Download src/modeling.py from pcsekhar/MLModels: direct link, hf CLI and curl.
- Browser
- Download file 3.93 kB
-
https://huggingface.co/spaces/pcsekhar/MLModels/resolve/main/src/modeling.py
- Command line
-
hf download hf://spaces/pcsekhar/MLModels/src/modeling.py
-
curl -L -o modeling.py https://huggingface.co/spaces/pcsekhar/MLModels/resolve/main/src/modeling.py
3.93 kB
| from __future__ import annotations | |
| from dataclasses import dataclass | |
| from math import sqrt | |
| from pathlib import Path | |
| from typing import Any | |
| import joblib | |
| import pandas as pd | |
| from sklearn.compose import ColumnTransformer | |
| from sklearn.ensemble import RandomForestRegressor | |
| from sklearn.impute import SimpleImputer | |
| from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score | |
| from sklearn.model_selection import train_test_split | |
| from sklearn.pipeline import Pipeline | |
| from sklearn.preprocessing import OneHotEncoder | |
| from src.data import DEFAULT_FEATURES, TARGET_COLUMN, select_model_frame | |
| NUMERIC_FEATURES = [ | |
| "OverallQual", | |
| "GrLivArea", | |
| "GarageCars", | |
| "TotalBsmtSF", | |
| "FullBath", | |
| "YearBuilt", | |
| ] | |
| CATEGORICAL_FEATURES = ["Neighborhood", "HouseStyle"] | |
| DEFAULT_MODEL_PATH = Path("models") / "house_price_model.joblib" | |
| class TrainedModel: | |
| pipeline: Pipeline | |
| feature_names: list[str] | |
| metrics: dict[str, float] | |
| class HousePriceModel: | |
| def __init__(self, trained: TrainedModel): | |
| self._trained = trained | |
| def metrics(self) -> dict[str, float]: | |
| return self._trained.metrics | |
| def feature_names(self) -> list[str]: | |
| return self._trained.feature_names | |
| def load(cls, path: str | Path = DEFAULT_MODEL_PATH) -> "HousePriceModel": | |
| payload = joblib.load(path) | |
| return cls( | |
| TrainedModel( | |
| pipeline=payload["pipeline"], | |
| feature_names=list(payload["feature_names"]), | |
| metrics=dict(payload["metrics"]), | |
| ) | |
| ) | |
| def predict(self, features: dict[str, Any]) -> float: | |
| frame = pd.DataFrame([{name: features.get(name) for name in self.feature_names}]) | |
| prediction = self._trained.pipeline.predict(frame)[0] | |
| return round(float(max(prediction, 0.0)), 2) | |
| def build_pipeline() -> Pipeline: | |
| numeric_pipeline = Pipeline( | |
| steps=[ | |
| ("imputer", SimpleImputer(strategy="median")), | |
| ] | |
| ) | |
| categorical_pipeline = Pipeline( | |
| steps=[ | |
| ("imputer", SimpleImputer(strategy="most_frequent")), | |
| ("encoder", OneHotEncoder(handle_unknown="ignore", sparse_output=False)), | |
| ] | |
| ) | |
| preprocessor = ColumnTransformer( | |
| transformers=[ | |
| ("num", numeric_pipeline, NUMERIC_FEATURES), | |
| ("cat", categorical_pipeline, CATEGORICAL_FEATURES), | |
| ] | |
| ) | |
| regressor = RandomForestRegressor(n_estimators=250, random_state=42, min_samples_leaf=2) | |
| return Pipeline(steps=[("preprocessor", preprocessor), ("regressor", regressor)]) | |
| def train_model(frame: pd.DataFrame, artifact_path: str | Path = DEFAULT_MODEL_PATH) -> TrainedModel: | |
| model_frame = select_model_frame(frame).dropna(subset=[TARGET_COLUMN]) | |
| features = model_frame[DEFAULT_FEATURES] | |
| target = model_frame[TARGET_COLUMN] | |
| if len(model_frame) >= 10: | |
| x_train, x_test, y_train, y_test = train_test_split( | |
| features, target, test_size=0.2, random_state=42 | |
| ) | |
| else: | |
| x_train, x_test, y_train, y_test = features, features, target, target | |
| pipeline = build_pipeline() | |
| pipeline.fit(x_train, y_train) | |
| predictions = pipeline.predict(x_test) | |
| metrics = { | |
| "rmse": round(sqrt(mean_squared_error(y_test, predictions)), 2), | |
| "mae": round(mean_absolute_error(y_test, predictions), 2), | |
| "r2": round(r2_score(y_test, predictions), 4), | |
| } | |
| trained = TrainedModel(pipeline=pipeline, feature_names=list(DEFAULT_FEATURES), metrics=metrics) | |
| artifact_path = Path(artifact_path) | |
| artifact_path.parent.mkdir(parents=True, exist_ok=True) | |
| joblib.dump( | |
| { | |
| "pipeline": trained.pipeline, | |
| "feature_names": trained.feature_names, | |
| "metrics": trained.metrics, | |
| }, | |
| artifact_path, | |
| ) | |
| return trained | |