plot_residuals.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestRegressor

# Load dataset
df = pd.read_csv("final_dataset.csv")

X = df[["rtt_avg_ms", "jitter_ms"]]
y = df["throughput_mbps"]

# Train-test split
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=42
)

# Scaling
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Best model
model = RandomForestRegressor(
    n_estimators=150,
    max_depth=6,
    min_samples_leaf=10,
    random_state=42
)
model.fit(X_train, y_train)

# Predictions
y_pred = model.predict(X_test)
residuals = y_test - y_pred

# Plot
plt.figure(figsize=(6,5))
plt.scatter(y_pred, residuals, alpha=0.7)
plt.axhline(0, linestyle="--")
plt.xlabel("Predicted Throughput (Mbps)")
plt.ylabel("Residual Error (Mbps)")
plt.title("Residual Plot")
plt.tight_layout()

# Save
plt.savefig("results/residual_plot.png")
plt.close()

print("✅ Saved: results/residual_plot.png")