1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
|
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import numpy as np
from numpy import array
from pyspark.mllib.common import callMLlibFunc
from pyspark.mllib.linalg import SparseVector, _convert_to_vector
__all__ = ['LabeledPoint', 'LinearModel', 'LinearRegressionModel', 'RidgeRegressionModel',
'LinearRegressionWithSGD', 'LassoWithSGD', 'RidgeRegressionWithSGD']
class LabeledPoint(object):
"""
The features and labels of a data point.
:param label: Label for this data point.
:param features: Vector of features for this point (NumPy array, list,
pyspark.mllib.linalg.SparseVector, or scipy.sparse column matrix)
"""
def __init__(self, label, features):
self.label = float(label)
self.features = _convert_to_vector(features)
def __reduce__(self):
return (LabeledPoint, (self.label, self.features))
def __str__(self):
return "(" + ",".join((str(self.label), str(self.features))) + ")"
def __repr__(self):
return "LabeledPoint(%s, %s)" % (self.label, self.features)
class LinearModel(object):
"""A linear model that has a vector of coefficients and an intercept."""
def __init__(self, weights, intercept):
self._coeff = _convert_to_vector(weights)
self._intercept = float(intercept)
@property
def weights(self):
return self._coeff
@property
def intercept(self):
return self._intercept
def __repr__(self):
return "(weights=%s, intercept=%r)" % (self._coeff, self._intercept)
class LinearRegressionModelBase(LinearModel):
"""A linear regression model.
>>> lrmb = LinearRegressionModelBase(np.array([1.0, 2.0]), 0.1)
>>> abs(lrmb.predict(np.array([-1.03, 7.777])) - 14.624) < 1e-6
True
>>> abs(lrmb.predict(SparseVector(2, {0: -1.03, 1: 7.777})) - 14.624) < 1e-6
True
"""
def predict(self, x):
"""
Predict the value of the dependent variable given a vector x
containing values for the independent variables.
"""
x = _convert_to_vector(x)
return self.weights.dot(x) + self.intercept
class LinearRegressionModel(LinearRegressionModelBase):
"""A linear regression model derived from a least-squares fit.
>>> from pyspark.mllib.regression import LabeledPoint
>>> data = [
... LabeledPoint(0.0, [0.0]),
... LabeledPoint(1.0, [1.0]),
... LabeledPoint(3.0, [2.0]),
... LabeledPoint(2.0, [3.0])
... ]
>>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), initialWeights=np.array([1.0]))
>>> abs(lrm.predict(np.array([0.0])) - 0) < 0.5
True
>>> abs(lrm.predict(np.array([1.0])) - 1) < 0.5
True
>>> abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5
True
>>> data = [
... LabeledPoint(0.0, SparseVector(1, {0: 0.0})),
... LabeledPoint(1.0, SparseVector(1, {0: 1.0})),
... LabeledPoint(3.0, SparseVector(1, {0: 2.0})),
... LabeledPoint(2.0, SparseVector(1, {0: 3.0}))
... ]
>>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), initialWeights=array([1.0]))
>>> abs(lrm.predict(array([0.0])) - 0) < 0.5
True
>>> abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5
True
"""
# train_func should take two parameters, namely data and initial_weights, and
# return the result of a call to the appropriate JVM stub.
# _regression_train_wrapper is responsible for setup and error checking.
def _regression_train_wrapper(train_func, modelClass, data, initial_weights):
first = data.first()
if not isinstance(first, LabeledPoint):
raise ValueError("data should be an RDD of LabeledPoint, but got %s" % first)
initial_weights = initial_weights or [0.0] * len(data.first().features)
weights, intercept = train_func(data, _convert_to_vector(initial_weights))
return modelClass(weights, intercept)
class LinearRegressionWithSGD(object):
@classmethod
def train(cls, data, iterations=100, step=1.0, miniBatchFraction=1.0,
initialWeights=None, regParam=0.0, regType=None, intercept=False):
"""
Train a linear regression model on the given data.
:param data: The training data.
:param iterations: The number of iterations (default: 100).
:param step: The step parameter used in SGD
(default: 1.0).
:param miniBatchFraction: Fraction of data to be used for each SGD
iteration.
:param initialWeights: The initial weights (default: None).
:param regParam: The regularizer parameter (default: 0.0).
:param regType: The type of regularizer used for training
our model.
