├── Docs └── Algorithm Comparison.docx ├── README.md ├── .gitignore ├── Notebooks ├── SVM │ ├── Linear SVM.ipynb │ ├── RBF SVM.ipynb │ ├── Polynomial SVM.ipynb │ ├── Sigmoid SVM.ipynb │ ├── Linear SVM with PCA.ipynb │ ├── RBF SVM with PCA.ipynb │ ├── Polynomial SVM with PCA.ipynb │ └── Sigmoid SVM with PCA.ipynb ├── Gaussian Naive Bayes │ ├── Gaussian Naive Bayes.ipynb │ └── Gaussian Naive Bayes with PCA.ipynb ├── Decision Tree │ ├── Decision Tree.ipynb │ └── Decision Tree with PCA.ipynb ├── K Nearest Neighbors │ ├── KNN.ipynb │ └── KNN with PCA.ipynb └── Random Forest │ ├── Random Forest.ipynb │ └── Random Forest with PCA.ipynb └── LICENSE /Docs/Algorithm Comparison.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rasoulghaznavi/MLSEED/HEAD/Docs/Algorithm Comparison.docx -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # MLSEED 2 | This project applies different kinds of ML algorithms on the SEED Dataset to classify the data into 3 states: Positive Emotion, Neutral, Negative Emotion. 3 | 4 | # Getting started 5 | The algorithms in this repo are applied to the 5th dimension (gamma band which is best for emotion recognition) of “de_LDS” features of the Dataset. There are 62 inputs (feature vectors) in each de_LDS for every subject of the experiment. All de_LDS features contribute to 6 | more than 150000 samples in the dataset. The objective is to train models to map them using 62 feature vectors to 3 labels. 7 | 8 | # Prerequisites 9 | The project is written in python using anaconda in jupyter notebook. Some of the libraries youl'll need in the project are: 10 | Tensorflow, 11 | sk-Learn, 12 | Numpy, 13 | Pandas, 14 | Matplotlib and 15 | Seaborn. 16 | 17 | # Author 18 | Rasoul Ghaznavi 19 | 20 | # Licence 21 | This project is licensed under the GNU General Public License v3.0. 22 | 23 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | *.egg-info/ 24 | .installed.cfg 25 | *.egg 26 | MANIFEST 27 | 28 | # PyInstaller 29 | # Usually these files are written by a python script from a template 30 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 31 | *.manifest 32 | *.spec 33 | 34 | # Installer logs 35 | pip-log.txt 36 | pip-delete-this-directory.txt 37 | 38 | # Unit test / coverage reports 39 | htmlcov/ 40 | .tox/ 41 | .coverage 42 | .coverage.* 43 | .cache 44 | nosetests.xml 45 | coverage.xml 46 | *.cover 47 | .hypothesis/ 48 | .pytest_cache/ 49 | 50 | # Translations 51 | *.mo 52 | *.pot 53 | 54 | # Django stuff: 55 | *.log 56 | local_settings.py 57 | db.sqlite3 58 | 59 | # Flask stuff: 60 | instance/ 61 | .webassets-cache 62 | 63 | # Scrapy stuff: 64 | .scrapy 65 | 66 | # Sphinx documentation 67 | docs/_build/ 68 | 69 | # PyBuilder 70 | target/ 71 | 72 | # Jupyter Notebook 73 | .ipynb_checkpoints 74 | 75 | # pyenv 76 | .python-version 77 | 78 | # celery beat schedule file 79 | celerybeat-schedule 80 | 81 | # SageMath parsed files 82 | *.sage.py 83 | 84 | # Environments 85 | .env 86 | .venv 87 | env/ 88 | venv/ 89 | ENV/ 90 | env.bak/ 91 | venv.bak/ 92 | 93 | # Spyder project settings 94 | .spyderproject 95 | .spyproject 96 | 97 | # Rope project settings 98 | .ropeproject 99 | 100 | # mkdocs documentation 101 | /site 102 | 103 | # mypy 104 | .mypy_cache/ 105 | -------------------------------------------------------------------------------- /Notebooks/SVM/Linear SVM.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Modelling, Training and Test" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 87 | "from sklearn.model_selection import train_test_split\n", 88 | "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20)" 89 | ] 90 | }, 91 | { 92 | "cell_type": "code", 93 | "execution_count": null, 94 | "metadata": {}, 95 | "outputs": [], 96 | "source": [ 97 | "#import SVC and perform linear SVM on the training dataset\n", 98 | "from sklearn.svm import SVC\n", 99 | "svclassifier = SVC(kernel='linear')\n", 100 | "svclassifier.fit(X_train, y_train)" 101 | ] 102 | }, 103 | { 104 | "cell_type": "code", 105 | "execution_count": null, 106 | "metadata": {}, 107 | "outputs": [], 108 | "source": [ 109 | "#apply the trained SVM on the test dataset\n", 110 | "y_pred = svclassifier.predict(X_test)" 111 | ] 112 | }, 113 | { 114 | "cell_type": "code", 115 | "execution_count": null, 116 | "metadata": {}, 117 | "outputs": [], 118 | "source": [ 119 | "# output the predicted values\n", 120 | "y_pred" 121 | ] 122 | }, 123 | { 124 | "cell_type": "code", 125 | "execution_count": null, 126 | "metadata": {}, 127 | "outputs": [], 128 | "source": [ 129 | "# import relevant metrics and print the confusion matrix and classification report\n", 130 | "from sklearn.metrics import classification_report, confusion_matrix\n", 131 | "print(confusion_matrix(y_test,y_pred))\n", 132 | "print(classification_report(y_test,y_pred))" 133 | ] 134 | }, 135 | { 136 | "cell_type": "code", 137 | "execution_count": null, 138 | "metadata": {}, 139 | "outputs": [], 140 | "source": [] 141 | } 142 | ], 143 | "metadata": { 144 | "kernelspec": { 145 | "display_name": "Python 3", 146 | "language": "python", 147 | "name": "python3" 148 | }, 149 | "language_info": { 150 | "codemirror_mode": { 151 | "name": "ipython", 152 | "version": 3 153 | }, 154 | "file_extension": ".py", 155 | "mimetype": "text/x-python", 156 | "name": "python", 157 | "nbconvert_exporter": "python", 158 | "pygments_lexer": "ipython3", 159 | "version": "3.7.3" 160 | } 161 | }, 162 | "nbformat": 4, 163 | "nbformat_minor": 2 164 | } 165 | -------------------------------------------------------------------------------- /Notebooks/SVM/RBF SVM.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Modelling, Training and Test" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 87 | "from sklearn.model_selection import train_test_split\n", 88 | "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20)" 89 | ] 90 | }, 91 | { 92 | "cell_type": "code", 93 | "execution_count": null, 94 | "metadata": {}, 95 | "outputs": [], 96 | "source": [ 97 | "#import SVC and perform linear SVM on the training dataset\n", 98 | "from sklearn.svm import SVC\n", 99 | "svclassifier = SVC(kernel='rbf', C=1, gamma=0.1)\n", 100 | "svclassifier.fit(X_train, y_train)" 101 | ] 102 | }, 103 | { 104 | "cell_type": "code", 105 | "execution_count": null, 106 | "metadata": {}, 107 | "outputs": [], 108 | "source": [ 109 | "#apply the trained SVM on the test dataset\n", 110 | "y_pred = svclassifier.predict(X_test)" 111 | ] 112 | }, 113 | { 114 | "cell_type": "code", 115 | "execution_count": null, 116 | "metadata": {}, 117 | "outputs": [], 118 | "source": [ 119 | "# output the predicted values\n", 120 | "y_pred" 121 | ] 122 | }, 123 | { 124 | "cell_type": "code", 125 | "execution_count": null, 126 | "metadata": {}, 127 | "outputs": [], 128 | "source": [ 129 | "# import relevant metrics and print the confusion matrix and classification report\n", 130 | "from sklearn.metrics import classification_report, confusion_matrix\n", 131 | "print(confusion_matrix(y_test,y_pred))\n", 132 | "print(classification_report(y_test,y_pred))" 133 | ] 134 | }, 135 | { 136 | "cell_type": "code", 137 | "execution_count": null, 138 | "metadata": {}, 139 | "outputs": [], 140 | "source": [] 141 | } 142 | ], 143 | "metadata": { 144 | "kernelspec": { 145 | "display_name": "Python 3", 146 | "language": "python", 147 | "name": "python3" 148 | }, 149 | "language_info": { 150 | "codemirror_mode": { 151 | "name": "ipython", 152 | "version": 3 153 | }, 154 | "file_extension": ".py", 155 | "mimetype": "text/x-python", 156 | "name": "python", 157 | "nbconvert_exporter": "python", 158 | "pygments_lexer": "ipython3", 159 | "version": "3.7.3" 160 | } 161 | }, 162 | "nbformat": 4, 163 | "nbformat_minor": 2 164 | } 165 | -------------------------------------------------------------------------------- /Notebooks/SVM/Polynomial SVM.