pcsekhar commited on
Commit
9e03a51
·
verified ·
1 Parent(s): 9c163c6

Deploy house price predictor

Browse files
.gitignore ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ __pycache__/
2
+ .pytest_cache/
3
+ .venv/
4
+ venv/
5
+ models/*.joblib
6
+ data/raw/
7
+ *.pyc
.hfignore ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ .git/
2
+ .pytest_cache/
3
+ __pycache__/
4
+ */__pycache__/
5
+ data/raw/
6
+ tests/
7
+ *.pyc
.pytest_cache/.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ # Created by pytest automatically.
2
+ *
.pytest_cache/CACHEDIR.TAG ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ Signature: 8a477f597d28d172789f06886806bc55
2
+ # This file is a cache directory tag created by pytest.
3
+ # For information about cache directory tags, see:
4
+ # https://bford.info/cachedir/spec.html
.pytest_cache/README.md ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ # pytest cache directory #
2
+
3
+ This directory contains data from the pytest's cache plugin,
4
+ which provides the `--lf` and `--ff` options, as well as the `cache` fixture.
5
+
6
+ **Do not** commit this to version control.
7
+
8
+ See [the docs](https://docs.pytest.org/en/stable/how-to/cache.html) for more information.
.pytest_cache/v/cache/lastfailed ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
.pytest_cache/v/cache/nodeids ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ [
2
+ "tests/test_api.py::test_predict_endpoint_returns_price",
3
+ "tests/test_pipeline.py::test_house_price_model_predicts_positive_value",
4
+ "tests/test_pipeline.py::test_train_model_persists_artifacts_and_reports_metrics"
5
+ ]
README.md CHANGED
@@ -1,12 +1,64 @@
1
  ---
2
- title: MLModels
3
- emoji: 💻
4
  colorFrom: blue
5
- colorTo: yellow
6
  sdk: gradio
7
- sdk_version: 6.13.0
8
  app_file: app.py
9
  pinned: false
10
  ---
11
 
12
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ title: House Price Prediction
3
+ emoji: 🏠
4
  colorFrom: blue
5
+ colorTo: green
6
  sdk: gradio
7
+ sdk_version: 5.0.0
8
  app_file: app.py
9
  pinned: false
10
  ---
11
 
12
+ # House Price Prediction
13
+
14
+ End-to-end machine learning app for predicting house sale prices with the Kaggle
15
+ `house-prices-advanced-regression-techniques` dataset.
16
+
17
+ ## Train
18
+
19
+ Set up Kaggle credentials, then download the dataset:
20
+
21
+ ```bash
22
+ python scripts/download_kaggle_data.py
23
+ ```
24
+
25
+ Train the model:
26
+
27
+ ```bash
28
+ python -m src.train
29
+ ```
30
+
31
+ If `data/raw/train.csv` is not present, training falls back to the included sample
32
+ dataset so the app remains runnable.
33
+
34
+ ## FastAPI
35
+
36
+ ```bash
37
+ uvicorn src.api:app --reload
38
+ ```
39
+
40
+ Prediction endpoint:
41
+
42
+ ```http
43
+ POST /predict
44
+ ```
45
+
46
+ ## Gradio
47
+
48
+ ```bash
49
+ python app.py
50
+ ```
51
+
52
+ ## Hugging Face Spaces
53
+
54
+ This repository is configured for a Gradio Space. The target Space is:
55
+
56
+ ```text
57
+ pcsekhar/MLModels
58
+ ```
59
+
60
+ Deploy with:
61
+
62
+ ```bash
63
+ hf upload --repo-type space --exclude "data/raw/*" --exclude ".git/*" --commit-message "Deploy house price predictor" pcsekhar/MLModels .
