Merge pull request #37 from CESNET/dev

Added missed updates for config and DatasetType to docs

Author: milankures

README.md

@@ -71,7 +71,7 @@ For detailed examples refer to [`Tutorial notebooks`](https://github.com/CESNET/
 
 ```python
 from cesnet_tszoo.datasets import CESNET_TimeSeries24
-from cesnet_tszoo.utils.enums import SourceType, AgreggationType
+from cesnet_tszoo.utils.enums import SourceType, AgreggationType, DatasetType
 from cesnet_tszoo.configs import TimeBasedConfig
 
 dataset = CESNET_TimeSeries24.get_dataset(data_root="/some_directory/", source_type=SourceType.INSTITUTIONS, aggregation=AgreggationType.AGG_1_DAY, dataset_type=DatasetType.TIME_BASED)
@@ -93,7 +93,7 @@ Time-based datasets are configured with [`TimeBasedConfig`](https://cesnet.githu
 #### Using [`DisjointTimeBasedCesnetDataset`](https://cesnet.github.io/cesnet-tszoo/reference_disjoint_time_based_cesnet_dataset/) dataset
 ```python
 from cesnet_tszoo.datasets import CESNET_TimeSeries24
-from cesnet_tszoo.utils.enums import SourceType, AgreggationType
+from cesnet_tszoo.utils.enums import SourceType, AgreggationType, DatasetType
 from cesnet_tszoo.configs import DisjointTimeBasedConfig
 
 dataset = CESNET_TimeSeries24.get_dataset("/some_directory/", source_type=SourceType.INSTITUTIONS, aggregation=AgreggationType.AGG_1_DAY, dataset_type=DatasetType.DISJOINT_TIME_BASED)
@@ -118,7 +118,7 @@ Disjoint-time-based datasets are configured with [`DisjointTimeBasedConfig`](htt
 
 ```python
 from cesnet_tszoo.datasets import CESNET_TimeSeries24
-from cesnet_tszoo.utils.enums import SourceType, AgreggationType
+from cesnet_tszoo.utils.enums import SourceType, AgreggationType, DatasetType
 from cesnet_tszoo.configs import SeriesBasedConfig
 
 dataset = CESNET_TimeSeries24.get_dataset(data_root="/some_directory/", source_type=SourceType.INSTITUTIONS, aggregation=AgreggationType.AGG_1_DAY, dataset_type=DatasetType.SERIES_BASED)

docs/benchmarks_tutorial.md

@@ -12,7 +12,7 @@ Benchmarks can consist of various parts:
 - identifier of used config
 - identifier of used annotations (for each AnnotationType)
 - identifier of related_results (only available for premade benchmarks)
-- Used SourceType and AggregationType
+- Used SourceType, AggregationType and DatasetType
 - Database name (here it would be CESNET_TimeSeries24)
 - Whether config or annotations are built-in
 
@@ -30,12 +30,12 @@ from cesnet_tszoo.benchmarks import load_benchmark
 # Can get related_results with `get_related_results` method.
 # Method `get_related_results` returns pandas Dataframe. 
 benchmark = load_benchmark(identifier="2e92831cb502", data_root="/some_directory/")
-dataset = benchmark.get_initialized_dataset(display_config_details=True, check_errors=False, workers="config")
+dataset = benchmark.get_initialized_dataset(display_config_details="text", check_errors=False, workers="config")
 
 # Imports custom benchmark
 # Looks for benchmark at: `os.path.join("/some_directory/", "tszoo", "benchmarks", identifier)`
 benchmark = load_benchmark(identifier="test2", data_root="/some_directory/")
-dataset = benchmark.get_initialized_dataset(display_config_details=True, check_errors=False, workers="config")
+dataset = benchmark.get_initialized_dataset(display_config_details="text", check_errors=False, workers="config")
 