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Modelling, Training and Test" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 87 | "from sklearn.model_selection import train_test_split\n", 88 | "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20)" 89 | ] 90 | }, 91 | { 92 | "cell_type": "code", 93 | "execution_count": null, 94 | "metadata": {}, 95 | "outputs": [], 96 | "source": [ 97 | "#import SVC and perform Polynomial SVM on the training dataset\n", 98 | "from sklearn.svm import SVC\n", 99 | "svclassifier = SVC(kernel='poly', C=1, gamma=0.1, degree=3)\n", 100 | "svclassifier.fit(X_train, y_train)" 101 | ] 102 | }, 103 | { 104 | "cell_type": "code", 105 | "execution_count": null, 106 | "metadata": {}, 107 | "outputs": [], 108 | "source": [ 109 | "#apply the trained SVM on the test dataset\n", 110 | "y_pred = svclassifier.predict(X_test)" 111 | ] 112 | }, 113 | { 114 | "cell_type": "code", 115 | "execution_count": null, 116 | "metadata": {}, 117 | "outputs": [], 118 | "source": [ 119 | "# output the predicted values\n", 120 | "y_pred" 121 | ] 122 | }, 123 | { 124 | "cell_type": "code", 125 | "execution_count": null, 126 | "metadata": {}, 127 | "outputs": [], 128 | "source": [ 129 | "# import relevant metrics and print the confusion matrix and classification report\n", 130 | "from sklearn.metrics import classification_report, confusion_matrix\n", 131 | "print(confusion_matrix(y_test,y_pred))\n", 132 | "print(classification_report(y_test,y_pred))" 133 | ] 134 | }, 135 | { 136 | "cell_type": "code", 137 | "execution_count": null, 138 | "metadata": {}, 139 | "outputs": [], 140 | "source": [] 141 | } 142 | ], 143 | "metadata": { 144 | "kernelspec": { 145 | "display_name": "Python 3", 146 | "language": "python", 147 | "name": "python3" 148 | }, 149 | "language_info": { 150 | "codemirror_mode": { 151 | "name": "ipython", 152 | "version": 3 153 | }, 154 | "file_extension": ".py", 155 | "mimetype": "text/x-python", 156 | "name": "python", 157 | "nbconvert_exporter": "python", 158 | "pygments_lexer": "ipython3", 159 | "version": "3.7.3" 160 | } 161 | }, 162 | "nbformat": 4, 163 | "nbformat_minor": 2 164 | } 165 | -------------------------------------------------------------------------------- /Notebooks/Gaussian Naive Bayes/Gaussian Naive Bayes.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Modelling, Training and Test" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 87 | "from sklearn.model_selection import train_test_split\n", 88 | "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20)" 89 | ] 90 | }, 91 | { 92 | "cell_type": "code", 93 | "execution_count": null, 94 | "metadata": {}, 95 | "outputs": [], 96 | "source": [ 97 | "#import GaussianNB and perform Gaussian Naive Bayes on the training dataset\n", 98 | "from sklearn.naive_bayes import GaussianNB\n", 99 | "estimator = GaussianNB()\n", 100 | "estimator.fit(X_train, y_train)" 101 | ] 102 | }, 103 | { 104 | "cell_type": "code", 105 | "execution_count": null, 106 | "metadata": {}, 107 | "outputs": [], 108 | "source": [ 109 | "#apply the trained estimator on the test dataset\n", 110 | "estimator.score(X_test, y_test)\n", 111 | "y_pred = estimator.predict(X_test)" 112 | ] 113 | }, 114 | { 115 | "cell_type": "code", 116 | "execution_count": null, 117 | "metadata": {}, 118 | "outputs": [], 119 | "source": [ 120 | "# output the predicted values\n", 121 | "y_pred" 122 | ] 123 | }, 124 | { 125 | "cell_type": "code", 126 | "execution_count": null, 127 | "metadata": {}, 128 | "outputs": [], 129 | "source": [ 130 | "# import relevant metrics and print the confusion matrix and classification report\n", 131 | "from sklearn.metrics import classification_report, confusion_matrix\n", 132 | "print(confusion_matrix(y_test,y_pred))\n", 133 | "print(classification_report(y_test,y_pred))" 134 | ] 135 | }, 136 | { 137 | "cell_type": "code", 138 | "execution_count": null, 139 | "metadata": {}, 140 | "outputs": [], 141 | "source": [] 142 | } 143 | ], 144 | "metadata": { 145 | "kernelspec": { 146 | "display_name": "Python 3", 147 | "language": "python", 148 | "name": "python3" 149 | }, 150 | "language_info": { 151 | "codemirror_mode": { 152 | "name": "ipython", 153 | "version": 3 154 | }, 155 | "file_extension": ".py", 156 | "mimetype": "text/x-python", 157 | "name": "python", 158 | "nbconvert_exporter": "python", 159 | "pygments_lexer": "ipython3", 160 | "version": "3.7.3" 161 | } 162 | }, 163 | "nbformat": 4, 164 | "nbformat_minor": 2 165 | } 166 | -------------------------------------------------------------------------------- /Notebooks/SVM/Sigmoid SVM.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Modelling, Training and Test" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 87 | "from sklearn.model_selection import train_test_split\n", 88 | "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20)" 89 | ] 90 | }, 91 | { 92 | "cell_type": "code", 93 | "execution_count": null, 94 | "metadata": {}, 95 | "outputs": [], 96 | "source": [ 97 | "#import SVC and perform Sogmoid SVM on the training dataset\n", 98 | "from sklearn.svm import SVC\n", 99 | "svclassifier = SVC(kernel='sigmoid', C=1, gamma=0.1)\n", 100 | "svclassifier.fit(X_train, y_train)\n" 101 | ] 102 | }, 103 | { 104 | "cell_type": "code", 105 | "execution_count": null, 106 | "metadata": {}, 107 | "outputs": [], 108 | "source": [ 109 | "#apply the trained SVM on the test dataset\n", 110 | "mean_accuracy=svclassifier.score(X_test, y_test)\n", 111 | "y_pred = svclassifier.predict(X_test)\n", 112 | "print(mean_accuracy)" 113 | ] 114 | }, 115 | { 116 | "cell_type": "code", 117 | "execution_count": null, 118 | "metadata": {}, 119 | "outputs": [], 120 | "source": [ 121 | "# output the predicted values\n", 122 | "y_pred" 123 | ] 124 | }, 125 | { 126 | "cell_type": "code", 127 | "execution_count": null, 128 | "metadata": {}, 129 | "outputs": [], 130 | "source": [ 131 | "# import relevant metrics and print the confusion matrix and classification report\n", 132 | "from sklearn.metrics import classification_report, confusion_matrix\n", 133 | "print(confusion_matrix(y_test,y_pred))\n", 134 | "print(classification_report(y_test,y_pred))" 135 | ] 136 | }, 137 | { 138 | "cell_type": "code", 139 | "execution_count": null, 140 | "metadata": {}, 141 | "outputs": [], 142 | "source": [] 143 | } 144 | ], 145 | "metadata": { 146 | "kernelspec": { 147 | "display_name": "Python 3", 148 | "language": "python", 149 | "name": "python3" 150 | }, 151 | "language_info": { 152 | "codemirror_mode": { 153 | "name": "ipython", 154 | "version": 3 155 | }, 156 | "file_extension": ".py", 157 | "mimetype": "text/x-python", 158 | "name": "python", 159 | "nbconvert_exporter": "python", 160 | "pygments_lexer": "ipython3", 161 | "version": "3.7.3" 162 | } 163 | }, 164 | "nbformat": 4, 165 | "nbformat_minor": 2 166 | } 167 | -------------------------------------------------------------------------------- /Notebooks/Decision Tree/Decision Tree.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Modelling, Training and Test" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 87 | "from sklearn.model_selection import train_test_split\n", 88 | "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20)" 89 | ] 90 | }, 91 | { 92 | "cell_type": "code", 93 | "execution_count": null, 94 | "metadata": {}, 95 | "outputs": [], 96 | "source": [ 97 | "#import DecisionTreeClassifier and start the training\n", 98 | "from sklearn.tree import DecisionTreeClassifier\n", 99 | "estimator = DecisionTreeClassifier(random_state=0)\n", 100 | "estimator.fit(X_train, y_train)" 101 | ] 102 | }, 103 | { 104 | "cell_type": "code", 105 | "execution_count": null, 106 | "metadata": {}, 107 | "outputs": [], 108 | "source": [ 109 | "#apply the trained estimator on the test dataset\n", 110 | "mean_accuracy=estimator.score(X_test, y_test)\n", 111 | "y_pred = estimator.predict(X_test)\n", 112 | "print(mean_accuracy)" 113 | ] 114 | }, 115 | { 116 | "cell_type": "code", 117 | "execution_count": null, 118 | "metadata": {}, 119 | "outputs": [], 120 | "source": [ 121 | "# output the predicted values\n", 122 | "y_pred" 123 | ] 124 | }, 125 | { 126 | "cell_type": "code", 127 | "execution_count": null, 128 | "metadata": {}, 129 | "outputs": [], 130 | "source": [ 131 | "# import relevant metrics and print the confusion matrix and classification report\n", 132 | "from sklearn.metrics import classification_report, confusion_matrix\n", 133 | "print(confusion_matrix(y_test,y_pred))\n", 134 | "print(classification_report(y_test,y_pred))" 135 | ] 136 | }, 137 | { 138 | "cell_type": "code", 139 | "execution_count": null, 140 | "metadata": {}, 141 | "outputs": [], 142 | "source": [] 143 | } 144 | ], 145 | "metadata": { 146 | "kernelspec": { 147 | "display_name": "Python 3", 148 | "language": "python", 149 | "name": "python3" 150 | }, 151 | "language_info": { 152 | "codemirror_mode": { 153 | "name": "ipython", 154 | "version": 3 155 | }, 156 | "file_extension": ".py", 157 | "mimetype": "text/x-python", 158 | "name": "python", 159 | "nbconvert_exporter": "python", 160 | "pygments_lexer": "ipython3", 161 | "version": "3.7.3" 162 | } 163 | }, 164 | "nbformat": 4, 165 | "nbformat_minor": 2 166 | } 167 | -------------------------------------------------------------------------------- /Notebooks/K Nearest Neighbors/KNN.