BlueHawk: Adds bluehawk code snippets

bluehawk/snippets/artifact.snippet.create_artifact.py

@@ -0,0 +1,6 @@
+import wandb
+
+run = wandb.init(project="artifacts-example", job_type="add-dataset")
+artifact = wandb.Artifact(name="example_artifact", type="dataset")
+artifact.add_file(local_path="./dataset.h5", name="training_dataset")
+artifact.save()

bluehawk/snippets/artifact.snippet.download_artifact-1.py

@@ -0,0 +1,3 @@
+artifact = run.use_artifact(
+    "training_dataset:latest"
+)  # returns a run object using the "my_data" artifact

bluehawk/snippets/artifact.snippet.download_artifact-2.py

@@ -0,0 +1,3 @@
+datadir = (
+    artifact.download()
+)  # downloads the full `my_data` artifact to the default directory.

bluehawk/snippets/create-a-report.snippet.create-a-report.py

@@ -0,0 +1,4 @@
+
+report = wr.Report(project="report_standard")
+report.save()
+

bluehawk/snippets/edit-a-report.snippet.add-code-block-python.py

@@ -0,0 +1,5 @@
+report = wr.Report(project="report-editing")
+
+report.blocks = [wr.CodeBlock(code=["Hello, World!"], language="python")]
+
+report.save()

bluehawk/snippets/edit-a-report.snippet.add-code-blocks.py

@@ -0,0 +1,10 @@
+report = wr.Report(project = "<project>")
+
+report.blocks = [
+    wr.CodeBlock(
+        code=["this:", "- is", "- a", "cool:", "- yaml", "- file"], language="yaml"
+    ),
+    wr.CodeBlock(code=["Hello, World!"], language="python")
+]
+
+report.save()

bluehawk/snippets/edit-a-report.snippet.add-html.py

@@ -0,0 +1,9 @@
+report = wr.Report(project = "<project>")
+
+report.blocks = [
+    wr.H1(text="How Programmatic Reports work"),
+    wr.H2(text="Heading 2"),
+    wr.UnorderedList(items=["Bullet 1", "Bullet 2"]),
+]
+
+report.save()

bluehawk/snippets/edit-a-report.snippet.add-markdown.py

@@ -0,0 +1,6 @@
+report = wr.Report(project = "<project>")
+
+report.blocks = [
+    wr.MarkdownBlock(text="Markdown cell with *italics* and **bold** and $e=mc^2$")
+]
+report.save()

bluehawk/snippets/edit-a-report.snippet.add-plots.py

@@ -0,0 +1,17 @@
+report = wr.Report(
+    project = "<project>",
+    title="<title>",
+    description="A descriptive description.",
+)
+
+blocks = [
+    wr.PanelGrid(
+        panels=[
+            wr.LinePlot(x="time", y="velocity"),
+            wr.ScatterPlot(x="time", y="acceleration"),
+        ]
+    )
+]
+
+report.blocks = blocks
+report.save()

bluehawk/snippets/edit-a-report.snippet.add-runset-no-panels.py

@@ -0,0 +1,14 @@
+report = wr.Report(
+    project = "<project>",
+    title="An amazing title",
+    description="A descriptive description.",
+)
+
+blocks = wr.PanelGrid(
+    runsets=[
+        wr.RunSet(project="<project>", entity="<entity>")
+    ]
+)
+
+report.blocks = [blocks]
+report.save()

bluehawk/snippets/edit-a-report.snippet.add-runsets-and-panels.py

@@ -0,0 +1,56 @@
+report = wr.Report(
+    project = "<project>",
+    title="An amazing title",
+    description="A descriptive description.",
+)
+
+blocks = wr.PanelGrid(
+    runsets=[
+        wr.RunSet(project="<project>", entity="<entity>")
+    ],
+    panels=[
+        wr.LinePlot(
+            title="line title",
+            x="x",
+            y=["y"],
+            range_x=[0, 100],
+            range_y=[0, 100],
+            log_x=True,
+            log_y=True,
+            title_x="x axis title",
+            title_y="y axis title",
+            ignore_outliers=True,
+            groupby="hyperparam1",
+            groupby_aggfunc="mean",
+            groupby_rangefunc="minmax",
+            smoothing_factor=0.5,
+            smoothing_type="gaussian",
+            smoothing_show_original=True,
+            max_runs_to_show=10,
+            plot_type="stacked-area",
+            font_size="large",
+            legend_position="west",
+        ),
+        wr.ScatterPlot(
+            title="scatter title",
+            x="y",
+            y="y",
+            # z='x',
+            range_x=[0, 0.0005],
+            range_y=[0, 0.0005],
+            # range_z=[0,1],
+            log_x=False,
+            log_y=False,
+            # log_z=True,
+            running_ymin=True,
+            running_ymean=True,
+            running_ymax=True,
+            font_size="small",
+            regression=True,
+        ),
+    ],
+
+)
+
+report.blocks = [blocks]
+report.save()

