{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "46bcfe02", "metadata": {}, "outputs": [], "source": [ "#Step1: Load the python packages for data analysis and data visualization\n", "\n", "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns" ] }, { "cell_type": "code", "execution_count": 2, "id": "05cb96f7", "metadata": {}, "outputs": [], "source": [ "#step2: load the dataset from your folder\n", "\n", "\n", "dataset=pd.read_csv('Cybercrime.csv')" ] }, { "cell_type": "code", "execution_count": 3, "id": "58f6a718", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
CardYearMonthDayAmountTransactionMCCIs Fraud?
00200291134.0925300No
1020029138.4825411No
20200292120.3425411No
30200292128.9525651No
40200293104.7125912No
...........................
19958420092129.7125411No
199594200922227.9425211No
199604200922413.9725912No
199614200932914.2725411No
199624200933113.5525812No
\n", "

19963 rows × 8 columns

\n", "
" ], "text/plain": [ " Card Year Month Day Amount Transaction MCC Is Fraud?\n", "0 0 2002 9 1 134.09 2 5300 No\n", "1 0 2002 9 1 38.48 2 5411 No\n", "2 0 2002 9 2 120.34 2 5411 No\n", "3 0 2002 9 2 128.95 2 5651 No\n", "4 0 2002 9 3 104.71 2 5912 No\n", "... ... ... ... ... ... ... ... ...\n", "19958 4 2009 2 12 9.71 2 5411 No\n", "19959 4 2009 2 22 27.94 2 5211 No\n", "19960 4 2009 2 24 13.97 2 5912 No\n", "19961 4 2009 3 29 14.27 2 5411 No\n", "19962 4 2009 3 31 13.55 2 5812 No\n", "\n", "[19963 rows x 8 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset" ] }, { "cell_type": "code", "execution_count": 4, "id": "c1fb4c57", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
CardYearMonthDayAmountTransactionMCC
count19963.00000019963.00000019963.00000019963.00000019963.00000019963.00000019963.000000
mean1.9107352011.0119226.56810115.74387681.2999891.6528085617.940239
std1.2377635.0481463.4774978.80137894.1590930.712738707.982901
min0.0000002002.0000001.0000001.000000-499.0000000.0000001711.000000
25%0.0000002007.0000004.0000008.00000036.6300002.0000005311.000000
50%2.0000002011.0000007.00000016.00000069.4500002.0000005499.000000
75%3.0000002015.00000010.00000023.000000125.6800002.0000005912.000000
max4.0000002020.00000012.00000031.0000001409.4000002.0000009402.000000
\n", "
" ], "text/plain": [ " Card Year Month Day Amount \\\n", "count 19963.000000 19963.000000 19963.000000 19963.000000 19963.000000 \n", "mean 1.910735 2011.011922 6.568101 15.743876 81.299989 \n", "std 1.237763 5.048146 3.477497 8.801378 94.159093 \n", "min 0.000000 2002.000000 1.000000 1.000000 -499.000000 \n", "25% 0.000000 2007.000000 4.000000 8.000000 36.630000 \n", "50% 2.000000 2011.000000 7.000000 16.000000 69.450000 \n", "75% 3.000000 2015.000000 10.000000 23.000000 125.680000 \n", "max 4.000000 2020.000000 12.000000 31.000000 1409.400000 \n", "\n", " Transaction MCC \n", "count 19963.000000 19963.000000 \n", "mean 1.652808 5617.940239 \n", "std 0.712738 707.982901 \n", "min 0.000000 1711.000000 \n", "25% 2.000000 5311.000000 \n", "50% 2.000000 5499.000000 \n", "75% 2.000000 5912.000000 \n", "max 2.000000 9402.000000 " ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#step4: ststistical analysis using describe()\n", "\n", "#a) mean of the dataset values\n", "\n", "#b) standard deviation of the dataset values\n", "\n", "#c) Minimum and maximum values and the data in 25%,50% and 75%\n", "\n", "dataset.describe()" ] }, { "cell_type": "code", "execution_count": 5, "id": "5cd6ef0a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Card 0\n", "Year 0\n", "Month 0\n", "Day 0\n", "Amount 0\n", "Transaction 0\n", "MCC 0\n", "Is Fraud? 0\n", "dtype: int64" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#step4: Checking missing values.\n", "\n", "dataset.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 6, "id": "1c4951c5", "metadata": {}, "outputs": [], "source": [ "# Online Transaction=1 have no Merchant state" ] }, { "cell_type": "code", "execution_count": 7, "id": "75d8e0d7", "metadata": {}, "outputs": [], "source": [ "#step7: Divide the data into dependent and independent variables\n", "\n", "#a)x=independent variable\n", "\n", "#b)y=dependent variabel\n", "\n", "X = dataset.iloc[:, :-1].values\n", "y = dataset.iloc[:, -1].values" ] }, { "cell_type": "code", "execution_count": 8, "id": "0b33b4b8", "metadata": {}, "outputs": [], "source": [ "#step9: Divide the data into training and testing using train test split\n", "\n", "from sklearn.model_selection import train_test_split\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 1)" ] }, { "cell_type": "code", "execution_count": 9, "id": "ac3dae74", "metadata": {}, "outputs": [], "source": [ "from sklearn.preprocessing import StandardScaler\n", "sc = StandardScaler()\n", "X_train = sc.fit_transform(X_train)\n", "X_test = sc.transform(X_test)" ] }, { "cell_type": "code", "execution_count": 10, "id": "6dd5ed06", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "RandomForestClassifier(criterion='entropy', n_estimators=10, random_state=0)" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#step10: RandomForest\n", "\n", "from sklearn.ensemble import RandomForestClassifier\n", "classifier = RandomForestClassifier(n_estimators = 10, random_state = 0, criterion='entropy')\n", "classifier.fit(X_train, y_train)" ] }, { "cell_type": "code", "execution_count": 11, "id": "4d45c4a6", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[['No' 'No']\n", " ['No' 'No']\n", " ['No' 'No']\n", " ...\n", " ['No' 'No']\n", " ['No' 'No']\n", " ['No' 'No']]\n" ] } ], "source": [ "\n", "#step11: predict the test dataset value\n", "y_pred = classifier.predict(X_test)\n", "print(np.concatenate((y_pred.reshape(len(y_pred),1), y_test.reshape(len(y_test),1)),1))" ] }, { "cell_type": "code", "execution_count": 12, "id": "a767e930", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[3987 0]\n", " [ 4 2]]\n" ] }, { "data": { "text/plain": [ "0.9989982469321312" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\n", "#step12: create confusion matrix and Accuracy\n", "\n", "from sklearn.metrics import confusion_matrix, accuracy_score\n", "cm = confusion_matrix(y_test, y_pred)\n", "print(cm)\n", "accuracy_score(y_test, y_pred)" ] }, { "cell_type": "code", "execution_count": 13, "id": "78268fc7", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "['No']\n" ] } ], "source": [ "print(classifier.predict(sc.transform([[0,2002,9,1,135,2,5300]])))" ] }, { "cell_type": "code", "execution_count": null, "id": "2e32197d", "metadata": {}, "outputs": [], "source": [ "import pickle\n", "pickle.dump(classifier,open(\"cybercrime.sav\", \"wb\"))" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.12" } }, "nbformat": 4, "nbformat_minor": 5 }