From 00f42598e5bd8210237f56a5aa48a9d7aec4dfc4 Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Sun, 9 May 2021 12:01:03 +1000
Subject: [PATCH 01/14] Add metadata saving

---
 .../config/experiment_1/train_config.yaml     |  1 +
 .../config/experiment_2/train_config.yaml     |  1 +
 ml_project/config/train_config.yaml           |  1 +
 .../heart_disease/entities/pipeline_config.py |  1 +
 .../heart_disease/features/build_features.py  | 19 ++++++++----
 ml_project/heart_disease/models/model.py      |  8 ++---
 .../heart_disease/models/train_model.py       |  8 +++--
 ml_project/heart_disease/utils.py             | 12 ++++++++
 .../tests/features/test_build_features.py     | 23 ++++++++++++++-
 ml_project/tests/models/test_pipelines.py     | 29 ++++++++++++++-----
 ml_project/tests/test_utils.py                | 11 +++++++
 11 files changed, 92 insertions(+), 22 deletions(-)
 create mode 100644 ml_project/heart_disease/utils.py
 create mode 100644 ml_project/tests/test_utils.py

diff --git a/ml_project/config/experiment_1/train_config.yaml b/ml_project/config/experiment_1/train_config.yaml
index d396f5c..b247c2e 100644
--- a/ml_project/config/experiment_1/train_config.yaml
+++ b/ml_project/config/experiment_1/train_config.yaml
@@ -1,5 +1,6 @@
 model_save_path: models/model_experiment_1.pkl
 pipeline_save_path: models/pipeline_experiment_1.pkl
+metadata_save_path: models/metadata_experiment_1.pkl
 data_load_config:
   data_path: data/heart.csv
   split_config:
diff --git a/ml_project/config/experiment_2/train_config.yaml b/ml_project/config/experiment_2/train_config.yaml
index 615016a..54983b4 100644
--- a/ml_project/config/experiment_2/train_config.yaml
+++ b/ml_project/config/experiment_2/train_config.yaml
@@ -1,5 +1,6 @@
 model_save_path: models/model_experiment_2.pkl
 pipeline_save_path: models/pipeline_experiment_2.pkl
+metadata_save_path: models/metadata_experiment_2.pkl
 data_load_config:
   data_path: data/heart.csv
   split_config:
diff --git a/ml_project/config/train_config.yaml b/ml_project/config/train_config.yaml
index eea124d..8030c70 100644
--- a/ml_project/config/train_config.yaml
+++ b/ml_project/config/train_config.yaml
@@ -1,5 +1,6 @@
 model_save_path: models/model.pkl
 pipeline_save_path: models/pipeline.pkl
+metadata_save_path: models/metadata.pkl
 data_load_config:
   data_path: data/heart.csv
   split_config:
diff --git a/ml_project/heart_disease/entities/pipeline_config.py b/ml_project/heart_disease/entities/pipeline_config.py
index 5b0e95c..2862d28 100644
--- a/ml_project/heart_disease/entities/pipeline_config.py
+++ b/ml_project/heart_disease/entities/pipeline_config.py
@@ -15,6 +15,7 @@ class TrainingConfig:
     evaluation_config: EvaluateModelConfig = field(default_factory=lambda: EvaluateModelConfig)
     model_save_path: str = omegaconf.MISSING
     pipeline_save_path: str = omegaconf.MISSING
+    metadata_save_path: str = omegaconf.MISSING
 
 
 @dataclass
diff --git a/ml_project/heart_disease/features/build_features.py b/ml_project/heart_disease/features/build_features.py
index 52de418..47903e0 100644
--- a/ml_project/heart_disease/features/build_features.py
+++ b/ml_project/heart_disease/features/build_features.py
@@ -1,5 +1,4 @@
-import pickle
-from typing import List
+from typing import List, Dict
 
 import numpy as np
 import pandas as pd
@@ -12,6 +11,7 @@
 from sklearn.random_projection import SparseRandomProjection
 
 from heart_disease.entities.feature_config import FeatureConfig
+from heart_disease.utils import serialize_object, deserialize_object
 
 
 class StatisticalFeaturesExtractor(TransformerMixin):
@@ -96,10 +96,17 @@ def extract_target(df: pd.DataFrame, config: FeatureConfig) -> pd.Series:
 
 
 def serialize_pipeline(pipeline: Pipeline, path: str):
-    with open(path, "wb") as f:
-        pickle.dump(pipeline, f)
+    serialize_object(pipeline, path)
 
 
 def deserialize_pipeline(path: str) -> Pipeline:
-    with open(path, "rb") as f:
-        return pickle.load(f)
+    return deserialize_object(path)
+
+
+def serialize_metadata(df: pd.DataFrame, config: FeatureConfig, path: str):
+    all_features = config.raw_features.numeric_features + config.raw_features.categorical_features
+    return serialize_object(df[all_features].dtypes.to_dict(), path)
+
+
+def deserialize_metadata(path: str) -> Dict[str, np.dtype]:
+    return deserialize_object(path)
diff --git a/ml_project/heart_disease/models/model.py b/ml_project/heart_disease/models/model.py
index 64048f1..5c8a30d 100644
--- a/ml_project/heart_disease/models/model.py
+++ b/ml_project/heart_disease/models/model.py
@@ -1,4 +1,3 @@
-import pickle
 from typing import Union, Dict, List
 
 import numpy as np
@@ -7,6 +6,7 @@
 from sklearn.metrics import get_scorer
 
 from heart_disease.entities.model_config import TrainModelConfig, ModelType
+from heart_disease.utils import deserialize_object, serialize_object
 
 Classifier = Union[RandomForestClassifier, ExtraTreesClassifier]
 
@@ -41,10 +41,8 @@ def save_metrics(metrics: Dict[str, float], path: str):
 
 
 def serialize_model(model: Classifier, path: str):
-    with open(path, "wb") as f:
-        pickle.dump(model, f)
+    serialize_object(model, path)
 
 
 def deserialize_model(path: str) -> Classifier:
-    with open(path, "rb") as f:
-        return pickle.load(f)
+    return deserialize_object(path)
diff --git a/ml_project/heart_disease/models/train_model.py b/ml_project/heart_disease/models/train_model.py
index a137b2f..4ad56b9 100644
--- a/ml_project/heart_disease/models/train_model.py
+++ b/ml_project/heart_disease/models/train_model.py
@@ -7,7 +7,8 @@
 
 from heart_disease.data.make_dataset import load_datasets
 from heart_disease.entities.pipeline_config import TrainingConfig
-from heart_disease.features.build_features import build_feature_pipeline, extract_target, serialize_pipeline
+from heart_disease.features.build_features import build_feature_pipeline, extract_target, serialize_pipeline, \
+    serialize_metadata
 from heart_disease.models.model import train_model, evaluate_model, serialize_model, save_metrics
 
 log = logging.getLogger(__name__)
@@ -35,11 +36,11 @@ def train_pipeline(cfg: TrainingConfig):
     log.info("Features built")
 
     log.info(f"Training model {cfg.model_config.model.value}...")
-    model = train_model(train_features, train_target, cfg.model_config)
+    model = train_model(train_features, train_target.values, cfg.model_config)
     log.info("Model trained")
 
     log.info("Evaluating model...")
-    metrics = evaluate_model(model, val_features, val_target, cfg.evaluation_config.metrics)
+    metrics = evaluate_model(model, val_features, val_target.values, cfg.evaluation_config.metrics)
     save_metrics(metrics, to_absolute_path(cfg.evaluation_config.metric_file_path))
     log.info("Model evaluated:")
     for metric, value in metrics.items():
@@ -48,6 +49,7 @@ def train_pipeline(cfg: TrainingConfig):
     log.info("Serializing...")
     serialize_model(model, to_absolute_path(cfg.model_save_path))
     serialize_pipeline(feature_pipeline, to_absolute_path(cfg.pipeline_save_path))
+    serialize_metadata(train_data, cfg.feature_config, to_absolute_path(cfg.metadata_save_path))
     log.info("Model and pipeline serialized")
 
