Merge pull request #56 from scaleapi/da/circleci

Fix all tests + first pass at CI

Author: ardila

.DS_Store

@@ -0,0 +1,98 @@
+# CircleCI jobs are only enabled to on Pull Requests and commits to master branch.
+# "Only build pull requests" enabled in Project's Advanced Settings.
+version: 2.1
+jobs:
+  build_test:
+    docker:
+      - image: python:3.6-slim-buster
+    resource_class: small
+    steps:
+      - checkout # checkout source code to working directory
+      - run:
+          name: Install Environment Dependencies
+          command: | # install dependencies
+            pip install --upgrade pip 
+            pip install poetry
+            poetry install
+      - run:
+          name: Black Formatting Check # Only validation, without re-formatting
+          command: |
+            poetry run black --check -t py36 .
+      - run:
+          name: Flake8 Lint Check # Uses setup.cfg for configuration
+          command: |
+            poetry run flake8 . --count --statistics
+      - run:
+          name: Pylint Lint Check # Uses .pylintrc for configuration
+          command: |
+            poetry run pylint nucleus
+      - run :
+          name: MyPy typing check
+          command: |
+            poetry run mypy --ignore-missing-imports nucleus
+      - run:
+          name: Pytest Test Cases
+          command: | # Run test suite, uses NUCLEUS_TEST_API_KEY env variable
+            mkdir test_results
+            poetry run coverage run --include=nucleus/* -m pytest --junitxml=test_results/junit.xml
+            poetry run coverage report
+            poetry run coverage html
+
+      - store_test_results:
+          path: htmlcov
+
+      - store_test_results:
+          path: test_results
+      
+      - store_artifacts:
+          path: test_results
+  pypi_publish:
+    docker:
+      - image: cimg/python:3.6
+    steps:
+      - checkout # checkout source code to working directory
+      - run:
+          name: Validate Tag Version # Check if the tag name matches the package version
+          command: |
+            PKG_VERSION=$(sed -n 's/^version = //p' pyproject.toml | sed -e 's/^"//' -e 's/"$//')
+            if [[ "$CIRCLE_TAG" != "v${PKG_VERSION}" ]]; then
+                echo "ERROR: Tag name ($CIRCLE_TAG) must match package version (v${PKG_VERSION})."
+                exit 1;
+            fi
+      - run:
+          name: Validate SDK Version Increment # Check if the version is already on PyPI
+          command: |
+            PKG_VERSION=$(sed -n 's/^version = //p' pyproject.toml | sed -e 's/^"//' -e 's/"$//')
+            if pip install "scale-nucleus>=${PKG_VERSION}" > /dev/null 2>&1;
+            then
+                echo "ERROR: You need to increment to a new version before publishing!"
+                echo "Version (${PKG_VERSION}) already exists on PyPI."
+                exit 1;
+            fi
+      - run:
+          name: Build
+          command: | # install env dependencies
+            poetry build
+      - run:
+          name: Publish to PyPI
+          command: |
+            if test -z "${PYPI_USERNAME}" || test -z "${PYPI_PASSWORD}" ; then
+                echo "ERROR: Please assign PYPI_USERNAME and PYPI_PASSWORD as environment variables"
+                exit 1
+            fi
+            poetry publish --username=$PYPI_USERNAME --password=$PYPI_PASSWORD
+workflows:
+  build_test_publish:
+    jobs:
+      - build_test:
+          filters:
+            tags:
+              only: /^v\d+\.\d+\.\d+$/ # Runs only for tags with the format [v1.2.3]
+      - pypi_publish:
+          requires:
+            - build_test
+          filters:
+            branches:
+              ignore: /.*/ # Runs for none of the branches
+            tags:
+              only: /^v\d+\.\d+\.\d+$/ # Runs only for tags with the format [v1.2.3]