bluehawk/snippets/edit-a-report.snippet.config-filters-0.py

@@ -0,0 +1,9 @@
+config = {
+    "learning_rate": 0.01,
+    "batch_size": 32,
+}
+
+with wandb.init(project="<project>", entity="<entity>", config=config) as run:
+    # Your training code here
+    pass
+

bluehawk/snippets/edit-a-report.snippet.config-filters-1.py

@@ -0,0 +1,5 @@
+runset = wr.Runset(
+  entity="<entity>",
+  project="<project>",
+  filters="Config('learning_rate') > 0.01"
+)

bluehawk/snippets/edit-a-report.snippet.config-filters-2.py

@@ -0,0 +1,5 @@
+runset = wr.Runset(
+  entity="<entity>",
+  project="<project>",
+  filters="Config('learning_rate') > 0.01 and Config('batch_size') == 32"
+)

bluehawk/snippets/edit-a-report.snippet.config-filters-3.py

@@ -0,0 +1,12 @@
+report = wr.Report(
+  entity="<entity>",
+  project="<project>",
+)
+
+report.blocks = [
+  wr.PanelGrid(
+      runsets=[runset]
+  )
+]
+
+report.save()

bluehawk/snippets/edit-a-report.snippet.embed-rich-media.py

@@ -0,0 +1,6 @@
+report = wr.Report(project = "<project>")
+
+report.blocks = [
+    wr.Video(url="https://www.youtube.com/embed/6riDJMI-Y8U")
+]
+report.save()

bluehawk/snippets/edit-a-report.snippet.group-runs-config.py

@@ -0,0 +1,21 @@
+# Create a report that groups runs by a config value
+report = wr.Report(
+  entity=entity,
+  project=project,
+  title="Grouped Runs Example",
+)
+
+# Create a runset that groups runs by the "group" config value
+runset = wr.Runset(
+  project=project,
+  entity=entity,
+  groupby=["config.group"] 
+)
+# Add the runset to a panel grid in the report
+report.blocks = [
+  wr.PanelGrid(
+      runsets=[runset],
+          )
+      ]
+# Save the report
+report.save()

bluehawk/snippets/edit-a-report.snippet.group-runs-metadata.py

@@ -0,0 +1,22 @@
+# Create a report that groups runs by their metadata (e.g., run name)
+report = wr.Report(
+  entity=entity,
+  project=project,
+  title="Grouped Runs by Metadata Example",
+)
+
+# Create a runset that groups runs by their name (metadata)
+runset = wr.Runset(
+  project=project,
+  entity=entity,
+  groupby=["Name"]  # Group by run names
+)
+
+# Add the runset to a panel grid in the report
+report.blocks = [
+  wr.PanelGrid(
+      runsets=[runset],
+          )
+      ]
+# Save the report
+report.save()

bluehawk/snippets/edit-a-report.snippet.group-runs-summary-metrics.py

@@ -0,0 +1,22 @@
+# Create a report that groups runs by a summary metric
+report = wr.Report(
+  entity=entity,
+  project=project,
+  title="Grouped Runs by Summary Metrics Example",
+)
+
+# Create a runset that groups runs by the "summary.acc" summary metric
+runset = wr.Runset(
+  project=project,
+  entity=entity,
+  groupby=["summary.acc"]  # Group by summary values 
+)
+
+# Add the runset to a panel grid in the report
+report.blocks = [
+  wr.PanelGrid(
+      runsets=[runset],
+          )
+      ]
+# Save the report
+report.save()

bluehawk/snippets/edit-a-report.snippet.metric-filters-0.py

@@ -0,0 +1,5 @@
+with wandb.init(project="<project>", entity="<entity>") as run:
+    for i in range(3):
+        run.name = f"run{i+1}"
+        # Your training code here
+        pass

bluehawk/snippets/edit-a-report.snippet.metric-filters-1.py

@@ -0,0 +1,5 @@
+runset = wr.Runset(
+  entity="<entity>",
+  project="<project>",
+  filters="Metric('displayName') in ['run1', 'run2', 'run3']"
+)

bluehawk/snippets/edit-a-report.snippet.metric-filters-2.py

@@ -0,0 +1,5 @@
+runset = wr.Runset(
+  entity="<entity>",
+  project="<project>",
+  filters="Metric('state') in ['finished']"
+)

bluehawk/snippets/edit-a-report.snippet.metric-filters-3.py

@@ -0,0 +1,5 @@
+runset = wr.Runset(
+  entity="<entity>",
+  project="<project>",
+  filters="Metric('state') not in ['crashed']"
+)