64
+ ```
app.py ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from __future__ import annotations
2
+
3
+ from pathlib import Path
4
+
5
+ import gradio as gr
6
+
7
+ from src.data import load_training_data
8
+ from src.modeling import DEFAULT_MODEL_PATH, HousePriceModel, train_model
9
+
10
+
11
+ MODEL_PATH = Path(DEFAULT_MODEL_PATH)
12
+
13
+
14
+ def ensure_model() -> HousePriceModel:
15
+ if not MODEL_PATH.exists():
16
+ train_model(load_training_data(), artifact_path=MODEL_PATH)
17
+ return HousePriceModel.load(MODEL_PATH)
18
+
19
+
20
+ MODEL = ensure_model()
21
+
22
+
23
+ def predict_price(
24
+ overall_qual: int,
25
+ gr_liv_area: int,
26
+ garage_cars: int,
27
+ total_bsmt_sf: int,
28
+ full_bath: int,
29
+ year_built: int,
30
+ neighborhood: str,
31
+ house_style: str,
32
+ ) -> str:
33
+ prediction = MODEL.predict(
34
+ {
35
+ "OverallQual": overall_qual,
36
+ "GrLivArea": gr_liv_area,
37
+ "GarageCars": garage_cars,
38
+ "TotalBsmtSF": total_bsmt_sf,
39
+ "FullBath": full_bath,
40
+ "YearBuilt": year_built,
41
+ "Neighborhood": neighborhood,
42
+ "HouseStyle": house_style,
43
+ }
44
+ )
45
+ return f"${prediction:,.0f}"
46
+
47
+
48
+ with gr.Blocks(title="House Price Predictor") as demo:
49
+ gr.Markdown("# House Price Predictor")
50
+ gr.Markdown("Predict sale prices using a model trained on the Kaggle House Prices dataset.")
51
+
52
+ with gr.Row():
53
+ with gr.Column():
54
+ overall_qual = gr.Slider(1, 10, value=7, step=1, label="Overall quality")
55
+ gr_liv_area = gr.Number(value=1800, label="Above-ground living area")
56
+ garage_cars = gr.Slider(0, 5, value=2, step=1, label="Garage capacity")
57
+ total_bsmt_sf = gr.Number(value=1000, label="Total basement square feet")
58
+ with gr.Column():
59
+ full_bath = gr.Slider(0, 5, value=2, step=1, label="Full bathrooms")
60
+ year_built = gr.Number(value=1995, label="Year built")
61
+ neighborhood = gr.Dropdown(
62
+ ["NAmes", "CollgCr", "OldTown", "Edwards", "Somerst", "NridgHt", "Gilbert", "NoRidge"],
63
+ value="Somerst",
64
+ label="Neighborhood",
65
+ allow_custom_value=True,
66
+ )
67
+ house_style = gr.Dropdown(
68
+ ["1Story", "2Story", "1.5Fin", "SLvl", "SFoyer"],
69
+ value="2Story",
70
+ label="House style",
71
+ allow_custom_value=True,
72
+ )
73
+
74
+ output = gr.Textbox(label="Predicted sale price", interactive=False)
75
+ predict_button = gr.Button("Predict", variant="primary")
76
+ predict_button.click(
77
+ fn=predict_price,
78
+ inputs=[
79
+ overall_qual,
80
+ gr_liv_area,
81
+ garage_cars,
82
+ total_bsmt_sf,
83
+ full_bath,
84
+ year_built,
85
+ neighborhood,
86
+ house_style,
87
+ ],
88
+ outputs=output,
89
+ api_name="predict",
90
+ )
91
+
92
+ gr.Markdown(
93
+ f"Model metrics: RMSE `{MODEL.metrics.get('rmse')}`, "
94
+ f"MAE `{MODEL.metrics.get('mae')}`, R2 `{MODEL.metrics.get('r2')}`"
95
+ )
96
+
97
+
98
+ if __name__ == "__main__":
99
+ demo.launch()
100
+
data/sample_house_prices.csv ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ OverallQual,GrLivArea,GarageCars,TotalBsmtSF,FullBath,YearBuilt,Neighborhood,HouseStyle,SalePrice
2
+ 5,1200,1,800,1,1960,NAmes,1Story,135000
3
+ 6,1500,2,900,2,1975,CollgCr,1Story,165000
4
+ 7,1800,2,1100,2,1990,Somerst,2Story,210000
5
+ 8,2100,3,1300,2,2001,NridgHt,2Story,260000
6
+ 9,2400,3,1500,3,2010,NoRidge,2Story,320000
7
+ 4,900,1,600,1,1950,OldTown,1Story,110000