.circleci/config.yml

@@ -169,14 +169,9 @@ pre-commit install
 ```
 
 **Best practices for testing:**
-(1). Before running pytest, please make sure to authenticate into AWS, since some of the unit tests rely on AWs resources:
+(1). Please run pytest from the root directory of the repo, i.e.
 ```
-gimme_okta_aws_creds
-```
-
-(2). Please run pytest from the root directory of the repo, i.e.
-```
-pytest tests/test_dataset.py
+poetry pytest tests/test_dataset.py
 ```
 
 

README.md

@@ -1,3 +1,4 @@
+from dataclasses import dataclass
 from enum import Enum
 from typing import Dict, Optional, Any, Union, List
 from .constants import (
@@ -21,10 +22,11 @@
     ANNOTATIONS_KEY,
 )
 
-from dataclasses import dataclass
-
 
 class Annotation:
+    reference_id: Optional[str] = None
+    item_id: Optional[str] = None
+
     def _check_ids(self):
         if bool(self.reference_id) == bool(self.item_id):
             raise Exception(
@@ -69,9 +71,9 @@ def to_payload(self) -> dict:
 class SegmentationAnnotation(Annotation):
     mask_url: str
     annotations: List[Segment]
+    annotation_id: Optional[str] = None
     reference_id: Optional[str] = None
     item_id: Optional[str] = None
-    annotation_id: Optional[str] = None
 
     def __post_init__(self):
         if not self.mask_url:
@@ -111,8 +113,8 @@ class AnnotationTypes(Enum):
     POLYGON = POLYGON_TYPE
 
 
-@dataclass
-class BoxAnnotation(Annotation):
+@dataclass  # pylint: disable=R0902
+class BoxAnnotation(Annotation):  # pylint: disable=R0902
     label: str
     x: Union[float, int]
     y: Union[float, int]

nucleus/annotation.py

@@ -1,4 +1,6 @@
+from dataclasses import dataclass
 import os.path
+from typing import Optional
 from .constants import (
     IMAGE_URL_KEY,
     METADATA_KEY,
@@ -7,16 +9,14 @@
     DATASET_ITEM_ID_KEY,
 )
 
-from dataclasses import dataclass
-
 
 @dataclass
 class DatasetItem:
 
     image_location: str
-    reference_id: str = None
-    item_id: str = None
-    metadata: dict = None
+    reference_id: Optional[str] = None
+    item_id: Optional[str] = None
+    metadata: Optional[dict] = None
 
     def __post_init__(self):
         self.image_url = self.image_location

nucleus/dataset_item.py

@@ -1,5 +1,3 @@
-from __future__ import annotations
-
 from typing import Dict, Optional, List, Any
 from .annotation import (
     BoxAnnotation,
@@ -30,7 +28,7 @@ class SegmentationPrediction(SegmentationAnnotation):
     # No need to define init or to_payload methods because
     # we default to functions defined in the parent class
     @classmethod
-    def from_json(cls, payload: dict) -> SegmentationPrediction:
+    def from_json(cls, payload: dict):
         return cls(
             mask_url=payload[MASK_URL_KEY],
             annotations=[
@@ -58,15 +56,15 @@ def __init__(
         metadata: Optional[Dict] = None,
     ):
         super().__init__(
-            label,
-            x,
-            y,
-            width,
-            height,
-            reference_id,
-            item_id,
-            annotation_id,
-            metadata,
+            label=label,
+            x=x,
+            y=y,
+            width=width,
+            height=height,
+            reference_id=reference_id,
+            item_id=item_id,
+            annotation_id=annotation_id,
+            metadata=metadata,
         )
         self.confidence = confidence
 
@@ -78,7 +76,7 @@ def to_payload(self) -> dict:
         return payload
 
     @classmethod
-    def from_json(cls, payload: dict) -> BoxPrediction:
+    def from_json(cls, payload: dict):
         geometry = payload.get(GEOMETRY_KEY, {})
         return cls(
             label=payload.get(LABEL_KEY, 0),
@@ -106,7 +104,12 @@ def __init__(
         metadata: Optional[Dict] = None,
     ):
         super().__init__(
-            label, vertices, reference_id, item_id, annotation_id, metadata
+            label=label,
+            vertices=vertices,
+            reference_id=reference_id,
+            item_id=item_id,
+            annotation_id=annotation_id,
+            metadata=metadata,
         )
         self.confidence = confidence
 
@@ -118,7 +121,7 @@ def to_payload(self) -> dict:
         return payload
 
     @classmethod
-    def from_json(cls, payload: dict) -> PolygonPrediction:
+    def from_json(cls, payload: dict):
         geometry = payload.get(GEOMETRY_KEY, {})
         return cls(
             label=payload.get(LABEL_KEY, 0),

nucleus/prediction.py

@@ -9,7 +9,7 @@ class Slice:
     def __init__(self, slice_id: str, client):
         self.slice_id = slice_id
         self._client = client
-    
+
     def __repr__(self):
         return f"Slice(slice_id='{self.slice_id}', client={self._client})"
 

