jerry-thomas 1.0.3__py3-none-any.whl → 2.0.1__py3-none-any.whl

datapipeline/templates/plugin_skeleton/example/postprocess.yaml

@@ -1,29 +0,0 @@
-#### example combination of postprocessing steps ######
-#### making sure data is complete after these combinations ######
-- drop: # example of dropping sparse partitions/vertical-axis for targets
-    axis: vertical
-    payload: targets
-    threshold: 0.9
-
-- drop: # example of dropping sparse partitions for features
-    axis: vertical
-    payload: features
-    threshold: 0.9
-
-- drop: # dropping vectors/horizontal-axis that has features which none
-    axis: horizontal
-    payload: features
-    threshold: 1
-
-- drop:
-    axis: horizontal
-    payload: targets
-    threshold: 1
-######
-# - fill:
-#     statistic: median
-#     window: 48
-#     min_samples: 6
-# - replace:
-#     payload: targets
-#     value: 0.0

datapipeline/templates/plugin_skeleton/example/project.yaml

@@ -1,23 +0,0 @@
-version: 1
-name: example
-paths:
-  streams: ./contracts
-  sources: ./sources
-  dataset: dataset.yaml
-  postprocess: postprocess.yaml
-  artifacts: ../artifacts/${project_name}/v${version}
-  tasks: ./tasks
-globals:
-  # Globals to use in your .yaml files via ${var_name}.
-  # Primary dataset cadence; referenced from dataset.yaml (group_by)
-  # and contracts via ${group_by}.
-  group_by: 1h
-  start_time: 2021-01-01T00:00:00Z
-  end_time: 2021-01-02T00:00:00Z
-  # Configure deterministic dataset split here (applied at serve time, after postprocess).
-  # Adjust `ratios` as needed; the active split is selected via serve tasks or CLI.
-  split:
-    mode: hash # hash | time (time uses boundaries/labels)
-    key: group # group | feature:<id> (entity-stable split)
-    seed: 42 # deterministic hash seed
-    ratios: { train: 0.8, val: 0.1, test: 0.1 }

datapipeline/templates/plugin_skeleton/example/tasks/metadata.yaml

@@ -1,3 +0,0 @@
-kind: metadata
-# window_mode: intersection # union|intersection|strict|relaxed (default: intersection)
-

datapipeline/templates/plugin_skeleton/example/tasks/scaler.yaml

@@ -1,9 +0,0 @@
-kind: scaler
-
-# Output path is relative to project.paths.artifacts; defaults to "scaler.pkl".
-# output: scaler.pkl
-
-# Split label to use when fitting scaler statistics.
-# Must match a label from globals.split.ratios.
-split_label: train
-

datapipeline/templates/plugin_skeleton/example/tasks/schema.yaml

@@ -1,2 +0,0 @@
-kind: schema
-

datapipeline/templates/plugin_skeleton/example/tasks/serve.test.yaml

@@ -1,4 +0,0 @@
-kind: serve
-name: test
-keep: test
-

datapipeline/templates/plugin_skeleton/example/tasks/serve.train.yaml

@@ -1,28 +0,0 @@
-kind: serve
-
-# Optional identifier for this serve task; defaults to filename stem.
-name: train
-
-# Active split label to serve; must match a label from globals.split.ratios.
-# Set to null to disable split filtering.
-keep: train
-#output:
-# transport: stdout | fs
-# format: print | json-lines | json | csv | pickle
-# When using fs transport, set a directory (and optionally filename) for outputs:
-# directory: artifacts/serve
-# filename: vectors.train
-
-# Default max number of vectors to emit (null = unlimited).
-# limit: 5
-# Optional pipeline stage preview (0-7); null lets the CLI decide.
-# stage: 7
-
-# Optional pacing between emitted vectors (milliseconds).
-# throttle_ms: null
-
-# Visuals/logging knobs (inherit CLI or jerry.yaml defaults when omitted):
-# visuals: AUTO   # AUTO | TQDM | RICH | OFF
-# progress: AUTO  # AUTO | SPINNER | BARS | OFF
-# log_level: INFO # CRITICAL | ERROR | WARNING | INFO | DEBUG
-

datapipeline/templates/plugin_skeleton/example/tasks/serve.val.yaml

@@ -1,4 +0,0 @@
-kind: serve
-name: val
-keep: val
-

datapipeline/templates/stubs/mapper.py.j2

@@ -1,22 +0,0 @@
-from typing import Any, Iterator
-
-from {{PACKAGE_NAME}}.domains.{{TARGET_DOMAIN}}.model import {{DomainRecord}}
-from {{PACKAGE_NAME}}.sources.{{ORIGIN}}.{{DATASET}}.dto import {{OriginDTO}}
-
-
-def {{FUNCTION_NAME}}(
-    stream: Iterator[{{OriginDTO}}],
-    **params: Any,
-) -> Iterator[{{DomainRecord}}]:
-    """Map raw {{ORIGIN}} DTOs to domain-level {{TARGET_DOMAIN}} records.
-
-    - Required on domain record: time and value.
-    - Additional options may be passed via kwargs (e.g., variant="..." or mode="...").
-    """
-    for dto in stream:
-        # TODO: construct {{DomainRecord}} from dto fields
-        yield {{DomainRecord}}(
-            time=dto.time, # must include time
-            value=dto.value, # must include value
-            # additional fields...
-            )