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Modelling, Training and Test" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 87 | "from sklearn.model_selection import train_test_split\n", 88 | "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20)" 89 | ] 90 | }, 91 | { 92 | "cell_type": "code", 93 | "execution_count": null, 94 | "metadata": {}, 95 | "outputs": [], 96 | "source": [ 97 | "#import KNeighborsClassifier and KNN on the training dataset\n", 98 | "from sklearn.neighbors import KNeighborsClassifier\n", 99 | "estimator = KNeighborsClassifier(n_neighbors=3)\n", 100 | "estimator.fit(X_train, y_train)" 101 | ] 102 | }, 103 | { 104 | "cell_type": "code", 105 | "execution_count": null, 106 | "metadata": {}, 107 | "outputs": [], 108 | "source": [ 109 | "#apply the trained estimator on the test dataset\n", 110 | "mean_accuracy=estimator.score(X_test, y_test)\n", 111 | "y_pred = estimator.predict(X_test)\n", 112 | "print(mean_accuracy)" 113 | ] 114 | }, 115 | { 116 | "cell_type": "code", 117 | "execution_count": null, 118 | "metadata": {}, 119 | "outputs": [], 120 | "source": [ 121 | "# output the predicted values\n", 122 | "y_pred" 123 | ] 124 | }, 125 | { 126 | "cell_type": "code", 127 | "execution_count": null, 128 | "metadata": {}, 129 | "outputs": [], 130 | "source": [ 131 | "# import relevant metrics and print the confusion matrix and classification report\n", 132 | "from sklearn.metrics import classification_report, confusion_matrix\n", 133 | "print(confusion_matrix(y_test,y_pred))\n", 134 | "print(classification_report(y_test,y_pred))" 135 | ] 136 | }, 137 | { 138 | "cell_type": "code", 139 | "execution_count": null, 140 | "metadata": {}, 141 | "outputs": [], 142 | "source": [] 143 | } 144 | ], 145 | "metadata": { 146 | "kernelspec": { 147 | "display_name": "Python 3", 148 | "language": "python", 149 | "name": "python3" 150 | }, 151 | "language_info": { 152 | "codemirror_mode": { 153 | "name": "ipython", 154 | "version": 3 155 | }, 156 | "file_extension": ".py", 157 | "mimetype": "text/x-python", 158 | "name": "python", 159 | "nbconvert_exporter": "python", 160 | "pygments_lexer": "ipython3", 161 | "version": "3.7.3" 162 | } 163 | }, 164 | "nbformat": 4, 165 | "nbformat_minor": 2 166 | } 167 | -------------------------------------------------------------------------------- /Notebooks/Random Forest/Random Forest.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Modelling, Training and Test" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 87 | "from sklearn.model_selection import train_test_split\n", 88 | "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20)" 89 | ] 90 | }, 91 | { 92 | "cell_type": "code", 93 | "execution_count": null, 94 | "metadata": {}, 95 | "outputs": [], 96 | "source": [ 97 | "#import RandomForestClassifier and RFC on the training dataset\n", 98 | "from sklearn.ensemble import RandomForestClassifier\n", 99 | "estimator = RandomForestClassifier(n_estimators=100, max_depth=2, random_state=0)\n", 100 | "estimator.fit(X_train, y_train)" 101 | ] 102 | }, 103 | { 104 | "cell_type": "code", 105 | "execution_count": null, 106 | "metadata": {}, 107 | "outputs": [], 108 | "source": [ 109 | "#apply the trained estimator on the test dataset\n", 110 | "mean_accuracy=estimator.score(X_test, y_test)\n", 111 | "y_pred = estimator.predict(X_test)\n", 112 | "print(mean_accuracy)\n", 113 | "print(estimator.feature_importances_)" 114 | ] 115 | }, 116 | { 117 | "cell_type": "code", 118 | "execution_count": null, 119 | "metadata": {}, 120 | "outputs": [], 121 | "source": [ 122 | "# output the predicted values\n", 123 | "y_pred" 124 | ] 125 | }, 126 | { 127 | "cell_type": "code", 128 | "execution_count": null, 129 | "metadata": {}, 130 | "outputs": [], 131 | "source": [ 132 | "# import relevant metrics and print the confusion matrix and classification report\n", 133 | "from sklearn.metrics import classification_report, confusion_matrix\n", 134 | "print(confusion_matrix(y_test,y_pred))\n", 135 | "print(classification_report(y_test,y_pred))" 136 | ] 137 | }, 138 | { 139 | "cell_type": "code", 140 | "execution_count": null, 141 | "metadata": {}, 142 | "outputs": [], 143 | "source": [] 144 | } 145 | ], 146 | "metadata": { 147 | "kernelspec": { 148 | "display_name": "Python 3", 149 | "language": "python", 150 | "name": "python3" 151 | }, 152 | "language_info": { 153 | "codemirror_mode": { 154 | "name": "ipython", 155 | "version": 3 156 | }, 157 | "file_extension": ".py", 158 | "mimetype": "text/x-python", 159 | "name": "python", 160 | "nbconvert_exporter": "python", 161 | "pygments_lexer": "ipython3", 162 | "version": "3.7.3" 163 | } 164 | }, 165 | "nbformat": 4, 166 | "nbformat_minor": 2 167 | } 168 | -------------------------------------------------------------------------------- /Notebooks/SVM/Linear SVM with PCA.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Perform PCA" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "# import PCA and perform it on the inputs in a loop from 1 principal component all the way to 62 principal components\n", 87 | "from sklearn.decomposition import PCA\n", 88 | "p=[]\n", 89 | "for c in range(1,62):\n", 90 | " pca=PCA(n_components=c)\n", 91 | " pcs=pca.fit_transform(X)\n", 92 | " p.append(pca.explained_variance_ratio_)\n", 93 | "p" 94 | ] 95 | }, 96 | { 97 | "cell_type": "code", 98 | "execution_count": null, 99 | "metadata": {}, 100 | "outputs": [], 101 | "source": [ 102 | "# put the sum of explained variance for diffetenct number of principal components\n", 103 | "sumc=[]\n", 104 | "a=0\n", 105 | "b=0\n", 106 | "for w in range(len(p)):\n", 107 | " a=p[w]\n", 108 | " b=np.sum(a)\n", 109 | " sumc.append(b)\n", 110 | " \n", 111 | "sumc" 112 | ] 113 | }, 114 | { 115 | "cell_type": "code", 116 | "execution_count": null, 117 | "metadata": {}, 118 | "outputs": [], 119 | "source": [ 120 | "# plot sum of the explained variances against the number of components (in my case %90 explained variance is achieved with 13 PCs)\n", 121 | "sump=[b*100 for b in sumc]\n", 122 | "xs=[d for d in range(1,62)]\n", 123 | "plt.plot(xs, sump, 'orange')\n", 124 | "plt.axis([0, 62, 0, 110])\n", 125 | "plt.axhline(y=90)\n", 126 | "plt.axvline(x=13)\n", 127 | "plt.show()" 128 | ] 129 | }, 130 | { 131 | "cell_type": "code", 132 | "execution_count": null, 133 | "metadata": {}, 134 | "outputs": [], 135 | "source": [ 136 | "# perform PCA on the inputs using the number of PCs that explain %90 of the variance in the dataset (in my case it was 13)\n", 137 | "pca13=PCA(n_components=13)\n", 138 | "pcs13=pca13.fit_transform(X)" 139 | ] 140 | }, 141 | { 142 | "cell_type": "code", 143 | "execution_count": null, 144 | "metadata": { 145 | "scrolled": true 146 | }, 147 | "outputs": [], 148 | "source": [ 149 | "# output the explained variance for each of the components\n", 150 | "ar=pca13.explained_variance_ratio_\n", 151 | "ar" 152 | ] 153 | }, 154 | { 155 | "cell_type": "code", 156 | "execution_count": null, 157 | "metadata": {}, 158 | "outputs": [], 159 | "source": [ 160 | "# output sum of the excplained variance\n", 161 | "sum=0\n", 162 | "for n in ar:\n", 163 | " sum+=n\n", 164 | "sum" 165 | ] 166 | }, 167 | { 168 | "cell_type": "code", 169 | "execution_count": null, 170 | "metadata": {}, 171 | "outputs": [], 172 | "source": [ 173 | "# define inputs as XP pandas data frame and add new headers\n", 174 | "XP=pd.DataFrame(data=pcs13,columns=['pc1','pc2','pc3','pc4','pc5','pc6','pc7','pc8','pc9','pc10','pc1','pc12','pc13'])" 175 | ] 176 | }, 177 | { 178 | "cell_type": "code", 179 | "execution_count": null, 180 | "metadata": {}, 181 | "outputs": [], 182 | "source": [ 183 | "# explore the new inputs\n", 184 | "XP.head()" 185 | ] 186 | }, 187 | { 188 | "cell_type": "markdown", 189 | "metadata": {}, 190 | "source": [ 191 | "# Modelling, Training and Test" 192 | ] 193 | }, 194 | { 195 | "cell_type": "code", 196 | "execution_count": null, 197 | "metadata": {}, 198 | "outputs": [], 199 | "source": [ 200 