# train_model.py
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
import joblib

# Load the collected data from CSV
data = pd.read_csv('wifi_signals.csv')

# Features (SignalStrength) and target (Location)
X = data[['SignalStrength']]
y = data['Location']

# Split the data into training and test sets (80% train, 20% test)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Train a Random Forest Classifier
model = RandomForestClassifier()
model.fit(X_train, y_train)

# Evaluate the model
y_pred = model.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print(f'Model Accuracy: {accuracy * 100:.2f}%')

# Save the trained model to a file
joblib.dump(model, 'wifi_model.pkl')