OpenI
/
tods
Not watched
1
0
Fork 0
Code
Releases 0 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
Browse Source

minor update Matrix Profile 

Former-commit-id: 219f70b1a2 [formerly 99f9e1eb69] [formerly f5f16ce532 [formerly 50352b3ff3]] [formerly 2e5704ad73 [formerly 5b29820537] [formerly 431b0ddb22 [formerly d798a8e4e3]]] [formerly b0d5d4d534 [formerly 44f4678454] [formerly ee808e7e44 [formerly 9859d0b436]] [formerly 50c9d7cea1 [formerly 601849d7bd] [formerly 5345efd370 [formerly e1d4a59360]]]] [formerly 7b34cd8f6c [formerly 9e168f96d0] [formerly f2571a9a02 [formerly f7858302f9]] [formerly b1528fd27d [formerly c2a264017d] [formerly 1a2af1e1fd [formerly 62d7e9b2ed]]] [formerly a953785cfa [formerly 27aa0afbf7] [formerly eee3141c0a [formerly 74cc095a2a]] [formerly 7a838661c9 [formerly 826360a453] [formerly 19b2607cc6 [formerly 9497930570]]]]] [formerly 601c051e8f [formerly 13bb1bb849] [formerly bb89c1bded [formerly 28b683f6e7]] [formerly 68265b09c5 [formerly 4ec648ef37] [formerly d76b272cc0 [formerly 2ee66794ec]]] [formerly 47aab2a490 [formerly 659e827756] [formerly 9dc3a20fd5 [formerly c4d0adb03f]] [formerly bf4c2ef7ff [formerly bdec0bac94] [formerly 0cae18b065 [formerly 4c3c172e47]]]] [formerly 2972f27f73 [formerly 84acd0a1b6] [formerly 232b8924f8 [formerly d925d6f4d3]] [formerly 5217d26dd9 [formerly 658eb7e5c8] [formerly c5c3d4f714 [formerly 2a0f1ff8c3]]] [formerly 1f89ca49a9 [formerly 7ae1036fb3] [formerly 10e5070850 [formerly 12ab0b78cd]] [formerly db6a58bc98 [formerly db92fd3772] [formerly 37fb024b8f [formerly c23effffc6]]]]]]
Former-commit-id: ef4232d8cb [formerly 77b26e468d] [formerly 3aaaca10c1 [formerly bea844e99d]] [formerly de3fd235c3 [formerly d920adf559] [formerly 13d3b270da [formerly d698f233e5]]] [formerly 6d767a08aa [formerly 46e3c38fde] [formerly 75d1c6fb5c [formerly 01103f969d]] [formerly 54a08fcd21 [formerly 41a1571a38] [formerly 20dcf58162 [formerly 343002311a]]]] [formerly 4feb51d60b [formerly 97764bb9f3] [formerly 57a357434f [formerly f61d9c7dba]] [formerly 24e3fc024d [formerly 0d3c84a67f] [formerly 5d363f96a1 [formerly 7910b082c3]]] [formerly 741cfa0b09 [formerly 6fcfe42121] [formerly 86df6392c0 [formerly 82d4124b2b]] [formerly 3120bc060c [formerly 839f6e0c8a] [formerly 37fb024b8f]]]]
Former-commit-id: a817081230 [formerly 2cbd88db2f] [formerly 11b1b009d2 [formerly cbc5bd4988]] [formerly 594c594b0c [formerly f7b92eb97e] [formerly c54cb5cb71 [formerly b88b1fa18c]]] [formerly 044a2fbb3f [formerly 1efe53be7f] [formerly 99c091f7db [formerly 734e2740f6]] [formerly 9dc8407f7e [formerly 4545ca14d8] [formerly e1bfd4d1da [formerly 6898b4a6a4]]]]
Former-commit-id: 3eaf18de9d [formerly dd877a066e] [formerly a4a8ae76c4 [formerly ce174d3cce]] [formerly a57fb2e9e1 [formerly df4f539b32] [formerly 48464db993 [formerly b37110284f]]]
Former-commit-id: 07096c4efb [formerly ef0477b822] [formerly 7944fb187e [formerly 56e573e9ef]]
Former-commit-id: fe6a976ab6 [formerly 6ce5c42aa8]
Former-commit-id: da363bbcc3
master
YileAllenChen1 4 years ago
parent
606d4e52e4
commit
46fb9aa772
3 changed files with 516 additions and 269 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. +128
    -269
      tods/detection_algorithm/MatrixProfile.py
  2. +381
    -0
      tods/detection_algorithm/MatrixProfile2.py
  3. +7
    -0
      tods/tests/detection_algorithm/test_MatrixProfile.py