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 201 | "from sklearn.model_selection import train_test_split\n", 202 | "X_train, X_test, y_train, y_test = train_test_split(XP, y, test_size = 0.20)" 203 | ] 204 | }, 205 | { 206 | "cell_type": "code", 207 | "execution_count": null, 208 | "metadata": {}, 209 | "outputs": [], 210 | "source": [ 211 | "#import SVC and perform linear SVM on the training dataset\n", 212 | "from sklearn.svm import SVC\n", 213 | "svclassifier = SVC(kernel='linear')\n", 214 | "svclassifier.fit(X_train, y_train)" 215 | ] 216 | }, 217 | { 218 | "cell_type": "code", 219 | "execution_count": null, 220 | "metadata": {}, 221 | "outputs": [], 222 | "source": [ 223 | "#apply the trained SVM on the test dataset\n", 224 | "y_pred = svclassifier.predict(X_test)" 225 | ] 226 | }, 227 | { 228 | "cell_type": "code", 229 | "execution_count": null, 230 | "metadata": {}, 231 | "outputs": [], 232 | "source": [ 233 | "# output the predicted values\n", 234 | "y_pred" 235 | ] 236 | }, 237 | { 238 | "cell_type": "code", 239 | "execution_count": null, 240 | "metadata": {}, 241 | "outputs": [], 242 | "source": [ 243 | "# import relevant metrics and print the confusion matrix and classification report\n", 244 | "from sklearn.metrics import classification_report, confusion_matrix\n", 245 | "print(confusion_matrix(y_test,y_pred))\n", 246 | "print(classification_report(y_test,y_pred))" 247 | ] 248 | }, 249 | { 250 | "cell_type": "code", 251 | "execution_count": null, 252 | "metadata": {}, 253 | "outputs": [], 254 | "source": [] 255 | } 256 | ], 257 | "metadata": { 258 | "kernelspec": { 259 | "display_name": "Python 3", 260 | "language": "python", 261 | "name": "python3" 262 | }, 263 | "language_info": { 264 | "codemirror_mode": { 265 | "name": "ipython", 266 | "version": 3 267 | }, 268 | "file_extension": ".py", 269 | "mimetype": "text/x-python", 270 | "name": "python", 271 | "nbconvert_exporter": "python", 272 | "pygments_lexer": "ipython3", 273 | "version": "3.7.3" 274 | } 275 | }, 276 | "nbformat": 4, 277 | "nbformat_minor": 2 278 | } 279 | -------------------------------------------------------------------------------- /Notebooks/SVM/RBF SVM with PCA.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Perform PCA" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "# import PCA and perform it on the inputs in a loop from 1 principal component all the way to 62 principal components\n", 87 | "from sklearn.decomposition import PCA\n", 88 | "p=[]\n", 89 | "for c in range(1,62):\n", 90 | " pca=PCA(n_components=c)\n", 91 | " pcs=pca.fit_transform(X)\n", 92 | " p.append(pca.explained_variance_ratio_)\n", 93 | "p" 94 | ] 95 | }, 96 | { 97 | "cell_type": "code", 98 | "execution_count": null, 99 | "metadata": {}, 100 | "outputs": [], 101 | "source": [ 102 | "# put the sum of explained variance for diffetenct number of principal components\n", 103 | "sumc=[]\n", 104 | "a=0\n", 105 | "b=0\n", 106 | "for w in range(len(p)):\n", 107 | " a=p[w]\n", 108 | " b=np.sum(a)\n", 109 | " sumc.append(b)\n", 110 | " \n", 111 | "sumc" 112 | ] 113 | }, 114 | { 115 | "cell_type": "code", 116 | "execution_count": null, 117 | "metadata": {}, 118 | "outputs": [], 119 | "source": [ 120 | "# plot sum of the explained variances against the number of components (in my case %90 explained variance is achieved with 13 PCs)\n", 121 | "sump=[b*100 for b in sumc]\n", 122 | "xs=[d for d in range(1,62)]\n", 123 | "plt.plot(xs, sump, 'orange')\n", 124 | "plt.axis([0, 62, 0, 110])\n", 125 | "plt.axhline(y=90)\n", 126 | "plt.axvline(x=13)\n", 127 | "plt.show()" 128 | ] 129 | }, 130 | { 131 | "cell_type": "code", 132 | "execution_count": null, 133 | "metadata": {}, 134 | "outputs": [], 135 | "source": [ 136 | "# perform PCA on the inputs using the number of PCs that explain %90 of the variance in the dataset (in my case it was 13)\n", 137 | "pca13=PCA(n_components=13)\n", 138 | "pcs13=pca13.fit_transform(X)" 139 | ] 140 | }, 141 | { 142 | "cell_type": "code", 143 | "execution_count": null, 144 | "metadata": { 145 | "scrolled": true 146 | }, 147 | "outputs": [], 148 | "source": [ 149 | "# output the explained variance for each of the components\n", 150 | "ar=pca13.explained_variance_ratio_\n", 151 | "ar" 152 | ] 153 | }, 154 | { 155 | "cell_type": "code", 156 | "execution_count": null, 157 | "metadata": {}, 158 | "outputs": [], 159 | "source": [ 160 | "# output sum of the excplained variance\n", 161 | "sum=0\n", 162 | "for n in ar:\n", 163 | " sum+=n\n", 164 | "sum" 165 | ] 166 | }, 167 | { 168 | "cell_type": "code", 169 | "execution_count": null, 170 | "metadata": {}, 171 | "outputs": [], 172 | "source": [ 173 | "# define inputs as XP pandas data frame and add new headers\n", 174 | "XP=pd.DataFrame(data=pcs13,columns=['pc1','pc2','pc3','pc4','pc5','pc6','pc7','pc8','pc9','pc10','pc1','pc12','pc13'])" 175 | ] 176 | }, 177 | { 178 | "cell_type": "code", 179 | "execution_count": null, 180 | "metadata": {}, 181 | "outputs": [], 182 | "source": [ 183 | "# explore the new inputs\n", 184 | "XP.head()" 185 | ] 186 | }, 187 | { 188 | "cell_type": "markdown", 189 | "metadata": {}, 190 | "source": [ 191 | "# Modelling, Training and Test" 192 | ] 193 | }, 194 | { 195 | "cell_type": "code", 196 | "execution_count": null, 197 | "metadata": {}, 198 | "outputs": [], 199 | "source": [ 200 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 201 | "from sklearn.model_selection import train_test_split\n", 202 | "X_train, X_test, y_train, y_test = train_test_split(XP, y, test_size = 0.20)" 203 | ] 204 | }, 205 | { 206 | "cell_type": "code", 207 | "execution_count": null, 208 | "metadata": {}, 209 | "outputs": [], 210 | "source": [ 211 | "#import SVC and perform linear SVM on the training dataset\n", 212 | "from sklearn.svm import SVC\n", 213 | "svclassifier = SVC(kernel='rbf', C=1, gamma=0.1)\n", 214 | "svclassifier.fit(X_train, y_train)" 215 | ] 216 | }, 217 | { 218 | "cell_type": "code", 219 | "execution_count": null, 220 | "metadata": {}, 221 | "outputs": [], 222 | "source": [ 223 | "#apply the trained SVM on the test dataset\n", 224 | "y_pred = svclassifier.predict(X_test)" 225 | ] 226 | }, 227 | { 228 | "cell_type": "code", 229 | "execution_count": null, 230 | "metadata": {}, 231 | "outputs": [], 232 | "source": [ 233 | "# output the predicted values\n", 234 | "y_pred" 235 | ] 236 | }, 237 | { 238 | "cell_type": "code", 239 | "execution_count": null, 240 | "metadata": {}, 241 | "outputs": [], 242 | "source": [ 243 | "# import relevant metrics and print the confusion matrix and classification report\n", 244 | "from sklearn.metrics import classification_report, confusion_matrix\n", 245 | "print(confusion_matrix(y_test,y_pred))\n", 246 | "print(classification_report(y_test,y_pred))" 247 | ] 248 | }, 249 | { 250 | "cell_type": "code", 251 | "execution_count": null, 252 | "metadata": {}, 253 | "outputs": [], 254 | "source": [] 255 | } 256 | ], 257 | "metadata": { 258 | "kernelspec": { 259 | "display_name": "Python 3", 260 | "language": "python", 261 | "name": "python3" 262 | }, 263 | "language_info": { 264 | "codemirror_mode": { 265 | "name": "ipython", 266 | "version": 3 267 | }, 268 | "file_extension": ".py", 269 | "mimetype": "text/x-python", 270 | "name": "python", 271 | "nbconvert_exporter": "python", 272 | "pygments_lexer": "ipython3", 273 | "version": "3.7.3" 274 | } 275 | }, 276 | "nbformat": 4, 277 | "nbformat_minor": 2 278 | } 279 | -------------------------------------------------------------------------------- /Notebooks/SVM/Polynomial SVM with PCA.