Live shopping data for fraud detection

fraud_live_data.csv

TransactionAmount	TransactionTime	MerchantInfo	LocationInfo	UserInfo	DeviceInfo
68.2	01/03/2023 14:30	LocalShop3	CityA	JohnDoe123	Mobile
95.4	02/03/2023 9:45	LocalShop2	CityB	AliceSmith456	Desktop
110.8	03/03/2023 16:15	OnlineStore1	CityC	BobJohnson789	Tablet
45.6	04/03/2023 12:00	OnlineStore1	CityA	EveWilliams123	Mobile
75.3	05/03/2023 10:30	OnlineStore2	CityB	CharlieBrown456	Desktop

fraud_training_data.csv

TransactionAmount	TransactionTime	MerchantInfo	LocationInfo	UserInfo	DeviceInfo	Label
110	04/01/2023 08:45	LocalShop2	CityC	User123	Mobile	0
85.7	06/01/2023 08:15	LocalShop2	CityB	User456	Desktop	1
80.4	08/01/2023 08:30	LocalShop2	CityA	User789	Tablet	0
65.2	10/01/2023 10:15	LocalShop2	CityC	User123	Mobile	0
55.9	12/01/2023 09:15	LocalShop2	CityB	User456	Desktop	1
90.8	14/01/2023 08:45	LocalShop2	CityA	User789	Tablet	0
115.4	16/01/2023 10:15	LocalShop2	CityC	User123	Mobile	0
102.3	18/01/2023 14:30	LocalShop2	CityB	User456	Desktop	1
110.2	19/01/2023 15:00	LocalShop2	CityA	User123	Mobile	0
120.1	21/01/2023 14:15	LocalShop2	CityB	User456	Desktop	1
82.1	23/01/2023 15:30	LocalShop2	CityC	User789	Tablet	0
75.2	25/01/2023 14:45	LocalShop2	CityA	User123	Mobile	0
68.4	27/01/2023 13:45	LocalShop2	CityB	User456	Desktop	1
120.8	29/01/2023 15:45	LocalShop2	CityC	User789	Tablet	0
53.9	31/01/2023 14:00	LocalShop2	CityA	User123	Mobile	0
98.6	02/02/2023 13:45	LocalShop2	CityB	User456	Desktop	1
87.2	04/02/2023 15:45	LocalShop2	CityC	User789	Tablet	0
89.6	06/02/2023 14:00	LocalShop2	CityA	User123	Mobile	0
54.2	08/02/2023 13:45	LocalShop2	CityB	User456	Desktop	1
50.2	01/01/2023 12:45	LocalShop2	CityB	User456	Desktop	1
120.3	02/01/2023 14:00	LocalShop2	CityA	User123	Mobile	0
65.8	03/01/2023 10:30	LocalShop3	CityB	User456	Desktop	1
120.1	05/01/2023 09:00	LocalShop3	CityA	User789	Tablet	0
70.9	07/01/2023 10:00	LocalShop3	CityC	User123	Mobile	0
100.3	09/01/2023 09:45	LocalShop3	CityB	User456	Desktop	1
75.3	11/01/2023 08:00	LocalShop3	CityA	User789	Tablet	0
110.2	13/01/2023 10:30	LocalShop3	CityC	User123	Mobile	0
105.3	15/01/2023 09:00	LocalShop3	CityB	User456	Desktop	1
95.9	17/01/2023 08:30	LocalShop3	CityA	User789	Tablet	0
45.7	20/01/2023 12:45	LocalShop3	CityC	User789	Tablet	0
55.3	22/01/2023 13:00	LocalShop3	CityA	User123	Mobile	0
60.5	24/01/2023 12:15	LocalShop3	CityB	User456	Desktop	1
50.9	26/01/2023 15:15	LocalShop3	CityC	User789	Tablet	0
105.1	28/01/2023 14:15	LocalShop3	CityA	User123	Mobile	0
63.2	30/01/2023 12:30	LocalShop3	CityB	User456	Desktop	1
117.4	01/02/2023 15:15	LocalShop3	CityC	User789	Tablet	0
114.9	03/02/2023 14:15	LocalShop3	CityA	User123	Mobile	0
103.2	05/02/2023 12:30	LocalShop3	CityB	User456	Desktop	1
121.3	07/02/2023 15:15	LocalShop3	CityC	User789	Tablet	0
73.9	09/02/2023 14:15	LocalShop3	CityA	User123	Mobile	0

predict_online_shopping_fraud_random_forest.py

import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline

print("-- loading training data --")
# Load your training dataset (replace 'training_data.csv' with your actual training dataset)
training_data = pd.read_csv('fraud_training_data.csv')

# Remove all non-empty rows
training_data = training_data.dropna()

# convert column TransactionTime to datetime format
training_data['TransactionTime'] = pd.to_datetime(training_data['TransactionTime'], format="%m/%d/%Y %H:%M", errors='coerce')

 
# Assume your training dataset has the specified feature columns and a label column
features = ['TransactionAmount', 'MerchantInfo', 'LocationInfo', 'UserInfo', 'DeviceInfo']
label = 'Label'

# Split data into features and label
X = training_data[features]
y = training_data[label]

# Define columns to be one-hot encoded
categorical_features = ['MerchantInfo', 'LocationInfo', 'UserInfo', 'DeviceInfo']

# Create a column transformer
preprocessor = ColumnTransformer(
    transformers=[
        ('cat', OneHotEncoder(handle_unknown='ignore'), categorical_features)
    ],
    remainder='passthrough'
)

# Create a pipeline with preprocessing and model
model = RandomForestClassifier()
pipeline = Pipeline([
    ('preprocessor', preprocessor),
    ('model', model)
])

# Train the model
pipeline.fit(X, y)

print("-- model trained --")

# Load your live data (replace 'live_data.csv' with the actual live data file)
print("-- loading live data --")
live_data = pd.read_csv('fraud_live_data.csv')

# Remove all non-empty rows
live_data = live_data.dropna()

# Convert 'TransactionTime' in live data to datetime format
training_data['TransactionTime'] = pd.to_datetime(training_data['TransactionTime'], format="%d/%m/%Y %I:%M:%S %p")

# Use only the specified features for live data
X_live = live_data[features]

# Make predictions on the live data
predictions = pipeline.predict(X_live)

# Add predictions to the live data
live_data['Prediction'] = ['Fraud' if pred == 1 else 'Not Fraud' for pred in predictions]

# Output the results
print("-- predictions made --")
print(live_data[['TransactionAmount', 'TransactionTime', 'MerchantInfo', 'LocationInfo', 'UserInfo', 'DeviceInfo', 'Prediction']])