+ 128
- 269
tods/detection_algorithm/MatrixProfile.py View File

@@ -1,99 +1,57 @@
from typing import Any, Callable, List, Dict, Union, Optional, Sequence, Tuple
from numpy import ndarray
from collections import OrderedDict
from scipy import sparse
import os
import sklearn
import numpy
import typing
import time
from scipy import sparse
from numpy import ndarray
from collections import OrderedDict
from typing import Any, Callable, List, Dict, Union, Optional, Sequence, Tuple
import pandas as pd

# Custom import commands if any
import warnings
import numpy as np
import pandas as pd
import logging, uuid
from scipy import sparse
from numpy import ndarray
from collections import OrderedDict
from common_primitives import dataframe_utils, utils
from sklearn.utils import check_array
from sklearn.exceptions import NotFittedError
# from numba import njit
from pyod.utils.utility import argmaxn

from d3m.container.numpy import ndarray as d3m_ndarray
from d3m.container import DataFrame as d3m_dataframe
from d3m.metadata import hyperparams, params, base as metadata_base
from d3m import utils
from d3m import container
from d3m.base import utils as base_utils
from d3m.exceptions import PrimitiveNotFittedError
from d3m.container import DataFrame as d3m_dataframe
from d3m.container.numpy import ndarray as d3m_ndarray
from d3m.primitive_interfaces import base, transformer
from d3m.metadata import base as metadata_base, hyperparams
from d3m.metadata import hyperparams, params, base as metadata_base
from d3m.primitive_interfaces.base import CallResult, DockerContainer

# from d3m.primitive_interfaces.supervised_learning import SupervisedLearnerPrimitiveBase
from d3m.primitive_interfaces.unsupervised_learning import UnsupervisedLearnerPrimitiveBase
from d3m.primitive_interfaces.transformer import TransformerPrimitiveBase

from d3m.primitive_interfaces.base import ProbabilisticCompositionalityMixin, ContinueFitMixin
from d3m import exceptions
import pandas
import uuid

from d3m import container, utils as d3m_utils

from .UODBasePrimitive import Params_ODBase, Hyperparams_ODBase, UnsupervisedOutlierDetectorBase
import stumpy
# from typing import Union

__all__ = ('MatrixProfile',)
Inputs = d3m_dataframe
Outputs = d3m_dataframe

Inputs = container.DataFrame
Outputs = container.DataFrame

class PrimitiveCount:
primitive_no = 0

class Params(Params_ODBase):
######## Add more Attributes #######
pass

class Hyperparams(hyperparams.Hyperparams):
window_size = hyperparams.UniformInt(
lower = 0,
upper = 100, #TODO: Define the correct the upper bound
default=50,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="window size to calculate"
)
# Keep previous
dataframe_resource = hyperparams.Hyperparameter[typing.Union[str, None]](
default=None,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Resource ID of a DataFrame to extract if there are multiple tabular resources inside a Dataset and none is a dataset entry point.",
)
use_columns = hyperparams.Set(
elements=hyperparams.Hyperparameter[int](-1),
default=(2,),
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="A set of column indices to force primitive to operate on. If any specified column cannot be parsed, it is skipped.",
)
exclude_columns = hyperparams.Set(
elements=hyperparams.Hyperparameter[int](-1),
default=(0,1,3,),
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="A set of column indices to not operate on. Applicable only if \"use_columns\" is not provided.",
)
return_result = hyperparams.Enumeration(
values=['append', 'replace', 'new'],
default='new',
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Should parsed columns be appended, should they replace original columns, or should only parsed columns be returned? This hyperparam is ignored if use_semantic_types is set to false.",
)
use_semantic_types = hyperparams.UniformBool(
default=False,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Controls whether semantic_types metadata will be used for filtering columns in input dataframe. Setting this to false makes the code ignore return_result and will produce only the output dataframe"
)
add_index_columns = hyperparams.UniformBool(
default=False,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Also include primary index columns if input data has them. Applicable only if \"return_result\" is set to \"new\".",
)
error_on_no_input = hyperparams.UniformBool(
default=True,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Throw an exception if no input column is selected/provided. Defaults to true to behave like sklearn. To prevent pipelines from breaking set this to False.",
)
return_semantic_type = hyperparams.Enumeration[str](
values=['https://metadata.datadrivendiscovery.org/types/Attribute',
'https://metadata.datadrivendiscovery.org/types/ConstructedAttribute'],
default='https://metadata.datadrivendiscovery.org/types/Attribute',
description='Decides what semantic type to attach to generated attributes',
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter']
)