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Perform PCA" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "# import PCA and perform it on the inputs in a loop from 1 principal component all the way to 62 principal components\n", 87 | "from sklearn.decomposition import PCA\n", 88 | "p=[]\n", 89 | "for c in range(1,62):\n", 90 | " pca=PCA(n_components=c)\n", 91 | " pcs=pca.fit_transform(X)\n", 92 | " p.append(pca.explained_variance_ratio_)\n", 93 | "p" 94 | ] 95 | }, 96 | { 97 | "cell_type": "code", 98 | "execution_count": null, 99 | "metadata": {}, 100 | "outputs": [], 101 | "source": [ 102 | "# put the sum of explained variance for diffetenct number of principal components\n", 103 | "sumc=[]\n", 104 | "a=0\n", 105 | "b=0\n", 106 | "for w in range(len(p)):\n", 107 | " a=p[w]\n", 108 | " b=np.sum(a)\n", 109 | " sumc.append(b)\n", 110 | " \n", 111 | "sumc" 112 | ] 113 | }, 114 | { 115 | "cell_type": "code", 116 | "execution_count": null, 117 | "metadata": {}, 118 | "outputs": [], 119 | "source": [ 120 | "# plot sum of the explained variances against the number of components (in my case %90 explained variance is achieved with 13 PCs)\n", 121 | "sump=[b*100 for b in sumc]\n", 122 | "xs=[d for d in range(1,62)]\n", 123 | "plt.plot(xs, sump, 'orange')\n", 124 | "plt.axis([0, 62, 0, 110])\n", 125 | "plt.axhline(y=90)\n", 126 | "plt.axvline(x=13)\n", 127 | "plt.show()" 128 | ] 129 | }, 130 | { 131 | "cell_type": "code", 132 | "execution_count": null, 133 | "metadata": {}, 134 | "outputs": [], 135 | "source": [ 136 | "# perform PCA on the inputs using the number of PCs that explain %90 of the variance in the dataset (in my case it was 13)\n", 137 | "pca13=PCA(n_components=13)\n", 138 | "pcs13=pca13.fit_transform(X)" 139 | ] 140 | }, 141 | { 142 | "cell_type": "code", 143 | "execution_count": null, 144 | "metadata": { 145 | "scrolled": true 146 | }, 147 | "outputs": [], 148 | "source": [ 149 | "# output the explained variance for each of the components\n", 150 | "ar=pca13.explained_variance_ratio_\n", 151 | "ar" 152 | ] 153 | }, 154 | { 155 | "cell_type": "code", 156 | "execution_count": null, 157 | "metadata": {}, 158 | "outputs": [], 159 | "source": [ 160 | "# output sum of the excplained variance\n", 161 | "sum=0\n", 162 | "for n in ar:\n", 163 | " sum+=n\n", 164 | "sum" 165 | ] 166 | }, 167 | { 168 | "cell_type": "code", 169 | "execution_count": null, 170 | "metadata": {}, 171 | "outputs": [], 172 | "source": [ 173 | "# define inputs as XP pandas data frame and add new headers\n", 174 | "XP=pd.DataFrame(data=pcs13,columns=['pc1','pc2','pc3','pc4','pc5','pc6','pc7','pc8','pc9','pc10','pc1','pc12','pc13'])" 175 | ] 176 | }, 177 | { 178 | "cell_type": "code", 179 | "execution_count": null, 180 | "metadata": {}, 181 | "outputs": [], 182 | "source": [ 183 | "# explore the new inputs\n", 184 | "XP.head()" 185 | ] 186 | }, 187 | { 188 | "cell_type": "markdown", 189 | "metadata": {}, 190 | "source": [ 191 | "# Modelling, Training and Test" 192 | ] 193 | }, 194 | { 195 | "cell_type": "code", 196 | "execution_count": null, 197 | "metadata": {}, 198 | "outputs": [], 199 | "source": [ 200 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 201 | "from sklearn.model_selection import train_test_split\n", 202 | "X_train, X_test, y_train, y_test = train_test_split(XP, y, test_size = 0.20)" 203 | ] 204 | }, 205 | { 206 | "cell_type": "code", 207 | "execution_count": null, 208 | "metadata": {}, 209 | "outputs": [], 210 | "source": [ 211 | "#import SVC and perform Polynomial SVM on the training dataset\n", 212 | "from sklearn.svm import SVC\n", 213 | "svclassifier = SVC(kernel='poly', C=1, gamma=0.1, degree=3)\n", 214 | "svclassifier.fit(X_train, y_train)" 215 | ] 216 | }, 217 | { 218 | "cell_type": "code", 219 | "execution_count": null, 220 | "metadata": {}, 221 | "outputs": [], 222 | "source": [ 223 | "#apply the trained SVM on the test dataset\n", 224 | "y_pred = svclassifier.predict(X_test)" 225 | ] 226 | }, 227 | { 228 | "cell_type": "code", 229 | "execution_count": null, 230 | "metadata": {}, 231 | "outputs": [], 232 | "source": [ 233 | "# output the predicted values\n", 234 | "y_pred" 235 | ] 236 | }, 237 | { 238 | "cell_type": "code", 239 | "execution_count": null, 240 | "metadata": {}, 241 | "outputs": [], 242 | "source": [ 243 | "# import relevant metrics and print the confusion matrix and classification report\n", 244 | "from sklearn.metrics import classification_report, confusion_matrix\n", 245 | "print(confusion_matrix(y_test,y_pred))\n", 246 | "print(classification_report(y_test,y_pred))" 247 | ] 248 | }, 249 | { 250 | "cell_type": "code", 251 | "execution_count": null, 252 | "metadata": {}, 253 | "outputs": [], 254 | "source": [] 255 | } 256 | ], 257 | "metadata": { 258 | "kernelspec": { 259 | "display_name": "Python 3", 260 | "language": "python", 261 | "name": "python3" 262 | }, 263 | "language_info": { 264 | "codemirror_mode": { 265 | "name": "ipython", 266 | "version": 3 267 | }, 268 | "file_extension": ".py", 269 | "mimetype": "text/x-python", 270 | "name": "python", 271 | "nbconvert_exporter": "python", 272 | "pygments_lexer": "ipython3", 273 | "version": "3.7.3" 274 | } 275 | }, 276 | "nbformat": 4, 277 | "nbformat_minor": 2 278 | } 279 | -------------------------------------------------------------------------------- /Notebooks/SVM/Sigmoid SVM with PCA.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Perform PCA" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "# import PCA and perform it on the inputs in a loop from 1 principal component all the way to 62 principal components\n", 87 | "from sklearn.decomposition import PCA\n", 88 | "p=[]\n", 89 | "for c in range(1,62):\n", 90 | " pca=PCA(n_components=c)\n", 91 | " pcs=pca.fit_transform(X)\n", 92 | " p.append(pca.explained_variance_ratio_)\n", 93 | "p" 94 | ] 95 | }, 96 | { 97 | "cell_type": "code", 98 | "execution_count": null, 99 | "metadata": {}, 100 | "outputs": [], 101 | "source": [ 102 | "# put the sum of explained variance for diffetenct number of principal components\n", 103 | "sumc=[]\n", 104 | "a=0\n", 105 | "b=0\n", 106 | "for w in range(len(p)):\n", 107 | " a=p[w]\n", 108 | " b=np.sum(a)\n", 109 | " sumc.append(b)\n", 110 | " \n", 111 | "sumc" 112 | ] 113 | }, 114 | { 115 | "cell_type": "code", 116 | "execution_count": null, 117 | "metadata": {}, 118 | "outputs": [], 119 | "source": [ 120 | "# plot sum of the explained variances against the number of components (in my case %90 explained variance is achieved with 13 PCs)\n", 121 | "sump=[b*100 for b in sumc]\n", 122 | "xs=[d for d in range(1,62)]\n", 123 | "plt.plot(xs, sump, 'orange')\n", 124 | "plt.axis([0, 62, 0, 110])\n", 125 | "plt.axhline(y=90)\n", 126 | "plt.axvline(x=13)\n", 127 | "plt.show()" 128 | ] 129 | }, 130 | { 131 | "cell_type": "code", 132 | "execution_count": null, 133 | "metadata": {}, 134 | "outputs": [], 135 | "source": [ 136 | "# perform PCA on the inputs using the number of PCs that explain %90 of the variance in the dataset (in my case it was 13)\n", 137 | "pca13=PCA(n_components=13)\n", 138 | "pcs13=pca13.fit_transform(X)" 139 | ] 140 | }, 141 | { 142 | "cell_type": "code", 143 | "execution_count": null, 144 | "metadata": { 145 | "scrolled": true 146 | }, 147 | "outputs": [], 148 | "source": [ 149 | "# output the explained variance for each of the components\n", 150 | "ar=pca13.explained_variance_ratio_\n", 151 | "ar" 152 | ] 153 | }, 154 | { 155 | "cell_type": "code", 156 | "execution_count": null, 157 | "metadata": {}, 158 | "outputs": [], 159 | "source": [ 160 | "# output sum of the excplained variance\n", 161 | "sum=0\n", 162 | "for n in ar:\n", 163 | " sum+=n\n", 164 | "sum" 165 | ] 166 | }, 167 | { 168 | "cell_type": "code", 169 | "execution_count": null, 170 | "metadata": {}, 171 | "outputs": [], 172 | "source": [ 173 | "# define inputs as XP pandas data frame and add new headers\n", 174 | "XP=pd.DataFrame(data=pcs13,columns=['pc1','pc2','pc3','pc4','pc5','pc6','pc7','pc8','pc9','pc10','pc1','pc12','pc13'])" 175 | ] 176 | }, 177 | { 178 | "cell_type": "code", 179 | "execution_count": null, 180 | "metadata": {}, 181 | "outputs": [], 182 | "source": [ 183 | "# explore the new inputs\n", 184 | "XP.head()" 185 | ] 186 | }, 187 | { 188 | "cell_type": "markdown", 189 | "metadata": {}, 190 | "source": [ 191 | "# Modelling, Training and Test" 192 | ] 193 | }, 194 | { 195 | "cell_type": "code", 196 | "execution_count": null, 197 | "metadata": {}, 198 | "outputs": [], 199 | "source": [ 200 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 201 | "from sklearn.model_selection import train_test_split\n", 202 | "X_train, X_test, y_train, y_test = train_test_split(XP, y, test_size = 0.20)" 203 | ] 204 | }, 205 | { 206 | "cell_type": "code", 207 | "execution_count": null, 208 | "metadata": {}, 209 | "outputs": [], 210 | "source": [ 211 | "#import SVC and perform linear SVM on the training dataset\n", 212 | "from sklearn.svm import SVC\n", 213 | "svclassifier = SVC(kernel='sigmoid', C=1, gamma=0.1)\n", 214 | "svclassifier.fit(X_train, y_train)" 215 | ] 216 | }, 217 | { 218 | "cell_type": "code", 219 | "execution_count": null, 220 | "metadata": {}, 221 | "outputs": [], 222 | "source": [ 