File size: 1,299 Bytes
1cde89b |
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 |
import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import r2_score
import joblib
# Generate synthetic training data for Hemoglobin model
np.random.seed(42)
size = 200
data = {
"mean_intensity": np.random.uniform(0.2, 0.5, size),
"bbox_width": np.random.uniform(0.05, 0.2, size),
"bbox_height": np.random.uniform(0.05, 0.2, size),
"eye_dist": np.random.uniform(0.2, 0.5, size),
"nose_len": np.random.uniform(0.2, 0.5, size),
"jaw_width": np.random.uniform(0.2, 0.5, size),
"avg_skin_tone": np.random.uniform(0.2, 0.5, size),
"hemoglobin": np.random.uniform(10.5, 17.5, size) # realistic Hb range
}
df = pd.DataFrame(data)
# Save dataset
df.to_csv("hemoglobin_dataset.csv", index=False)
# Train-test split
X = df.drop(columns=["hemoglobin"])
y = df["hemoglobin"]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Train model
model = RandomForestRegressor(n_estimators=100, random_state=42)
model.fit(X_train, y_train)
# Evaluate
y_pred = model.predict(X_test)
print("R2 Score:", r2_score(y_test, y_pred))
# Save model
joblib.dump(model, "hemoglobin_model.pkl")
print("Model saved as hemoglobin_model.pkl")
|