diff --git a/demo-project/src/demo_project/requirements.in b/demo-project/src/demo_project/requirements.in
index dd53d43f3a..d035f9438e 100644
--- a/demo-project/src/demo_project/requirements.in
+++ b/demo-project/src/demo_project/requirements.in
@@ -6,7 +6,7 @@ jupyter~=1.0
jupyter_client>=5.1, <7.0
jupyterlab~=3.0
kedro~=0.18.0
-kedro-datasets[pandas.CSVDataset,pandas.ExcelDataset, pandas.ParquetDataset, plotly.PlotlyDataset]<=2.0.0
+git+https://github.com/kedro-org/kedro-plugins.git@main#egg=kedro-datasets[pandas.ParquetDataset,pandas.CSVDataset,pandas.ExcelDataset,plotly.JSONDataset]&subdirectory=kedro-datasets # temporary pin until the next release of kedro-datasets
nbstripout~=0.4
pytest-cov~=2.5
pytest-mock>=1.7.1, <2.0
diff --git a/demo-project/src/docker_requirements.txt b/demo-project/src/docker_requirements.txt
index 1934ea38d1..46b3b18fda 100644
--- a/demo-project/src/docker_requirements.txt
+++ b/demo-project/src/docker_requirements.txt
@@ -1,5 +1,5 @@
kedro>=0.18.0
-kedro-datasets[pandas.CSVDataset,pandas.ExcelDataset, pandas.ParquetDataset, plotly.PlotlyDataset, matplotlib.MatplotlibWriter]<=2.0.0
+git+https://github.com/kedro-org/kedro-plugins.git@main#egg=kedro-datasets[pandas.ParquetDataset,pandas.CSVDataset,pandas.ExcelDataset,plotly.JSONDataset]&subdirectory=kedro-datasets # temporary pin until the next release of kedro-datasets
scikit-learn~=1.0
pillow~=9.0
seaborn~=0.11.2
diff --git a/package/kedro_viz/api/rest/responses.py b/package/kedro_viz/api/rest/responses.py
index 885fdd8142..08fb3c76bd 100644
--- a/package/kedro_viz/api/rest/responses.py
+++ b/package/kedro_viz/api/rest/responses.py
@@ -131,11 +131,9 @@ class Config:
class DataNodeMetadataAPIResponse(BaseAPIResponse):
filepath: Optional[str]
type: str
- plot: Optional[Dict]
- image: Optional[str]
- tracking_data: Optional[Dict]
run_command: Optional[str]
- preview: Optional[Dict]
+ preview: Optional[Union[Dict, str]]
+ preview_type: Optional[str]
stats: Optional[Dict]
class Config:
diff --git a/package/kedro_viz/data_access/repositories/tracking_datasets.py b/package/kedro_viz/data_access/repositories/tracking_datasets.py
index e4471c3d2c..d8d06cb9a0 100644
--- a/package/kedro_viz/data_access/repositories/tracking_datasets.py
+++ b/package/kedro_viz/data_access/repositories/tracking_datasets.py
@@ -8,8 +8,8 @@
TRACKING_DATASET_GROUPS,
TrackingDatasetGroup,
TrackingDatasetModel,
- get_dataset_type,
)
+from kedro_viz.models.utils import get_dataset_type
if TYPE_CHECKING:
try:
diff --git a/package/kedro_viz/integrations/kedro/data_loader.py b/package/kedro_viz/integrations/kedro/data_loader.py
index 8e242c09a9..3ffd608bca 100644
--- a/package/kedro_viz/integrations/kedro/data_loader.py
+++ b/package/kedro_viz/integrations/kedro/data_loader.py
@@ -3,9 +3,7 @@
load data from projects created in a range of Kedro versions.
"""
# pylint: disable=import-outside-toplevel, protected-access
-# pylint: disable=missing-function-docstring
-import base64
import json
import logging
from pathlib import Path
@@ -14,24 +12,7 @@
from kedro import __version__
from kedro.framework.session import KedroSession
from kedro.framework.session.store import BaseSessionStore
-
-try:
- from kedro_datasets import ( # isort:skip
- json as json_dataset,
- matplotlib,
- plotly,
- tracking,
- )
-except ImportError: # kedro_datasets is not installed.
- from kedro.extras.datasets import ( # Safe since ImportErrors are suppressed within kedro.
