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

add missing files 

Former-commit-id: 3f7cfc37e8 [formerly b74d2356a8] [formerly 3c458d75c2 [formerly a2a165609a]] [formerly 2e3b925ec7 [formerly e31b06239f] [formerly 31ea5772a1 [formerly 0a384a8984]]] [formerly 2bf9721c55 [formerly 493f4c3014] [formerly f1974f2891 [formerly 81227824d7]] [formerly f3db06651b [formerly 8d78b06e9e] [formerly f907ef71f5 [formerly cf532ec083]]]] [formerly 946bb68241 [formerly 96ba9ceb7d] [formerly 180343f152 [formerly 9fbd0ca43a]] [formerly cb24f146f1 [formerly 414b396fc2] [formerly d304cadd7f [formerly 329acba2f7]]] [formerly 44cbbbdeb6 [formerly 3b1d52222c] [formerly 795250861e [formerly d0ab4d27cb]] [formerly 99abf724fd [formerly 5f40093539] [formerly 3fb7bbd40a [formerly 908f6374bf]]]]] [formerly 156900ecff [formerly f7b387c445] [formerly 92c76931e3 [formerly c7731b7d46]] [formerly 339e1c29e8 [formerly 20a8356f5a] [formerly 5b71a77b6b [formerly 6a57734672]]] [formerly 6717e7f53e [formerly a432c417ff] [formerly 1fe8593ba4 [formerly 568256d572]] [formerly d841eea05b [formerly 58c80baa94] [formerly b2e4d6bc92 [formerly 809a919c22]]]] [formerly 7d24f921fc [formerly 5f16493568] [formerly 32434bfce5 [formerly 773ffcf350]] [formerly 174627e114 [formerly cf159d2675] [formerly 09c70e1cc9 [formerly 2b9c213aad]]] [formerly b6c669ab04 [formerly 7c0b650d34] [formerly 2e210feb12 [formerly 7143d46ab4]] [formerly bbf4c5f3aa [formerly b6370d4615] [formerly b7147eadb4 [formerly 501035efa9]]]]]]
Former-commit-id: 49012012f6 [formerly b9bb9e1499] [formerly 4a6c600048 [formerly e7e139db3f]] [formerly 78b2a6c046 [formerly f641bd1128] [formerly 1c7a591504 [formerly 67689a8d9c]]] [formerly 797c03e482 [formerly 2bbff2c4db] [formerly 9ab8c745ee [formerly dc5e07cb3f]] [formerly 12fcc4027f [formerly ec3f1d9078] [formerly b3d4bcd0a5 [formerly d73228793c]]]] [formerly 912e6c46ec [formerly 52270242af] [formerly c8b312f42a [formerly d40c96306e]] [formerly 84e9e155a4 [formerly 8a8acd041a] [formerly 6115e6e49f [formerly 643cff68df]]] [formerly ee555be73d [formerly 5a214858f4] [formerly 5cc2dade41 [formerly c792c83235]] [formerly 5932e3f807 [formerly 3390f186bc] [formerly b7147eadb4]]]]
Former-commit-id: 71accf5c5f [formerly 52bc81705b] [formerly 367a0893b3 [formerly e5f4ba0713]] [formerly e7f38d4073 [formerly bea0027d20] [formerly a0d9e910f1 [formerly e936a0d13e]]] [formerly 2eb4bfb3fc [formerly 5769769ddc] [formerly 61e28b2083 [formerly 4d1b5b5d39]] [formerly d939d3e623 [formerly 091ffd784f] [formerly bf0416419e [formerly 0f38b48d92]]]]
Former-commit-id: 71dff5394c [formerly faebf231de] [formerly 2f13c6357f [formerly 3014c51839]] [formerly d8ff0b66fc [formerly c0403e6401] [formerly 4f37326f4f [formerly 035a2e6ff3]]]
Former-commit-id: 1e2d5f638a [formerly e49643e7de] [formerly 3fe5eb8c6b [formerly a5428797f0]]
Former-commit-id: 887b61afe5 [formerly dba4aebac6]
Former-commit-id: 66f8f84a57
master
YileAllenChen1 5 years ago
parent
3ff248de99
commit
ced19bb59d
6 changed files with 535 additions and 0 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. +70
    -0
      examples/build_Autocorrelation_pipeline.py
  2. +70
    -0
      examples/build_DeepLog_pipeline.py
  3. +70
    -0
      examples/build_MatrixProfile_pipeline.py
  4. +70
    -0
      examples/build_SOD_pipeline.py
  5. +134
    -0
      tods/tests/test_Autocorrelation.py
  6. +121
    -0
      tods/tests/test_TimeIntervalTransform.py