class Hyperparams(Hyperparams_ODBase):
######## Add more Attributes #######
pass

class MP:
"""
@@ -103,6 +61,28 @@ class MP:
self._window_size = window_size
return

def fit(self, X, y=None):
"""Fit detector. y is ignored in unsupervised methods.
Parameters
----------
X : numpy array of shape (n_samples, n_features)
The input samples.
y : Ignored
Not used, present for API consistency by convention.
Returns
-------
self : object
Fitted estimator.
"""

# validate inputs X and y (optional)
# X = check_array(X)
# self._set_n_classes(y)
# self.decision_scores_ = self.decision_function(X)
# self._process_decision_scores()
return self

def produce(self, data):

"""
@@ -113,15 +93,47 @@ class MP:
nparray

"""
"""
#print(data.shape[0s])
rows = data.shape[0]
columns = data.shape[1]
convert_data = np.reshape(data, (columns, rows))
T_data = data.transpose()
#print(T_data)
transformed_columns=utils.pandas.DataFrame()
for col in data.columns:
transformed_columns=d3m_dataframe
print(len(data))
for col in range(len(data)):
output = stumpy.stump(data[col], m = self._window_size)
output = pd.DataFrame(output)
#print("output", output)
transformed_columns=pd.concat([transformed_columns,output],axis=1)
#transformed_columns[col]=output
#print(transformed_columns)
return transformed_columns
# transformed_data = []
# for row in T_data:
# print(row)
# output = stumpy.stump(row, m = self._window_size)
# print(output)
"""
#input from UODBasePrimitive is np.ndarray not dataframe
print("data ",type(data))
transformed_columns=utils.pandas.DataFrame()
for col in data:
print(col)
output = stumpy.stump(col, m = self._window_size)
output = pd.DataFrame(output)
transformed_columns=pd.concat([transformed_columns,output])
#print(transformed_columns)
return transformed_columns

class MatrixProfilePrimitive(transformer.TransformerPrimitiveBase[Inputs, Outputs, Hyperparams]):
def predict(self, data):
return self.produce(data)
class MatrixProfile(UnsupervisedOutlierDetectorBase[Inputs, Outputs, Params, Hyperparams]):
"""

A primitive that performs matrix profile on a DataFrame using Stumpy package
Stumpy documentation: https://stumpy.readthedocs.io/en/latest/index.html

@@ -137,7 +149,7 @@ class MatrixProfilePrimitive(transformer.TransformerPrimitiveBase[Inputs, Output
ignore_trivial : bool
Set to `True` if this is a self-join. Otherwise, for AB-join, set this
to `False`. Default is `True`.
Returns
Returnsfdsf
-------
out : ndarray
The first column consists of the matrix profile, the second column
@@ -147,7 +159,6 @@ class MatrixProfilePrimitive(transformer.TransformerPrimitiveBase[Inputs, Output
"""

metadata = metadata_base.PrimitiveMetadata({
'__author__': "DATA Lab @Texas A&M University",
'name': "Matrix Profile",
@@ -163,219 +174,67 @@ class MatrixProfilePrimitive(transformer.TransformerPrimitiveBase[Inputs, Output
})


