCAN",
"ElasticNet",
"ExponentialSmoothing",
"ForestInference",
"GaussianRandomProjection",
"Handle",
"HDBSCAN",
"IncrementalPCA",
"KernelDensity",
"KernelExplainer",
"KernelRidge",
"KMeans",
"KNeighborsClassifier",
"KNeighborsRegressor",
"Lasso",
"LinearRegression",
"LinearSVC",
"LinearSVR",
"LogisticRegression",
"MBSGDClassifier",
"MBSGDRegressor",
"NearestNeighbors",
"PCA",
"PermutationExplainer",
"QN",
"RandomForestClassifier",
"RandomForestRegressor",
"Ridge",
"SGD",
"SparseRandomProjection",
"SVC",
"SVR",
"TruncatedSVD",
"TSNE",
"UMAP",
# Functions
"johnson_lindenstrauss_min_dim",
"make_arima",
"make_blobs",
"make_classification",
"make_regression",
"stationarity",
]
21 changes: 17 additions & 4 deletions python/cuml/_thirdparty/sklearn/preprocessing/_data.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -258,7 +258,9 @@ class MinMaxScaler(TransformerMixin,
Examples
--------
>>> from cuml.preprocessing import MinMaxScaler
>>> import cupy as cp
>>> data = [[-1, 2], [-0.5, 6], [0, 10], [1, 18]]
>>> data = cp.array(data)
>>> scaler = MinMaxScaler()
>>> print(scaler.fit(data))
MinMaxScaler()
Expand All @@ -269,7 +271,7 @@ class MinMaxScaler(TransformerMixin,
[0.25 0.25]
[0.5 0.5 ]
[1. 1. ]]
>>> print(scaler.transform([[2, 2]]))
>>> print(scaler.transform(cp.array([[2, 2]])))
[[1.5 0. ]]
See also
Expand Down Expand Up @@ -577,7 +579,9 @@ class StandardScaler(TransformerMixin,
Examples
--------
>>> from cuml.preprocessing import StandardScaler
>>> import cupy as cp
>>> data = [[0, 0], [0, 0], [1, 1], [1, 1]]
>>> data = cp.array(data)
>>> scaler = StandardScaler()
>>> print(scaler.fit(data))
StandardScaler()
Expand All @@ -588,7 +592,7 @@ class StandardScaler(TransformerMixin,
[-1. -1.]
[ 1. 1.]
[ 1. 1.]]
>>> print(scaler.transform([[2, 2]]))
>>> print(scaler.transform(cp.array([[2, 2]])))
[[3. 3.]]
See also
Expand Down Expand Up @@ -649,7 +653,7 @@ def fit(self, X, y=None) -> "StandardScaler":
The data used to compute the mean and standard deviation
used for later scaling along the features axis.
y
y : None
Ignored
"""