nucleus/slice.py

@@ -36,12 +36,19 @@ python = "^3.6"
 grequests = "^0.6.0"
 requests = "^2.25.1"
 tqdm = "^4.60.0"
+boto3 = "^1.17.53"
+mypy = "^0.812"
+coverage = "^5.5"
+dataclasses = { version = "^0.7", python = "^3.6.1, <3.7" }
 
 [tool.poetry.dev-dependencies]
 poetry = "^1.1.5"
 pytest = "^6.2.3"
 pylint = "^2.7.4"
-boto3 = "^1.17.51"
+black = "^20.8b1"
+flake8 = "^3.9.1"
+mypy = "^0.812"
+coverage = "^5.5"
 
 
 [build-system]

pyproject.toml

@@ -1,28 +1,25 @@
 from pathlib import Path
+import time
 from urllib.parse import urlparse
-import boto3
+
 from nucleus import DatasetItem, BoxPrediction
 
 PRESIGN_EXPIRY_SECONDS = 60 * 60 * 24 * 2  # 2 days
 
 TEST_MODEL_NAME = "[PyTest] Test Model"
-TEST_MODEL_REFERENCE = "[PyTest] Test Model Reference"
 TEST_MODEL_RUN = "[PyTest] Test Model Run"
 TEST_DATASET_NAME = "[PyTest] Test Dataset"
 TEST_SLICE_NAME = "[PyTest] Test Slice"
 
-TEST_MODEL_NAME = "[PyTest] Test Model Name"
-TEST_MODEL_REFERENCE = "[PyTest] Test Model Reference"
-TEST_MODEL_RUN = "[PyTest] Test Model Run Reference"
-TEST_DATASET_NAME = "[PyTest] Test Dataset"
-TEST_SLICE_NAME = "[PyTest] Test Slice"
+
 TEST_IMG_URLS = [
-    "s3://scaleapi-cust-lidar/Hesai/raw_data/2019-5-11/hesai_data_1557540003/undistorted/front_camera/1557540143.650423lf.jpg",
-    "s3://scaleapi-cust-lidar/Hesai/raw_data/2019-5-11/hesai_data_1557540003/undistorted/back_camera/1557540143.600352lf.jpg",
-    "s3://scaleapi-cust-lidar/Hesai/raw_data/2019-5-11/hesai_data_1557540003/undistorted/right_camera/1557540143.681730lf.jpg",
-    "s3://scaleapi-cust-lidar/Hesai/raw_data/2019-5-11/hesai_data_1557540003/undistorted/front_left_camera/1557540143.639619lf.jpg",
-    "s3://scaleapi-cust-lidar/Hesai/raw_data/2019-5-11/hesai_data_1557540003/undistorted/front_right_camera/1557540143.661212lf.jpg",
+    "http://farm1.staticflickr.com/107/309278012_7a1f67deaa_z.jpg",
+    "http://farm9.staticflickr.com/8001/7679588594_4e51b76472_z.jpg",
+    "http://farm6.staticflickr.com/5295/5465771966_76f9773af1_z.jpg",
+    "http://farm4.staticflickr.com/3449/4002348519_8ddfa4f2fb_z.jpg",
+    "http://farm1.staticflickr.com/6/7617223_d84fcbce0e_z.jpg",
 ]
+
 TEST_DATASET_ITEMS = [
     DatasetItem(TEST_IMG_URLS[0], "1"),
     DatasetItem(TEST_IMG_URLS[1], "2"),
@@ -39,30 +36,6 @@
 ]
 
 
-def get_signed_url(url):
-    bucket, key = get_s3_details(url)
-    return s3_sign(bucket, key)
-
-
-def get_s3_details(url):
-    # Expects S3 URL format to be https://<BUCKET>.s3.amazonaws.com/<KEY>
-    parsed = urlparse(url)
-    bucket = parsed.netloc[: parsed.netloc.find(".")]
-    return bucket, parsed.path[1:]
-
-
-def s3_sign(bucket, key):
-    s3 = boto3.client("s3")
-    return s3.generate_presigned_url(
-        ClientMethod="get_object",
-        Params={
-            "Bucket": bucket,
-            "Key": key,
-        },
-        ExpiresIn=PRESIGN_EXPIRY_SECONDS,
-    )
-
-
 def reference_id_from_url(url):
     return Path(url).name
 
@@ -96,20 +69,21 @@ def reference_id_from_url(url):
     for i in range(len(TEST_IMG_URLS))
 ]
 
-TEST_MASK_URL = "https://scale-ml.s3.amazonaws.com/home/nucleus/mscoco_masks_uint8/000000000285.png"
+
+TEST_MASK_URL = "https://raw.githubusercontent.com/scaleapi/nucleus-python-client/master/tests/testdata/000000000285.png"
+
 TEST_SEGMENTATION_ANNOTATIONS = [
     {
         "reference_id": reference_id_from_url(TEST_IMG_URLS[i]),
         "annotation_id": f"[Pytest] Segmentation Annotation Id{i}",
-        "mask_url": get_signed_url(TEST_MASK_URL),
+        "mask_url": TEST_MASK_URL,
         "annotations": [
             {"label": "bear", "index": 2},
             {"label": "grass-merged", "index": 1},
         ],
     }
     for i in range(len(TEST_IMG_URLS))
 ]
-
 TEST_SEGMENTATION_PREDICTIONS = TEST_SEGMENTATION_ANNOTATIONS
 
 TEST_BOX_PREDICTIONS = [
@@ -122,7 +96,8 @@ def reference_id_from_url(url):
     for i in range(len(TEST_POLYGON_ANNOTATIONS))
 ]
 
-TEST_INDEX_EMBEDDINGS_FILE = "https://scale-ml.s3.amazonaws.com/home/nucleus/pytest/pytest_embeddings_payload.json"
+TEST_INDEX_EMBEDDINGS_FILE = "https://raw.githubusercontent.com/scaleapi/nucleus-python-client/master/tests/testdata/pytest_embeddings_payload.json"
+
 
 # Asserts that a box annotation instance matches a dict representing its properties.
 # Useful to check annotation uploads/updates match.
@@ -184,4 +159,4 @@ def assert_polygon_prediction_matches_dict(
     assert_polygon_annotation_matches_dict(
         prediction_instance, prediction_dict
     )
-    assert prediction_instance.confidence == prediction_dict["confidence"]
+    assert prediction_instance.confidence == prediction_dict["confidence"]