- json as json_dataset,
- matplotlib,
- plotly,
- tracking,
- )
-
from kedro.io import DataCatalog
-from kedro.io.core import get_filepath_str
from kedro.pipeline import Pipeline
logger = logging.getLogger(__name__)
@@ -129,50 +110,3 @@ def load_data(
stats_dict = _get_dataset_stats(project_path)
return catalog, pipelines_dict, session_store, stats_dict
-
-
-# Try to access the attribute to trigger the import of dependencies, only modify the _load
-# if dependencies are installed.
-# These datasets do not have _load methods defined (tracking and matplotlib) or do not
-# load to json (plotly), hence the need to define _load here.
-try:
- getattr(matplotlib, "MatplotlibWriter") # Trigger the lazy import
-
- def matplotlib_writer_load(dataset: matplotlib.MatplotlibWriter) -> str:
- load_path = get_filepath_str(dataset._get_load_path(), dataset._protocol)
- with dataset._fs.open(load_path, mode="rb") as img_file:
- base64_bytes = base64.b64encode(img_file.read())
- return base64_bytes.decode("utf-8")
-
- matplotlib.MatplotlibWriter._load = matplotlib_writer_load
-except (ImportError, AttributeError):
- pass
-
-try:
- getattr(plotly, "JSONDataset") # Trigger import
- plotly.JSONDataset._load = json_dataset.JSONDataset._load
-except (ImportError, AttributeError):
- getattr(plotly, "JSONDataSet") # Trigger import
- plotly.JSONDataSet._load = json_dataset.JSONDataSet._load
-
-
-try:
- getattr(plotly, "PlotlyDataset") # Trigger import
- plotly.PlotlyDataset._load = json_dataset.JSONDataset._load
-except (ImportError, AttributeError):
- getattr(plotly, "PlotlyDataSet") # Trigger import
- plotly.PlotlyDataSet._load = json_dataset.JSONDataSet._load
-
-try:
- getattr(tracking, "JSONDataset") # Trigger import
- tracking.JSONDataset._load = json_dataset.JSONDataset._load
-except (ImportError, AttributeError):
- getattr(tracking, "JSONDataSet") # Trigger import
- tracking.JSONDataSet._load = json_dataset.JSONDataSet._load
-
-try:
- getattr(tracking, "MetricsDataset") # Trigger import
- tracking.MetricsDataset._load = json_dataset.JSONDataset._load
-except (ImportError, AttributeError):
- getattr(tracking, "MetricsDataSet") # Trigger import
- tracking.MetricsDataSet._load = json_dataset.JSONDataSet._load
diff --git a/package/kedro_viz/models/experiment_tracking.py b/package/kedro_viz/models/experiment_tracking.py
index 96e61a586e..7512984621 100644
--- a/package/kedro_viz/models/experiment_tracking.py
+++ b/package/kedro_viz/models/experiment_tracking.py
@@ -63,7 +63,7 @@ class TrackingDatasetGroup(str, Enum):
JSON = "json"
-# Map dataset types (as produced by get_dataset_type) to their group
+# Map dataset types to their group
TRACKING_DATASET_GROUPS = {
"plotly.plotly_dataset.PlotlyDataset": TrackingDatasetGroup.PLOT,
"plotly.json_dataset.JSONDataset": TrackingDatasetGroup.PLOT,
@@ -110,9 +110,11 @@ def load_tracking_data(self, run_id: str):
try:
if TRACKING_DATASET_GROUPS[self.dataset_type] is TrackingDatasetGroup.PLOT:
- self.runs[run_id] = {self.dataset._filepath.name: self.dataset.load()}
+ self.runs[run_id] = {
+ self.dataset._filepath.name: self.dataset.preview() # type: ignore
+ }
else:
- self.runs[run_id] = self.dataset.load()
+ self.runs[run_id] = self.dataset.preview() # type: ignore
except Exception as exc: # pylint: disable=broad-except # pragma: no cover
logger.warning(
"'%s' with version '%s' could not be loaded. Full exception: %s: %s",
diff --git a/package/kedro_viz/models/flowchart.py b/package/kedro_viz/models/flowchart.py
index 4212b727c2..8e1f04fa4e 100644
--- a/package/kedro_viz/models/flowchart.py
+++ b/package/kedro_viz/models/flowchart.py
@@ -1,4 +1,5 @@
"""`kedro_viz.models.flowchart` defines data models to represent Kedro entities in a viz graph."""