 ```
 
@@ -55,13 +55,14 @@ dataset = benchmark.get_initialized_dataset(display_config_details=True, check_e
 ```python
 
 from cesnet_tszoo.datasets import CESNET_TimeSeries24
+from cesnet_tszoo.utils.enums import SourceType, AgreggationType, DatasetType
 from cesnet_tszoo.configs import TimeBasedConfig                                                                            
 
 time_based_dataset = CESNET_TimeSeries24.get_dataset(data_root="/some_directory/", source_type=SourceType.IP_ADDRESSES_FULL, aggregation=AgreggationType.AGG_1_DAY, dataset_type=DatasetType.TIME_BASED, display_details=True)
 config = TimeBasedConfig([1548925, 443967], train_time_period=1.0, features_to_take=["n_flows", "n_packets", "n_bytes"], transform_with=None)
 
 # Call on time-based dataset to use created config -> must be done before saving exporting benchmark
-time_based_dataset.set_dataset_config_and_initialize(config, workers=0, display_config_details=True)
+time_based_dataset.set_dataset_config_and_initialize(config, workers=0, display_config_details="text")
 
 time_based_dataset.save_benchmark(identifier="test1", force_write=True)
 
@@ -84,13 +85,13 @@ from cesnet_tszoo.configs import TimeBasedConfig
 
 config = TimeBasedConfig([1548925, 443967], train_time_period=1.0, features_to_take=["n_flows", "n_packets", "n_bytes"], transform_with=None)
 
-time_based_dataset.set_dataset_config_and_initialize(config, workers=0, display_config_details=True)
+time_based_dataset.set_dataset_config_and_initialize(config, workers=0, display_config_details="text")
 
 # Exports config
 time_based_dataset.save_config(identifier="test_config1", create_with_details_file=True, force_write=True)
 
 # Imports custom config
-time_based_dataset.import_config(identifier="test_config1", display_config_details=True, workers="config")
+time_based_dataset.import_config(identifier="test_config1", display_config_details="text", workers="config")
 
 ```
 

docs/getting_started.md

@@ -8,7 +8,7 @@
 ### Download a dataset
 ```python
 from cesnet_tszoo.datasets import CESNET_TimeSeries24
-from cesnet_tszoo.utils.enums import SourceType, AgreggationType
+from cesnet_tszoo.utils.enums import SourceType, AgreggationType, DatasetType
 
 dataset = CESNET_TimeSeries24.get_dataset("/some_directory/", source_type=SourceType.INSTITUTIONS, aggregation=AgreggationType.AGG_1_DAY, dataset_type=DatasetType.TIME_BASED)
 ```
@@ -47,7 +47,7 @@ Set up logging to get more information from the package.
 #### Using [`TimeBasedCesnetDataset`](reference_time_based_cesnet_dataset.md#cesnet_tszoo.datasets.time_based_cesnet_dataset.TimeBasedCesnetDataset) dataset
 ```python
 from cesnet_tszoo.datasets import CESNET_TimeSeries24
-from cesnet_tszoo.utils.enums import SourceType, AgreggationType
+from cesnet_tszoo.utils.enums import SourceType, AgreggationType, DatasetType
 from cesnet_tszoo.configs import TimeBasedConfig
 
 dataset = CESNET_TimeSeries24.get_dataset("/some_directory/", source_type=SourceType.INSTITUTIONS, aggregation=AgreggationType.AGG_1_DAY, dataset_type=DatasetType.TIME_BASED)
@@ -71,7 +71,7 @@ Can load data using:
 #### Using [`DisjointTimeBasedCesnetDataset`](reference_disjoint_time_based_cesnet_dataset.md#cesnet_tszoo.datasets.disjoint_time_based_cesnet_dataset.DisjointTimeBasedCesnetDataset) dataset
 ```python
 from cesnet_tszoo.datasets import CESNET_TimeSeries24
-from cesnet_tszoo.utils.enums import SourceType, AgreggationType
+from cesnet_tszoo.utils.enums import SourceType, AgreggationType, DatasetType
 from cesnet_tszoo.configs import DisjointTimeBasedConfig
 