223 | "#apply the trained SVM on the test dataset\n", 224 | "mean_accuracy=svclassifier.score(X_test, y_train)\n", 225 | "y_pred = svclassifier.predict(X_test)\n", 226 | "print(mean_accuracy)" 227 | ] 228 | }, 229 | { 230 | "cell_type": "code", 231 | "execution_count": null, 232 | "metadata": {}, 233 | "outputs": [], 234 | "source": [ 235 | "# output the predicted values\n", 236 | "y_pred" 237 | ] 238 | }, 239 | { 240 | "cell_type": "code", 241 | "execution_count": null, 242 | "metadata": {}, 243 | "outputs": [], 244 | "source": [ 245 | "# import relevant metrics and print the confusion matrix and classification report\n", 246 | "from sklearn.metrics import classification_report, confusion_matrix\n", 247 | "print(confusion_matrix(y_test,y_pred))\n", 248 | "print(classification_report(y_test,y_pred))" 249 | ] 250 | }, 251 | { 252 | "cell_type": "code", 253 | "execution_count": null, 254 | "metadata": {}, 255 | "outputs": [], 256 | "source": [] 257 | } 258 | ], 259 | "metadata": { 260 | "kernelspec": { 261 | "display_name": "Python 3", 262 | "language": "python", 263 | "name": "python3" 264 | }, 265 | "language_info": { 266 | "codemirror_mode": { 267 | "name": "ipython", 268 | "version": 3 269 | }, 270 | "file_extension": ".py", 271 | "mimetype": "text/x-python", 272 | "name": "python", 273 | "nbconvert_exporter": "python", 274 | "pygments_lexer": "ipython3", 275 | "version": "3.7.3" 276 | } 277 | }, 278 | "nbformat": 4, 279 | "nbformat_minor": 2 280 | } 281 | -------------------------------------------------------------------------------- /Notebooks/K Nearest Neighbors/KNN with PCA.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Perform PCA" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "# import PCA and perform it on the inputs in a loop from 1 principal component all the way to 62 principal components\n", 87 | "from sklearn.decomposition import PCA\n", 88 | "p=[]\n", 89 | "for c in range(1,62):\n", 90 | " pca=PCA(n_components=c)\n", 91 | " pcs=pca.fit_transform(X)\n", 92 | " p.append(pca.explained_variance_ratio_)\n", 93 | "p" 94 | ] 95 | }, 96 | { 97 | "cell_type": "code", 98 | "execution_count": null, 99 | "metadata": {}, 100 | "outputs": [], 101 | "source": [ 102 | "# put the sum of explained variance for diffetenct number of principal components\n", 103 | "sumc=[]\n", 104 | "a=0\n", 105 | "b=0\n", 106 | "for w in range(len(p)):\n", 107 | " a=p[w]\n", 108 | " b=np.sum(a)\n", 109 | " sumc.append(b)\n", 110 | " \n", 111 | "sumc" 112 | ] 113 | }, 114 | { 115 | "cell_type": "code", 116 | "execution_count": null, 117 | "metadata": {}, 118 | "outputs": [], 119 | "source": [ 120 | "# plot sum of the explained variances against the number of components (in my case %90 explained variance is achieved with 13 PCs)\n", 121 | "sump=[b*100 for b in sumc]\n", 122 | "xs=[d for d in range(1,62)]\n", 123 | "plt.plot(xs, sump, 'orange')\n", 124 | "plt.axis([0, 62, 0, 110])\n", 125 | "plt.axhline(y=90)\n", 126 | "plt.axvline(x=13)\n", 127 | "plt.show()" 128 | ] 129 | }, 130 | { 131 | "cell_type": "code", 132 | "execution_count": null, 133 | "metadata": {}, 134 | "outputs": [], 135 | "source": [ 136 | "# perform PCA on the inputs using the number of PCs that explain %90 of the variance in the dataset (in my case it was 13)\n", 137 | "pca13=PCA(n_components=13)\n", 138 | "pcs13=pca13.fit_transform(X)" 139 | ] 140 | }, 141 | { 142 | "cell_type": "code", 143 | "execution_count": null, 144 | "metadata": { 145 | "scrolled": true 146 | }, 147 | "outputs": [], 148 | "source": [ 149 | "# output the explained variance for each of the components\n", 150 | "ar=pca13.explained_variance_ratio_\n", 151 | "ar" 152 | ] 153 | }, 154 | { 155 | "cell_type": "code", 156 | "execution_count": null, 157 | "metadata": {}, 158 | "outputs": [], 159 | "source": [ 160 | "# output sum of the excplained variance\n", 161 | "sum=0\n", 162 | "for n in ar:\n", 163 | " sum+=n\n", 164 | "sum" 165 | ] 166 | }, 167 | { 168 | "cell_type": "code", 169 | "execution_count": null, 170 | "metadata": {}, 171 | "outputs": [], 172 | "source": [ 173 | "# define inputs as XP pandas data frame and add new headers\n", 174 | "XP=pd.DataFrame(data=pcs13,columns=['pc1','pc2','pc3','pc4','pc5','pc6','pc7','pc8','pc9','pc10','pc1','pc12','pc13'])" 175 | ] 176 | }, 177 | { 178 | "cell_type": "code", 179 | "execution_count": null, 180 | "metadata": {}, 181 | "outputs": [], 182 | "source": [ 183 | "# explore the new inputs\n", 184 | "XP.head()" 185 | ] 186 | }, 187 | { 188 | "cell_type": "markdown", 189 | "metadata": {}, 190 | "source": [ 191 | "# Modelling, Training and Test" 192 | ] 193 | }, 194 | { 195 | "cell_type": "code", 196 | "execution_count": null, 197 | "metadata": {}, 198 | "outputs": [], 199 | "source": [ 200 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 201 | "from sklearn.model_selection import train_test_split\n", 202 | "X_train, X_test, y_train, y_test = train_test_split(XP, y, test_size = 0.20)" 203 | ] 204 | }, 205 | { 206 | "cell_type": "code", 207 | "execution_count": null, 208 | "metadata": {}, 209 | "outputs": [], 210 | "source": [ 211 | "#import KNeighborsClassifier and KNN on the training dataset\n", 212 | "from sklearn.neighbors import KNeighborsClassifier\n", 213 | "estimator = KNeighborsClassifier(n_neighbors=3)\n", 214 | "estimator.fit(X_train, y_train)" 215 | ] 216 | }, 217 | { 218 | "cell_type": "code", 219 | "execution_count": null, 220 | "metadata": {}, 221 | "outputs": [], 222 | "source": [ 223 | "#apply the trained SVM on the test dataset\n", 224 | "mean_accuracy=estimator.score(X_test, y_train)\n", 225 | "y_pred = estimator.predict(X_test)\n", 226 | "print(mean_accuracy)" 227 | ] 228 | }, 229 | { 230 | "cell_type": "code", 231 | "execution_count": null, 232 | "metadata": {}, 233 | "outputs": [], 234 | "source": [ 235 | "# output the predicted values\n", 236 | "y_pred" 237 | ] 238 | }, 239 | { 240 | "cell_type": "code", 241 | "execution_count": null, 242 | "metadata": {}, 243 | "outputs": [], 244 | "source": [ 245 | "# import relevant metrics and print the confusion matrix and classification report\n", 246 | "from sklearn.metrics import classification_report, confusion_matrix\n", 247 | "print(confusion_matrix(y_test,y_pred))\n", 248 | "print(classification_report(y_test,y_pred))" 249 | ] 250 | }, 251 | { 252 | "cell_type": "code", 253 | "execution_count": null, 254 | "metadata": {}, 255 | "outputs": [], 256 | "source": [] 257 | } 258 | ], 259 | "metadata": { 260 | "kernelspec": { 261 | "display_name": "Python 3", 262 | "language": "python", 263 | "name": "python3" 264 | }, 265 | "language_info": { 266 | "codemirror_mode": { 267 | "name": "ipython", 268 | "version": 3 269 | }, 270 | "file_extension": ".py", 271 | "mimetype": "text/x-python", 272 | "name": "python", 273 | "nbconvert_exporter": "python", 274 | "pygments_lexer": "ipython3", 275 | "version": "3.7.3" 276 | } 277 | }, 278 | "nbformat": 4, 279 | "nbformat_minor": 2 280 | } 281 | -------------------------------------------------------------------------------- /Notebooks/Gaussian Naive Bayes/Gaussian Naive Bayes with PCA.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Perform PCA" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "# import PCA and perform it on the inputs in a loop from 1 principal component all the way to 62 principal components\n", 87 | "from sklearn.decomposition import PCA\n", 88 | "p=[]\n", 89 | "for c in range(1,62):\n", 90 | " pca=PCA(n_components=c)\n", 91 | " pcs=pca.fit_transform(X)\n", 92 | " p.append(pca.explained_variance_ratio_)\n", 93 | "p" 94 | ] 95 | }, 96 | { 97 | "cell_type": "code", 98 | "execution_count": null, 99 | "metadata": {}, 100 | "outputs": [], 101 | "source": [ 102 | "# put the sum of explained variance for diffetenct number of principal components\n", 103 | "sumc=[]\n", 104 | "a=0\n", 105 | "b=0\n", 106 | "for w in range(len(p)):\n", 107 | " a=p[w]\n", 108 | " b=np.sum(a)\n", 109 | " sumc.append(b)\n", 110 | " \n", 111 | "sumc" 112 | ] 113 | }, 114 | { 115 | "cell_type": "code", 116 | "execution_count": null, 117 | "metadata": {}, 118 | "outputs": [], 119 | "source": [ 120 | "# plot sum of the explained variances against the number of components (in my case %90 explained variance is achieved with 13 PCs)\n", 121 | "sump=[b*100 for b in sumc]\n", 122 | "xs=[d for d in range(1,62)]\n", 123 | "plt.plot(xs, sump, 'orange')\n", 