def __init__(self, *, hyperparams: Hyperparams) -> None:
super().__init__(hyperparams=hyperparams)
self._clf = MP(window_size = hyperparams['window_size'])
self.primitiveNo = PrimitiveCount.primitive_no
PrimitiveCount.primitive_no+=1
def __init__(self, *,
hyperparams: Hyperparams, #
random_seed: int = 0,
docker_containers: Dict[str, DockerContainer] = None) -> None:
super().__init__(hyperparams=hyperparams, random_seed=random_seed, docker_containers=docker_containers)

def produce(self, *, inputs: Inputs, timeout: float = None, iterations: int = None) -> base.CallResult[Outputs]:
self._clf = MP(window_size=hyperparams['window_size'])

def set_training_data(self, *, inputs: Inputs) -> None:
"""
Set training data for outlier detection.
Args:

inputs: Container DataFrame

timeout: Default

iterations: Default

Returns:

Container DataFrame containing Matrix Profile of selected columns
None
"""
super().set_training_data(inputs=inputs)

# Get cols to fit.
self._fitted = False
self._training_inputs, self._training_indices = self._get_columns_to_fit(inputs, self.hyperparams)
self._input_column_names = self._training_inputs.columns


if len(self._training_indices) > 0:
self._fitted = True
else: # pragma: no cover
if self.hyperparams['error_on_no_input']:
raise RuntimeError("No input columns were selected")
self.logger.warn("No input columns were selected")

if not self._fitted: # pragma: no cover
raise PrimitiveNotFittedError("Primitive not fitted.")
sk_inputs = inputs
if self.hyperparams['use_semantic_types']: # pragma: no cover
sk_inputs = inputs.iloc[:, self._training_indices]
output_columns = []
if len(self._training_indices) > 0:
sk_output = self._clf.produce(sk_inputs)
if sparse.issparse(sk_output): # pragma: no cover
sk_output = sk_output.toarray()
outputs = self._wrap_predictions(inputs, sk_output)
if len(outputs.columns) == len(self._input_column_names): # pragma: no cover
outputs.columns = self._input_column_names
output_columns = [outputs]

else: # pragma: no cover
if self.hyperparams['error_on_no_input']:
raise RuntimeError("No input columns were selected")
self.logger.warn("No input columns were selected")

outputs = base_utils.combine_columns(return_result=self.hyperparams['return_result'],
add_index_columns=self.hyperparams['add_index_columns'],
inputs=inputs, column_indices=self._training_indices,
columns_list=output_columns)

#print(outputs.columns)
#outputs.columns = [str(x) for x in outputs.columns]

return CallResult(outputs)

def _update_metadata(self, outputs): # pragma: no cover
outputs.metadata = outputs.metadata.generate(outputs)
@classmethod
def _get_columns_to_fit(cls, inputs: Inputs, hyperparams: Hyperparams): # pragma: no cover

def fit(self, *, timeout: float = None, iterations: int = None) -> CallResult[None]:
"""
Fit model with training data.
Args:
*: Container DataFrame. Time series data up to fit.

Select columns to fit.
Args:
inputs: Container DataFrame
hyperparams: d3m.metadata.hyperparams.Hyperparams

Returns:
list

"""

if not hyperparams['use_semantic_types']:
return inputs, list(range(len(inputs.columns)))

inputs_metadata = inputs.metadata


def can_produce_column(column_index: int) -> bool:
return cls._can_produce_column(inputs_metadata, column_index, hyperparams)

columns_to_produce, columns_not_to_produce = base_utils.get_columns_to_use(inputs_metadata,
use_columns=hyperparams['use_columns'],
exclude_columns=hyperparams['exclude_columns'],
can_use_column=can_produce_column)


"""
Encountered error: when hyperparams['use_columns'] = (2,3) and hyperparams['exclude_columns'] is (1,2)
columns_to_produce is still [2]
"""
return inputs.iloc[:, columns_to_produce], columns_to_produce

@classmethod
def _can_produce_column(cls, inputs_metadata: metadata_base.DataMetadata, column_index: int, hyperparams: Hyperparams) -> bool: # pragma: no cover

Returns:
None
"""
return super().fit()

Output whether a column can be processed.
Args:
inputs_metadata: d3m.metadata.base.DataMetadata
column_index: int