 
diff --git a/ml_project/heart_disease/utils.py b/ml_project/heart_disease/utils.py
new file mode 100644
index 0000000..144b839
--- /dev/null
+++ b/ml_project/heart_disease/utils.py
@@ -0,0 +1,12 @@
+import pickle
+from typing import Any
+
+
+def serialize_object(obj: Any, path: str):
+    with open(path, "wb") as f:
+        pickle.dump(obj, f)
+
+
+def deserialize_object(path: str) -> Any:
+    with open(path, "rb") as f:
+        return pickle.load(f)
diff --git a/ml_project/tests/features/test_build_features.py b/ml_project/tests/features/test_build_features.py
index 3679602..442df2f 100644
--- a/ml_project/tests/features/test_build_features.py
+++ b/ml_project/tests/features/test_build_features.py
@@ -9,7 +9,7 @@
 from heart_disease.entities.feature_config import FeatureConfig, RandomProjectionFeaturesConfig, \
     KMeansFeaturesConfig, StatisticalFeaturesConfig, PolynomialFeaturesConfig
 from heart_disease.features.build_features import \
-    StatisticalFeaturesExtractor, KMeansFeaturesExtractor
+    StatisticalFeaturesExtractor, KMeansFeaturesExtractor, serialize_metadata, deserialize_metadata
 from heart_disease.features.build_features import \
     build_categorical_feature_pipeline, \
     build_numerical_feature_pipeline, \
@@ -132,3 +132,24 @@ def test_serialize_pipeline(
     serialize_pipeline(pipeline, filename)
     loaded_pipeline = deserialize_pipeline(filename)
     assert np.all(pipeline.transform(dataset) == loaded_pipeline.transform(dataset))
+
+
+def test_serialize_metadata(
+        dataset: pd.DataFrame,
+        numerical_features: List[str],
+        categorical_features: List[str],
+        tmp_path: Path,
+        statistics: OrderedDict[str, Callable],
+        target_column: str
+):
+    filename = str(tmp_path / "metadata.pkl")
+    projection_features = 5
+    polynomial_degree = 2
+    n_clusters = 2
+    config = get_feature_config(target_column, categorical_features, n_clusters, numerical_features, polynomial_degree,
+                                projection_features, statistics)
+    serialize_metadata(dataset, config, filename)
+    metadata = deserialize_metadata(filename)
+    for k, v in metadata.items():
+        assert dataset[k].dtype == v
+    assert set(metadata.keys()) == set(numerical_features + categorical_features)
diff --git a/ml_project/tests/models/test_pipelines.py b/ml_project/tests/models/test_pipelines.py
index 16b6c9e..2bb24d3 100644
--- a/ml_project/tests/models/test_pipelines.py
+++ b/ml_project/tests/models/test_pipelines.py
@@ -25,6 +25,7 @@ def train_model(
     model_save_path = str(tmpdir / "model.pkl")
     pipeline_save_path = str(tmpdir / "pipeline.pkl")
     metrics_path = str(tmpdir / "metrics.yaml")
+    metadata_path = str(tmpdir / "metadata.pkl")
     projection_features = 5
     polynomial_degree = 2
     n_clusters = 2
@@ -51,9 +52,10 @@ def train_model(
         ),
         pipeline_save_path=pipeline_save_path,
         model_save_path=model_save_path,
+        metadata_save_path=metadata_path
     )
     train_pipeline(config)
-    return metrics_path, model_save_path, pipeline_save_path
+    return metrics_path, model_save_path, pipeline_save_path, metadata_path
 
 
 def test_train_pipeline(
@@ -65,11 +67,18 @@ def test_train_pipeline(
         metrics: List[str],
         statistics: OrderedDict[str, Callable]
 ):
-    metrics_path, model_save_path, pipeline_save_path = train_model(categorical_features, dataset_file, metrics,
-                                                                    numerical_features, statistics, target_column,
-                                                                    tmpdir)
+    metrics_path, model_save_path, pipeline_save_path, metadata_path = train_model(
+        categorical_features,
+        dataset_file,
+        metrics,
+        numerical_features,
+        statistics,
+        target_column,
+        tmpdir
+    )
     assert Path(model_save_path).exists()
     assert Path(pipeline_save_path).exists()
+    assert Path(metadata_path).exists()
     assert Path(metrics_path).exists()
     with open(metrics_path, "r") as f:
         metric_values = yaml.safe_load(f)
@@ -90,9 +99,15 @@ def test_predict_pipeline(
         statistics: OrderedDict[str, Callable]
 ):
     output = str(tmpdir / "output.txt")
-    _, model_save_path, pipeline_save_path = train_model(categorical_features, dataset_file, metrics,
-                                                         numerical_features, statistics, target_column,
-                                                         tmpdir)
+    _, model_save_path, pipeline_save_path, _ = train_model(
+        categorical_features,
+        dataset_file,
+        metrics,
+        numerical_features,
+        statistics,
+        target_column,
+        tmpdir
+    )
     config = PredictConfig(
         model_load_path=model_save_path,
         pipeline_load_path=pipeline_save_path,
diff --git a/ml_project/tests/test_utils.py b/ml_project/tests/test_utils.py
new file mode 100644
index 0000000..b9eeefe
--- /dev/null
+++ b/ml_project/tests/test_utils.py
@@ -0,0 +1,11 @@
+from pathlib import Path
+
+from heart_disease.utils import serialize_object, deserialize_object
+
+
+def test_serialize_object(tmp_path: Path):
+    path = str(tmp_path / "path.pkl")
+    objects = [1, 2.0, "test", {1, 2, "test2"}, {"hello": "there", "general": 42}, ["one", 2, 3.0]]
+    for obj in objects:
+        serialize_object(obj, path)
+        assert deserialize_object(path) == obj

From b7fd1b5e3aa9a1f5ca0ccf85b9f0475bcbb12a9b Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Sun, 9 May 2021 15:41:01 +1000
Subject: [PATCH 02/14] Add API for online predictions

---
 .../heart_disease/features/build_features.py  |   4 +
 .../heart_disease/models/train_model.py       |  10 +-
 ml_project/online_inference/__init__.py       |   0
 ml_project/online_inference/api.py            |  58 +++++++++
 ml_project/online_inference/schemas.py        |  21 +++
 ml_project/requirements.txt                   |   3 +
 ml_project/tests/conftest.py                  | 120 +++++++++++++++---
 ml_project/tests/models/test_models.py        |   1 -
 ml_project/tests/models/test_pipelines.py     |  92 ++------------
 ml_project/tests/online_inference/__init__.py |   0
 ml_project/tests/online_inference/test_api.py |  84 ++++++++++++
 11 files changed, 287 insertions(+), 106 deletions(-)
 create mode 100644 ml_project/online_inference/__init__.py
 create mode 100644 ml_project/online_inference/api.py
 create mode 100644 ml_project/online_inference/schemas.py
 create mode 100644 ml_project/tests/online_inference/__init__.py
 create mode 100644 ml_project/tests/online_inference/test_api.py

diff --git a/ml_project/heart_disease/features/build_features.py b/ml_project/heart_disease/features/build_features.py
index 47903e0..f286d5f 100644
--- a/ml_project/heart_disease/features/build_features.py
+++ b/ml_project/heart_disease/features/build_features.py
@@ -95,6 +95,10 @@ def extract_target(df: pd.DataFrame, config: FeatureConfig) -> pd.Series:
     return target
 
 
+def extract_raw_features(df: pd.DataFrame, config: FeatureConfig) -> pd.DataFrame:
+    return df[config.raw_features.numeric_features + config.raw_features.categorical_features]
+
+
 def serialize_pipeline(pipeline: Pipeline, path: str):
     serialize_object(pipeline, path)
 
diff --git a/ml_project/heart_disease/models/train_model.py b/ml_project/heart_disease/models/train_model.py
index 4ad56b9..6a9a4da 100644
--- a/ml_project/heart_disease/models/train_model.py
+++ b/ml_project/heart_disease/models/train_model.py
@@ -8,7 +8,7 @@
 from heart_disease.data.make_dataset import load_datasets
 from heart_disease.entities.pipeline_config import TrainingConfig
 from heart_disease.features.build_features import build_feature_pipeline, extract_target, serialize_pipeline, \
-    serialize_metadata
+    serialize_metadata, extract_raw_features
 from heart_disease.models.model import train_model, evaluate_model, serialize_model, save_metrics
 
 log = logging.getLogger(__name__)
@@ -28,9 +28,11 @@ def train_pipeline(cfg: TrainingConfig):
 