8
+ 6,1600,2,950,2,1982,NAmes,1Story,175000
9
+ 7,2000,2,1250,2,1998,Gilbert,2Story,235000
10
+ 8,2200,3,1350,2,2005,Somerst,2Story,275000
11
+ 5,1300,1,850,1,1965,Edwards,1Story,140000
12
+ 7,1750,2,1050,2,1993,CollgCr,2Story,205000
13
+ 9,2600,3,1600,3,2012,NridgHt,2Story,345000
requirements.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ pandas
2
+ scikit-learn
3
+ joblib
4
+ fastapi
5
+ uvicorn
6
+ gradio
7
+ pydantic
8
+ kaggle
9
+ pytest
10
+ httpx
scripts/download_kaggle_data.py ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from __future__ import annotations
2
+
3
+ import argparse
4
+ import subprocess
5
+ from pathlib import Path
6
+
7
+
8
+ COMPETITION = "house-prices-advanced-regression-techniques"
9
+
10
+
11
+ def main() -> None:
12
+ parser = argparse.ArgumentParser(description="Download Kaggle House Prices data.")
13
+ parser.add_argument("--output", type=Path, default=Path("data/raw"))
14
+ args = parser.parse_args()
15
+ args.output.mkdir(parents=True, exist_ok=True)
16
+ subprocess.run(
17
+ [
18
+ "kaggle",
19
+ "competitions",
20
+ "download",
21
+ "-c",
22
+ COMPETITION,
23
+ "-p",
24
+ str(args.output),
25
+ "--unzip",
26
+ ],
27
+ check=True,
28
+ )
29
+
30
+
31
+ if __name__ == "__main__":
32
+ main()
33
+
src/__init__.py ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ """House price prediction package."""
2
+
src/api.py ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from __future__ import annotations
2
+
3
+ from pathlib import Path
4
+
5
+ from fastapi import FastAPI
6
+
7
+ from src.data import load_training_data
8
+ from src.modeling import DEFAULT_MODEL_PATH, HousePriceModel
9
+ from src.modeling import train_model
10
+ from src.schemas import HouseFeatures, PredictionResponse
11
+
12
+
13
+ def create_app(model_path: str | Path = DEFAULT_MODEL_PATH) -> FastAPI:
14
+ app = FastAPI(title="House Price Prediction API", version="1.0.0")
15
+ model_path = Path(model_path)
16
+ if not model_path.exists():
17
+ train_model(load_training_data(), artifact_path=model_path)
18
+ model = HousePriceModel.load(model_path)
19
+
20
+ @app.get("/health")
21
+ def health() -> dict[str, str]:
22
+ return {"status": "ok"}
23
+
24
+ @app.get("/metrics")
25
+ def metrics() -> dict[str, float]:
26
+ return model.metrics
27
+
28
+ @app.post("/predict", response_model=PredictionResponse)
29
+ def predict(features: HouseFeatures) -> PredictionResponse:
30
+ return PredictionResponse(predicted_price=model.predict(features.model_dump()))
31
+
32
+ return app
33
+
34
+
35
+ app = create_app()
src/data.py ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from __future__ import annotations
2
+
3
+ from pathlib import Path
4
+
5
+ import pandas as pd
6
+
7
+
8
+ PROJECT_ROOT = Path(__file__).resolve().parents[1]
9
+ DATA_DIR = PROJECT_ROOT / "data"
10
+ RAW_TRAIN_PATH = DATA_DIR / "raw" / "train.csv"
11
+ SAMPLE_TRAIN_PATH = DATA_DIR / "sample_house_prices.csv"
12
+
13
+
14
+ DEFAULT_FEATURES = [
15
+ "OverallQual",
16
+ "GrLivArea",
17
+ "GarageCars",
18
+ "TotalBsmtSF",
19
+ "FullBath",
20
+ "YearBuilt",
21
+ "Neighborhood",
22
+ "HouseStyle",
23
+ ]
24
+ TARGET_COLUMN = "SalePrice"
25
+
26
+
27
+ def load_training_data(path: str | Path | None = None) -> pd.DataFrame:
28
+ """Load Kaggle training data, falling back to the included sample dataset."""