Returns:
bool

def produce(self, *, inputs: Inputs, timeout: float = None, iterations: int = None) -> CallResult[Outputs]:
"""

column_metadata = inputs_metadata.query((metadata_base.ALL_ELEMENTS, column_index))

accepted_structural_types = (int, float, np.integer, np.float64) #changed numpy to np
accepted_semantic_types = set()
accepted_semantic_types.add("https://metadata.datadrivendiscovery.org/types/Attribute")

if not issubclass(column_metadata['structural_type'], accepted_structural_types):
return False

semantic_types = set(column_metadata.get('semantic_types', []))

if len(semantic_types) == 0:
cls.logger.warning("No semantic types found in column metadata")
return False

# Making sure all accepted_semantic_types are available in semantic_types
if len(accepted_semantic_types - semantic_types) == 0:
return True

return False

def _wrap_predictions(self, inputs: Inputs, predictions: ndarray) -> Outputs:

"""

Wrap predictions into dataframe
Process the testing data.
Args:
inputs: Container Dataframe
predictions: array-like data (n_samples, n_features)
inputs: Container DataFrame. Time series data up to outlier detection.

Returns:
Dataframe
Container DataFrame
1 marks Outliers, 0 marks normal.
"""
print("inputs ",type(inputs))
return super().produce(inputs=inputs, timeout=timeout, iterations=iterations)

outputs = d3m_dataframe(predictions, generate_metadata=True)
target_columns_metadata = self._add_target_columns_metadata(outputs.metadata, self.hyperparams, self.primitiveNo)
outputs.metadata = self._update_predictions_metadata(inputs.metadata, outputs, target_columns_metadata)
return outputs



@classmethod
def _update_predictions_metadata(cls, inputs_metadata: metadata_base.DataMetadata, outputs: Optional[Outputs],
target_columns_metadata: List[OrderedDict]) -> metadata_base.DataMetadata:

def get_params(self) -> Params:
"""
Return parameters.
Args:
None

Updata metadata for selected columns.
Args:
inputs_metadata: metadata_base.DataMetadata
outputs: Container Dataframe
target_columns_metadata: list

Returns:
d3m.metadata.base.DataMetadata

Returns:
class Params
"""
return super().get_params()

outputs_metadata = metadata_base.DataMetadata().generate(value=outputs)

for column_index, column_metadata in enumerate(target_columns_metadata):
column_metadata.pop("structural_type", None)
outputs_metadata = outputs_metadata.update_column(column_index, column_metadata)

return outputs_metadata


@classmethod
def _add_target_columns_metadata(cls, outputs_metadata: metadata_base.DataMetadata, hyperparams, primitiveNo):
def set_params(self, *, params: Params) -> None:
"""
Add target columns metadata
Set parameters for outlier detection.
Args:
outputs_metadata: metadata.base.DataMetadata
hyperparams: d3m.metadata.hyperparams.Hyperparams
params: class Params

Returns:
List[OrderedDict]
None
"""
outputs_length = outputs_metadata.query((metadata_base.ALL_ELEMENTS,))['dimension']['length']
target_columns_metadata: List[OrderedDict] = []
for column_index in range(outputs_length):
column_name = "{0}{1}_{2}".format(cls.metadata.query()['name'], primitiveNo, column_index)
column_metadata = OrderedDict()
semantic_types = set()
semantic_types.add(hyperparams["return_semantic_type"])
column_metadata['semantic_types'] = list(semantic_types)

column_metadata["name"] = str(column_name)
target_columns_metadata.append(column_metadata)
return target_columns_metadata
super().set_params(params=params)