     log.info("Building features...")
     feature_pipeline = build_feature_pipeline(cfg.feature_config)
-    feature_pipeline.fit(train_data)
-    train_features = feature_pipeline.transform(train_data)
-    val_features = feature_pipeline.transform(val_data)
+    raw_train_features = extract_raw_features(train_data, cfg.feature_config)
+    raw_val_features = extract_raw_features(val_data, cfg.feature_config)
+    feature_pipeline.fit(raw_train_features)
+    train_features = feature_pipeline.transform(raw_train_features)
+    val_features = feature_pipeline.transform(raw_val_features)
     train_target = extract_target(train_data, cfg.feature_config)
     val_target = extract_target(val_data, cfg.feature_config)
     log.info("Features built")
diff --git a/ml_project/online_inference/__init__.py b/ml_project/online_inference/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/ml_project/online_inference/api.py b/ml_project/online_inference/api.py
new file mode 100644
index 0000000..906ad35
--- /dev/null
+++ b/ml_project/online_inference/api.py
@@ -0,0 +1,58 @@
+import logging
+from typing import List, Dict
+
+import numpy as np
+import pandas as pd
+from dotenv import load_dotenv
+from fastapi import FastAPI, HTTPException, Request
+
+from heart_disease.features.build_features import deserialize_metadata, deserialize_pipeline
+from heart_disease.models.model import deserialize_model
+from online_inference.schemas import HeartDiseaseModel, HeartDiseaseResponseModel, Settings
+
+logger = logging.getLogger(__name__)
+
+load_dotenv()
+settings = Settings()
+app = FastAPI(
+    title="Heart disease prediction",
+)
+
+
+@app.on_event("startup")
+def load_artifacts():
+    app.state.metadata = deserialize_metadata(str(settings.metadata_path))
+    app.state.pipeline = deserialize_pipeline(str(settings.pipeline_path))
+    app.state.model = deserialize_model(str(settings.model_path))
+
+
+def rebuild_dataframe(params: HeartDiseaseModel, metadata: Dict[str, np.dtype]) -> pd.DataFrame:
+    try:
+        data = pd.DataFrame(params.features, columns=params.columns)
+    except ValueError:
+        error_msg = "Failed to construct DataFrame from passed data"
+        logger.exception(error_msg)
+        raise HTTPException(status_code=400, detail=error_msg)
+    for key, dtype in metadata.items():
+        if key not in data.columns:
+            error_msg = f"Column {key} not found in data"
+            logger.error(error_msg)
+            raise HTTPException(status_code=400, detail=error_msg)
+        if data[key].dtype != dtype:
+            try:
+                data[key] = data[key].astype(dtype)
+            except ValueError:
+                error_msg = f"Failed to cast column {key} to dtype {dtype}"
+                logger.exception(error_msg)
+                raise HTTPException(status_code=400, detail=error_msg)
+    return data
+
+
+@app.post("/predict", response_model=List[HeartDiseaseResponseModel])
+def predict(request: Request, params: HeartDiseaseModel):
+    data = rebuild_dataframe(params, app.state.metadata)
+    processed_features = request.app.state.pipeline.transform(data)
+    predictions = request.app.state.model.predict(processed_features)
+    return [
+        HeartDiseaseResponseModel(id=id_, has_disease=pred == 1) for id_, pred in zip(params.ids, predictions)
+    ]
diff --git a/ml_project/online_inference/schemas.py b/ml_project/online_inference/schemas.py
new file mode 100644
index 0000000..fa15805
--- /dev/null
+++ b/ml_project/online_inference/schemas.py
@@ -0,0 +1,21 @@
+from typing import Dict, Union, List
+from pathlib import Path
+
+from pydantic import BaseModel, BaseSettings
+
+
+class HeartDiseaseModel(BaseModel):
+    ids: List[int]
+    features: List[List[Union[int, float]]]
+    columns: List[str]
+
+
+class HeartDiseaseResponseModel(BaseModel):
+    id: int
+    has_disease: bool
+
+
+class Settings(BaseSettings):
+    model_path: Path
+    pipeline_path: Path
+    metadata_path: Path
diff --git a/ml_project/requirements.txt b/ml_project/requirements.txt
index 960b888..827181c 100644
--- a/ml_project/requirements.txt
+++ b/ml_project/requirements.txt
@@ -12,3 +12,6 @@ seaborn==0.11.1
 scikit-learn==0.24.1
 hydra-core==1.0.6
 pytest==6.2.3
+uvicorn[standard]==0.13.4
+fastapi==0.64.0
+python-dotenv==0.17.1
diff --git a/ml_project/tests/conftest.py b/ml_project/tests/conftest.py
index 5206648..1427de9 100644
--- a/ml_project/tests/conftest.py
+++ b/ml_project/tests/conftest.py
@@ -1,6 +1,5 @@
 from collections import OrderedDict
-from pathlib import Path
-from typing import List, Union, Dict, Callable
+from typing import List, Union, Dict, Callable, Tuple
 
 import numpy as np
 import pandas as pd
@@ -8,9 +7,14 @@
 from numpy.random import Generator, PCG64
 
 from heart_disease.data.make_dataset import read_data
+from heart_disease.entities.data_loading_config import DataLoadingConfig
 from heart_disease.entities.feature_config import FeatureConfig, RandomProjectionFeaturesConfig, \
     StatisticalFeaturesConfig, KMeansFeaturesConfig, PolynomialFeaturesConfig, RawFeaturesConfig
-from heart_disease.features.build_features import build_feature_pipeline
+from heart_disease.entities.model_config import TrainModelConfig, EvaluateModelConfig, ModelType
+from heart_disease.entities.pipeline_config import TrainingConfig
+from heart_disease.entities.splitting_config import SplittingConfig
+from heart_disease.features.build_features import build_feature_pipeline, extract_raw_features
+from heart_disease.models.train_model import train_pipeline
 
 
 def get_row_generators(rng: Generator) -> Dict[str, Callable]:
@@ -32,17 +36,17 @@ def get_row_generators(rng: Generator) -> Dict[str, Callable]:
     }
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def categorical_features() -> List[str]:
     return ["thal", "ca", "slope", "exang", "restecg", "fbs", "cp", "sex"]
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def numerical_features() -> List[str]:
     return ["age", "trestbps", "chol", "thalach", "oldpeak"]
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def target_column() -> str:
     return "target"
 
@@ -54,31 +58,48 @@ def generate_random_row(row_generators: Dict[str, Callable]) -> Dict[str, Union[
     return row
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def dataset_filename() -> str:
     return "data.csv"
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def dataset_size() -> int:
     return 200
 
 
-@pytest.fixture(scope='function')
-def dataset_file(tmp_path: Path, dataset_filename: str, dataset_size: int) -> str:
+@pytest.fixture(scope="session")
+def dataset_file(tmp_path_factory, dataset_filename: str, dataset_size: int) -> str:
+    path = tmp_path_factory.mktemp("path")
     rng = Generator(PCG64(12345))
     data = pd.DataFrame.from_records([generate_random_row(get_row_generators(rng)) for _ in range(dataset_size)])
-    dataset_path = tmp_path / dataset_filename
+    dataset_path = path / dataset_filename
     data.to_csv(dataset_path, index=False)
     return str(dataset_path)
 
 
-@pytest.fixture(scope='function')
+@pytest.fixture(scope="session")
+def test_dataset_file(tmp_path_factory, dataset_filename: str, dataset_size: int, target_column: str) -> str:
+    path = tmp_path_factory.mktemp("path")
+    rng = Generator(PCG64(12345))
+    data = pd.DataFrame.from_records([generate_random_row(get_row_generators(rng)) for _ in range(dataset_size)])
+    data.drop(columns=[target_column, ], inplace=True)
+    dataset_path = path / dataset_filename
+    data.to_csv(dataset_path, index=False)
+    return str(dataset_path)
+
+
+@pytest.fixture(scope="session")
 def dataset(dataset_file: str) -> pd.DataFrame:
     return read_data(dataset_file)
 
 
-@pytest.fixture(scope='function')
+@pytest.fixture(scope="session")
+def test_dataset(test_dataset_file: str) -> pd.DataFrame:
+    return read_data(test_dataset_file)
+
+
+@pytest.fixture(scope="session")
 def features(
         dataset: pd.DataFrame,
         categorical_features: List[str],
@@ -92,16 +113,16 @@ def features(
     config = get_feature_config(target_column, categorical_features, n_clusters, numerical_features, polynomial_degree,
                                 projection_features, statistics)
     pipeline = build_feature_pipeline(config)
-    transformed_features = pipeline.fit_transform(dataset)
+    transformed_features = pipeline.fit_transform(extract_raw_features(dataset, config))
     return transformed_features
 
 
-@pytest.fixture(scope='function')
+@pytest.fixture(scope="session")
 def target(dataset: pd.DataFrame, target_column: str) -> np.ndarray:
     return dataset[target_column].values
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def statistics() -> OrderedDict[str, Callable]:
     return OrderedDict(sum=np.sum, var=lambda x, **kwargs: np.var(x, ddof=1, **kwargs), median=np.median,
                        mean=np.mean, std=lambda x, **kwargs: np.std(x, ddof=1, **kwargs), max=np.max, min=np.min)
@@ -132,6 +153,71 @@ def get_feature_config(
     return config
 
 
-@pytest.fixture(scope='session')
+@pytest.fixture(scope="session")
 def metrics() -> List[str]:
     return ["accuracy", "f1", "precision", "recall"]
+
+
+@pytest.fixture(scope="session")
+def metrics_path(tmp_path_factory) -> str:
+    return str(tmp_path_factory.mktemp("path") / "metrics.yaml")
+
+
+@pytest.fixture(scope="session")
+def model_save_path(tmp_path_factory) -> str:
+    return str(tmp_path_factory.mktemp("path") / "model.pkl")
+
+
+@pytest.fixture(scope="session")
+def pipeline_save_path(tmp_path_factory) -> str:
+    return str(tmp_path_factory.mktemp("path") / "pipeline.pkl")
+
+
+@pytest.fixture(scope="session")
+def metadata_path(tmp_path_factory) -> str:
+    return str(tmp_path_factory.mktemp("path") / "metadata.pkl")
+
+
+@pytest.fixture(scope="session")
+def train_artifacts(
+        categorical_features: List[str],
+        dataset_file: str,
+        metrics: List[str],
+        numerical_features: List[str],
+        statistics: OrderedDict[str, Callable],
+        model_save_path: str,
+        pipeline_save_path: str,
+        metrics_path: str,
+        metadata_path: str,
+        target_column: str
+) -> Tuple[str, str, str, str]:
+    projection_features = 5
+    polynomial_degree = 2
+    n_clusters = 2
+    feature_config = get_feature_config(target_column, categorical_features, n_clusters, numerical_features,
+                                        polynomial_degree,
+                                        projection_features, statistics)
+    config = TrainingConfig(
+        data_load_config=DataLoadingConfig(
+            split_config=SplittingConfig(
+                random_state=42,
+                val_size=0.2
+            ),
+            data_path=dataset_file
+        ),
+        feature_config=feature_config,
+        model_config=TrainModelConfig(
+            model=ModelType.random_forest,
+            random_state=42,
+            params=dict(n_estimators=55)
+        ),
+        evaluation_config=EvaluateModelConfig(
+            metrics=metrics,
+            metric_file_path=metrics_path
+        ),
+        pipeline_save_path=pipeline_save_path,
+        model_save_path=model_save_path,
+        metadata_save_path=metadata_path
+    )
+    train_pipeline(config)
+    return metrics_path, model_save_path, pipeline_save_path, metadata_path
diff --git a/ml_project/tests/models/test_models.py b/ml_project/tests/models/test_models.py
index 699b738..650b9a6 100644
--- a/ml_project/tests/models/test_models.py
+++ b/ml_project/tests/models/test_models.py
@@ -21,7 +21,6 @@ def test_predict(features: np.ndarray, target: np.ndarray):
     config = TrainModelConfig(model=ModelType.random_forest, random_state=42, params=dict(n_estimators=50))
     model = train_model(features, target, config)
     predicted = predict_model(model, features)
-    print(predicted.shape, target.shape)
     assert predicted.shape[0] == target.shape[0]
 