+
# pylint: disable=protected-access, missing-function-docstring
import abc
import hashlib
@@ -586,52 +587,16 @@ def set_viz_metadata(cls, _, values):
return None
- # TODO: improve this scheme.
- def is_plot_node(self):
- """Check if the current node is a plot node.
- Currently it only recognises one underlying dataset as a plot node.
- In the future, we might want to make this generic.
- """
- return self.dataset_type in (
- "plotly.plotly_dataset.PlotlyDataset",
- "plotly.json_dataset.JSONDataset",
- "plotly.plotly_dataset.PlotlyDataSet",
- "plotly.json_dataset.JSONDataSet",
- )
-
- def is_image_node(self):
- """Check if the current node is a matplotlib image node."""
- return self.dataset_type == "matplotlib.matplotlib_writer.MatplotlibWriter"
-
- def is_metric_node(self):
- """Check if the current node is a metrics node."""
- return self.dataset_type in (
- "tracking.metrics_dataset.MetricsDataset",
- "tracking.metrics_dataset.MetricsDataSet",
- )
-
- def is_json_node(self):
- """Check if the current node is a JSONDataset node."""
- return self.dataset_type in (
- "tracking.json_dataset.JSONDataset",
- "tracking.json_dataset.JSONDataSet",
- )
-
- def is_tracking_node(self):
- """Checks if the current node is a tracking data node"""
- return self.is_json_node() or self.is_metric_node()
-
- def is_preview_node(self):
- """Checks if the current node has a preview"""
- if not (self.viz_metadata and self.viz_metadata.get("preview_args", None)):
- return False
-
- return True
-
def get_preview_args(self):
"""Gets the preview arguments for a dataset"""
return self.viz_metadata.get("preview_args", None)
+ def is_preview_disabled(self):
+ """Checks if the dataset has a preview disabled"""
+ return (
+ self.viz_metadata is not None and self.viz_metadata.get("preview") is False
+ )
+
class TranscodedDataNode(GraphNode):
"""Represent a graph node of type data
@@ -718,24 +683,15 @@ class DataNodeMetadata(GraphNodeMetadata):
# The path to the actual data file for the underlying dataset
filepath: Optional[str]
- plot: Optional[Dict] = Field(
- None, description="The optional plot data if the underlying dataset has a plot"
- )
-
- # The image data if the underlying dataset has a image
- # currently only applicable for matplotlib.MatplotlibWriter
- image: Optional[str] = Field(
- None, description="The image data if the underlying dataset has a image"
- )
- tracking_data: Optional[Dict] = Field(
- None,
- description="The tracking data if the underlying dataset has a tracking dataset",
- )
run_command: Optional[str] = Field(
None, description="Command to run the pipeline to this node"
)
- preview: Optional[Dict] = Field(
- None, description="Preview data for the underlying datanode"
+ preview: Optional[Union[Dict, str]] = Field(
+ None, description="Preview data for the underlying data node"
+ )
+
+ preview_type: Optional[str] = Field(
+ None, description="Type of preview for the dataset"
)
stats: Optional[Dict] = Field(None, description="The statistics for the data node.")