29
+ if path is not None:
30
+ return pd.read_csv(path)
31
+
32
+ if RAW_TRAIN_PATH.exists():
33
+ return pd.read_csv(RAW_TRAIN_PATH)
34
+
35
+ return pd.read_csv(SAMPLE_TRAIN_PATH)
36
+
37
+
38
+ def select_model_frame(frame: pd.DataFrame) -> pd.DataFrame:
39
+ required = [*DEFAULT_FEATURES, TARGET_COLUMN]
40
+ missing = [column for column in required if column not in frame.columns]
41
+ if missing:
42
+ raise ValueError(f"Training data is missing required columns: {', '.join(missing)}")
43
+ return frame[required].copy()
44
+
src/modeling.py ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from __future__ import annotations
2
+
3
+ from dataclasses import dataclass
4
+ from math import sqrt
5
+ from pathlib import Path
6
+ from typing import Any
7
+
8
+ import joblib
9
+ import pandas as pd
10
+ from sklearn.compose import ColumnTransformer
11
+ from sklearn.ensemble import RandomForestRegressor
12
+ from sklearn.impute import SimpleImputer
13
+ from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
14
+ from sklearn.model_selection import train_test_split
15
+ from sklearn.pipeline import Pipeline
16
+ from sklearn.preprocessing import OneHotEncoder
17
+
18
+ from src.data import DEFAULT_FEATURES, TARGET_COLUMN, select_model_frame
19
+
20
+
21
+ NUMERIC_FEATURES = [
22
+ "OverallQual",
23
+ "GrLivArea",
24
+ "GarageCars",
25
+ "TotalBsmtSF",
26
+ "FullBath",
27
+ "YearBuilt",
28
+ ]
29
+ CATEGORICAL_FEATURES = ["Neighborhood", "HouseStyle"]
30
+ DEFAULT_MODEL_PATH = Path("models") / "house_price_model.joblib"
31
+
32
+
33
+ @dataclass(frozen=True)
34
+ class TrainedModel:
35
+ pipeline: Pipeline
36
+ feature_names: list[str]
37
+ metrics: dict[str, float]
38
+
39
+
40
+ class HousePriceModel:
41
+ def __init__(self, trained: TrainedModel):
42
+ self._trained = trained
43
+
44
+ @property
45
+ def metrics(self) -> dict[str, float]:
46
+ return self._trained.metrics
47
+
48
+ @property
49
+ def feature_names(self) -> list[str]:
50
+ return self._trained.feature_names
51
+
52
+ @classmethod
53
+ def load(cls, path: str | Path = DEFAULT_MODEL_PATH) -> "HousePriceModel":
54
+ payload = joblib.load(path)
55
+ return cls(
56
+ TrainedModel(
57
+ pipeline=payload["pipeline"],
58
+ feature_names=list(payload["feature_names"]),
59
+ metrics=dict(payload["metrics"]),
60
+ )
61
+ )
62
+
63
+ def predict(self, features: dict[str, Any]) -> float:
64
+ frame = pd.DataFrame([{name: features.get(name) for name in self.feature_names}])
65
+ prediction = self._trained.pipeline.predict(frame)[0]
66
+ return round(float(max(prediction, 0.0)), 2)
67
+
68
+
69
+ def build_pipeline() -> Pipeline:
70
+ numeric_pipeline = Pipeline(
71
+ steps=[
72
+ ("imputer", SimpleImputer(strategy="median")),
73
+ ]
74
+ )
75
+ categorical_pipeline = Pipeline(
76
+ steps=[
77
