train_model.py

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error,r2_score
from sklearn.preprocessing import LabelEncoder
import joblib

# load datasets
X = pd.read_csv("delhi_traffic_features.csv")

categorical_cols = [
    "time_of_day","traffic_density_level"
]

encoder = LabelEncoder()
for col in categorical_cols:
    X[col] = encoder.fit_transform(X[col])

X = X[
    [
        "distance_km","average_speed_kmph","time_of_day","traffic_density_level"
    ]
]    


# Keep only numeric features
X = X.select_dtypes(include=["number"])

y_df = pd.read_csv("delhi_traffic_target.csv")

# convert tar to 1D
y = y_df.select_dtypes(include=["number"]).iloc[:,0]

# split data
X_train, X_test, y_train, y_test= train_test_split(X,y,test_size=0.2,random_state=42)

# model
model = RandomForestRegressor(
    n_estimators=100,
    random_state=42,
    n_jobs=-1
)

# train model
model.fit(X_train,y_train)

# test model
y_pred = model.predict(X_test)

# evaluation
print("MAE:",mean_absolute_error(y_test,y_pred))
print("R2 Score:",r2_score(y_test,y_pred))

# model save
joblib.dump(model,"travel_time_model.pkl")

print("Model trained and saved")