Spaces:
Sleeping
Sleeping
File size: 1,548 Bytes
d7f4720 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 | import json
from joblib import dump
from sklearn.datasets import load_breast_cancer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import MinMaxScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.metrics import recall_score
from src.utils import MODEL_PATH, META_PATH
def load_data():
data = load_breast_cancer()
return data.data, data.target, list(data.feature_names), list(data.target_names)
def train(smoke=False):
X, y, feature_names, target_names = load_data()
Xtr, Xte, ytr, yte = train_test_split(
X, y, test_size=0.2, random_state=42, stratify=y
)
pipe = Pipeline([
("scaler", MinMaxScaler()),
("rf", RandomForestClassifier(random_state=42))
])
if smoke:
params = {"rf__n_estimators": [50]}
cv = 2
else:
params = {"rf__n_estimators": [100, 200], "rf__max_depth": [None, 8, 12]}
cv = 5
grid = GridSearchCV(pipe, params, scoring="recall", cv=cv, n_jobs=-1)
grid.fit(Xtr, ytr)
best = grid.best_estimator_
yhat = best.predict(Xte)
rec = recall_score(yte, yhat)
dump(best, MODEL_PATH)
META_PATH.write_text(json.dumps({
"best_params": grid.best_params_,
"cv": cv,
"recall_test": rec,
"feature_names": feature_names,
"target_names": target_names
}, indent=2))
return rec
if __name__ == "__main__":
r = train(smoke=False)
print(f"Recall (test): {r:.4f}")
|