:Allowed values:
- "l1" for using L1 regularization (lasso),
- "l2" for using L2 regularization (ridge),
- None for no regularization
(default: None)
@param intercept: Boolean parameter which indicates the use
or not of the augmented representation for
training data (i.e. whether bias features
are activated or not).
"""
def train(rdd, i):
return callMLlibFunc("trainLinearRegressionModelWithSGD", rdd, int(iterations),
float(step), float(miniBatchFraction), i, float(regParam),
regType, bool(intercept))
return _regression_train_wrapper(train, LinearRegressionModel, data, initialWeights)
class LassoModel(LinearRegressionModelBase):
"""A linear regression model derived from a least-squares fit with an
l_1 penalty term.
>>> from pyspark.mllib.regression import LabeledPoint
>>> data = [
... LabeledPoint(0.0, [0.0]),
... LabeledPoint(1.0, [1.0]),
... LabeledPoint(3.0, [2.0]),
... LabeledPoint(2.0, [3.0])
... ]
>>> lrm = LassoWithSGD.train(sc.parallelize(data), initialWeights=array([1.0]))
>>> abs(lrm.predict(np.array([0.0])) - 0) < 0.5
True
>>> abs(lrm.predict(np.array([1.0])) - 1) < 0.5
True
>>> abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5
True
>>> data = [
... LabeledPoint(0.0, SparseVector(1, {0: 0.0})),
... LabeledPoint(1.0, SparseVector(1, {0: 1.0})),
... LabeledPoint(3.0, SparseVector(1, {0: 2.0})),
... LabeledPoint(2.0, SparseVector(1, {0: 3.0}))
... ]
>>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), initialWeights=array([1.0]))
>>> abs(lrm.predict(np.array([0.0])) - 0) < 0.5
True
>>> abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5
True
"""
class LassoWithSGD(object):
@classmethod
def train(cls, data, iterations=100, step=1.0, regParam=0.01,
miniBatchFraction=1.0, initialWeights=None):
"""Train a Lasso regression model on the given data."""
def train(rdd, i):
return callMLlibFunc("trainLassoModelWithSGD", rdd, int(iterations), float(step),
float(regParam), float(miniBatchFraction), i)
return _regression_train_wrapper(train, LassoModel, data, initialWeights)
class RidgeRegressionModel(LinearRegressionModelBase):
"""A linear regression model derived from a least-squares fit with an
l_2 penalty term.
>>> from pyspark.mllib.regression import LabeledPoint
>>> data = [
... LabeledPoint(0.0, [0.0]),
... LabeledPoint(1.0, [1.0]),
... LabeledPoint(3.0, [2.0]),
... LabeledPoint(2.0, [3.0])
... ]
>>> lrm = RidgeRegressionWithSGD.train(sc.parallelize(data), initialWeights=array([1.0]))
>>> abs(lrm.predict(np.array([0.0])) - 0) < 0.5
True
>>> abs(lrm.predict(np.array([1.0])) - 1) < 0.5
True
>>> abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5
True
>>> data = [
... LabeledPoint(0.0, SparseVector(1, {0: 0.0})),
... LabeledPoint(1.0, SparseVector(1, {0: 1.0})),
... LabeledPoint(3.0, SparseVector(1, {0: 2.0})),
... LabeledPoint(2.0, SparseVector(1, {0: 3.0}))
... ]
>>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), initialWeights=array([1.0]))
>>> abs(lrm.predict(np.array([0.0])) - 0) < 0.5
True
>>> abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5
True
"""
class RidgeRegressionWithSGD(object):
@classmethod
def train(cls, data, iterations=100, step=1.0, regParam=0.01,
miniBatchFraction=1.0, initialWeights=None):
"""Train a ridge regression model on the given data."""
def train(rdd, i):
return callMLlibFunc("trainRidgeModelWithSGD", rdd, int(iterations), float(step),
float(regParam), float(miniBatchFraction), i)
return _regression_train_wrapper(train, RidgeRegressionModel, data, initialWeights)
def _test():
import doctest
from pyspark import SparkContext
import pyspark.mllib.regression
globs = pyspark.mllib.regression.__dict__.copy()
globs['sc'] = SparkContext('local[4]', 'PythonTest', batchSize=2)
(failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS)
globs['sc'].stop()
if failure_count:
exit(-1)
if __name__ == "__main__":
_test()
|