+ ("imputer", SimpleImputer(strategy="most_frequent")),
78
+ ("encoder", OneHotEncoder(handle_unknown="ignore", sparse_output=False)),
79
+ ]
80
+ )
81
+ preprocessor = ColumnTransformer(
82
+ transformers=[
83
+ ("num", numeric_pipeline, NUMERIC_FEATURES),
84
+ ("cat", categorical_pipeline, CATEGORICAL_FEATURES),
85
+ ]
86
+ )
87
+ regressor = RandomForestRegressor(n_estimators=250, random_state=42, min_samples_leaf=2)
88
+ return Pipeline(steps=[("preprocessor", preprocessor), ("regressor", regressor)])
89
+
90
+
91
+ def train_model(frame: pd.DataFrame, artifact_path: str | Path = DEFAULT_MODEL_PATH) -> TrainedModel:
92
+ model_frame = select_model_frame(frame).dropna(subset=[TARGET_COLUMN])
93
+ features = model_frame[DEFAULT_FEATURES]
94
+ target = model_frame[TARGET_COLUMN]
95
+
96
+ if len(model_frame) >= 10:
97
+ x_train, x_test, y_train, y_test = train_test_split(
98
+ features, target, test_size=0.2, random_state=42
99
+ )
100
+ else:
101
+ x_train, x_test, y_train, y_test = features, features, target, target
102
+
103
+ pipeline = build_pipeline()
104
+ pipeline.fit(x_train, y_train)
105
+ predictions = pipeline.predict(x_test)
106
+ metrics = {
107
+ "rmse": round(sqrt(mean_squared_error(y_test, predictions)), 2),
108
+ "mae": round(mean_absolute_error(y_test, predictions), 2),
109
+ "r2": round(r2_score(y_test, predictions), 4),
110
+ }
111
+ trained = TrainedModel(pipeline=pipeline, feature_names=list(DEFAULT_FEATURES), metrics=metrics)
112
+
113
+ artifact_path = Path(artifact_path)
114
+ artifact_path.parent.mkdir(parents=True, exist_ok=True)
115
+ joblib.dump(
116
+ {
117
+ "pipeline": trained.pipeline,
118
+ "feature_names": trained.feature_names,
119
+ "metrics": trained.metrics,
120
+ },
121
+ artifact_path,
122
+ )
123
+ return trained
src/schemas.py ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from __future__ import annotations
2
+
3
+ from pydantic import BaseModel, Field
4
+
5
+
6
+ class HouseFeatures(BaseModel):
7
+ OverallQual: int = Field(7, ge=1, le=10)
8
+ GrLivArea: int = Field(1800, ge=200)
9
+ GarageCars: int = Field(2, ge=0, le=5)
10
+ TotalBsmtSF: int = Field(1000, ge=0)
11
+ FullBath: int = Field(2, ge=0, le=5)
12
+ YearBuilt: int = Field(1995, ge=1800, le=2026)
13
+ Neighborhood: str = "Somerst"
14
+ HouseStyle: str = "2Story"
15
+
16
+
17
+ class PredictionResponse(BaseModel):
18
+ predicted_price: float
19
+ currency: str = "USD"
20
+
src/train.py ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from __future__ import annotations
2
+
3
+ import argparse
4
+ from pathlib import Path
5
+
6
+ from src.data import load_training_data
7
+ from src.modeling import DEFAULT_MODEL_PATH, train_model
8
+
9
+
10
+ def main() -> None:
11
+ parser = argparse.ArgumentParser(description="Train the house price prediction model.")