124 | "plt.axis([0, 62, 0, 110])\n", 125 | "plt.axhline(y=90)\n", 126 | "plt.axvline(x=13)\n", 127 | "plt.show()" 128 | ] 129 | }, 130 | { 131 | "cell_type": "code", 132 | "execution_count": null, 133 | "metadata": {}, 134 | "outputs": [], 135 | "source": [ 136 | "# perform PCA on the inputs using the number of PCs that explain %90 of the variance in the dataset (in my case it was 13)\n", 137 | "pca13=PCA(n_components=13)\n", 138 | "pcs13=pca13.fit_transform(X)" 139 | ] 140 | }, 141 | { 142 | "cell_type": "code", 143 | "execution_count": null, 144 | "metadata": { 145 | "scrolled": true 146 | }, 147 | "outputs": [], 148 | "source": [ 149 | "# output the explained variance for each of the components\n", 150 | "ar=pca13.explained_variance_ratio_\n", 151 | "ar" 152 | ] 153 | }, 154 | { 155 | "cell_type": "code", 156 | "execution_count": null, 157 | "metadata": {}, 158 | "outputs": [], 159 | "source": [ 160 | "# output sum of the excplained variance\n", 161 | "sum=0\n", 162 | "for n in ar:\n", 163 | " sum+=n\n", 164 | "sum" 165 | ] 166 | }, 167 | { 168 | "cell_type": "code", 169 | "execution_count": null, 170 | "metadata": {}, 171 | "outputs": [], 172 | "source": [ 173 | "# define inputs as XP pandas data frame and add new headers\n", 174 | "XP=pd.DataFrame(data=pcs13,columns=['pc1','pc2','pc3','pc4','pc5','pc6','pc7','pc8','pc9','pc10','pc1','pc12','pc13'])" 175 | ] 176 | }, 177 | { 178 | "cell_type": "code", 179 | "execution_count": null, 180 | "metadata": {}, 181 | "outputs": [], 182 | "source": [ 183 | "# explore the new inputs\n", 184 | "XP.head()" 185 | ] 186 | }, 187 | { 188 | "cell_type": "markdown", 189 | "metadata": {}, 190 | "source": [ 191 | "# Modelling, Training and Test" 192 | ] 193 | }, 194 | { 195 | "cell_type": "code", 196 | "execution_count": null, 197 | "metadata": {}, 198 | "outputs": [], 199 | "source": [ 200 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 201 | "from sklearn.model_selection import train_test_split\n", 202 | "X_train, X_test, y_train, y_test = train_test_split(XP, y, test_size = 0.20)" 203 | ] 204 | }, 205 | { 206 | "cell_type": "code", 207 | "execution_count": null, 208 | "metadata": {}, 209 | "outputs": [], 210 | "source": [ 211 | "#import GaussianNB and perform Gaussian Naive Bayes on the training dataset\n", 212 | "from sklearn.naive_bayes import GaussianNB\n", 213 | "estimator = GaussianNB()\n", 214 | "estimator.fit(X_train, y_train)" 215 | ] 216 | }, 217 | { 218 | "cell_type": "code", 219 | "execution_count": null, 220 | "metadata": {}, 221 | "outputs": [], 222 | "source": [ 223 | "#apply the trained SVM on the test dataset\n", 224 | "mean_accuracy=estimator.score(X_test, y_train)\n", 225 | "y_pred = estimator.predict(X_test)\n", 226 | "print(mean_accuracy)" 227 | ] 228 | }, 229 | { 230 | "cell_type": "code", 231 | "execution_count": null, 232 | "metadata": {}, 233 | "outputs": [], 234 | "source": [ 235 | "# output the predicted values\n", 236 | "y_pred" 237 | ] 238 | }, 239 | { 240 | "cell_type": "code", 241 | "execution_count": null, 242 | "metadata": {}, 243 | "outputs": [], 244 | "source": [ 245 | "# import relevant metrics and print the confusion matrix and classification report\n", 246 | "from sklearn.metrics import classification_report, confusion_matrix\n", 247 | "print(confusion_matrix(y_test,y_pred))\n", 248 | "print(classification_report(y_test,y_pred))" 249 | ] 250 | }, 251 | { 252 | "cell_type": "code", 253 | "execution_count": null, 254 | "metadata": {}, 255 | "outputs": [], 256 | "source": [] 257 | } 258 | ], 259 | "metadata": { 260 | "kernelspec": { 261 | "display_name": "Python 3", 262 | "language": "python", 263 | "name": "python3" 264 | }, 265 | "language_info": { 266 | "codemirror_mode": { 267 | "name": "ipython", 268 | "version": 3 269 | }, 270 | "file_extension": ".py", 271 | "mimetype": "text/x-python", 272 | "name": "python", 273 | "nbconvert_exporter": "python", 274 | "pygments_lexer": "ipython3", 275 | "version": "3.7.3" 276 | } 277 | }, 278 | "nbformat": 4, 279 | "nbformat_minor": 2 280 | } 281 | -------------------------------------------------------------------------------- /Notebooks/Decision Tree/Decision Tree with PCA.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Perform PCA" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "# import PCA and perform it on the inputs in a loop from 1 principal component all the way to 62 principal components\n", 87 | "from sklearn.decomposition import PCA\n", 88 | "p=[]\n", 89 | "for c in range(1,62):\n", 90 | " pca=PCA(n_components=c)\n", 91 | " pcs=pca.fit_transform(X)\n", 92 | " p.append(pca.explained_variance_ratio_)\n", 93 | "p" 94 | ] 95 | }, 96 | { 97 | "cell_type": "code", 98 | "execution_count": null, 99 | "metadata": {}, 100 | "outputs": [], 101 | "source": [ 102 | "# put the sum of explained variance for diffetenct number of principal components\n", 103 | "sumc=[]\n", 104 | "a=0\n", 105 | "b=0\n", 106 | "for w in range(len(p)):\n", 107 | " a=p[w]\n", 108 | " b=np.sum(a)\n", 109 | " sumc.append(b)\n", 110 | " \n", 111 | "sumc" 112 | ] 113 | }, 114 | { 115 | "cell_type": "code", 116 | "execution_count": null, 117 | "metadata": {}, 118 | "outputs": [], 119 | "source": [ 120 | "# plot sum of the explained variances against the number of components (in my case %90 explained variance is achieved with 13 PCs)\n", 121 | "sump=[b*100 for b in sumc]\n", 122 | "xs=[d for d in range(1,62)]\n", 123 | "plt.plot(xs, sump, 'orange')\n", 124 | "plt.axis([0, 62, 0, 110])\n", 125 | "plt.axhline(y=90)\n", 126 | "plt.axvline(x=13)\n", 127 | "plt.show()" 128 | ] 129 | }, 130 | { 131 | "cell_type": "code", 132 | "execution_count": null, 133 | "metadata": {}, 134 | "outputs": [], 135 | "source": [ 136 | "# perform PCA on the inputs using the number of PCs that explain %90 of the variance in the dataset (in my case it was 13)\n", 137 | "pca13=PCA(n_components=13)\n", 138 | "pcs13=pca13.fit_transform(X)" 139 | ] 140 | }, 141 | { 142 | "cell_type": "code", 143 | "execution_count": null, 144 | "metadata": { 145 | "scrolled": true 146 | }, 147 | "outputs": [], 148 | "source": [ 149 | "# output the explained variance for each of the components\n", 150 | "ar=pca13.explained_variance_ratio_\n", 151 | "ar" 152 | ] 153 | }, 154 | { 155 | "cell_type": "code", 156 | "execution_count": null, 157 | "metadata": {}, 158 | "outputs": [], 159 | "source": [ 160 | "# output sum of the excplained variance\n", 161 | "sum=0\n", 162 | "for n in ar:\n", 163 | " sum+=n\n", 164 | "sum" 165 | ] 166 | }, 167 | { 168 | "cell_type": "code", 169 | "execution_count": null, 170 | "metadata": {}, 171 | "outputs": [], 172 | "source": [ 173 | "# define inputs as XP pandas data frame and add new headers\n", 174 | "XP=pd.DataFrame(data=pcs13,columns=['pc1','pc2','pc3','pc4','pc5','pc6','pc7','pc8','pc9','pc10','pc1','pc12','pc13'])" 175 | ] 176 | }, 177 | { 178 | "cell_type": "code", 179 | "execution_count": null, 180 | "metadata": {}, 181 | "outputs": [], 182 | "source": [ 183 | "# explore the new inputs\n", 184 | "XP.head()" 185 | ] 186 | }, 187 | { 188 | "cell_type": "markdown", 189 | "metadata": {}, 190 | "source": [ 191 | "# Modelling, Training and Test" 192 | ] 193 | }, 194 | { 195 | "cell_type": "code", 196 | "execution_count": null, 197 | "metadata": {}, 198 | "outputs": [], 199 | "source": [ 200 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 201 | "from sklearn.model_selection import train_test_split\n", 202 | "X_train, X_test, y_train, y_test = train_test_split(XP, y, test_size = 0.20)" 203 | ] 204 | }, 205 | { 206 | "cell_type": "code", 207 | "execution_count": null, 208 | "metadata": {}, 209 | "outputs": [], 210 | "source": [ 211 | "#import DecisionTreeClassifier and start the training\n", 212 | "from sklearn.tree import DecisionTreeClassifier\n", 213 | "estimator = RandomForestClassifier(n_estimators=100, max_depth=2, random_state=0)\n", 214 | "estimator.fit(X_train, y_train)" 215 | ] 216 | }, 217 | { 218 | "cell_type": "code", 219 | "execution_count": null, 220 | "metadata": {}, 221 | "outputs": [], 222 | "source": [ 223 | "#apply the trained estimator on the test dataset\n", 224 | "mean_accuracy=estimator.score(X_test, y_test)\n", 225 | "y_pred = estimator.predict(X_test)\n", 226 | "print(mean_accuracy)" 227 | ] 228 | }, 229 | { 230 | "cell_type": "code", 231 | "execution_count": null, 232 | "metadata": {}, 233 | "outputs": [], 