 
diff --git a/ml_project/tests/models/test_pipelines.py b/ml_project/tests/models/test_pipelines.py
index 2bb24d3..52bf651 100644
--- a/ml_project/tests/models/test_pipelines.py
+++ b/ml_project/tests/models/test_pipelines.py
@@ -1,81 +1,17 @@
 from pathlib import Path
-from typing import List, Callable, OrderedDict
+from typing import Tuple
 
 import numpy as np
 import yaml
 
-from heart_disease.entities.data_loading_config import DataLoadingConfig
-from heart_disease.entities.model_config import TrainModelConfig, EvaluateModelConfig, ModelType
-from heart_disease.entities.pipeline_config import TrainingConfig, PredictConfig
-from heart_disease.entities.splitting_config import SplittingConfig
+from heart_disease.entities.pipeline_config import PredictConfig
 from heart_disease.models.predict_model import predict
-from heart_disease.models.train_model import train_pipeline
-from tests.conftest import get_feature_config
-
-
-def train_model(
-        categorical_features: List[str],
-        dataset_file: str,
-        metrics: List[str],
-        numerical_features: List[str],
-        statistics: OrderedDict[str, Callable],
-        target_column: str,
-        tmpdir: Path
-):
-    model_save_path = str(tmpdir / "model.pkl")
-    pipeline_save_path = str(tmpdir / "pipeline.pkl")
-    metrics_path = str(tmpdir / "metrics.yaml")
-    metadata_path = str(tmpdir / "metadata.pkl")
-    projection_features = 5
-    polynomial_degree = 2
-    n_clusters = 2
-    feature_config = get_feature_config(target_column, categorical_features, n_clusters, numerical_features,
-                                        polynomial_degree,
-                                        projection_features, statistics)
-    config = TrainingConfig(
-        data_load_config=DataLoadingConfig(
-            split_config=SplittingConfig(
-                random_state=42,
-                val_size=0.2
-            ),
-            data_path=dataset_file
-        ),
-        feature_config=feature_config,
-        model_config=TrainModelConfig(
-            model=ModelType.random_forest,
-            random_state=42,
-            params=dict(n_estimators=55)
-        ),
-        evaluation_config=EvaluateModelConfig(
-            metrics=metrics,
-            metric_file_path=metrics_path
-        ),
-        pipeline_save_path=pipeline_save_path,
-        model_save_path=model_save_path,
-        metadata_save_path=metadata_path
-    )
-    train_pipeline(config)
-    return metrics_path, model_save_path, pipeline_save_path, metadata_path
 
 
 def test_train_pipeline(
-        tmpdir: Path,
-        dataset_file: str,
-        categorical_features: List[str],
-        numerical_features: List[str],
-        target_column: str,
-        metrics: List[str],
-        statistics: OrderedDict[str, Callable]
+        train_artifacts: Tuple[str, str, str, str]
 ):
-    metrics_path, model_save_path, pipeline_save_path, metadata_path = train_model(
-        categorical_features,
-        dataset_file,
-        metrics,
-        numerical_features,
-        statistics,
-        target_column,
-        tmpdir
-    )
+    metrics_path, model_save_path, pipeline_save_path, metadata_path = train_artifacts
     assert Path(model_save_path).exists()
     assert Path(pipeline_save_path).exists()
     assert Path(metadata_path).exists()
@@ -90,28 +26,16 @@ def test_train_pipeline(
 
 def test_predict_pipeline(
         tmpdir: Path,
-        dataset_file: str,
+        train_artifacts: Tuple[str, str, str, str],
+        test_dataset_file: str,
         dataset_size: int,
-        categorical_features: List[str],
-        numerical_features: List[str],
-        target_column: str,
-        metrics: List[str],
-        statistics: OrderedDict[str, Callable]
 ):
+    metrics_path, model_save_path, pipeline_save_path, metadata_path = train_artifacts
     output = str(tmpdir / "output.txt")
-    _, model_save_path, pipeline_save_path, _ = train_model(
-        categorical_features,
-        dataset_file,
-        metrics,
-        numerical_features,
-        statistics,
-        target_column,
-        tmpdir
-    )
     config = PredictConfig(
         model_load_path=model_save_path,
         pipeline_load_path=pipeline_save_path,
-        data_path=dataset_file,
+        data_path=test_dataset_file,
         output_path=output
     )
     predict(config)
diff --git a/ml_project/tests/online_inference/__init__.py b/ml_project/tests/online_inference/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/ml_project/tests/online_inference/test_api.py b/ml_project/tests/online_inference/test_api.py
new file mode 100644
index 0000000..8449ecc
--- /dev/null
+++ b/ml_project/tests/online_inference/test_api.py
@@ -0,0 +1,84 @@
+from typing import Tuple, List
+
+import pandas as pd
+import pytest
+from dotenv import load_dotenv
+from fastapi.testclient import TestClient
+from pydantic import parse_obj_as
+
+from online_inference.schemas import HeartDiseaseModel, HeartDiseaseResponseModel
+
+
+@pytest.fixture(scope="session")
+def test_client(tmp_path_factory, train_artifacts: Tuple[str, str, str, str]):
+    # Alas, FastAPI currently cannot use DI in events.
+    # Setting up .env config manually
+    # https://github.com/tiangolo/fastapi/issues/2057
+
+    path = tmp_path_factory.mktemp("path")
+
+    _, model_save_path, pipeline_save_path, metadata_path = train_artifacts
+    new_env = path / ".env"
+    with open(new_env, "w") as f:
+        print(f"model_path={model_save_path}", file=f)
+        print(f"pipeline_path={pipeline_save_path}", file=f)
+        print(f"metadata_path={metadata_path}", file=f)
+    load_dotenv(dotenv_path=new_env)
+
+    from online_inference.api import app
+    client = TestClient(app)
+    return client
+
+
+def test_predict(test_dataset: pd.DataFrame, test_client: TestClient):
+    ids = list(range(test_dataset.shape[0]))
+    request = HeartDiseaseModel(
+        ids=ids,
+        features=test_dataset.values.tolist(),
+        columns=test_dataset.columns.tolist()
+    )
+    with test_client as client:
+        response = client.post("/predict", data=request.json())
+    assert response.status_code == 200
+    preds = parse_obj_as(List[HeartDiseaseResponseModel], response.json())
+    assert len(preds) == test_dataset.shape[0]
+    assert set([i.id for i in preds]) == set(ids)
+
+
+def test_predict_wrong_shape(test_dataset: pd.DataFrame, test_client: TestClient):
+    ids = list(range(test_dataset.shape[0]))
+    request = HeartDiseaseModel(
+        ids=ids,
+        features=test_dataset.values.tolist(),
+        columns=test_dataset.columns.tolist()[:-1]
+    )
+    with test_client as client:
+        response = client.post("/predict", data=request.json())
+    assert response.status_code == 400
+
+
+def test_predict_wrong_column(test_dataset: pd.DataFrame, test_client: TestClient):
+    ids = list(range(test_dataset.shape[0]))
+    columns = test_dataset.columns.tolist()[:-1] + ["obviously_extra_column"]
+    request = HeartDiseaseModel(
+        ids=ids,
+        features=test_dataset.values.tolist(),
+        columns=columns
+    )
+    with test_client as client:
+        response = client.post("/predict", data=request.json())
+    assert response.status_code == 400
+
+
+def test_predict_wrong_dtype(test_dataset: pd.DataFrame, test_client: TestClient, categorical_features: List[str]):
+    dataset_copy = test_dataset.copy(deep=True)
+    ids = list(range(dataset_copy.shape[0]))
+    dataset_copy[categorical_features[0]] = float('nan')
+    request = HeartDiseaseModel(
+        ids=ids,
+        features=dataset_copy.values.tolist(),
+        columns=dataset_copy.columns.tolist()
+    )
+    with test_client as client:
+        response = client.post("/predict", data=request.json())
+    assert response.status_code == 400

From d36a68b3af246a84330ac8ffeb2e71d70a1660bd Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Sun, 9 May 2021 15:51:58 +1000
Subject: [PATCH 03/14] Ignore extra columns

---
 ml_project/online_inference/api.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ml_project/online_inference/api.py b/ml_project/online_inference/api.py
index 906ad35..dc95111 100644
--- a/ml_project/online_inference/api.py
+++ b/ml_project/online_inference/api.py
@@ -45,7 +45,7 @@ def rebuild_dataframe(params: HeartDiseaseModel, metadata: Dict[str, np.dtype])
                 error_msg = f"Failed to cast column {key} to dtype {dtype}"
                 logger.exception(error_msg)
                 raise HTTPException(status_code=400, detail=error_msg)
-    return data
+    return data[list(metadata.keys())]
 
 
 @app.post("/predict", response_model=List[HeartDiseaseResponseModel])

From 6e8769cd30c94c598aa82a1699134307fb3eb198 Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Sun, 9 May 2021 15:52:09 +1000
Subject: [PATCH 04/14] Add request script