@@ -769,35 +725,39 @@ def set_run_command(cls, _):
return f"kedro run --to-outputs={cls.data_node.name}"
return None
- @validator("plot", always=True)
- def set_plot(cls, _):
- if cls.data_node.is_plot_node():
- return cls.data_node.kedro_obj.load()
- return None
+ @validator("preview", always=True)
+ def set_preview(cls, _):
+ if cls.data_node.is_preview_disabled() or not hasattr(cls.dataset, "preview"):
+ return None
- @validator("image", always=True)
- def set_image(cls, _):
- if cls.data_node.is_image_node():
- return cls.data_node.kedro_obj.load()
- return None
+ try:
+ preview_args = (
+ cls.data_node.get_preview_args() if cls.data_node.viz_metadata else None
+ )
+ if preview_args is None:
+ return cls.dataset.preview()
+ return cls.dataset.preview(**preview_args)
- @validator("tracking_data", always=True)
- def set_tracking_data(cls, _):
- if cls.data_node.is_tracking_node():
- return cls.data_node.kedro_obj.load()
- return None
+ except Exception as exc: # pylint: disable=broad-except
+ logger.warning(
+ "'%s' could not be previewed. Full exception: %s: %s",
+ cls.data_node.name,
+ type(exc).__name__,
+ exc,
+ )
+ return None
- @validator("preview", always=True)
- def set_preview(cls, _):
- if not (cls.data_node.is_preview_node() and hasattr(cls.dataset, "_preview")):
+ @validator("preview_type", always=True)
+ def set_preview_type(cls, _):
+ if cls.data_node.is_preview_disabled() or not hasattr(cls.dataset, "preview"):
return None
try:
- return cls.dataset._preview(**cls.data_node.get_preview_args())
+ return inspect.signature(cls.dataset.preview).return_annotation.__name__
except Exception as exc: # pylint: disable=broad-except # pragma: no cover
logger.warning(
- "'%s' could not be previewed. Full exception: %s: %s",
+ "'%s' did not have preview type. Full exception: %s: %s",
cls.data_node.name,
type(exc).__name__,
exc,
diff --git a/package/test_requirements.txt b/package/test_requirements.txt
index 6db009dbeb..5fa8487c9b 100644
--- a/package/test_requirements.txt
+++ b/package/test_requirements.txt
@@ -1,7 +1,7 @@
-r requirements.txt
kedro >=0.18.0
-kedro-datasets[pandas.ParquetDataset, pandas.CSVDataset, pandas.ExcelDataset, plotly.JSONDataset]<=2.0.0
+git+https://github.com/kedro-org/kedro-plugins.git@main#egg=kedro-datasets[pandas.ParquetDataset,pandas.CSVDataset,pandas.ExcelDataset,plotly.JSONDataset]&subdirectory=kedro-datasets # temporary pin until the next release of kedro-datasets
kedro-telemetry>=0.1.1 # for testing telemetry integration
bandit~=1.7
behave~=1.2
diff --git a/package/tests/conftest.py b/package/tests/conftest.py
index 2a7e793ea7..e788bfc389 100644
--- a/package/tests/conftest.py
+++ b/package/tests/conftest.py
@@ -267,11 +267,17 @@ def json(self):
@pytest.fixture
def example_data_frame():
data = {
- "id": ["35029", "30292"],
- "company_rating": ["100%", "67%"],
- "company_location": ["Niue", "Anguilla"],
- "total_fleet_count": ["4.0", "6.0"],
- "iata_approved": ["f", "f"],
+ "id": ["35029", "30292", "12345", "67890", "54321", "98765", "11111"],
+ "company_rating": ["100%", "67%", "80%", "95%", "72%", "88%", "75%"],
+ "company_location": [
+ "Niue",
+ "Anguilla",
+ "Barbados",
+ "Fiji",
+ "Grenada",
+ "Jamaica",
+ "Trinidad and Tobago",
+ ],
}
yield pd.DataFrame(data)
@@ -292,10 +298,32 @@ def example_csv_dataset(tmp_path, example_data_frame):
@pytest.fixture
-def example_data_node():
+def example_csv_filepath(tmp_path, example_data_frame):
+ csv_file_path = tmp_path / "temporary_test_data.csv"
+ example_data_frame.to_csv(csv_file_path, index=False)
+ yield csv_file_path
+
+
+@pytest.fixture
+def example_data_node(example_csv_filepath):
dataset_name = "uk.data_science.model_training.dataset"
metadata = {"kedro-viz": {"preview_args": {"nrows": 3}}}
- kedro_dataset = CSVDataset(filepath="test.csv", metadata=metadata)
+ kedro_dataset = CSVDataset(filepath=example_csv_filepath, metadata=metadata)
+ data_node = GraphNode.create_data_node(
+ dataset_name=dataset_name,
+ layer="raw",
+ tags=set(),
+ dataset=kedro_dataset,
+ stats={"rows": 10, "columns": 5, "file_size": 1024},
+ )
+
+ yield data_node
+
+
+@pytest.fixture
+def example_data_node_without_viz_metadata(example_csv_filepath):
+ dataset_name = "uk.data_science.model_training.dataset"
+ kedro_dataset = CSVDataset(filepath=example_csv_filepath)