+ 381
- 0
tods/detection_algorithm/MatrixProfile2.py View File

@@ -0,0 +1,381 @@
import os
import sklearn
import numpy
import typing
import time
from scipy import sparse
from numpy import ndarray
from collections import OrderedDict
from typing import Any, Callable, List, Dict, Union, Optional, Sequence, Tuple

import numpy as np
import pandas as pd
import logging, uuid
from scipy import sparse
from numpy import ndarray
from collections import OrderedDict
from common_primitives import dataframe_utils, utils

from d3m import utils
from d3m import container
from d3m.base import utils as base_utils
from d3m.exceptions import PrimitiveNotFittedError
from d3m.container import DataFrame as d3m_dataframe
from d3m.container.numpy import ndarray as d3m_ndarray
from d3m.primitive_interfaces import base, transformer
from d3m.metadata import base as metadata_base, hyperparams
from d3m.metadata import hyperparams, params, base as metadata_base
from d3m.primitive_interfaces.base import CallResult, DockerContainer

import stumpy

__all__ = ('MatrixProfile',)

Inputs = container.DataFrame
Outputs = container.DataFrame

class PrimitiveCount:
primitive_no = 0


class Hyperparams(hyperparams.Hyperparams):
window_size = hyperparams.UniformInt(
lower = 0,
upper = 100, #TODO: Define the correct the upper bound
default=50,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="window size to calculate"
)
# Keep previous
dataframe_resource = hyperparams.Hyperparameter[typing.Union[str, None]](
default=None,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Resource ID of a DataFrame to extract if there are multiple tabular resources inside a Dataset and none is a dataset entry point.",
)
use_columns = hyperparams.Set(
elements=hyperparams.Hyperparameter[int](-1),
default=(2,),
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="A set of column indices to force primitive to operate on. If any specified column cannot be parsed, it is skipped.",
)
exclude_columns = hyperparams.Set(
elements=hyperparams.Hyperparameter[int](-1),
default=(0,1,3,),
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="A set of column indices to not operate on. Applicable only if \"use_columns\" is not provided.",
)
return_result = hyperparams.Enumeration(
values=['append', 'replace', 'new'],
default='new',
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Should parsed columns be appended, should they replace original columns, or should only parsed columns be returned? This hyperparam is ignored if use_semantic_types is set to false.",
)
use_semantic_types = hyperparams.UniformBool(
default=False,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Controls whether semantic_types metadata will be used for filtering columns in input dataframe. Setting this to false makes the code ignore return_result and will produce only the output dataframe"
)
add_index_columns = hyperparams.UniformBool(
default=False,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Also include primary index columns if input data has them. Applicable only if \"return_result\" is set to \"new\".",
)
error_on_no_input = hyperparams.UniformBool(
default=True,
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
description="Throw an exception if no input column is selected/provided. Defaults to true to behave like sklearn. To prevent pipelines from breaking set this to False.",
)
return_semantic_type = hyperparams.Enumeration[str](
values=['https://metadata.datadrivendiscovery.org/types/Attribute',
'https://metadata.datadrivendiscovery.org/types/ConstructedAttribute'],
default='https://metadata.datadrivendiscovery.org/types/Attribute',
description='Decides what semantic type to attach to generated attributes',
semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter']
)


class MP:
"""
This is the class for matrix profile function
"""
def __init__(self, window_size):
self._window_size = window_size
return

def produce(self, data):

"""

Args:
data: dataframe column
Returns:
nparray

"""
transformed_columns=utils.pandas.DataFrame()
for col in data.columns:
output = stumpy.stump(data[col], m = self._window_size)
output = pd.DataFrame(output)
transformed_columns=pd.concat([transformed_columns,output],axis=1)
return transformed_columns

class MatrixProfile(transformer.TransformerPrimitiveBase[Inputs, Outputs, Hyperparams]):
"""
A primitive that performs matrix profile on a DataFrame using Stumpy package
Stumpy documentation: https://stumpy.readthedocs.io/en/latest/index.html

Parameters
----------
T_A : ndarray
The time series or sequence for which to compute the matrix profile
m : int
Window size
T_B : ndarray
The time series or sequence that contain your query subsequences
of interest. Default is `None` which corresponds to a self-join.
ignore_trivial : bool
Set to `True` if this is a self-join. Otherwise, for AB-join, set this
to `False`. Default is `True`.
Returns
-------
out : ndarray
The first column consists of the matrix profile, the second column
consists of the matrix profile indices, the third column consists of
the left matrix profile indices, and the fourth column consists of
the right matrix profile indices.
"""