 dataset = CESNET_TimeSeries24.get_dataset("/some_directory/", source_type=SourceType.INSTITUTIONS, aggregation=AgreggationType.AGG_1_DAY, dataset_type=DatasetType.DISJOINT_TIME_BASED)
@@ -97,7 +97,7 @@ Can load data using:
 #### Using [`SeriesBasedCesnetDataset`](reference_series_based_cesnet_dataset.md#cesnet_tszoo.datasets.series_based_cesnet_dataset.SeriesBasedCesnetDataset) dataset
 ```python
 from cesnet_tszoo.datasets import CESNET_TimeSeries24
-from cesnet_tszoo.utils.enums import SourceType, AgreggationType
+from cesnet_tszoo.utils.enums import SourceType, AgreggationType, DatasetType
 from cesnet_tszoo.configs import SeriesBasedConfig
 
 dataset = CESNET_TimeSeries24.get_dataset("/some_directory/", source_type=SourceType.INSTITUTIONS, aggregation=AgreggationType.AGG_1_DAY, dataset_type=DatasetType.SERIES_BASED)

docs/using_datasets.md

@@ -17,11 +17,11 @@ from cesnet_tszoo.benchmarks import load_benchmark
 
 # Imports built-in benchmark
 benchmark = load_benchmark(identifier="2e92831cb502", data_root="/some_directory/")
-dataset = benchmark.get_initialized_dataset(display_config_details=True, check_errors=False, workers="config")
+dataset = benchmark.get_initialized_dataset(display_config_details="text", check_errors=False, workers="config")
 
 # Imports custom benchmark
 benchmark = load_benchmark(identifier="test2", data_root="/some_directory/")
-dataset = benchmark.get_initialized_dataset(display_config_details=True, check_errors=False, workers="config")
+dataset = benchmark.get_initialized_dataset(display_config_details="text", check_errors=False, workers="config")
 
 ```
 
@@ -36,7 +36,7 @@ from cesnet_tszoo.configs import TimeBasedConfig # For time-based dataset
 from cesnet_tszoo.configs import SeriesBasedConfig # For series-based dataset   
 from cesnet_tszoo.configs import DisjointTimeBasedConfig # For disjoint-time-based dataset
 
-from cesnet_tszoo.utils.enums import AgreggationType, SourceType # Used for specifying which dataset to use
+from cesnet_tszoo.utils.enums import SourceType, AgreggationType, DatasetType # Used for specifying which dataset to use
 from cesnet_tszoo.datasets import CESNET_TimeSeries24
 
 # Time-based

docs/utilities.md

@@ -26,7 +26,7 @@ logging.basicConfig(
 - Recommended to call at least once after download
 
 ```python
-from cesnet_tszoo.utils.enums import AgreggationType, SourceType
+from cesnet_tszoo.utils.enums import SourceType, AgreggationType, DatasetType
 from cesnet_tszoo.datasets import CESNET_TimeSeries24                                                                
 
 # Can be called at dataset creation
@@ -71,7 +71,7 @@ Returns all data in dictionary related to set.
 from cesnet_tszoo.configs import TimeBasedConfig   
 
 config = TimeBasedConfig(20, train_time_period=0.5)
-time_based_dataset.set_dataset_config_and_initialize(config, workers=0, display_config_details=False)
+time_based_dataset.set_dataset_config_and_initialize(config, workers=0, display_config_details=None)
 
 time_based_dataset.get_data_about_set(about=SplitType.TRAIN)
 
@@ -148,7 +148,7 @@ dataset.plot(ts_id=10, plot_type="line", features="n_flows", feature_per_plot=Tr
 - You can check whether dataset has additional data, with method `display_dataset_details`.
 
 ```python
-from cesnet_tszoo.utils.enums import AgreggationType, SourceType
+from cesnet_tszoo.utils.enums import SourceType, AgreggationType, DatasetType
 from cesnet_tszoo.datasets import CESNET_TimeSeries24                                                                
 
 time_based_dataset = CESNET_TimeSeries24.get_dataset(data_root="/some_directory/", source_type=SourceType.IP_ADDRESSES_SAMPLE, aggregation=AgreggationType.AGG_1_DAY, dataset_type=DatasetType.TIME_BASED, display_details=True)

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "cesnet_tszoo"
-version = "2.1.1"
+version = "2.1.2"
 authors = [
     { name = "Milan Kureš", email = "[email protected]" },
     { name = "Josef Koumar", email = "[email protected]" },