train.py

import pandas as pd
import joblib
from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split

# Load data
df = pd.read_csv("data/transactions.csv")

# Feature engineering
df["hour"] = pd.to_datetime(df["time"], format="%H:%M").dt.hour
df.drop(columns=["check_id", "time"], inplace=True)

# Encode categorical variables
categorical_cols = ["employee_id", "terminal_id"]
encoders = {}

for col in categorical_cols:
    enc = LabelEncoder()
    df[col] = enc.fit_transform(df[col])
    encoders[col] = enc

# Features and target
X = df.drop(columns=["suspicious"])
y = df["suspicious"]

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

# Train model
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

# Save model and encoders
joblib.dump(model, "model/model.pkl")
joblib.dump(encoders, "model/encoders.pkl")

print("Training complete. Model saved.")