234 | "source": [ 235 | "# output the predicted values\n", 236 | "y_pred" 237 | ] 238 | }, 239 | { 240 | "cell_type": "code", 241 | "execution_count": null, 242 | "metadata": {}, 243 | "outputs": [], 244 | "source": [ 245 | "# import relevant metrics and print the confusion matrix and classification report\n", 246 | "from sklearn.metrics import classification_report, confusion_matrix\n", 247 | "print(confusion_matrix(y_test,y_pred))\n", 248 | "print(classification_report(y_test,y_pred))" 249 | ] 250 | }, 251 | { 252 | "cell_type": "code", 253 | "execution_count": null, 254 | "metadata": {}, 255 | "outputs": [], 256 | "source": [] 257 | } 258 | ], 259 | "metadata": { 260 | "kernelspec": { 261 | "display_name": "Python 3", 262 | "language": "python", 263 | "name": "python3" 264 | }, 265 | "language_info": { 266 | "codemirror_mode": { 267 | "name": "ipython", 268 | "version": 3 269 | }, 270 | "file_extension": ".py", 271 | "mimetype": "text/x-python", 272 | "name": "python", 273 | "nbconvert_exporter": "python", 274 | "pygments_lexer": "ipython3", 275 | "version": "3.7.3" 276 | } 277 | }, 278 | "nbformat": 4, 279 | "nbformat_minor": 2 280 | } 281 | -------------------------------------------------------------------------------- /Notebooks/Random Forest/Random Forest with PCA.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Import Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": null, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "# Import necessary libraries to get started\n", 17 | "import pandas as pd\n", 18 | "import numpy as np\n", 19 | "import matplotlib.pyplot as plt\n", 20 | "%matplotlib inline\n", 21 | "import seaborn as sns\n", 22 | "sns.set()" 23 | ] 24 | }, 25 | { 26 | "cell_type": "markdown", 27 | "metadata": {}, 28 | "source": [ 29 | "# Data Preprocessing" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "# Import the dataset\n", 39 | "data = pd.read_csv(\"eeg_data.csv\")" 40 | ] 41 | }, 42 | { 43 | "cell_type": "code", 44 | "execution_count": null, 45 | "metadata": {}, 46 | "outputs": [], 47 | "source": [ 48 | "# data exploration\n", 49 | "data.head()" 50 | ] 51 | }, 52 | { 53 | "cell_type": "code", 54 | "execution_count": null, 55 | "metadata": {}, 56 | "outputs": [], 57 | "source": [ 58 | "# define inputs as X and outputs as y\n", 59 | "X = data.drop('63', axis=1)\n", 60 | "y = data['63']" 61 | ] 62 | }, 63 | { 64 | "cell_type": "code", 65 | "execution_count": null, 66 | "metadata": {}, 67 | "outputs": [], 68 | "source": [ 69 | "# verify that outputs are selected correctly\n", 70 | "y.head()" 71 | ] 72 | }, 73 | { 74 | "cell_type": "markdown", 75 | "metadata": {}, 76 | "source": [ 77 | "# Perform PCA" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": null, 83 | "metadata": {}, 84 | "outputs": [], 85 | "source": [ 86 | "# import PCA and perform it on the inputs in a loop from 1 principal component all the way to 62 principal components\n", 87 | "from sklearn.decomposition import PCA\n", 88 | "p=[]\n", 89 | "for c in range(1,62):\n", 90 | " pca=PCA(n_components=c)\n", 91 | " pcs=pca.fit_transform(X)\n", 92 | " p.append(pca.explained_variance_ratio_)\n", 93 | "p" 94 | ] 95 | }, 96 | { 97 | "cell_type": "code", 98 | "execution_count": null, 99 | "metadata": {}, 100 | "outputs": [], 101 | "source": [ 102 | "# put the sum of explained variance for diffetenct number of principal components\n", 103 | "sumc=[]\n", 104 | "a=0\n", 105 | "b=0\n", 106 | "for w in range(len(p)):\n", 107 | " a=p[w]\n", 108 | " b=np.sum(a)\n", 109 | " sumc.append(b)\n", 110 | " \n", 111 | "sumc" 112 | ] 113 | }, 114 | { 115 | "cell_type": "code", 116 | "execution_count": null, 117 | "metadata": {}, 118 | "outputs": [], 119 | "source": [ 120 | "# plot sum of the explained variances against the number of components (in my case %90 explained variance is achieved with 13 PCs)\n", 121 | "sump=[b*100 for b in sumc]\n", 122 | "xs=[d for d in range(1,62)]\n", 123 | "plt.plot(xs, sump, 'orange')\n", 124 | "plt.axis([0, 62, 0, 110])\n", 125 | "plt.axhline(y=90)\n", 126 | "plt.axvline(x=13)\n", 127 | "plt.show()" 128 | ] 129 | }, 130 | { 131 | "cell_type": "code", 132 | "execution_count": null, 133 | "metadata": {}, 134 | "outputs": [], 135 | "source": [ 136 | "# perform PCA on the inputs using the number of PCs that explain %90 of the variance in the dataset (in my case it was 13)\n", 137 | "pca13=PCA(n_components=13)\n", 138 | "pcs13=pca13.fit_transform(X)" 139 | ] 140 | }, 141 | { 142 | "cell_type": "code", 143 | "execution_count": null, 144 | "metadata": { 145 | "scrolled": true 146 | }, 147 | "outputs": [], 148 | "source": [ 149 | "# output the explained variance for each of the components\n", 150 | "ar=pca13.explained_variance_ratio_\n", 151 | "ar" 152 | ] 153 | }, 154 | { 155 | "cell_type": "code", 156 | "execution_count": null, 157 | "metadata": {}, 158 | "outputs": [], 159 | "source": [ 160 | "# output sum of the excplained variance\n", 161 | "sum=0\n", 162 | "for n in ar:\n", 163 | " sum+=n\n", 164 | "sum" 165 | ] 166 | }, 167 | { 168 | "cell_type": "code", 169 | "execution_count": null, 170 | "metadata": {}, 171 | "outputs": [], 172 | "source": [ 173 | "# define inputs as XP pandas data frame and add new headers\n", 174 | "XP=pd.DataFrame(data=pcs13,columns=['pc1','pc2','pc3','pc4','pc5','pc6','pc7','pc8','pc9','pc10','pc1','pc12','pc13'])" 175 | ] 176 | }, 177 | { 178 | "cell_type": "code", 179 | "execution_count": null, 180 | "metadata": {}, 181 | "outputs": [], 182 | "source": [ 183 | "# explore the new inputs\n", 184 | "XP.head()" 185 | ] 186 | }, 187 | { 188 | "cell_type": "markdown", 189 | "metadata": {}, 190 | "source": [ 191 | "# Modelling, Training and Test" 192 | ] 193 | }, 194 | { 195 | "cell_type": "code", 196 | "execution_count": null, 197 | "metadata": {}, 198 | "outputs": [], 199 | "source": [ 200 | "#import sklearn's model selection and split the data set into %80 training and %20 test\n", 201 | "from sklearn.model_selection import train_test_split\n", 202 | "X_train, X_test, y_train, y_test = train_test_split(XP, y, test_size = 0.20)" 203 | ] 204 | }, 205 | { 206 | "cell_type": "code", 207 | "execution_count": null, 208 | "metadata": {}, 209 | "outputs": [], 210 | "source": [ 211 | "#import RandomForestClassifier and RFC on the training dataset\n", 212 | "from sklearn.ensemble import RandomForestClassifier\n", 213 | "estimator = RandomForestClassifier(n_estimators=100, max_depth=2, random_state=0)\n", 214 | "estimator.fit(X_train, y_train)" 215 | ] 216 | }, 217 | { 218 | "cell_type": "code", 219 | "execution_count": null, 220 | "metadata": {}, 221 | "outputs": [], 222 | "source": [ 223 | "#apply the trained estimator on the test dataset\n", 224 | "mean_accuracy=estimator.score(X_test, y_test)\n", 225 | "y_pred = estimator.predict(X_test)\n", 226 | "print(mean_accuracy)\n", 227 | "print(estimator.feature_importances_)" 228 | ] 229 | }, 230 | { 231 | "cell_type": "code", 232 | "execution_count": null, 233 | "metadata": {}, 234 | "outputs": [], 235 | "source": [ 236 | "# output the predicted values\n", 237 | "y_pred" 238 | ] 239 | }, 240 | { 241 | "cell_type": "code", 242 | "execution_count": null, 243 | "metadata": {}, 244 | "outputs": [], 245 | "source": [ 246 | "# import relevant metrics and print the confusion matrix and classification report\n", 247 | "from sklearn.metrics import classification_report, confusion_matrix\n", 248 | "print(confusion_matrix(y_test,y_pred))\n", 249 | "print(classification_report(y_test,y_pred))" 250 | ] 251 | }, 252 | { 253 | "cell_type": "code", 254 | "execution_count": null, 255 | "metadata": {}, 256 | "outputs": [], 257 | "source": [] 258 | } 259 | ], 260 | "metadata": { 261 | "kernelspec": { 262 | "display_name": "Python 3", 263 | "language": "python", 264 | "name": "python3" 265 | }, 266 | "language_info": { 267 | "codemirror_mode": { 268 | "name": "ipython", 269 | "version": 3 270 | }, 271 | "file_extension": ".py", 272 | "mimetype": "text/x-python", 273 | "name": "python", 274 | "nbconvert_exporter": "python", 275 | "pygments_lexer": "ipython3", 276 | "version": "3.7.3" 277 | } 278 | }, 279 | "nbformat": 4, 280 | "nbformat_minor": 2 281 | } 282 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | 635 | Copyright (C) 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | --------------------------------------------------------------------------------