data_node = GraphNode.create_data_node(
dataset_name=dataset_name,
layer="raw",
diff --git a/package/tests/test_api/test_apps.py b/package/tests/test_api/test_apps.py
index ac64bb5318..310c2b679f 100644
--- a/package/tests/test_api/test_apps.py
+++ b/package/tests/test_api/test_apps.py
@@ -82,7 +82,11 @@ class TestNodeMetadataEndpoint:
(
"13399a82",
200,
- {"filepath": "raw_data.csv", "type": "pandas.csv_dataset.CSVDataset"},
+ {
+ "filepath": "raw_data.csv",
+ "preview_type": "TablePreview",
+ "type": "pandas.csv_dataset.CSVDataset",
+ },
),
],
)
diff --git a/package/tests/test_api/test_rest/test_responses.py b/package/tests/test_api/test_rest/test_responses.py
index d1ea4794ad..68c655847d 100644
--- a/package/tests/test_api/test_rest/test_responses.py
+++ b/package/tests/test_api/test_rest/test_responses.py
@@ -630,6 +630,7 @@ def test_data_node_metadata(self, client):
assert response.json() == {
"filepath": "model_inputs.csv",
"type": "pandas.csv_dataset.CSVDataset",
+ "preview_type": "TablePreview",
"run_command": "kedro run --to-outputs=model_inputs",
"stats": {"columns": 12, "rows": 29768},
}
@@ -638,6 +639,7 @@ def test_data_node_metadata_for_free_input(self, client):
response = client.get("/api/nodes/13399a82")
assert response.json() == {
"filepath": "raw_data.csv",
+ "preview_type": "TablePreview",
"type": "pandas.csv_dataset.CSVDataset",
}
diff --git a/package/tests/test_models/test_flowchart.py b/package/tests/test_models/test_flowchart.py
index fb40ccb47f..87cc505701 100644
--- a/package/tests/test_models/test_flowchart.py
+++ b/package/tests/test_models/test_flowchart.py
@@ -1,5 +1,3 @@
-# pylint: disable=too-many-public-methods
-import base64
from functools import partial
from pathlib import Path
from textwrap import dedent
@@ -125,11 +123,6 @@ def test_create_data_node(self, dataset_name, expected_modular_pipelines):
assert data_node.stats["rows"] == 10
assert data_node.stats["columns"] == 5
assert data_node.stats["file_size"] == 1024
- assert not data_node.is_plot_node()
- assert not data_node.is_metric_node()
- assert not data_node.is_image_node()
- assert not data_node.is_json_node()
- assert not data_node.is_tracking_node()
@pytest.mark.parametrize(
"transcoded_dataset_name, original_name",
@@ -379,76 +372,82 @@ def test_data_node_metadata(self):
)
data_node_metadata = DataNodeMetadata(data_node=data_node)
assert data_node_metadata.type == "pandas.csv_dataset.CSVDataset"
+ assert data_node_metadata.preview_type == "TablePreview"
assert data_node_metadata.filepath == "/tmp/dataset.csv"
assert data_node_metadata.run_command == "kedro run --to-outputs=dataset"
assert data_node_metadata.stats["rows"] == 10
assert data_node_metadata.stats["columns"] == 2
- def test_preview_args_not_exist(self):
- metadata = {"kedro-viz": {"something": 3}}
+ def test_get_preview_args(self):
+ metadata = {"kedro-viz": {"preview_args": {"nrows": 3}}}
dataset = CSVDataset(filepath="test.csv", metadata=metadata)
data_node = GraphNode.create_data_node(
dataset_name="dataset", tags=set(), layer=None, dataset=dataset, stats=None
)
- assert not data_node.is_preview_node()
+ assert data_node.get_preview_args() == {"nrows": 3}
- def test_get_preview_args(self):
- metadata = {"kedro-viz": {"preview_args": {"nrows": 3}}}
+ def test_is_preview_disabled(self):
+ metadata = {"kedro-viz": {"preview": False}}
dataset = CSVDataset(filepath="test.csv", metadata=metadata)
data_node = GraphNode.create_data_node(
dataset_name="dataset", tags=set(), layer=None, dataset=dataset, stats=None
)
- assert data_node.is_preview_node()
- assert data_node.get_preview_args() == {"nrows": 3}
+ assert data_node.is_preview_disabled() is True
- def test_preview_data_node_metadata(self, example_data_node, mocker):
- mock_preview_data = {
+ def test_preview_data_node_metadata(self, example_data_node):
+ expected_preview_data = {
"columns": ["id", "company_rating", "company_location"],
"index": [0, 1, 2],
"data": [
- [1, "90%", "London"],
- [2, "80%", "Paris"],
- [3, "40%", "Milan"],
+ [35029, "100%", "Niue"],
+ [30292, "67%", "Anguilla"],
+ [12345, "80%", "Barbados"],
],
}
+ preview_node_metadata = DataNodeMetadata(data_node=example_data_node)