---
 ml_project/online_inference/make_request.py | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
 create mode 100644 ml_project/online_inference/make_request.py

diff --git a/ml_project/online_inference/make_request.py b/ml_project/online_inference/make_request.py
new file mode 100644
index 0000000..bbd7753
--- /dev/null
+++ b/ml_project/online_inference/make_request.py
@@ -0,0 +1,18 @@
+import requests
+
+from heart_disease.data.make_dataset import read_data
+
+DATA_PATH = "data/heart.csv"
+
+if __name__ == '__main__':
+    data = read_data(DATA_PATH)
+    response = requests.post(
+        "http://localhost:8000/predict",
+        json={
+            "ids": list(range(data.shape[0])),
+            "features": data.values.tolist(),
+            "columns": data.columns.tolist()
+        },
+    )
+    print(response.status_code)
+    print(response.json())

From f6d426d7c5f3f7e77dc5c4b8a1f4bba02f76abdf Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Sun, 9 May 2021 16:28:17 +1000
Subject: [PATCH 05/14] Separate requirements.txt

---
 ml_project/Makefile             | 2 +-
 ml_project/dev_requirements.txt | 4 ++++
 ml_project/requirements.txt     | 3 ---
 3 files changed, 5 insertions(+), 4 deletions(-)
 create mode 100644 ml_project/dev_requirements.txt

diff --git a/ml_project/Makefile b/ml_project/Makefile
index 5aa376b..de6a2f6 100644
--- a/ml_project/Makefile
+++ b/ml_project/Makefile
@@ -23,7 +23,7 @@ endif
 ## Install Python Dependencies
 requirements: test_environment
 	$(PYTHON_INTERPRETER) -m pip install -U pip setuptools wheel
-	$(PYTHON_INTERPRETER) -m pip install -r requirements.txt
+	$(PYTHON_INTERPRETER) -m pip install -r dev_requirements.txt
 
 ## Build EDA report
 eda_report: requirements
diff --git a/ml_project/dev_requirements.txt b/ml_project/dev_requirements.txt
new file mode 100644
index 0000000..93c9460
--- /dev/null
+++ b/ml_project/dev_requirements.txt
@@ -0,0 +1,4 @@
+# local package
+-e .
+
+-r requirements.txt
diff --git a/ml_project/requirements.txt b/ml_project/requirements.txt
index 827181c..6211586 100644
--- a/ml_project/requirements.txt
+++ b/ml_project/requirements.txt
@@ -1,6 +1,3 @@
-# local package
--e .
-
 # external requirements
 click==7.1.2
 coverage==5.5

From 06d4af509afaf455c762ae834cee065016390983 Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Sun, 9 May 2021 16:28:40 +1000
Subject: [PATCH 06/14] Add Dockerfile and instructions to run

---
 ml_project/Dockerfile | 19 +++++++++++++++++++
 ml_project/README.md  | 22 ++++++++++++++++++++++
 2 files changed, 41 insertions(+)
 create mode 100644 ml_project/Dockerfile

diff --git a/ml_project/Dockerfile b/ml_project/Dockerfile
new file mode 100644
index 0000000..176971a
--- /dev/null
+++ b/ml_project/Dockerfile
@@ -0,0 +1,19 @@
+FROM python:3.9.2-buster
+
+COPY requirements.txt ./requirements.txt
+RUN pip install -r requirements.txt
+
+COPY heart_disease heart_disease
+COPY online_inference online_inference
+
+COPY models/model.pkl model.pkl
+COPY models/pipeline.pkl pipeline.pkl
+COPY models/metadata.pkl metadata.pkl
+
+WORKDIR .
+
+ENV model_path="/model.pkl"
+ENV pipeline_path="/pipeline.pkl"
+ENV metadata_path="/metadata.pkl"
+
+CMD ["uvicorn", "online_inference.api:app", "--host", "0.0.0.0", "--port", "80"]
diff --git a/ml_project/README.md b/ml_project/README.md
index 535f65e..9cae78a 100644
--- a/ml_project/README.md
+++ b/ml_project/README.md
@@ -39,3 +39,25 @@ make requirements
 
 Пути к файлам можно указывать через файлы конфигов, либо через 
 параметры командной строки (e.g. `python -m heart_disease.models.predict_model data_path="data/new_data.csv"`)
+
+
+Сборка образа
+-----------------
+```shell
+python -m heart_disease.models.train_model
+docker build . -t ml_project:latest
+```
+
+Публикация образа
+-----------------
+```shell
+docker tag ml_project:latest polikutinevgeny/ml_project:latest
+docker push polikutinevgeny/ml_project:latest
+```
+
+Запуск образа
+-------------
+```shell
+docker pull polikutinevgeny/ml_project:latest
+docker run -p 8000:80 polikutinevgeny/ml_project:latest
+```

From 9539dbb002a22a0d11f641e65d30ff9ba88b6f41 Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Sun, 9 May 2021 16:29:27 +1000
Subject: [PATCH 07/14] Add request instructions

