diff --git a/README.md b/README.md index a2162a3..43719f3 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,6 @@ # ethereum-fraud-detection This repository contains attempts of using MLP and SOM neural networks to detect fraud in ethereum transactions +- Activate a venv environment +- Install the requirements using `pip install -r requirements.txt` - Run the different notebooks on Jupyter \ No newline at end of file diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..ccb7c34 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,109 @@ +absl-py==0.12.0 +appnope==0.1.2 +argon2-cffi==20.1.0 +astunparse==1.6.3 +async-generator==1.10 +attrs==20.3.0 +backcall==0.2.0 +bleach==3.3.0 +cached-property==1.5.2 +cachetools==4.2.1 +certifi==2020.12.5 +cffi==1.14.5 +chardet==4.0.0 +cycler==0.10.0 +decorator==4.4.2 +defusedxml==0.7.1 +entrypoints==0.3 +flatbuffers==1.12 +gast==0.3.3 +google-auth==1.28.0 +google-auth-oauthlib==0.4.4 +google-pasta==0.2.0 +grpcio==1.32.0 +h5py==2.10.0 +idna==2.10 +imbalanced-learn==0.8.0 +imblearn==0.0 +importlib-metadata==3.10.0 +ipykernel==5.5.3 +ipython==7.22.0 +ipython-genutils==0.2.0 +ipywidgets==7.6.3 +jedi==0.18.0 +Jinja2==2.11.3 +joblib==1.0.1 +jsonschema==3.2.0 +jupyter==1.0.0 +jupyter-client==6.1.12 +jupyter-console==6.4.0 +jupyter-core==4.7.1 +jupyterlab-pygments==0.1.2 +jupyterlab-widgets==1.0.0 +Keras==2.4.3 +Keras-Preprocessing==1.1.2 +kiwisolver==1.3.1 +Markdown==3.3.4 +MarkupSafe==1.1.1 +matplotlib==3.4.1 +mistune==0.8.4 +nbclient==0.5.3 +nbconvert==6.0.7 +nbformat==5.1.2 +nest-asyncio==1.5.1 +notebook==6.3.0 +numpy==1.19.5 +oauthlib==3.1.0 +opt-einsum==3.3.0 +packaging==20.9 +pandas==1.2.3 +pandocfilters==1.4.3 +parso==0.8.2 +pexpect==4.8.0 +pickleshare==0.7.5 +Pillow==8.1.2 +prometheus-client==0.9.0 +prompt-toolkit==3.0.18 +protobuf==3.15.6 +ptyprocess==0.7.0 +pyasn1==0.4.8 +pyasn1-modules==0.2.8 +pycparser==2.20 +Pygments==2.8.1 +pyparsing==2.4.7 +pyrsistent==0.17.3 +python-dateutil==2.8.1 +pytz==2021.1 +PyYAML==5.4.1 +pyzmq==22.0.3 +qtconsole==5.0.3 +QtPy==1.9.0 +requests==2.25.1 +requests-oauthlib==1.3.0 +rsa==4.7.2 +scikit-learn==0.24.1 +scipy==1.6.2 +seaborn==0.11.1 +Send2Trash==1.5.0 +six==1.15.0 +sns==0.1 +susi==1.1.2 +tensorboard==2.4.1 +tensorboard-plugin-wit==1.8.0 +tensorflow==2.4.1 +tensorflow-estimator==2.4.0 +termcolor==1.1.0 +terminado==0.9.4 +testpath==0.4.4 +threadpoolctl==2.1.0 +tornado==6.1 +tqdm==4.59.0 +traitlets==5.0.5 +typing-extensions==3.7.4.3 +urllib3==1.26.4 +wcwidth==0.2.5 +webencodings==0.5.1 +Werkzeug==1.0.1 +widgetsnbextension==3.5.1 +wrapt==1.12.1 +zipp==3.4.1 diff --git a/test_som.ipynb b/test_som.ipynb deleted file mode 100644 index 2cce15d..0000000 --- a/test_som.ipynb +++ /dev/null @@ -1,260 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": 1, - "metadata": { - "collapsed": true - }, - "outputs": [], - "source": [ - "import numpy as np\n", - "import susi\n", - "import matplotlib.pyplot as plt\n", - "from sklearn.model_selection import train_test_split\n", - "from sklearn.preprocessing import StandardScaler\n", - "from sklearn.datasets import make_classification\n" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "outputs": [], - "source": [ - "n_features = 5\n", - "\n", - "# get the data\n", - "X, y = make_classification(n_features=n_features, n_redundant=0, n_informative=2,\n", - " random_state=1, n_clusters_per_class=1)\n", - "\n", - "# split the data\n", - "X_train, X_test, y_train, y_test = train_test_split(\n", - " X, y, test_size=0.5, random_state=1, shuffle=True)" - ], - "metadata": { - "collapsed": false, - "pycharm": { - "name": "#%%\n" - } - } - }, - { - "cell_type": "code", - "execution_count": 