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_plot_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_image_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_tracking_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_preview_node", return_value=True
- )
- mocker.patch(
- "kedro_datasets.pandas.CSVDataset._preview", return_value=mock_preview_data
+ assert preview_node_metadata.preview == expected_preview_data
+
+ def test_preview_data_node_metadata_exception(self, caplog):
+ empty_dataset = CSVDataset(filepath="temp.csv")
+ dataset_name = "dataset"
+ empty_data_node = GraphNode.create_data_node(
+ dataset_name=dataset_name,
+ tags=set(),
+ layer=None,
+ dataset=empty_dataset,
+ stats=None,
)
- preview_node_metadata = DataNodeMetadata(data_node=example_data_node)
+ DataNodeMetadata(data_node=empty_data_node)
- assert preview_node_metadata.preview == mock_preview_data
+ assert f" '{dataset_name}' could not be previewed" in caplog.text
- def test_preview_data_node_metadata_not_exist(self, example_data_node, mocker):
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_plot_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_image_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_tracking_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_preview_node", return_value=True
+ def test_preview_default_data_node_metadata(
+ self, example_data_node_without_viz_metadata
+ ):
+ expected_preview_data = {
+ "columns": ["id", "company_rating", "company_location"],
+ "index": [0, 1, 2, 3, 4],
+ "data": [
+ [35029, "100%", "Niue"],
+ [30292, "67%", "Anguilla"],
+ [12345, "80%", "Barbados"],
+ [67890, "95%", "Fiji"],
+ [54321, "72%", "Grenada"],
+ ],
+ }
+ preview_node_metadata = DataNodeMetadata(
+ data_node=example_data_node_without_viz_metadata
)
- mocker.patch("kedro_datasets.pandas.CSVDataset._preview", return_value=False)
+
+ assert preview_node_metadata.preview == expected_preview_data
+
+ def test_preview_data_node_metadata_not_exist(self, example_data_node, mocker):
+ mocker.patch("kedro_datasets.pandas.CSVDataset.preview", return_value=False)
preview_node_metadata = DataNodeMetadata(data_node=example_data_node)
- assert preview_node_metadata.plot is None
+ assert preview_node_metadata.preview is False
def test_transcoded_data_node_metadata(self):
dataset = CSVDataset(filepath="/tmp/dataset.csv")
@@ -489,171 +488,6 @@ def test_partitioned_data_node_metadata(self):
data_node_metadata = DataNodeMetadata(data_node=data_node)
assert data_node_metadata.filepath == "partitioned/"
- # TODO: these test should ideally use a "real" catalog entry to create actual rather
- # than mock DataNode. Or if the loading functionality is tested elsewhere,
- # perhaps they are not needed at all. At the moment they don't actually test much.
- def test_plotly_data_node_metadata(self, example_data_node, mocker):
- mock_plot_data = {
- "data": [
- {
- "x": ["giraffes", "orangutans", "monkeys"],
- "y": [20, 14, 23],
- "type": "bar",
- }
- ]
- }
-
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_plot_node", return_value=True
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_image_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_tracking_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_preview_node", return_value=False
- )
- mocker.patch("kedro.io.core.AbstractDataset.load", return_value=mock_plot_data)
-
- plotly_node_metadata = DataNodeMetadata(data_node=example_data_node)
- assert plotly_node_metadata.plot == mock_plot_data
-
- def test_plotly_data_node_dataset_not_exist(self, example_data_node, mocker):
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_plot_node", return_value=True
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_image_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_tracking_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_preview_node", return_value=False
- )
- mocker.patch("kedro.io.core.AbstractDataset.load", return_value=None)
-
- plotly_node_metadata = DataNodeMetadata(data_node=example_data_node)
- assert plotly_node_metadata.plot is None
-
- # @patch("base64.b64encode")
- def test_image_data_node_metadata(self, example_data_node, mocker):
- mock_image_data = base64.b64encode(
- b"iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAA"
- b"AAC0lEQVQYV2NgYAAAAAMAAWgmWQ0AAAAASUVORK5CYII="
- )
-
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_image_node", return_value=True