Expand Down Expand Up @@ -893,9 +897,11 @@ class MaxAbsScaler(TransformerMixin,
Examples
--------
>>> from cuml.preprocessing import MaxAbsScaler
>>> import cupy as cp
>>> X = [[ 1., -1., 2.],
... [ 2., 0., 0.],
... [ 0., 1., -1.]]
>>> X = cp.array(X)
>>> transformer = MaxAbsScaler().fit(X)
>>> transformer
MaxAbsScaler()
Expand Down Expand Up @@ -1151,9 +1157,11 @@ class RobustScaler(TransformerMixin,
Examples
--------
>>> from cuml.preprocessing import RobustScaler
>>> import cupy as cp
>>> X = [[ 1., -2., 2.],
... [ -2., 1., 3.],
... [ 4., 1., -2.]]
>>> X = cp.array(X)
>>> transformer = RobustScaler().fit(X)
>>> transformer
RobustScaler()
Expand Down Expand Up @@ -1786,9 +1794,11 @@ class Normalizer(TransformerMixin,
Examples
--------
>>> from cuml.preprocessing import Normalizer
>>> import cupy as cp
>>> X = [[4, 1, 2, 2],
... [1, 3, 9, 3],
... [5, 7, 5, 1]]
>>> X = cp.array(X)
>>> transformer = Normalizer().fit(X) # fit does nothing.
>>> transformer
Normalizer()
Expand Down Expand Up @@ -1913,9 +1923,11 @@ class Binarizer(TransformerMixin,
Examples
--------
>>> from cuml.preprocessing import Binarizer
>>> import cupy as cp
>>> X = [[ 1., -1., 2.],
... [ 2., 0., 0.],
... [ 0., 1., -1.]]
>>> X = cp.array(X)
>>> transformer = Binarizer().fit(X) # fit does nothing.
>>> transformer
Binarizer()
Expand Down Expand Up @@ -1996,7 +2008,8 @@ def add_dummy_feature(X, value=1.0):
--------
>>> from cuml.preprocessing import add_dummy_feature
>>> add_dummy_feature([[0, 1], [1, 0]])
>>> import cupy as cp
>>> add_dummy_feature(cp.array([[0, 1], [1, 0]]))
array([[1., 0., 1.],
[1., 1., 0.]])
"""
Expand Down
13 changes: 8 additions & 5 deletions python/cuml/_thirdparty/sklearn/preprocessing/_discretization.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -103,19 +103,22 @@ class KBinsDiscretizer(TransformerMixin,
Examples
--------
>>> from cuml.preprocessing import KBinsDiscretizer
>>> import numpy as np
>>> X = [[-2, 1, -4, -1],
... [-1, 2, -3, -0.5],
... [ 0, 3, -2, 0.5],
... [ 1, 4, -1, 2]]
>>> X = np.array(X)
>>> est = KBinsDiscretizer(n_bins=3, encode='ordinal', strategy='uniform')
>>> est.fit(X)
KBinsDiscretizer(...)
>>> Xt = est.transform(X)
>>> Xt # doctest: +SKIP
array([[ 0., 0., 0., 0.],
[ 1., 1., 1., 0.],
[ 2., 2., 2., 1.],
[ 2., 2., 2., 2.]])
>>> Xt
array([[0, 0, 0, 0],
[1, 1, 1, 0],
[2, 2, 2, 1],
[2, 2, 2, 2]], dtype=int32)
Sometimes it may be useful to convert the data back into the original
feature space. The ``inverse_transform`` function converts the binned
Expand Down
43 changes: 20 additions & 23 deletions python/cuml/cluster/dbscan.pyx
View file
Original file line number Diff line number Diff line change
Expand Up @@ -111,29 +111,26 @@ class DBSCAN(Base,
.. code-block:: python
# Both import methods supported
from cuml import DBSCAN
from cuml.cluster import DBSCAN
import cudf
import numpy as np
gdf_float = cudf.DataFrame()
gdf_float['0'] = np.asarray([1.0,2.0,5.0], dtype = np.float32)
gdf_float['1'] = np.asarray([4.0,2.0,1.0], dtype = np.float32)
gdf_float['2'] = np.asarray([4.0,2.0,1.0], dtype = np.float32)
dbscan_float = DBSCAN(eps = 1.0, min_samples = 1)
dbscan_float.fit(gdf_float)
print(dbscan_float.labels_)
Output:
.. code-block:: python
0 0
1 1
2 2
>>> # Both import methods supported
>>> from cuml import DBSCAN
>>> from cuml.cluster import DBSCAN
>>>
>>> import cudf
>>> import numpy as np
>>>
>>> gdf_float = cudf.DataFrame()
>>> gdf_float['0'] = np.asarray([1.0,2.0,5.0], dtype = np.float32)
>>> gdf_float['1'] = np.asarray([4.0,2.0,1.0], dtype = np.float32)
>>> gdf_float['2'] = np.asarray([4.0,2.0,1.0], dtype = np.float32)
>>>
>>> dbscan_float = DBSCAN(eps = 1.0, min_samples = 1)
>>> dbscan_float.fit(gdf_float)
DBSCAN()
>>> dbscan_float.labels_
0 0
1 1
2 2
dtype: int32
Parameters
-----------
Expand Down
2 changes: 1 addition & 1 deletion python/cuml/cluster/hdbscan.pyx
View file
Original file line number Diff line number Diff line change
Expand Up @@ -323,7 +323,7 @@ class HDBSCAN(Base, ClusterMixin, CMajorInputTagMixin):
for new points in future (e.g. using approximate_predict), as
the approximate_predict function is not aware of this argument.
metric : string or callable, optional (default='minkowski')
metric : string or callable, optional (default='euclidean')
The metric to use when calculating distance between instances in a
feature array. If metric is a string or callable, it must be one of
the options allowed by metrics.pairwise.pairwise_distances for its
Expand Down
Loading

0 comments on commit f7570fb

Please sign in to comment.