FastAPI Application

The main module contains the FastAPI application with REST API endpoints.

Endpoints

Module Reference

FastAPI backend for 5D neural network interpolation system.

class main.FeatureStats(**data)

Bases: BaseModel

Parameters:

data (Any)

min_avg: float

max_avg: float

target_mean: float

target_std: float

target_min: float

target_max: float

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class main.FeatureRange(**data)

Bases: BaseModel

Parameters:

data (Any)

min: float

max: float

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class main.UploadResponse(**data)

Bases: BaseModel

Parameters:

data (Any)

status: str

message: str

n_samples: Optional[int]

n_features: Optional[int]

missing_values: Optional[int]

duplicate_rows: Optional[int]

memory_usage_mb: Optional[float]

feature_stats: Optional[FeatureStats]

feature_ranges: Optional[List[FeatureRange]]

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class main.TrainRequest(**data)

Bases: BaseModel

Parameters:

data (Any)

hidden_sizes: List[int]

learning_rate: float

max_iter: int

random_state: int

train_size: float

val_size: float

test_size: float

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class main.LossHistoryItem(**data)

Bases: BaseModel

Parameters:

data (Any)

epoch: int

loss: float

val_loss: float

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class main.PredictionSample(**data)

Bases: BaseModel

Parameters:

data (Any)

true: float

pred: float

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class main.TrainResponse(**data)

Bases: BaseModel

Parameters:

data (Any)

status: str

message: str

train_r2: Optional[float]

val_r2: Optional[float]

test_r2: Optional[float]

train_mse: Optional[float]

val_mse: Optional[float]

test_mse: Optional[float]

epochs_used: Optional[int]

training_time_seconds: Optional[float]

loss_history: Optional[List[LossHistoryItem]]

predictions_sample: Optional[List[PredictionSample]]

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class main.PredictRequest(**data)

Bases: BaseModel

Parameters:

data (Any)

features: List[float]

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class main.PredictResponse(**data)

Bases: BaseModel

Parameters:

data (Any)

status: str

prediction: float

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

async main.root()

async main.health_check()

async main.upload_dataset(file=File(PydanticUndefined))

Upload a .pkl dataset file with ‘X’ and ‘y’ keys. X must have 5 features.

Parameters:

file (UploadFile)

async main.train_model(request)

Train a neural network model on the uploaded dataset.

Requires a dataset to be uploaded first via /upload endpoint.

Parameters:

request (TrainRequest)

async main.predict(request)

Make a prediction using the trained model.

Requires a model to be trained first via /train endpoint.

Parameters:

request (PredictRequest)