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_plot_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_tracking_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_preview_node", return_value=False
- )
- mocker.patch("kedro.io.core.AbstractDataset.load", return_value=mock_image_data)
-
- image_node_metadata = DataNodeMetadata(data_node=example_data_node)
- assert image_node_metadata.image == mock_image_data
-
- def test_image_data_node_dataset_not_exist(self, example_data_node, mocker):
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_image_node", return_value=True
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_plot_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_tracking_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_preview_node", return_value=False
- )
- mocker.patch("kedro.io.core.AbstractDataset.load", return_value=None)
-
- image_node_metadata = DataNodeMetadata(data_node=example_data_node)
- assert image_node_metadata.image is None
-
- def test_tracking_data_node_metadata_exist(self, example_data_node, mocker):
- mock_tracking_data = {
- "recommendations": "test string",
- "recommended_controls": False,
- "projected_optimization": 0.0013902,
- }
-
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_tracking_node", return_value=True
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_image_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_plot_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_metric_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_preview_node", return_value=False
- )
- mocker.patch(
- "kedro.io.core.AbstractDataset.load", return_value=mock_tracking_data
- )
-
- tracking_node_metadata = DataNodeMetadata(data_node=example_data_node)
-
- assert tracking_node_metadata.tracking_data == mock_tracking_data
- assert tracking_node_metadata.plot is None
-
- def test_tracking_data_node_metadata_not_exist(self, example_data_node, mocker):
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_tracking_node", return_value=True
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_image_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_plot_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_metric_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_preview_node", return_value=False
- )
- mocker.patch("kedro.io.core.AbstractDataset.load", return_value=None)
-
- tracking_node_metadata = DataNodeMetadata(data_node=example_data_node)
-
- assert tracking_node_metadata.tracking_data is None
- assert tracking_node_metadata.plot is None
-
- def test_metrics_data_node_metadata_dataset_not_exist(
- self, example_data_node, mocker
- ):
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_metric_node", return_value=True
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_image_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_plot_node", return_value=False
- )
- mocker.patch(
- "kedro_viz.models.flowchart.DataNode.is_preview_node", return_value=False
- )
- mocker.patch("kedro.io.core.AbstractDataset.load", return_value=None)
-
- metrics_node_metadata = DataNodeMetadata(data_node=example_data_node)
- assert metrics_node_metadata.plot is None
-
def test_parameters_metadata_all_parameters(self):
parameters = {"test_split_ratio": 0.3, "num_epochs": 1000}
parameters_dataset = MemoryDataset(data=parameters)
diff --git a/src/components/metadata-modal/metadata-modal.js b/src/components/metadata-modal/metadata-modal.js
index 747616ff16..56f8f6e561 100644
--- a/src/components/metadata-modal/metadata-modal.js
+++ b/src/components/metadata-modal/metadata-modal.js
@@ -11,11 +11,11 @@ import { getClickedNodeMetaData } from '../../selectors/metadata';
import './metadata-modal.scss';
const MetadataModal = ({ metadata, onToggle, visible }) => {
- const hasPlot = Boolean(metadata?.plot);
- const hasImage = Boolean(metadata?.image);
- const hasPreview = Boolean(metadata?.preview);
+ const hasPlot = metadata?.previewType === 'PlotlyPreview';
+ const hasImage = metadata?.previewType === 'ImagePreview';
+ const hasTable = metadata?.previewType === 'TablePreview';
- if (!visible.metadataModal || (!hasPlot && !hasImage && !hasPreview)) {
+ if (!visible.metadataModal || (!hasPlot && !hasImage && !hasTable)) {
return null;
}
@@ -44,16 +44,16 @@ const MetadataModal = ({ metadata, onToggle, visible }) => {
{metadata.name}
- {hasPreview && (
+ {hasTable && (
- Previewing first {metadata.preview.data.length} rows
+ Previewing first {metadata.preview.length} rows
)}
{hasPlot && (
)}
@@ -63,17 +63,17 @@ const MetadataModal = ({ metadata, onToggle, visible }) => {
)}
- {hasPreview && (
+ {hasTable && (
)}
- {!hasPreview && (
+ {!hasTable && (
@@ -277,7 +290,7 @@ const MetaData = ({
)}
- {hasPreviewData && (
+ {hasTable && (
<>
state.node.outputs,
(state) => state.node.code,
(state) => state.node.parameters,
- (state) => state.node.plot,
- (state) => state.node.image,
- (state) => state.node.trackingData,
(state) => state.node.datasetType,
(state) => state.node.originalType,
(state) => state.node.transcodedTypes,
(state) => state.node.runCommand,
(state) => state.node.preview,
+ (state) => state.node.previewType,
(state) => state.node.stats,
(state) => state.isPrettyName,
],
@@ -59,27 +57,18 @@ export const getClickedNodeMetaData = createSelector(
nodeOutputs,
nodeCodes,
nodeParameters,
- nodePlot,
- nodeImage,
- nodeTrackingData,
nodeDatasetTypes,
nodeOriginalTypes,
nodeTranscodedTypes,
nodeRunCommand,
preview,
+ previewType,
stats,
isPrettyName
) => {
if (!nodeId || Object.keys(nodeType).length === 0) {
return null;
}
- //rounding of tracking data
- nodeTrackingData[nodeId] &&
- Object.entries(nodeTrackingData[nodeId]).forEach(([key, value]) => {
- if (typeof value === 'number') {
- nodeTrackingData[nodeId][key] = Math.round(value * 100) / 100;
- }
- });
const metadata = {
id: nodeId,
@@ -95,9 +84,6 @@ export const getClickedNodeMetaData = createSelector(
runCommand: nodeRunCommand[nodeId],
code: nodeCodes[nodeId],
filepath: nodeFilepaths[nodeId],
- plot: nodePlot[nodeId],
- image: nodeImage[nodeId],
- trackingData: nodeTrackingData[nodeId],
datasetType: nodeDatasetTypes[nodeId],
originalType: nodeOriginalTypes[nodeId],
transcodedTypes: nodeTranscodedTypes[nodeId],
@@ -116,6 +102,7 @@ export const getClickedNodeMetaData = createSelector(
: nodeOutputs[nodeId] &&
nodeOutputs[nodeId].map((nodeOutput) => stripNamespace(nodeOutput)),
preview: preview && preview[nodeId],
+ previewType: previewType && previewType[nodeId],
stats: stats && stats[nodeId],
};
diff --git a/src/store/normalize-data.js b/src/store/normalize-data.js
index d5908b163c..1546526930 100644
--- a/src/store/normalize-data.js
+++ b/src/store/normalize-data.js
@@ -151,8 +151,6 @@ const addNode = (state) => (node) => {
state.node.code[id] = node.code;
state.node.parameters[id] = node.parameters;
state.node.filepath[id] = node.filepath;
- state.node.plot[id] = node.plot;
- state.node.image[id] = node.image;
state.node.datasetType[id] = node.dataset_type;
state.node.originalType[id] = node.original_type;
state.node.transcodedTypes[id] = node.transcoded_types;
diff --git a/src/utils/data/node_json_data.mock.json b/src/utils/data/node_json_data.mock.json
index 42e0f4ec52..3568ae8aed 100644
--- a/src/utils/data/node_json_data.mock.json
+++ b/src/utils/data/node_json_data.mock.json
@@ -1,7 +1,8 @@
{
"filepath": "/Users/Documents/project-src/test/data/01_raw/iris.csv",
"type": "tracking.json_dataset.JSONDataset",
- "tracking_data": {
+ "preview_type": "JSONTrackingPreview",
+ "preview": {
"recommendations": "dummy_recommendation",
"recommended_controls": 0.2701227292578884,
"projected_optimization": 0.32414727510946606
diff --git a/src/utils/data/node_metrics_data.mock.json b/src/utils/data/node_metrics_data.mock.json
index 575fc8c4f8..c311053f31 100644
--- a/src/utils/data/node_metrics_data.mock.json
+++ b/src/utils/data/node_metrics_data.mock.json
@@ -1,7 +1,8 @@
{
"filepath": "/Users/Documents/project-src/test/data/01_raw/iris.csv",
"type": "tracking.metrics_dataset.MetricsDataset",
- "tracking_data": {
+ "preview_type": "MetricsTrackingPreview",
+ "preview": {
"recommendations": 0.2160981834063107,
"recommended_controls": 0.2701227292578884,
"projected_optimization": 0.32414727510946606
diff --git a/src/utils/data/node_plot.mock.json b/src/utils/data/node_plot.mock.json
index b9388935e1..1298df306e 100644
--- a/src/utils/data/node_plot.mock.json
+++ b/src/utils/data/node_plot.mock.json
@@ -1,6 +1,7 @@
{
"type": "plotly.plotly_dataset.PlotlyDataset",
- "plot": {
+ "preview_type": "PlotlyPreview",
+ "preview": {
"data": [
{
"uid": "babced",