3, - "outputs": [ - { - "data": { - "text/plain": "array([[ 1.36586461, 0.32352735, -0.44222928, 0.84917607, -0.10999149],\n [ 0.97139534, -0.23794194, 1.19268607, 1.0576549 , 1.15528789],\n [ 1.25704434, -0.23643695, 0.35249436, -0.62373281, 0.7278135 ],\n [ 0.44118981, 0.45015551, -0.10839207, -1.88873982, 1.7653351 ],\n [ 1.34740825, -0.41302931, 0.85328122, -0.54245992, 1.83471763],\n [ 0.9292506 , 2.0546241 , -0.74996962, -1.21258781, 0.05340954],\n [ 0.62567337, -0.66134424, 1.3887794 , 1.23187251, 3.03085711],\n [ 1.07258847, -1.34267579, -0.3264995 , 1.24328724, 1.11438298],\n [ 0.87226739, -0.19505734, 0.92001793, 1.02600767, 0.80539342],\n [ 0.85335555, -1.77756638, -2.413503 , -1.29936179, -0.77785883],\n [ 1.18468624, -0.27909772, -0.8805776 , 0.96548233, 1.62284909],\n [ 0.10593645, -0.34390071, -0.59384307, -1.53556118, -1.00016919],\n [ 1.1437713 , 0.2764993 , 0.26246745, 1.17718111, -0.7332716 ],\n [ 0.85877496, -0.38483225, 1.00088142, -0.67204982, 1.45810824],\n [ 1.46893146, -0.86131636, -1.39662042, 1.03345052, 0.67471153],\n [ 1.22867367, 1.76795995, -1.42655542, -1.73963799, -0.47537288],\n [ 0.55853873, -0.44873803, -0.19022103, 0.82550695, -0.67244804],\n [ 1.98519313, 0.1094027 , 1.55880554, 1.22382712, -1.2197444 ],\n [ 0.84806927, 0.65458015, 0.82458463, 0.82798737, -0.05118845],\n [ 1.66752297, -1.02188594, 0.47761018, -0.493857 , 0.79452824],\n [ 0.6109426 , 0.7147896 , -1.75592564, -0.94495995, 0.85270406],\n [ 1.14809657, 0.66102029, 0.20183018, 1.17353145, 1.79215821],\n [ 1.12641981, -1.17598267, 0.4611641 , 0.94459507, 1.01012718],\n [ 0.94781411, 1.70459417, 1.19783084, -1.23912256, 1.04008915],\n [ 0.85771953, 0.72171129, -0.82246719, -1.39003042, -0.625342 ],\n [ 0.6236295 , -0.53722302, -0.70134443, 0.93640333, 0.15626385],\n [ 1.838294 , -1.23685338, -0.58652394, 1.32551412, 0.87583893],\n [ 0.5630779 , 0.79502609, -1.52568032, 1.06796368, -0.37443832],\n [ 1.06523311, 0.93916874, -0.55749472, -1.23017555, -1.94332341],\n [ 0.98042741, -0.54577417, 2.44936865, 1.10018476, -0.19883786],\n [ 0.35413361, -1.67419581, -0.66575452, 0.90394545, 0.82502982],\n [ 0.62368852, 2.13782807, 0.56438286, -1.18913787, -0.785534 ],\n [ 0.46739791, -0.10288722, 0.84086156, -0.54706224, 1.14690038],\n [ 1.12062155, 1.20845633, -0.42914228, -1.18013412, 1.1157018 ],\n [ 0.6675918 , -0.19899818, -0.11877117, -1.44620987, 1.86647138],\n [ 1.24549398, -1.47115693, 2.06578332, 1.00277655, -0.8301719 ],\n [ 0.85982375, 1.09899633, -0.72239191, -1.15649503, -0.90163449],\n [ 0.98379959, -0.79954749, 0.057121 , -1.278618 , -0.2915946 ],\n [ 0.69174373, 1.10417433, 0.45161595, -1.20257258, -0.28173627],\n [ 0.89891716, 0.9561217 , 0.6210827 , 0.84146721, -0.70584051],\n [ 0.96457205, 2.05117344, -1.04458938, 1.21828168, 0.585662 ],\n [ 0.77528533, -0.41163916, -2.11416392, 0.78655651, 1.27852808],\n [ 0.87699465, -1.23312074, -0.12046457, 0.89189141, -1.18231813],\n [ 1.32720112, 0.45112294, -1.40232915, -0.5789623 , -0.6949209 ],\n [ 1.02242019, -0.16819884, 0.00854895, 1.15080755, -0.17418034],\n [ 0.89551051, -0.78191168, 1.39984394, 0.8780991 , -0.43750898],\n [ 1.17867274, -0.44317193, 0.61853913, 1.17899425, 1.81053491],\n [ 1.21619061, -1.11487105, 0.5154138 , -1.36419132, -0.76730983],\n [ 0.92686981, -0.10534471, -0.91844004, -1.09230828, 0.63019567],\n [ 1.16777676, 1.6169496 , 0.12910158, 1.01313574, 0.50274088]])" - }, - "execution_count": 3, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "X_train" - ], - "metadata": { - "collapsed": false, - "pycharm": { - "name": "#%%\n" - } - } - }, - { - "cell_type": "code", - "execution_count": 4, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "(50, 5) (50, 5)\n" - ] - } - ], - "source": [ - "# scale the data\n", - "scaler = StandardScaler()\n", - "X_train = scaler.fit_transform(X_train)\n", - "X_test = scaler.transform(X_test)\n", - "\n", - "print(X_train.shape, X_test.shape)\n" - ], - "metadata": { - "collapsed": false, - "pycharm": { - "name": "#%%\n" - } - } - }, - { - "cell_type": "code", - "execution_count": 5, - "outputs": [ - { - "data": { - "text/plain": "array([ 3.53050922e-16, -1.33226763e-17, 8.88178420e-18, 1.55431223e-17,\n -4.88498131e-17])" - }, - "execution_count": 5, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "X_train\n", - "\n", - "np.mean(X_train, axis=0)\n", - "\n" - ], - "metadata": { - "collapsed": false, - "pycharm": { - "name": "#%%\n" - } - } - }, - { - "cell_type": "code", - "execution_count": 6, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Accuracy: 86.0 %\n" - ] - } - ], - "source": [ - "som = susi.SOMClassifier(\n", - " n_rows=40,\n", - " n_columns=40,\n", - " n_iter_unsupervised=1000,\n", - " n_iter_supervised=1000,\n", - " random_state=0)\n", - "som.fit(X_train, y_train)\n", - "y_pred = som.predict(X_test)\n", - "print(\"Accuracy: {0:.1f} %\".format(som.score(X_test, y_test)*100))" - ], - "metadata": { - "collapsed": false, - "pycharm": { - "name": "#%%\n" - } - } - }, - { - "cell_type": "code", - "execution_count": 7, - "outputs": [ - { - "data": { - "text/plain": "
", - "image/png": "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\n" - }, - "metadata": { - "needs_background": "light" - }, - "output_type": "display_data" - } - ], - "source": [ - "\n", - "# calculate probabilities\n", - "proba = som.predict_proba(X_test)\n", - "\n", - "# plot probabilities\n", - "class_index = 0\n", - "plt.hist(proba[:, class_index])\n", - "plt.xlabel(f\"Probability for class {class_index}\")\n", - "plt.ylabel(\"Number of datapoints\")\n", - "plt.show()" - ], - "metadata": { - "collapsed": false, - "pycharm": { - "name": "#%%\n" - } - } - }, - { - "cell_type": "code", - "execution_count": 8, - "outputs": [ - { - "data": { - "text/plain": "
", - "image/png": "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\n" - }, - "metadata": { - "needs_background": "light" - }, - "output_type": "display_data" - } - ], - "source": [ - "from susi.SOMPlots import plot_umatrix, plot_estimation_map\n", - "\n", - "u_matrix = som.get_u_matrix()\n", - "plot_umatrix(u_matrix, 40, 40)\n", - "plt.show()" - ], - "metadata": { - "collapsed": false, - "pycharm": { - "name": "#%%\n" - } - } - }, - { - "cell_type": "code", - "execution_count": 9, - "outputs": [ - { - "data": { - "text/plain": "
", - "image/png": "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\n" - }, - "metadata": { - "needs_background": "light" - }, - "output_type": "display_data" - } - ], - "source": [ - "\n", - "estimation_map = som.get_estimation_map().squeeze()\n", - "plot_estimation_map(estimation_map)\n", - "plt.show()" - ], - "metadata": { - "collapsed": false, - "pycharm": { - "name": "#%%\n" - } - } - } - ], - "metadata": { - "kernelspec": { - "name": "pycharm-14024ecd", - "language": "python", - "display_name": "PyCharm (ethereum-fraud-detection)" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 2 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython2", - "version": "2.7.6" - } - }, - "nbformat": 4, - "nbformat_minor": 0 -} \ No newline at end of file