metadata = metadata_base.PrimitiveMetadata({
'__author__': "DATA Lab @Texas A&M University",
'name': "Matrix Profile",
#'python_path': 'd3m.primitives.tods.feature_analysis.matrix_profile',
'python_path': 'd3m.primitives.tods.detection_algorithm.matrix_profile',
'source': {'name': "DATALAB @Taxes A&M University", 'contact': 'mailto:khlai037@tamu.edu',
'uris': ['https://gitlab.com/lhenry15/tods/-/blob/Yile/anomaly-primitives/anomaly_primitives/MatrixProfile.py']},
'algorithm_types': [metadata_base.PrimitiveAlgorithmType.MATRIX_PROFILE,],
'primitive_family': metadata_base.PrimitiveFamily.FEATURE_CONSTRUCTION,
'id': str(uuid.uuid3(uuid.NAMESPACE_DNS, 'MatrixProfilePrimitive')),
'hyperparams_to_tune': ['window_size'],
'version': '0.0.2',
})


def __init__(self, *, hyperparams: Hyperparams) -> None:
super().__init__(hyperparams=hyperparams)
self._clf = MP(window_size = hyperparams['window_size'])
self.primitiveNo = PrimitiveCount.primitive_no
PrimitiveCount.primitive_no+=1

def produce(self, *, inputs: Inputs, timeout: float = None, iterations: int = None) -> base.CallResult[Outputs]:

"""

Args:

inputs: Container DataFrame

timeout: Default

iterations: Default

Returns:

Container DataFrame containing Matrix Profile of selected columns
"""

# Get cols to fit.
self._fitted = False
self._training_inputs, self._training_indices = self._get_columns_to_fit(inputs, self.hyperparams)
self._input_column_names = self._training_inputs.columns


if len(self._training_indices) > 0:
self._fitted = True
else: # pragma: no cover
if self.hyperparams['error_on_no_input']:
raise RuntimeError("No input columns were selected")
self.logger.warn("No input columns were selected")

if not self._fitted: # pragma: no cover
raise PrimitiveNotFittedError("Primitive not fitted.")
sk_inputs = inputs
if self.hyperparams['use_semantic_types']: # pragma: no cover
sk_inputs = inputs.iloc[:, self._training_indices]
output_columns = []
if len(self._training_indices) > 0:
sk_output = self._clf.produce(sk_inputs)
if sparse.issparse(sk_output): # pragma: no cover
sk_output = sk_output.toarray()
outputs = self._wrap_predictions(inputs, sk_output)
if len(outputs.columns) == len(self._input_column_names): # pragma: no cover
outputs.columns = self._input_column_names
output_columns = [outputs]

else: # pragma: no cover
if self.hyperparams['error_on_no_input']:
raise RuntimeError("No input columns were selected")
self.logger.warn("No input columns were selected")

outputs = base_utils.combine_columns(return_result=self.hyperparams['return_result'],
add_index_columns=self.hyperparams['add_index_columns'],
inputs=inputs, column_indices=self._training_indices,
columns_list=output_columns)

#print(outputs.columns)
#outputs.columns = [str(x) for x in outputs.columns]

return CallResult(outputs)

def _update_metadata(self, outputs): # pragma: no cover
outputs.metadata = outputs.metadata.generate(outputs)
@classmethod
def _get_columns_to_fit(cls, inputs: Inputs, hyperparams: Hyperparams): # pragma: no cover

"""

Select columns to fit.
Args:
inputs: Container DataFrame
hyperparams: d3m.metadata.hyperparams.Hyperparams

Returns:
list

"""

if not hyperparams['use_semantic_types']:
return inputs, list(range(len(inputs.columns)))

inputs_metadata = inputs.metadata


def can_produce_column(column_index: int) -> bool:
return cls._can_produce_column(inputs_metadata, column_index, hyperparams)

columns_to_produce, columns_not_to_produce = base_utils.get_columns_to_use(inputs_metadata,
use_columns=hyperparams['use_columns'],
exclude_columns=hyperparams['exclude_columns'],
can_use_column=can_produce_column)


"""
Encountered error: when hyperparams['use_columns'] = (2,3) and hyperparams['exclude_columns'] is (1,2)
columns_to_produce is still [2]
"""
return inputs.iloc[:, columns_to_produce], columns_to_produce