---
 ml_project/README.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/ml_project/README.md b/ml_project/README.md
index 9cae78a..000c736 100644
--- a/ml_project/README.md
+++ b/ml_project/README.md
@@ -61,3 +61,6 @@ docker push polikutinevgeny/ml_project:latest
 docker pull polikutinevgeny/ml_project:latest
 docker run -p 8000:80 polikutinevgeny/ml_project:latest
 ```
+
+Протыкать скриптом:
+`python -m online_inference.make_request`

From c3ffef227dd3e715537a9002df157d9fd55e46ea Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Sat, 22 May 2021 12:32:25 +1000
Subject: [PATCH 08/14] Move online inference into a "separate" package.

---
 Dockerfile                                    | 28 +++++++++++++++++++
 README.md                                     | 24 ++++++++++++++++
 ml_project/tests/conftest.py => conftest.py   |  0
 ml_project/Dockerfile                         | 19 -------------
 ml_project/README.md                          | 25 -----------------
 ml_project/{online_inference => }/__init__.py |  0
 ml_project/setup.py                           | 10 +++++++
 .../tests/features/test_build_features.py     |  2 +-
 .../__init__.py                               |  0
 online_inference/api/__init__.py              |  0
 .../api}/api.py                               | 19 ++++++++-----
 .../api}/make_request.py                      |  7 ++---
 .../api}/schemas.py                           |  0
 online_inference/requirements.txt             |  6 ++++
 online_inference/tests/__init__.py            |  0
 .../tests}/test_api.py                        |  4 +--
 16 files changed, 86 insertions(+), 58 deletions(-)
 create mode 100644 Dockerfile
 rename ml_project/tests/conftest.py => conftest.py (100%)
 delete mode 100644 ml_project/Dockerfile
 rename ml_project/{online_inference => }/__init__.py (100%)
 rename {ml_project/tests/online_inference => online_inference}/__init__.py (100%)
 create mode 100644 online_inference/api/__init__.py
 rename {ml_project/online_inference => online_inference/api}/api.py (78%)
 rename {ml_project/online_inference => online_inference/api}/make_request.py (74%)
 rename {ml_project/online_inference => online_inference/api}/schemas.py (100%)
 create mode 100644 online_inference/requirements.txt
 create mode 100644 online_inference/tests/__init__.py
 rename {ml_project/tests/online_inference => online_inference/tests}/test_api.py (95%)

diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..3b496ac
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,28 @@
+FROM python:3.9.2-buster AS build
+
+COPY ml_project ml_project
+WORKDIR /ml_project
+RUN pip install --upgrade build
+RUN python -m build
+
+FROM python:3.9.2-buster
+
+COPY online_inference/requirements.txt ./requirements.txt
+RUN pip install -r requirements.txt
+
+COPY --from=build /ml_project/dist dist
+RUN pip install dist/*.whl && rm -rf dist
+
+COPY online_inference/api api
+
+COPY ml_project/models/model.pkl model.pkl
+COPY ml_project/models/pipeline.pkl pipeline.pkl
+COPY ml_project/models/metadata.pkl metadata.pkl
+
+WORKDIR .
+
+ENV model_path="/model.pkl"
+ENV pipeline_path="/pipeline.pkl"
+ENV metadata_path="/metadata.pkl"
+
+CMD ["uvicorn", "api.api:app", "--host", "0.0.0.0", "--port", "80"]
diff --git a/README.md b/README.md
index 9224c6f..9d1129e 100644
--- a/README.md
+++ b/README.md
@@ -3,3 +3,27 @@
 Репозиторий для курса "Машинное обучение в продакшене" MADE.
 
 [Профиль](https://data.mail.ru/profile/e.polikutin/)
+
+Сборка образа
+-----------------
+```shell
+python -m heart_disease.models.train_model
+docker build . -t ml_project:latest
+```
+
+Публикация образа
+-----------------
+```shell
+docker tag ml_project:latest polikutinevgeny/ml_project:latest
+docker push polikutinevgeny/ml_project:latest
+```
+
+Запуск образа
+-------------
+```shell
+docker pull polikutinevgeny/ml_project:latest
+docker run -p 8000:80 polikutinevgeny/ml_project:latest
+```
+
+Протыкать скриптом:
+`python -m online_inference.api.make_request`
diff --git a/ml_project/tests/conftest.py b/conftest.py
similarity index 100%
rename from ml_project/tests/conftest.py
rename to conftest.py
diff --git a/ml_project/Dockerfile b/ml_project/Dockerfile
deleted file mode 100644
index 176971a..0000000
--- a/ml_project/Dockerfile
+++ /dev/null
@@ -1,19 +0,0 @@
-FROM python:3.9.2-buster
-
-COPY requirements.txt ./requirements.txt
-RUN pip install -r requirements.txt
-
-COPY heart_disease heart_disease
-COPY online_inference online_inference
-
-COPY models/model.pkl model.pkl
-COPY models/pipeline.pkl pipeline.pkl
-COPY models/metadata.pkl metadata.pkl
-
-WORKDIR .
-
-ENV model_path="/model.pkl"
-ENV pipeline_path="/pipeline.pkl"
-ENV metadata_path="/metadata.pkl"
-
-CMD ["uvicorn", "online_inference.api:app", "--host", "0.0.0.0", "--port", "80"]
diff --git a/ml_project/README.md b/ml_project/README.md
index 000c736..535f65e 100644
--- a/ml_project/README.md
+++ b/ml_project/README.md
@@ -39,28 +39,3 @@ make requirements
 
 Пути к файлам можно указывать через файлы конфигов, либо через 
 параметры командной строки (e.g. `python -m heart_disease.models.predict_model data_path="data/new_data.csv"`)
-
-
-Сборка образа
------------------
-```shell
-python -m heart_disease.models.train_model
-docker build . -t ml_project:latest
-```
-
-Публикация образа
------------------
-```shell
-docker tag ml_project:latest polikutinevgeny/ml_project:latest
-docker push polikutinevgeny/ml_project:latest
-```
-
-Запуск образа
--------------
-```shell
-docker pull polikutinevgeny/ml_project:latest
-docker run -p 8000:80 polikutinevgeny/ml_project:latest
-```
-
-Протыкать скриптом:
-`python -m online_inference.make_request`
diff --git a/ml_project/online_inference/__init__.py b/ml_project/__init__.py
similarity index 100%
rename from ml_project/online_inference/__init__.py
rename to ml_project/__init__.py
diff --git a/ml_project/setup.py b/ml_project/setup.py
index 0c16588..6c87d12 100644
--- a/ml_project/setup.py
+++ b/ml_project/setup.py
@@ -1,4 +1,13 @@
 from setuptools import find_packages, setup
+import pathlib
+import pkg_resources
+
+with pathlib.Path('requirements.txt').open() as requirements_txt:
+    install_requires = [
+        str(requirement)
+        for requirement
+        in pkg_resources.parse_requirements(requirements_txt)
+    ]
 
 setup(
     name='heart_disease',
@@ -7,4 +16,5 @@
     description='Predicting heart disease',
     author='Evgenii Polikutin',
     license='MIT',
+    install_requires=install_requires
 )
diff --git a/ml_project/tests/features/test_build_features.py b/ml_project/tests/features/test_build_features.py
index 442df2f..7849a6c 100644
--- a/ml_project/tests/features/test_build_features.py
+++ b/ml_project/tests/features/test_build_features.py
@@ -17,7 +17,7 @@
     serialize_pipeline, \
     deserialize_pipeline, \
     extract_target
-from tests.conftest import get_feature_config
+from conftest import get_feature_config
 
 EPS = 1e-6
 
diff --git a/ml_project/tests/online_inference/__init__.py b/online_inference/__init__.py
similarity index 100%
rename from ml_project/tests/online_inference/__init__.py
rename to online_inference/__init__.py
diff --git a/online_inference/api/__init__.py b/online_inference/api/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/ml_project/online_inference/api.py b/online_inference/api/api.py
similarity index 78%
rename from ml_project/online_inference/api.py
rename to online_inference/api/api.py
index dc95111..e440f50 100644
--- a/ml_project/online_inference/api.py
+++ b/online_inference/api/api.py
@@ -1,14 +1,14 @@
 import logging
-from typing import List, Dict
+import pickle
+from pathlib import Path
+from typing import List, Dict, Any
 
 import numpy as np
 import pandas as pd
 from dotenv import load_dotenv
 from fastapi import FastAPI, HTTPException, Request
 
-from heart_disease.features.build_features import deserialize_metadata, deserialize_pipeline
-from heart_disease.models.model import deserialize_model
-from online_inference.schemas import HeartDiseaseModel, HeartDiseaseResponseModel, Settings
+from .schemas import HeartDiseaseModel, HeartDiseaseResponseModel, Settings
 
 logger = logging.getLogger(__name__)
 
@@ -19,11 +19,16 @@
 )
 
 
+def deserialize_object(path: Path) -> Any:
+    with open(path, "rb") as f:
+        return pickle.load(f)
+
+
 @app.on_event("startup")
 def load_artifacts():
-    app.state.metadata = deserialize_metadata(str(settings.metadata_path))
-    app.state.pipeline = deserialize_pipeline(str(settings.pipeline_path))
-    app.state.model = deserialize_model(str(settings.model_path))
+    app.state.metadata = deserialize_object(settings.metadata_path)
+    app.state.pipeline = deserialize_object(settings.pipeline_path)
+    app.state.model = deserialize_object(settings.model_path)
 
 
 def rebuild_dataframe(params: HeartDiseaseModel, metadata: Dict[str, np.dtype]) -> pd.DataFrame:
diff --git a/ml_project/online_inference/make_request.py b/online_inference/api/make_request.py
similarity index 74%
rename from ml_project/online_inference/make_request.py
rename to online_inference/api/make_request.py
index bbd7753..4684e4a 100644
--- a/ml_project/online_inference/make_request.py
+++ b/online_inference/api/make_request.py
@@ -1,11 +1,10 @@
 import requests
+import pandas as pd
 
-from heart_disease.data.make_dataset import read_data
-
-DATA_PATH = "data/heart.csv"
+DATA_PATH = "ml_project/data/heart.csv"
 
 if __name__ == '__main__':
-    data = read_data(DATA_PATH)
+    data = pd.read_csv(DATA_PATH)
     response = requests.post(
         "http://localhost:8000/predict",
         json={
diff --git a/ml_project/online_inference/schemas.py b/online_inference/api/schemas.py
similarity index 100%
rename from ml_project/online_inference/schemas.py
rename to online_inference/api/schemas.py
diff --git a/online_inference/requirements.txt b/online_inference/requirements.txt
new file mode 100644
index 0000000..c54630a
--- /dev/null
+++ b/online_inference/requirements.txt
@@ -0,0 +1,6 @@
+pandas==1.2.4
+scikit-learn==0.24.1
+pytest==6.2.3
+uvicorn[standard]==0.13.4
+fastapi==0.64.0
+python-dotenv==0.17.1
diff --git a/online_inference/tests/__init__.py b/online_inference/tests/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/ml_project/tests/online_inference/test_api.py b/online_inference/tests/test_api.py
similarity index 95%
rename from ml_project/tests/online_inference/test_api.py
rename to online_inference/tests/test_api.py
index 8449ecc..d82b20e 100644
--- a/ml_project/tests/online_inference/test_api.py
+++ b/online_inference/tests/test_api.py
@@ -6,7 +6,7 @@
 from fastapi.testclient import TestClient
 from pydantic import parse_obj_as
 
-from online_inference.schemas import HeartDiseaseModel, HeartDiseaseResponseModel
+from online_inference.api.schemas import HeartDiseaseModel, HeartDiseaseResponseModel
 
 
 @pytest.fixture(scope="session")
@@ -25,7 +25,7 @@ def test_client(tmp_path_factory, train_artifacts: Tuple[str, str, str, str]):
         print(f"metadata_path={metadata_path}", file=f)
     load_dotenv(dotenv_path=new_env)
 
-    from online_inference.api import app
+    from online_inference.api.api import app
     client = TestClient(app)
     return client
 

From 2c725730cf28da82ce3ee22e12b2b0c034a9d8ab Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Tue, 25 May 2021 20:46:39 +1000
Subject: [PATCH 09/14] Remove dependency on heart_disease package in online
 inference

---
 Dockerfile                                    | 28 ----------
 ml_project/__init__.py                        |  0
 ml_project/heart_disease/utils.py             |  8 +--
 ml_project/requirements.txt                   |  3 +-
 conftest.py => ml_project/tests/conftest.py   |  0
 .../tests/features/test_build_features.py     |  2 +-
 online_inference/.env                         |  3 ++
 online_inference/Dockerfile                   | 18 +++++++
 README.md => online_inference/README.md       |  4 +-
 online_inference/__init__.py                  |  0
 online_inference/api/api.py                   |  4 +-
 online_inference/{api => }/make_request.py    |  2 +-
 online_inference/requirements.txt             |  4 +-
 online_inference/tests/conftest.py            | 53 +++++++++++++++++++
 online_inference/tests/test_api.py            | 32 +++--------
 15 files changed, 96 insertions(+), 65 deletions(-)
 delete mode 100644 Dockerfile
 delete mode 100644 ml_project/__init__.py
 rename conftest.py => ml_project/tests/conftest.py (100%)
 create mode 100644 online_inference/.env
 create mode 100644 online_inference/Dockerfile
 rename README.md => online_inference/README.md (85%)
 delete mode 100644 online_inference/__init__.py
 rename online_inference/{api => }/make_request.py (90%)
 create mode 100644 online_inference/tests/conftest.py

diff --git a/Dockerfile b/Dockerfile
deleted file mode 100644
index 3b496ac..0000000
--- a/Dockerfile
+++ /dev/null
@@ -1,28 +0,0 @@
-FROM python:3.9.2-buster AS build
-
-COPY ml_project ml_project
-WORKDIR /ml_project
-RUN pip install --upgrade build
-RUN python -m build
-
-FROM python:3.9.2-buster
-
-COPY online_inference/requirements.txt ./requirements.txt
-RUN pip install -r requirements.txt
-
-COPY --from=build /ml_project/dist dist
-RUN pip install dist/*.whl && rm -rf dist
-
-COPY online_inference/api api
-
-COPY ml_project/models/model.pkl model.pkl
-COPY ml_project/models/pipeline.pkl pipeline.pkl
-COPY ml_project/models/metadata.pkl metadata.pkl
-
-WORKDIR .
-
-ENV model_path="/model.pkl"
-ENV pipeline_path="/pipeline.pkl"
-ENV metadata_path="/metadata.pkl"
-
-CMD ["uvicorn", "api.api:app", "--host", "0.0.0.0", "--port", "80"]
diff --git a/ml_project/__init__.py b/ml_project/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/ml_project/heart_disease/utils.py b/ml_project/heart_disease/utils.py
index 144b839..a2fd51f 100644
--- a/ml_project/heart_disease/utils.py
+++ b/ml_project/heart_disease/utils.py
@@ -1,12 +1,14 @@
-import pickle
+import cloudpickle
 from typing import Any
 
+cloudpickle.register_deep_serialization("heart_disease")
+
 
 def serialize_object(obj: Any, path: str):
     with open(path, "wb") as f:
-        pickle.dump(obj, f)
+        cloudpickle.dump(obj, f)
 
 
 def deserialize_object(path: str) -> Any:
     with open(path, "rb") as f:
-        return pickle.load(f)
+        return cloudpickle.load(f)
diff --git a/ml_project/requirements.txt b/ml_project/requirements.txt
index 6211586..05c6058 100644
--- a/ml_project/requirements.txt
+++ b/ml_project/requirements.txt
@@ -9,6 +9,5 @@ seaborn==0.11.1
 scikit-learn==0.24.1
 hydra-core==1.0.6
 pytest==6.2.3
-uvicorn[standard]==0.13.4
-fastapi==0.64.0
 python-dotenv==0.17.1
+git+git://github.com/polikutinevgeny/cloudpickle.git@206-deep-serialization
diff --git a/conftest.py b/ml_project/tests/conftest.py
similarity index 100%
rename from conftest.py
rename to ml_project/tests/conftest.py
diff --git a/ml_project/tests/features/test_build_features.py b/ml_project/tests/features/test_build_features.py
index 7849a6c..442df2f 100644
--- a/ml_project/tests/features/test_build_features.py
+++ b/ml_project/tests/features/test_build_features.py
@@ -17,7 +17,7 @@
     serialize_pipeline, \
     deserialize_pipeline, \
     extract_target
-from conftest import get_feature_config
+from tests.conftest import get_feature_config
 
 EPS = 1e-6
 
diff --git a/online_inference/.env b/online_inference/.env
new file mode 100644
index 0000000..b7f27c9
--- /dev/null
+++ b/online_inference/.env
@@ -0,0 +1,3 @@
+model_path=model.pkl
+pipeline_path=pipeline.pkl
+metadata_path=metadata.pkl
diff --git a/online_inference/Dockerfile b/online_inference/Dockerfile
new file mode 100644
index 0000000..81782a8
--- /dev/null
+++ b/online_inference/Dockerfile
@@ -0,0 +1,18 @@
+FROM python:3.9.2-buster
+
+COPY requirements.txt ./requirements.txt
+RUN pip install -r requirements.txt
+
+COPY api api
+
+COPY model.pkl model.pkl
+COPY pipeline.pkl pipeline.pkl
+COPY metadata.pkl metadata.pkl
+
+WORKDIR .
+
+ENV model_path="/model.pkl"
+ENV pipeline_path="/pipeline.pkl"
+ENV metadata_path="/metadata.pkl"
+
+CMD ["uvicorn", "api.api:app", "--host", "0.0.0.0", "--port", "80"]
diff --git a/README.md b/online_inference/README.md
similarity index 85%
rename from README.md
rename to online_inference/README.md
index 9d1129e..a5c01a4 100644
--- a/README.md
+++ b/online_inference/README.md
@@ -6,8 +6,8 @@
 
 Сборка образа
 -----------------
+Сначала обучить и положить артефакты рядом, затем:
 ```shell
-python -m heart_disease.models.train_model
 docker build . -t ml_project:latest
 ```
 
@@ -26,4 +26,4 @@ docker run -p 8000:80 polikutinevgeny/ml_project:latest
 ```
 