12
+ parser.add_argument("--data", type=Path, default=None, help="Path to Kaggle train.csv")
13
+ parser.add_argument("--output", type=Path, default=DEFAULT_MODEL_PATH, help="Model artifact path")
14
+ args = parser.parse_args()
15
+
16
+ frame = load_training_data(args.data)
17
+ trained = train_model(frame, artifact_path=args.output)
18
+ print(f"Saved model to {args.output}")
19
+ print(f"Metrics: {trained.metrics}")
20
+
21
+
22
+ if __name__ == "__main__":
23
+ main()
24
+
tests/__init__.py ADDED
@@ -0,0 +1 @@
 
 
1
+
tests/test_api.py ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from pathlib import Path
2
+
3
+ from fastapi.testclient import TestClient
4
+
5
+ from src.api import create_app
6
+ from src.modeling import train_model
7
+ from tests.test_pipeline import sample_training_frame
8
+
9
+
10
+ def test_predict_endpoint_returns_price(tmp_path: Path) -> None:
11
+ artifact_path = tmp_path / "house_price_model.joblib"
12
+ train_model(sample_training_frame(), artifact_path=artifact_path)
13
+ client = TestClient(create_app(model_path=artifact_path))
14
+
15
+ response = client.post(
16
+ "/predict",
17
+ json={
18
+ "OverallQual": 7,
19
+ "GrLivArea": 1850,
20
+ "GarageCars": 2,
21
+ "TotalBsmtSF": 1050,
22
+ "FullBath": 2,
23
+ "YearBuilt": 1995,
24
+ "Neighborhood": "Somerst",
25
+ "HouseStyle": "2Story",
26
+ },
27
+ )
28
+
29
+ assert response.status_code == 200
30
+ body = response.json()
31
+ assert body["predicted_price"] > 0
32
+ assert body["currency"] == "USD"
tests/test_pipeline.py ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from pathlib import Path
2
+
3
+ import pandas as pd
4
+
5
+ from src.modeling import HousePriceModel, train_model
6
+
7
+
8
+ def sample_training_frame() -> pd.DataFrame:
9
+ return pd.DataFrame(
10
+ {
11
+ "OverallQual": [5, 6, 7, 8, 9, 4, 6, 7],
12
+ "GrLivArea": [1200, 1500, 1800, 2100, 2400, 900, 1600, 2000],
13
+ "GarageCars": [1, 2, 2, 3, 3, 1, 2, 2],
14
+ "TotalBsmtSF": [800, 900, 1100, 1300, 1500, 600, 950, 1250],
15
+ "FullBath": [1, 2, 2, 2, 3, 1, 2, 2],
16
+ "YearBuilt": [1960, 1975, 1990, 2001, 2010, 1950, 1982, 1998],
17
+ "Neighborhood": ["NAmes", "CollgCr", "Somerst", "NridgHt", "NoRidge", "OldTown", "NAmes", "Gilbert"],
18
+ "HouseStyle": ["1Story", "1Story", "2Story", "2Story", "2Story", "1Story", "1Story", "2Story"],
19
+ "SalePrice": [135000, 165000, 210000, 260000, 320000, 110000, 175000, 235000],
20
+ }
21
+ )
22
+
23
+
24
+ def test_train_model_persists_artifacts_and_reports_metrics(tmp_path: Path) -> None:
25
+ artifact_path = tmp_path / "house_price_model.joblib"
26
+
27
+ trained = train_model(sample_training_frame(), artifact_path=artifact_path)
28
+
29
+ assert artifact_path.exists()
30
+ assert trained.metrics["rmse"] >= 0
31
+ assert trained.metrics["r2"] <= 1
32
+ assert "OverallQual" in trained.feature_names
33
+ assert "SalePrice" not in trained.feature_names
34
+
35
+
36
+ def test_house_price_model_predicts_positive_value(tmp_path: Path) -> None:
37
+ artifact_path = tmp_path / "house_price_model.joblib"
38
+ trained = train_model(sample_training_frame(), artifact_path=artifact_path)
39
+ model = HousePriceModel.load(artifact_path)
40
+
41
+ prediction = model.predict(
42
+ {
43
+ "OverallQual": 7,
44
+ "GrLivArea": 1850,
45
+ "GarageCars": 2,
46
+ "TotalBsmtSF": 1050,
47
+ "FullBath": 2,
48
+ "YearBuilt": 1995,
49
+ "Neighborhood": "Somerst",
50
+ "HouseStyle": "2Story",
51
+ }
52
+ )
53
+
54
+ assert prediction > 0
55
+ assert model.metrics == trained.metrics