+ 70
- 0
examples/build_Autocorrelation_pipeline.py View File

@@ -0,0 +1,70 @@
from d3m import index
from d3m.metadata.base import ArgumentType
from d3m.metadata.pipeline import Pipeline, PrimitiveStep

# -> dataset_to_dataframe -> column_parser -> extract_columns_by_semantic_types(attributes) -> imputer -> random_forest
# extract_columns_by_semantic_types(targets) -> ^

# Creating pipeline
pipeline_description = Pipeline()
pipeline_description.add_input(name='inputs')

# Step 0: dataset_to_dataframe
step_0 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.dataset_to_dataframe.Common'))
step_0.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='inputs.0')
step_0.add_output('produce')
pipeline_description.add_step(step_0)

# Step 1: column_parser
step_1 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.column_parser.Common'))
step_1.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
step_1.add_output('produce')
pipeline_description.add_step(step_1)

# Step 2: extract_columns_by_semantic_types(attributes)
step_2 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.extract_columns_by_semantic_types.Common'))
step_2.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
step_2.add_output('produce')
step_2.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
data=['https://metadata.datadrivendiscovery.org/types/Attribute'])
pipeline_description.add_step(step_2)

# Step 3: extract_columns_by_semantic_types(targets)
step_3 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.extract_columns_by_semantic_types.Common'))
step_3.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
step_3.add_output('produce')
step_3.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
data=['https://metadata.datadrivendiscovery.org/types/TrueTarget'])
pipeline_description.add_step(step_3)

attributes = 'steps.2.produce'
targets = 'steps.3.produce'

# Step 4: processing
step_4 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler'))
step_4.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference=attributes)
step_4.add_output('produce')
pipeline_description.add_step(step_4)

# Step 5: algorithm`
step_5 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.feature_analysis.auto_correlation'))
step_5.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.4.produce')
step_5.add_output('produce')
pipeline_description.add_step(step_5)

# Step 6: Predictions
step_6 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.construct_predictions.Common'))
step_6.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.5.produce')
step_6.add_argument(name='reference', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
step_6.add_output('produce')
pipeline_description.add_step(step_6)

# Final Output
pipeline_description.add_output(name='output predictions', data_reference='steps.6.produce')

# Output to json
data = pipeline_description.to_json()
with open('example_pipeline.json', 'w') as f:
f.write(data)
print(data)


+ 70
- 0
examples/build_DeepLog_pipeline.py View File

@@ -0,0 +1,70 @@
from d3m import index
from d3m.metadata.base import ArgumentType
from d3m.metadata.pipeline import Pipeline, PrimitiveStep

# -> dataset_to_dataframe -> column_parser -> extract_columns_by_semantic_types(attributes) -> imputer -> random_forest
# extract_columns_by_semantic_types(targets) -> ^

# Creating pipeline
pipeline_description = Pipeline()
pipeline_description.add_input(name='inputs')

# Step 0: dataset_to_dataframe
step_0 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.dataset_to_dataframe.Common'))
step_0.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='inputs.0')
step_0.add_output('produce')
pipeline_description.add_step(step_0)

# Step 1: column_parser
step_1 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.column_parser.Common'))
step_1.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
step_1.add_output('produce')
pipeline_description.add_step(step_1)

# Step 2: extract_columns_by_semantic_types(attributes)
step_2 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.extract_columns_by_semantic_types.Common'))
step_2.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
step_2.add_output('produce')
step_2.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
data=['https://metadata.datadrivendiscovery.org/types/Attribute'])
pipeline_description.add_step(step_2)