@classmethod
def _can_produce_column(cls, inputs_metadata: metadata_base.DataMetadata, column_index: int, hyperparams: Hyperparams) -> bool: # pragma: no cover

"""

Output whether a column can be processed.
Args:
inputs_metadata: d3m.metadata.base.DataMetadata
column_index: int

Returns:
bool

"""

column_metadata = inputs_metadata.query((metadata_base.ALL_ELEMENTS, column_index))

accepted_structural_types = (int, float, np.integer, np.float64) #changed numpy to np
accepted_semantic_types = set()
accepted_semantic_types.add("https://metadata.datadrivendiscovery.org/types/Attribute")

if not issubclass(column_metadata['structural_type'], accepted_structural_types):
return False

semantic_types = set(column_metadata.get('semantic_types', []))

if len(semantic_types) == 0:
cls.logger.warning("No semantic types found in column metadata")
return False

# Making sure all accepted_semantic_types are available in semantic_types
if len(accepted_semantic_types - semantic_types) == 0:
return True

return False

def _wrap_predictions(self, inputs: Inputs, predictions: ndarray) -> Outputs:

"""

Wrap predictions into dataframe
Args:
inputs: Container Dataframe
predictions: array-like data (n_samples, n_features)

Returns:
Dataframe

"""

outputs = d3m_dataframe(predictions, generate_metadata=True)
target_columns_metadata = self._add_target_columns_metadata(outputs.metadata, self.hyperparams, self.primitiveNo)
outputs.metadata = self._update_predictions_metadata(inputs.metadata, outputs, target_columns_metadata)
return outputs



@classmethod
def _update_predictions_metadata(cls, inputs_metadata: metadata_base.DataMetadata, outputs: Optional[Outputs],
target_columns_metadata: List[OrderedDict]) -> metadata_base.DataMetadata:

"""

Updata metadata for selected columns.
Args:
inputs_metadata: metadata_base.DataMetadata
outputs: Container Dataframe
target_columns_metadata: list

Returns:
d3m.metadata.base.DataMetadata

"""

outputs_metadata = metadata_base.DataMetadata().generate(value=outputs)

for column_index, column_metadata in enumerate(target_columns_metadata):
column_metadata.pop("structural_type", None)
outputs_metadata = outputs_metadata.update_column(column_index, column_metadata)

return outputs_metadata


@classmethod
def _add_target_columns_metadata(cls, outputs_metadata: metadata_base.DataMetadata, hyperparams, primitiveNo):
"""
Add target columns metadata
Args:
outputs_metadata: metadata.base.DataMetadata
hyperparams: d3m.metadata.hyperparams.Hyperparams

Returns:
List[OrderedDict]
"""
outputs_length = outputs_metadata.query((metadata_base.ALL_ELEMENTS,))['dimension']['length']
target_columns_metadata: List[OrderedDict] = []
for column_index in range(outputs_length):
column_name = "{0}{1}_{2}".format(cls.metadata.query()['name'], primitiveNo, column_index)
column_metadata = OrderedDict()
semantic_types = set()
semantic_types.add(hyperparams["return_semantic_type"])
column_metadata['semantic_types'] = list(semantic_types)

column_metadata["name"] = str(column_name)
target_columns_metadata.append(column_metadata)
return target_columns_metadata

+ 7
- 0
tods/tests/detection_algorithm/test_MatrixProfile.py View File

@@ -58,10 +58,17 @@ class MatrixProfileTest(unittest.TestCase):
hyperparams_class = MatrixProfilePrimitive.metadata.get_hyperparams()
hyperparams = hyperparams_class.defaults()
hyperparams = hyperparams.replace({'window_size': 3})
<<<<<<< Updated upstream:tods/tests/detection_algorithm/test_MatrixProfile.py

primitive = MatrixProfilePrimitive(hyperparams=hyperparams)
#primitive.set_training_data(inputs=main)
#primitive.fit()
=======
#print(type(main))
primitive = MatrixProfile(hyperparams=hyperparams)
primitive.set_training_data(inputs=main)
primitive.fit()
>>>>>>> Stashed changes:tods/tests/test_MatrixProfile.py
new_main = primitive.produce(inputs=main).value
print(new_main)



Write Preview
Loading…
Cancel
Save