bluehawk/snippets/edit-a-report.snippet.summary-metric-filters.py

@@ -0,0 +1,11 @@
+runset = wr.Runset(
+  entity="<entity>",
+  project="<project>",
+  filters="SummaryMetric('accuracy') > 0.9"
+)
+
+runset = wr.Runset(
+  entity="<entity>",
+  project="<project>",
+  filters="Metric('state') in ['finished'] and SummaryMetric('train/train_loss') < 0.5"
+)

bluehawk/snippets/edit-a-report.snippet.tag-filters.py

@@ -0,0 +1,5 @@
+runset = wr.Runset(
+  entity="<entity>",
+  project="<project>",
+  filters="Tags('training') == 'training'"
+)

bluehawk/snippets/group_runs.snippet.group_runs.py

@@ -0,0 +1,17 @@
+
+import wandb
+import wandb_workspaces.reports.v2 as wr
+
+entity = "<entity>"
+project = "<project>"
+
+for group in ["control", "experiment_a", "experiment_b"]:
+    for i in range(3):
+        with wandb.init(entity=entity, project=project, group=group, config={"group": group, "run": i}, name=f"{group}_run_{i}") as run:
+            # Simulate some training
+            for step in range(100):
+                run.log({
+                    "acc": 0.5 + (step / 100) * 0.3 + (i * 0.05),
+                    "loss": 1.0 - (step / 100) * 0.5
+                })
+

bluehawk/snippets/import_wandb.snippet.import_wandb.py

@@ -0,0 +1 @@
+import wandb

bluehawk/snippets/import_wandb.snippet.import_wandb_and_workspaces.py

@@ -0,0 +1,2 @@
+import wandb
+import wandb_workspaces.reports.v2 as wr

bluehawk/snippets/import_wandb.snippet.import_wandb_workspaces.py

@@ -0,0 +1 @@
+import wandb_workspaces.reports.v2 as wr

bluehawk/snippets/models_quickart.snippet.publish_model.py

@@ -0,0 +1,17 @@
+
+# Artifact name specifies the specific artifact version within our team's project
+artifact_name = f'{TEAM_ENTITY}/{PROJECT}/{model_artifact_name}:v0'
+print("Artifact name: ", artifact_name)
+
+REGISTRY_NAME = "Model" # Name of the registry in W&B
+COLLECTION_NAME = "DemoModels"  # Name of the collection in the registry
+
+# Create a target path for our artifact in the registry
+target_path = f"wandb-registry-{REGISTRY_NAME}/{COLLECTION_NAME}"
+print("Target path: ", target_path)
+
+run = wandb.init(entity=TEAM_ENTITY, project=PROJECT)
+model_artifact = run.use_artifact(artifact_or_name=artifact_name, type="model")
+run.link_artifact(artifact=model_artifact, target_path=target_path)
+run.finish()
+

bluehawk/snippets/models_quickart.snippet.query_registry.py

@@ -0,0 +1,29 @@
+
+# Initialize wandb API
+api = wandb.Api()
+
+# Find all artifact versions that contains the string `model` and 
+# has either the tag `text-classification` or an `latest` alias
+registry_filters = {
+    "name": {"$regex": "model"}
+}
+
+# Use logical $or operator to filter artifact versions
+version_filters = {
+    "$or": [
+        {"tag": "text-classification"},
+        {"alias": "latest"}
+    ]
+}
+
+# Returns an iterable of all artifact versions that match the filters
+artifacts = api.registries(filter=registry_filters).collections().versions(filter=version_filters)
+
+# Print out the name, collection, aliases, tags, and created_at date of each artifact found
+for art in artifacts:
+    print(f"artifact name: {art.name}")
+    print(f"collection artifact belongs to: { art.collection.name}")
+    print(f"artifact aliases: {art.aliases}")
+    print(f"tags attached to artifact: {art.tags}")
+    print(f"artifact created at: {art.created_at}\n")
+

bluehawk/snippets/models_quickart.snippet.retrieve_model.py

@@ -0,0 +1,12 @@
+
+REGISTRY_NAME = "Model"  # Name of the registry in W&B
+COLLECTION_NAME = "DemoModels"  # Name of the collection in the registry
+VERSION = 0 # Version of the artifact to retrieve
+
+model_artifact_name = f"wandb-registry-{REGISTRY_NAME}/{COLLECTION_NAME}:v{VERSION}"
+print(f"Model artifact name: {model_artifact_name}")
+
+run = wandb.init(entity=TEAM_ENTITY, project=PROJECT)
+registry_model = run.use_artifact(artifact_or_name=model_artifact_name)
+local_model_path = registry_model.download()
+