 Протыкать скриптом:
-`python -m online_inference.api.make_request`
+`python -m make_request`
diff --git a/online_inference/__init__.py b/online_inference/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/online_inference/api/api.py b/online_inference/api/api.py
index e440f50..6296d5e 100644
--- a/online_inference/api/api.py
+++ b/online_inference/api/api.py
@@ -1,5 +1,5 @@
 import logging
-import pickle
+import cloudpickle
 from pathlib import Path
 from typing import List, Dict, Any
 
@@ -21,7 +21,7 @@
 
 def deserialize_object(path: Path) -> Any:
     with open(path, "rb") as f:
-        return pickle.load(f)
+        return cloudpickle.load(f)
 
 
 @app.on_event("startup")
diff --git a/online_inference/api/make_request.py b/online_inference/make_request.py
similarity index 90%
rename from online_inference/api/make_request.py
rename to online_inference/make_request.py
index 4684e4a..8e41f81 100644
--- a/online_inference/api/make_request.py
+++ b/online_inference/make_request.py
@@ -1,7 +1,7 @@
 import requests
 import pandas as pd
 
-DATA_PATH = "ml_project/data/heart.csv"
+DATA_PATH = "../ml_project/data/heart.csv"
 
 if __name__ == '__main__':
     data = pd.read_csv(DATA_PATH)
diff --git a/online_inference/requirements.txt b/online_inference/requirements.txt
index c54630a..f6e6362 100644
--- a/online_inference/requirements.txt
+++ b/online_inference/requirements.txt
@@ -1,6 +1,8 @@
 pandas==1.2.4
-scikit-learn==0.24.1
 pytest==6.2.3
 uvicorn[standard]==0.13.4
 fastapi==0.64.0
 python-dotenv==0.17.1
+scikit-learn==0.24.1
+omegaconf==2.0.6
+git+git://github.com/polikutinevgeny/cloudpickle.git@206-deep-serialization
diff --git a/online_inference/tests/conftest.py b/online_inference/tests/conftest.py
new file mode 100644
index 0000000..474a811
--- /dev/null
+++ b/online_inference/tests/conftest.py
@@ -0,0 +1,53 @@
+from typing import Union, Dict, Callable, List
+
+import pandas as pd
+import pytest
+from numpy.random import Generator, PCG64
+
+
+def get_row_generators(rng: Generator) -> Dict[str, Callable]:
+    return {
+        "age": lambda: rng.normal(54, 9),
+        "trestbps": lambda: rng.normal(131, 18),
+        "chol": lambda: rng.normal(246, 52),
+        "thalach": lambda: rng.normal(150, 23),
+        "oldpeak": lambda: rng.uniform(0, 6.2),
+        "thal": lambda: rng.integers(0, 4),
+        "ca": lambda: rng.integers(0, 5),
+        "slope": lambda: rng.integers(0, 3),
+        "exang": lambda: rng.integers(0, 2),
+        "restecg": lambda: rng.integers(0, 3),
+        "fbs": lambda: rng.integers(0, 2),
+        "cp": lambda: rng.integers(0, 4),
+        "sex": lambda: rng.integers(0, 2),
+    }
+
+
+@pytest.fixture(scope="session")
+def categorical_features() -> List[str]:
+    return ["thal", "ca", "slope", "exang", "restecg", "fbs", "cp", "sex"]
+
+
+def generate_random_row(row_generators: Dict[str, Callable]) -> Dict[str, Union[int, float]]:
+    row = {}
+    for key, generator in row_generators.items():
+        row[key] = generator()
+    return row
+
+
+@pytest.fixture(scope="session")
+def dataset_filename() -> str:
+    return "data.csv"
+
+
+@pytest.fixture(scope="session")
+def dataset_size() -> int:
+    return 200
+
+
+@pytest.fixture(scope="session")
+def test_dataset(tmp_path_factory, dataset_filename: str, dataset_size: int) -> pd.DataFrame:
+    path = tmp_path_factory.mktemp("path")
+    rng = Generator(PCG64(12345))
+    data = pd.DataFrame.from_records([generate_random_row(get_row_generators(rng)) for _ in range(dataset_size)])
+    return data
diff --git a/online_inference/tests/test_api.py b/online_inference/tests/test_api.py
index d82b20e..633055f 100644
--- a/online_inference/tests/test_api.py
+++ b/online_inference/tests/test_api.py
@@ -6,31 +6,13 @@
 from fastapi.testclient import TestClient
 from pydantic import parse_obj_as
 
-from online_inference.api.schemas import HeartDiseaseModel, HeartDiseaseResponseModel
+from api.api import app
+from api.schemas import HeartDiseaseModel, HeartDiseaseResponseModel, Settings
 
+test_client = TestClient(app)
 
-@pytest.fixture(scope="session")
-def test_client(tmp_path_factory, train_artifacts: Tuple[str, str, str, str]):
-    # Alas, FastAPI currently cannot use DI in events.
-    # Setting up .env config manually
-    # https://github.com/tiangolo/fastapi/issues/2057
 