# Step 3: extract_columns_by_semantic_types(targets)
step_3 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.extract_columns_by_semantic_types.Common'))
step_3.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
step_3.add_output('produce')
step_3.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
data=['https://metadata.datadrivendiscovery.org/types/TrueTarget'])
pipeline_description.add_step(step_3)

attributes = 'steps.2.produce'
targets = 'steps.3.produce'

# Step 4: processing
step_4 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler'))
step_4.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference=attributes)
step_4.add_output('produce')
pipeline_description.add_step(step_4)

# Step 5: algorithm`
step_5 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.detection_algorithm.deeplog'))
step_5.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.4.produce')
step_5.add_output('produce')
pipeline_description.add_step(step_5)

# Step 6: Predictions
step_6 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.construct_predictions.Common'))
step_6.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.5.produce')
step_6.add_argument(name='reference', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
step_6.add_output('produce')
pipeline_description.add_step(step_6)

# Final Output
pipeline_description.add_output(name='output predictions', data_reference='steps.6.produce')

# Output to json
data = pipeline_description.to_json()
with open('example_pipeline.json', 'w') as f:
f.write(data)
print(data)


+ 70
- 0
examples/build_MatrixProfile_pipeline.py View File

@@ -0,0 +1,70 @@
from d3m import index
from d3m.metadata.base import ArgumentType
from d3m.metadata.pipeline import Pipeline, PrimitiveStep

# -> dataset_to_dataframe -> column_parser -> extract_columns_by_semantic_types(attributes) -> imputer -> random_forest
# extract_columns_by_semantic_types(targets) -> ^

# Creating pipeline
pipeline_description = Pipeline()
pipeline_description.add_input(name='inputs')

# Step 0: dataset_to_dataframe
step_0 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.dataset_to_dataframe.Common'))
step_0.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='inputs.0')
step_0.add_output('produce')
pipeline_description.add_step(step_0)

# Step 1: column_parser
step_1 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.column_parser.Common'))
step_1.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
step_1.add_output('produce')
pipeline_description.add_step(step_1)

# Step 2: extract_columns_by_semantic_types(attributes)
step_2 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.extract_columns_by_semantic_types.Common'))
step_2.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
step_2.add_output('produce')
step_2.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
data=['https://metadata.datadrivendiscovery.org/types/Attribute'])
pipeline_description.add_step(step_2)

# Step 3: extract_columns_by_semantic_types(targets)
step_3 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.extract_columns_by_semantic_types.Common'))
step_3.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
step_3.add_output('produce')
step_3.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
data=['https://metadata.datadrivendiscovery.org/types/TrueTarget'])
pipeline_description.add_step(step_3)

attributes = 'steps.2.produce'
targets = 'steps.3.produce'

# Step 4: processing
step_4 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler'))
step_4.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference=attributes)
step_4.add_output('produce')
pipeline_description.add_step(step_4)

# Step 5: algorithm`
step_5 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.detection_algorithm.matrix_profile'))
step_5.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.4.produce')
step_5.add_output('produce')
pipeline_description.add_step(step_5)

# Step 6: Predictions
step_6 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.construct_predictions.Common'))
step_6.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.5.produce')
step_6.add_argument(name='reference', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
step_6.add_output('produce')
pipeline_description.add_step(step_6)

# Final Output
pipeline_description.add_output(name='output predictions', data_reference='steps.6.produce')

# Output to json
data = pipeline_description.to_json()
with open('example_pipeline.json', 'w') as f:
f.write(data)
print(data)


+ 70
- 0
examples/build_SOD_pipeline.py View File

@@ -0,0 +1,70 @@
from d3m import index
from d3m.metadata.base import ArgumentType
from d3m.metadata.pipeline import Pipeline, PrimitiveStep

# -> dataset_to_dataframe -> column_parser -> extract_columns_by_semantic_types(attributes) -> imputer -> random_forest
# extract_columns_by_semantic_types(targets) -> ^

# Creating pipeline
pipeline_description = Pipeline()
pipeline_description.add_input(name='inputs')

# Step 0: dataset_to_dataframe
step_0 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.dataset_to_dataframe.Common'))
step_0.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='inputs.0')
step_0.add_output('produce')
pipeline_description.add_step(step_0)

# Step 1: column_parser
step_1 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.column_parser.Common'))
step_1.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
step_1.add_output('produce')
pipeline_description.add_step(step_1)

# Step 2: extract_columns_by_semantic_types(attributes)
step_2 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.extract_columns_by_semantic_types.Common'))
step_2.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
step_2.add_output('produce')
step_2.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
data=['https://metadata.datadrivendiscovery.org/types/Attribute'])
pipeline_description.add_step(step_2)

# Step 3: extract_columns_by_semantic_types(targets)
step_3 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.extract_columns_by_semantic_types.Common'))
step_3.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
step_3.add_output('produce')
step_3.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
data=['https://metadata.datadrivendiscovery.org/types/TrueTarget'])
pipeline_description.add_step(step_3)

attributes = 'steps.2.produce'
targets = 'steps.3.produce'

# Step 4: processing
step_4 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.timeseries_processing.transformation.axiswise_scaler'))
step_4.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference=attributes)
step_4.add_output('produce')
pipeline_description.add_step(step_4)

# Step 5: algorithm`
step_5 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.detection_algorithm.pyod_sod'))
step_5.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.4.produce')
step_5.add_output('produce')
pipeline_description.add_step(step_5)

# Step 6: Predictions
step_6 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.data_transformation.construct_predictions.Common'))
step_6.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.5.produce')
step_6.add_argument(name='reference', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
step_6.add_output('produce')
pipeline_description.add_step(step_6)

# Final Output
pipeline_description.add_output(name='output predictions', data_reference='steps.6.produce')

# Output to json
data = pipeline_description.to_json()
with open('example_pipeline.json', 'w') as f:
f.write(data)
print(data)


+ 134
- 0
tods/tests/test_Autocorrelation.py View File

@@ -0,0 +1,134 @@
import unittest


from datetime import datetime

from d3m import container, utils
from d3m.metadata import base as metadata_base

from feature_analysis import AutoCorrelation


#import utils as test_utils

import numpy as np
import pandas as pd

class AutoCorrelationTestCase(unittest.TestCase):
def test_basic(self):
self.maxDiff = None
main = container.DataFrame({'d3mIndex': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
'timestamp': [1472918400, 1472918700, 1472919000, 1472919300,
1472919600, 1472919900, 1472920200, 1472920500, 1472920800, 1472921100],
'value': [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0],
'ground_truth': [0, 1, 0, 1, 0, 1, 0, 1, 0, 1]},
columns = ['d3mIndex', 'timestamp', 'value', 'ground_truth'], generate_metadata = True)
"""
main.metadata = main.metadata.update_column(0, {'name': 'd3mIndex_'})
main.metadata = main.metadata.update_column(1, {'name': 'timestamp_'})
main.metadata = main.metadata.update_column(2, {'name': 'value_'})
main.metadata = main.metadata.update_column(3, {'name': 'ground_truth_'})
"""

#print(main)

self.assertEqual(utils.to_json_structure(main.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema': metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 10,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 4,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {'structural_type': 'numpy.int64', 'name': 'd3mIndex'},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {'structural_type': 'numpy.int64', 'name': 'timestamp'},
}, {
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {'structural_type': 'numpy.float64', 'name': 'value'},
}, {
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {'structural_type': 'numpy.int64', 'name': 'ground_truth'},
}])

hyperparams_class = AutoCorrelation.AutoCorrelation.metadata.get_hyperparams().defaults()
hyperparams_class = hyperparams_class.replace({'nlags': 2})
#hyperparams_class = hyperparams_class.replace({'use_semantic_types': True})
primitive = AutoCorrelation.AutoCorrelation(hyperparams=hyperparams_class)
new_main = primitive.produce(inputs=main).value
print(new_main)
new_main_drop = new_main['value_acf']
new_main_drop = new_main_drop.reset_index(drop = True)


expected_result = pd.DataFrame({'acf':[1.000000, 0.700000, 0.412121, 0.148485, -0.078788, -0.257576, -0.375758, -0.421212, -0.381818, -0.245455]})
new_main_drop.reset_index()

self.assertEqual(all(new_main_drop), all(expected_result))


#print(main.metadata.to_internal_simple_structure())
#print(new_main.metadata.to_internal_simple_structure())

self.assertEqual(utils.to_json_structure(main.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema': metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 10,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 4,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {'structural_type': 'numpy.int64', 'name': 'd3mIndex'},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {'structural_type': 'numpy.int64', 'name': 'timestamp'},
}, {
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {'structural_type': 'numpy.float64', 'name': 'value'},
}, {
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {'structural_type': 'numpy.int64', 'name': 'ground_truth'},
}])

params = primitive.get_params()
primitive.set_params(params=params)


if __name__ == '__main__':
unittest.main()

+ 121
- 0
tods/tests/test_TimeIntervalTransform.py View File

@@ -0,0 +1,121 @@
import unittest


from datetime import datetime

from d3m import container, utils
from d3m.metadata import base as metadata_base

from data_processing import TimeIntervalTransform


#import utils as test_utils

import numpy as np

class TimeIntervalTransformTestCase(unittest.TestCase):
def test_basic(self):
self.maxDiff = None
main = container.DataFrame({'d3mIndex': [0, 1, 2, 3, 4, 5, 6, 7],
'timestamp': [1472918400, 1472918700, 1472919000, 1472919300,
1472919600, 1472919900, 1472920200, 1472920500],
'value': [0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0],
'ground_truth': [0, 1, 0, 1, 0, 1, 0,1]},
columns = ['d3mIndex', 'timestamp', 'value', 'ground_truth'], generate_metadata = True)
"""
main.metadata = main.metadata.update_column(0, {'name': 'd3mIndex_'})
main.metadata = main.metadata.update_column(1, {'name': 'timestamp_'})
main.metadata = main.metadata.update_column(2, {'name': 'value_'})
main.metadata = main.metadata.update_column(3, {'name': 'ground_truth_'})
"""

#print(main)

self.assertEqual(utils.to_json_structure(main.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema': metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 8,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 4,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {'structural_type': 'numpy.int64', 'name': 'd3mIndex'},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {'structural_type': 'numpy.int64', 'name': 'timestamp'},
}, {
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {'structural_type': 'numpy.float64', 'name': 'value'},
}, {
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {'structural_type': 'numpy.int64', 'name': 'ground_truth'},
}])

hyperparams_class = TimeIntervalTransform.TimeIntervalTransform.metadata.get_hyperparams()
primitive = TimeIntervalTransform.TimeIntervalTransform(hyperparams=hyperparams_class.defaults())
new_main = primitive.produce(inputs=main).value
new_rows = len(new_main.index)
self.assertEqual(new_rows, 8)

#print(main.metadata.to_internal_simple_structure())
#print(new_main.metadata.to_internal_simple_structure())

self.assertEqual(utils.to_json_structure(main.metadata.to_internal_simple_structure()), [{
'selector': [],
'metadata': {
# 'top_level': 'main',
'schema': metadata_base.CONTAINER_SCHEMA_VERSION,
'structural_type': 'd3m.container.pandas.DataFrame',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/Table'],
'dimension': {
'name': 'rows',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularRow'],
'length': 8,
},
},
}, {
'selector': ['__ALL_ELEMENTS__'],
'metadata': {
'dimension': {
'name': 'columns',
'semantic_types': ['https://metadata.datadrivendiscovery.org/types/TabularColumn'],
'length': 4,
},
},
}, {
'selector': ['__ALL_ELEMENTS__', 0],
'metadata': {'structural_type': 'numpy.int64', 'name': 'd3mIndex'},
}, {
'selector': ['__ALL_ELEMENTS__', 1],
'metadata': {'structural_type': 'numpy.int64', 'name': 'timestamp'},
}, {
'selector': ['__ALL_ELEMENTS__', 2],
'metadata': {'structural_type': 'numpy.float64', 'name': 'value'},
}, {
'selector': ['__ALL_ELEMENTS__', 3],
'metadata': {'structural_type': 'numpy.int64', 'name': 'ground_truth'},
}])

params = primitive.get_params()
primitive.set_params(params=params)


if __name__ == '__main__':
unittest.main()


Write Preview
Loading…
Cancel
Save