diff --git a/Experiments.ipynb b/Experiments.ipynb new file mode 100644 index 0000000..e81ee88 --- /dev/null +++ b/Experiments.ipynb @@ -0,0 +1,336 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 8, + "id": "initial_id", + "metadata": { + "jupyter": { + "is_executing": true + } + }, + "outputs": [], + "source": [ + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "id": "67503952-9074-4cdb-9d7e-d9142f7c319c", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
agesexcptrestbpscholfbsrestecgthalachexangoldpeakslopecathalgoal
063111452331215002.330.06.00
167141602860210811.523.03.02
267141202290212912.622.07.01
337131302500018703.530.03.00
441021302040217201.410.03.00
\n", + "
" + ], + "text/plain": [ + " age sex cp trestbps chol fbs restecg thalach exang oldpeak slope \\\n", + "0 63 1 1 145 233 1 2 150 0 2.3 3 \n", + "1 67 1 4 160 286 0 2 108 1 1.5 2 \n", + "2 67 1 4 120 229 0 2 129 1 2.6 2 \n", + "3 37 1 3 130 250 0 0 187 0 3.5 3 \n", + "4 41 0 2 130 204 0 2 172 0 1.4 1 \n", + "\n", + " ca thal goal \n", + "0 0.0 6.0 0 \n", + "1 3.0 3.0 2 \n", + "2 2.0 7.0 1 \n", + "3 0.0 3.0 0 \n", + "4 0.0 3.0 0 " + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = pd.read_csv('./data/dataset_cleaned.csv')\n", + "df.dropna(inplace=True)\n", + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "id": "8fa945ef-34d4-4e4c-a1cd-f1e1e6da79e7", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0]], dtype=int64)" + ] + }, + "execution_count": 60, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# extract all columns except 'goal' --> X\n", + "X = df.loc[:, df.columns != 'goal']\n", + "# extract only the column 'goal' --> y\n", + "y = df.loc[:, 'goal']\n", + "\n", + "# add new axis to y, new shape: (n, 1)\n", + "y = y.to_numpy()\n", + "y = y.reshape((len(y),1))\n", + "\n", + "# binarize y\n", + "y[y>0] = 1" + ] + }, + { + "cell_type": "code", + "execution_count": 91, + "id": "2bbee865-c000-43da-84d9-ce7e04874110", + "metadata": {}, + "outputs": [], + "source": [ + "def get_model(n_features):\n", + " model = tf.keras.models.Sequential([\n", + " tf.keras.layers.InputLayer(shape=(n_features,)),\n", + " tf.keras.layers.Dense(30, activation='relu'),\n", + " tf.keras.layers.Dense(30, activation='relu'),\n", + " tf.keras.layers.Dense(30, activation='relu'),\n", + " tf.keras.layers.Dense(1, activation='sigmoid')\n", + " ], name='test')\n", + " model.compile(optimizer=tf.keras.optimizers.Adam(), \n", + " loss=tf.keras.losses.BinaryCrossentropy())\n", + " return model" + ] + }, + { + "cell_type": "code", + "execution_count": 97, + "id": "38eb4f87-ca3c-4ecf-a8ca-29422822d933", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Training fold 0 for 5 epochs\n", + "Train samples:\t237\n", + "Test samples:\t60\n", + "Accuracy of fold 0: 0.6166666666666667\n", + "Training fold 1 for 5 epochs\n", + "Train samples:\t237\n", + "Test samples:\t60\n", + "Accuracy of fold 1: 0.75\n", + "Training fold 2 for 5 epochs\n", + "Train samples:\t238\n", + "Test samples:\t59\n", + "Accuracy of fold 2: 0.6949152542372882\n", + "Training fold 3 for 5 epochs\n", + "Train samples:\t238\n", + "Test samples:\t59\n", + "Accuracy of fold 3: 0.7457627118644068\n", + "Training fold 4 for 5 epochs\n", + "Train samples:\t238\n", + "Test samples:\t59\n", + "Accuracy of fold 4: 0.6610169491525424\n", + "Avg accuracy 0.6936723163841808\n" + ] + } + ], + "source": [ + "from sklearn.model_selection import KFold\n", + "from sklearn import decomposition\n", + "import tensorflow as tf\n", + "\n", + "# number of components extracted from the pca\n", + "n_features = 5 \n", + "\n", + "epochs = 5\n", + "\n", + "# used to split the dataset into k folds\n", + "kf = KFold(n_splits=5)\n", + "\n", + "accuracies = []\n", + "for i, (train_idx, test_idx) in enumerate(kf.split(X)):\n", + " print(f'Training fold {i} for {epochs} epochs')\n", + "\n", + " # extract train and test data from the cleaned dataset\n", + " X_train, X_test = X.iloc[train_idx], X.iloc[test_idx]\n", + " y_train, y_test = y[train_idx], y[test_idx]\n", + "\n", + " print(f'Train samples:\\t{len(X_train)}')\n", + " print(f'Test samples:\\t{len(X_test)}')\n", + "\n", + " # do pca based on the train data of the given fold to extract 'n_features'\n", + " pca = decomposition.PCA(n_components=n_features)\n", + " pca.fit(X_train)\n", + " X_train = pca.transform(X_train)\n", + "\n", + " # train the model using the components extracted from pca\n", + " model = get_model(n_features)\n", + " model.fit(X_train, y_train, epochs=epochs, verbose=0)\n", + "\n", + " # transform test data using on the pca model trained on the train data\n", + " X_test = pca.transform(X_test)\n", + " y_pred = model.predict(X_test, verbose=0)\n", + " y_pred = y_pred > 0.5\n", + "\n", + " # calculate the accuracy of the train data for the current fold\n", + " accuracy = sum(y_pred == y_test)[0] / len(y_pred)\n", + " accuracies.append(accuracy)\n", + " print(f'Accuracy of fold {i}: {accuracy}')\n", + "\n", + "# calculate the average accuracy over all folds\n", + "avg_accuracy = sum(accuracies) / len(accuracies)\n", + "print(f'Avg accuracy {avg_accuracy}')" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.7" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/Exploration.ipynb b/Exploration.ipynb index 77413ab..be2a4a6 100644 --- a/Exploration.ipynb +++ b/Exploration.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 120, + "execution_count": 3, "id": "37d611da-6f56-46d8-905a-62026750150c", "metadata": { "tags": [] @@ -25,7 +25,7 @@ }, { "cell_type": "code", - "execution_count": 127, + "execution_count": 6, "id": "ae26378f-c104-4664-a313-ed8d9edfed42", "metadata": { "tags": [] @@ -174,7 +174,7 @@ "4 0.0 3.0 0 " ] }, - "execution_count": 127, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -186,6 +186,16 @@ "df.head()" ] }, + { + "cell_type": "code", + "execution_count": 8, + "id": "feef6121-af85-4bd5-a04f-f2ff38b3c556", + "metadata": {}, + "outputs": [], + "source": [ + "# df.to_csv('./data/dataset_cleaned.csv', index=False)" + ] + }, { "cell_type": "code", "execution_count": 128, @@ -496,7 +506,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.5" + "version": "3.11.7" } }, "nbformat": 4,