-    path = tmp_path_factory.mktemp("path")
-
-    _, model_save_path, pipeline_save_path, metadata_path = train_artifacts
-    new_env = path / ".env"
-    with open(new_env, "w") as f:
-        print(f"model_path={model_save_path}", file=f)
-        print(f"pipeline_path={pipeline_save_path}", file=f)
-        print(f"metadata_path={metadata_path}", file=f)
-    load_dotenv(dotenv_path=new_env)
-
-    from online_inference.api.api import app
-    client = TestClient(app)
-    return client
-
-
-def test_predict(test_dataset: pd.DataFrame, test_client: TestClient):
+def test_predict(test_dataset: pd.DataFrame):
     ids = list(range(test_dataset.shape[0]))
     request = HeartDiseaseModel(
         ids=ids,
@@ -45,7 +27,7 @@ def test_predict(test_dataset: pd.DataFrame, test_client: TestClient):
     assert set([i.id for i in preds]) == set(ids)
 
 
-def test_predict_wrong_shape(test_dataset: pd.DataFrame, test_client: TestClient):
+def test_predict_wrong_shape(test_dataset: pd.DataFrame):
     ids = list(range(test_dataset.shape[0]))
     request = HeartDiseaseModel(
         ids=ids,
@@ -57,7 +39,7 @@ def test_predict_wrong_shape(test_dataset: pd.DataFrame, test_client: TestClient
     assert response.status_code == 400
 
 
-def test_predict_wrong_column(test_dataset: pd.DataFrame, test_client: TestClient):
+def test_predict_wrong_column(test_dataset: pd.DataFrame):
     ids = list(range(test_dataset.shape[0]))
     columns = test_dataset.columns.tolist()[:-1] + ["obviously_extra_column"]
     request = HeartDiseaseModel(
@@ -70,7 +52,7 @@ def test_predict_wrong_column(test_dataset: pd.DataFrame, test_client: TestClien
     assert response.status_code == 400
 
 
-def test_predict_wrong_dtype(test_dataset: pd.DataFrame, test_client: TestClient, categorical_features: List[str]):
+def test_predict_wrong_dtype(test_dataset: pd.DataFrame, categorical_features: List[str]):
     dataset_copy = test_dataset.copy(deep=True)
     ids = list(range(dataset_copy.shape[0]))
     dataset_copy[categorical_features[0]] = float('nan')

From f2c2fb05c724340766a374388a01e5949e95ba73 Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Tue, 25 May 2021 20:48:48 +1000
Subject: [PATCH 10/14] Cleanup formatting

---
 online_inference/api/api.py     | 2 +-
 online_inference/api/schemas.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/online_inference/api/api.py b/online_inference/api/api.py
index 6296d5e..9383a51 100644
--- a/online_inference/api/api.py
+++ b/online_inference/api/api.py
@@ -1,8 +1,8 @@
 import logging
-import cloudpickle
 from pathlib import Path
 from typing import List, Dict, Any
 
+import cloudpickle
 import numpy as np
 import pandas as pd
 from dotenv import load_dotenv
diff --git a/online_inference/api/schemas.py b/online_inference/api/schemas.py
index fa15805..e829017 100644
--- a/online_inference/api/schemas.py
+++ b/online_inference/api/schemas.py
@@ -1,5 +1,5 @@
-from typing import Dict, Union, List
 from pathlib import Path
+from typing import Union, List
 
 from pydantic import BaseModel, BaseSettings
 

From 779a1ba26e454018a36f03ad370e71474adda42b Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Tue, 25 May 2021 21:03:15 +1000
Subject: [PATCH 11/14] Bring README back

---
 README.md                  | 5 +++++
 online_inference/README.md | 6 ------
 2 files changed, 5 insertions(+), 6 deletions(-)
 create mode 100644 README.md

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..9224c6f
--- /dev/null
+++ b/README.md
@@ -0,0 +1,5 @@
+# Машинное обучение в продакшене
+
+Репозиторий для курса "Машинное обучение в продакшене" MADE.
+
+[Профиль](https://data.mail.ru/profile/e.polikutin/)
diff --git a/online_inference/README.md b/online_inference/README.md
index a5c01a4..2f6aaa8 100644
--- a/online_inference/README.md
+++ b/online_inference/README.md
@@ -1,9 +1,3 @@
-# Машинное обучение в продакшене
-
-Репозиторий для курса "Машинное обучение в продакшене" MADE.
-
-[Профиль](https://data.mail.ru/profile/e.polikutin/)
-
 Сборка образа
 -----------------
 Сначала обучить и положить артефакты рядом, затем:

From 7f2b484b367e63f788e5e7ca7e2df2e670fcd0da Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Tue, 25 May 2021 21:10:05 +1000
Subject: [PATCH 12/14] Update make_request.py to not depend on data from
 ml_project

---
 online_inference/make_request.py |  2 +-
 online_inference/subset.csv      | 10 ++++++++++
 2 files changed, 11 insertions(+), 1 deletion(-)
 create mode 100644 online_inference/subset.csv

diff --git a/online_inference/make_request.py b/online_inference/make_request.py
index 8e41f81..899e114 100644
--- a/online_inference/make_request.py
+++ b/online_inference/make_request.py
@@ -1,7 +1,7 @@
 import requests
 import pandas as pd
 
-DATA_PATH = "../ml_project/data/heart.csv"
+DATA_PATH = "subset.csv"
 
 if __name__ == '__main__':
     data = pd.read_csv(DATA_PATH)
diff --git a/online_inference/subset.csv b/online_inference/subset.csv
new file mode 100644
index 0000000..a9457ec
--- /dev/null
+++ b/online_inference/subset.csv
@@ -0,0 +1,10 @@
+age,sex,cp,trestbps,chol,fbs,restecg,thalach,exang,oldpeak,slope,ca,thal,target
+63,1,3,145,233,1,0,150,0,2.3,0,0,1,1
+37,1,2,130,250,0,1,187,0,3.5,0,0,2,1
+41,0,1,130,204,0,0,172,0,1.4,2,0,2,1
+56,1,1,120,236,0,1,178,0,0.8,2,0,2,1
+57,0,0,120,354,0,1,163,1,0.6,2,0,2,1
+57,1,0,140,192,0,1,148,0,0.4,1,0,1,1
+56,0,1,140,294,0,0,153,0,1.3,1,0,2,1
+44,1,1,120,263,0,1,173,0,0,2,0,3,1
+52,1,2,172,199,1,1,162,0,0.5,2,0,3,1

From bfbf8a1fe853459a3c6d2e39f88a2ca01cf36178 Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Tue, 25 May 2021 21:15:24 +1000
Subject: [PATCH 13/14] Extract constant

---
 online_inference/api/api.py | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/online_inference/api/api.py b/online_inference/api/api.py
index 9383a51..4ef6367 100644
--- a/online_inference/api/api.py
+++ b/online_inference/api/api.py
@@ -10,6 +10,8 @@
 
 from .schemas import HeartDiseaseModel, HeartDiseaseResponseModel, Settings
 
+VALIDATION_ERROR_STATUS_CODE = 400
+
 logger = logging.getLogger(__name__)
 
 load_dotenv()
@@ -37,22 +39,26 @@ def rebuild_dataframe(params: HeartDiseaseModel, metadata: Dict[str, np.dtype])
     except ValueError:
         error_msg = "Failed to construct DataFrame from passed data"
         logger.exception(error_msg)
-        raise HTTPException(status_code=400, detail=error_msg)
+        raise_validation_error(error_msg)
     for key, dtype in metadata.items():
         if key not in data.columns:
             error_msg = f"Column {key} not found in data"
             logger.error(error_msg)
-            raise HTTPException(status_code=400, detail=error_msg)
+            raise_validation_error(error_msg)
         if data[key].dtype != dtype:
             try:
                 data[key] = data[key].astype(dtype)
             except ValueError:
                 error_msg = f"Failed to cast column {key} to dtype {dtype}"
                 logger.exception(error_msg)
-                raise HTTPException(status_code=400, detail=error_msg)
+                raise_validation_error(error_msg)
     return data[list(metadata.keys())]
 
 
+def raise_validation_error(error_msg):
+    raise HTTPException(status_code=VALIDATION_ERROR_STATUS_CODE, detail=error_msg)
+
+
 @app.post("/predict", response_model=List[HeartDiseaseResponseModel])
 def predict(request: Request, params: HeartDiseaseModel):
     data = rebuild_dataframe(params, app.state.metadata)

From c3b57be16a17d6cf2354050d3780c294086fa2e4 Mon Sep 17 00:00:00 2001
From: Evgenii Polikutin <polikutinevgeny@gmail.com>
Date: Tue, 25 May 2021 21:18:36 +1000
Subject: [PATCH 14/14] Add startup logging

---
 online_inference/api/api.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/online_inference/api/api.py b/online_inference/api/api.py
index 4ef6367..2e3e19d 100644
--- a/online_inference/api/api.py
+++ b/online_inference/api/api.py
@@ -28,9 +28,11 @@ def deserialize_object(path: Path) -> Any:
 
 @app.on_event("startup")
 def load_artifacts():
+    logger.info("Loading artifacts...")
     app.state.metadata = deserialize_object(settings.metadata_path)
     app.state.pipeline = deserialize_object(settings.pipeline_path)
     app.state.model = deserialize_object(settings.model_path)
+    logger.info("Artifacts loaded")
 
 
 def rebuild_dataframe(params: HeartDiseaseModel, metadata: Dict[str, np.dtype]) -> pd.DataFrame: