2024-06-05 11:20:55 +02:00
{
"cells": [
{
"cell_type": "code",
2024-06-07 09:51:06 +02:00
"execution_count": 1,
2024-06-05 11:20:55 +02:00
"id": "initial_id",
"metadata": {
"jupyter": {
"is_executing": true
}
},
"outputs": [],
"source": [
2024-06-05 12:27:29 +02:00
"import pandas as pd\n",
2024-06-07 09:36:01 +02:00
"from sklearn.preprocessing import MinMaxScaler, StandardScaler\n",
"from sklearn.model_selection import KFold\n",
"from sklearn import decomposition"
2024-06-05 11:20:55 +02:00
]
},
{
"cell_type": "code",
2024-06-07 09:36:01 +02:00
"execution_count": 2,
2024-06-05 11:20:55 +02:00
"id": "67503952-9074-4cdb-9d7e-d9142f7c319c",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>age</th>\n",
" <th>trestbps</th>\n",
" <th>chol</th>\n",
" <th>thalach</th>\n",
" <th>oldpeak</th>\n",
2024-06-05 12:27:29 +02:00
" <th>sex_0</th>\n",
" <th>sex_1</th>\n",
" <th>cp_1</th>\n",
" <th>cp_2</th>\n",
" <th>cp_3</th>\n",
" <th>...</th>\n",
" <th>slope_1</th>\n",
" <th>slope_2</th>\n",
" <th>slope_3</th>\n",
" <th>thal_3.0</th>\n",
" <th>thal_6.0</th>\n",
" <th>thal_7.0</th>\n",
" <th>ca_0.0</th>\n",
" <th>ca_1.0</th>\n",
" <th>ca_2.0</th>\n",
" <th>ca_3.0</th>\n",
2024-06-05 11:20:55 +02:00
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
2024-06-05 12:27:29 +02:00
" <td>0.708333</td>\n",
" <td>0.481132</td>\n",
" <td>0.244292</td>\n",
" <td>0.603053</td>\n",
" <td>0.370968</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
2024-06-05 11:20:55 +02:00
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
2024-06-05 12:27:29 +02:00
" <td>0.791667</td>\n",
" <td>0.622642</td>\n",
" <td>0.365297</td>\n",
" <td>0.282443</td>\n",
" <td>0.241935</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
2024-06-05 11:20:55 +02:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
2024-06-05 12:27:29 +02:00
" <td>0.791667</td>\n",
" <td>0.245283</td>\n",
" <td>0.235160</td>\n",
" <td>0.442748</td>\n",
" <td>0.419355</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
2024-06-05 11:20:55 +02:00
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
2024-06-05 12:27:29 +02:00
" <td>0.166667</td>\n",
" <td>0.339623</td>\n",
" <td>0.283105</td>\n",
" <td>0.885496</td>\n",
" <td>0.564516</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
2024-06-05 11:20:55 +02:00
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
2024-06-05 12:27:29 +02:00
" <td>0.250000</td>\n",
" <td>0.339623</td>\n",
" <td>0.178082</td>\n",
" <td>0.770992</td>\n",
" <td>0.225806</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>...</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
" <td>False</td>\n",
2024-06-05 11:20:55 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
2024-06-05 12:27:29 +02:00
"<p>5 rows ×
2024-06-05 11:20:55 +02:00
"</div>"
],
"text/plain": [
2024-06-05 12:27:29 +02:00
" age trestbps chol thalach oldpeak sex_0 sex_1 cp_1 \\\n",
"0 0.708333 0.481132 0.244292 0.603053 0.370968 False True True \n",
"1 0.791667 0.622642 0.365297 0.282443 0.241935 False True False \n",
"2 0.791667 0.245283 0.235160 0.442748 0.419355 False True False \n",
"3 0.166667 0.339623 0.283105 0.885496 0.564516 False True False \n",
"4 0.250000 0.339623 0.178082 0.770992 0.225806 True False False \n",
2024-06-05 11:20:55 +02:00
"\n",
2024-06-05 12:27:29 +02:00
" cp_2 cp_3 ... slope_1 slope_2 slope_3 thal_3.0 thal_6.0 thal_7.0 \\\n",
"0 False False ... False False True False True False \n",
"1 False False ... False True False True False False \n",
"2 False False ... False True False False False True \n",
"3 False True ... False False True True False False \n",
"4 True False ... True False False True False False \n",
"\n",
" ca_0.0 ca_1.0 ca_2.0 ca_3.0 \n",
"0 True False False False \n",
"1 False False False True \n",
"2 False False True False \n",
"3 True False False False \n",
"4 True False False False \n",
"\n",
"[5 rows x 28 columns]"
2024-06-05 11:20:55 +02:00
]
},
2024-06-07 09:36:01 +02:00
"execution_count": 2,
2024-06-05 11:20:55 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv('./data/dataset_cleaned.csv')\n",
2024-06-05 12:27:29 +02:00
"\n",
2024-06-05 11:20:55 +02:00
"# 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",
2024-06-05 12:27:29 +02:00
"y[y>0] = 1\n",
"\n",
"factor_columns = ['sex', 'cp', 'fbs', 'restecg', 'exang', 'slope', 'thal', 'ca']\n",
"numeric_columns = [column for column in X.columns if column not in factor_columns]\n",
"\n",
"# transform factors into onehot vectors\n",
"X = pd.get_dummies(X, columns=factor_columns)\n",
"\n",
"# min max scaling of numeric columns\n",
"scaler = MinMaxScaler()\n",
"X[numeric_columns] = scaler.fit_transform(X[numeric_columns])\n",
"\n",
"X.head()"
2024-06-05 11:20:55 +02:00
]
},
{
"cell_type": "code",
2024-06-07 09:51:06 +02:00
"execution_count": 3,
2024-06-05 11:20:55 +02:00
"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(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",
2024-06-07 09:51:06 +02:00
"execution_count": 4,
2024-06-05 11:20:55 +02:00
"id": "38eb4f87-ca3c-4ecf-a8ca-29422822d933",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-06-07 09:51:06 +02:00
"Training 10 folds for 20 epochs\n",
"Fold 0\n",
"\tTrain samples:\t267\tTest samples:\t30\n",
"\tAccuracy: 90.000%\n",
"Fold 1\n",
"\tTrain samples:\t267\tTest samples:\t30\n",
"\tAccuracy: 80.000%\n",
"Fold 2\n",
"\tTrain samples:\t267\tTest samples:\t30\n",
"\tAccuracy: 90.000%\n",
"Fold 3\n",
"\tTrain samples:\t267\tTest samples:\t30\n",
"\tAccuracy: 90.000%\n",
"Fold 4\n",
"\tTrain samples:\t267\tTest samples:\t30\n",
"WARNING:tensorflow:5 out of the last 5 calls to <function TensorFlowTrainer.make_predict_function.<locals>.one_step_on_data_distributed at 0x0000023D0BD63C40> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.\n",
"\tAccuracy: 90.000%\n",
"Fold 5\n",
"\tTrain samples:\t267\tTest samples:\t30\n",
"WARNING:tensorflow:6 out of the last 6 calls to <function TensorFlowTrainer.make_predict_function.<locals>.one_step_on_data_distributed at 0x0000023D0D548CC0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.\n",
"\tAccuracy: 86.667%\n",
"Fold 6\n",
"\tTrain samples:\t267\tTest samples:\t30\n",
"\tAccuracy: 80.000%\n",
"Fold 7\n",
"\tTrain samples:\t268\tTest samples:\t29\n",
"\tAccuracy: 86.207%\n",
"Fold 8\n",
"\tTrain samples:\t268\tTest samples:\t29\n",
"\tAccuracy: 79.310%\n",
"Fold 9\n",
"\tTrain samples:\t268\tTest samples:\t29\n",
"\tAccuracy: 82.759%\n",
"Avg accuracy 85.494%\n"
2024-06-05 11:20:55 +02:00
]
}
],
"source": [
"import tensorflow as tf\n",
"\n",
2024-06-07 09:36:01 +02:00
"use_pca = True\n",
2024-06-05 11:20:55 +02:00
"# number of components extracted from the pca\n",
2024-06-05 12:27:29 +02:00
"n_features = 8\n",
2024-06-07 09:36:01 +02:00
"n_features = n_features if use_pca else len(X.columns)\n",
2024-06-05 11:20:55 +02:00
"\n",
2024-06-05 12:27:29 +02:00
"epochs = 20\n",
"k_folds = 10\n",
2024-06-05 11:20:55 +02:00
"\n",
"# used to split the dataset into k folds\n",
2024-06-05 12:27:29 +02:00
"kf = KFold(n_splits=k_folds)\n",
2024-06-05 11:20:55 +02:00
"\n",
"accuracies = []\n",
2024-06-07 09:51:06 +02:00
"print(f'Training {k_folds} folds for {epochs} epochs')\n",
2024-06-05 11:20:55 +02:00
"for i, (train_idx, test_idx) in enumerate(kf.split(X)):\n",
"\n",
2024-06-07 09:51:06 +02:00
" print(f'Fold {i}')\n",
" \n",
2024-06-05 11:20:55 +02:00
" # 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",
2024-06-07 09:51:06 +02:00
" print(f'\\tTrain samples:\\t{len(X_train)}\\tTest samples:\\t{len(X_test)}')\n",
2024-06-05 11:20:55 +02:00
"\n",
2024-06-07 09:36:01 +02:00
" if use_pca:\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",
2024-06-05 11:20:55 +02:00
"\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",
2024-06-07 09:36:01 +02:00
" if use_pca:\n",
" # transform test data using on the pca model trained on the train data\n",
" X_test = pca.transform(X_test)\n",
" \n",
2024-06-05 11:20:55 +02:00
" y_pred = model.predict(X_test, verbose=0)\n",
2024-06-07 09:36:01 +02:00
" y_pred = y_pred > 0.5 # threshold to binarize\n",
2024-06-05 11:20:55 +02:00
"\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",
2024-06-07 09:51:06 +02:00
" print(f'\\tAccuracy: {accuracy:.3%}')\n",
2024-06-05 11:20:55 +02:00
"\n",
"# calculate the average accuracy over all folds\n",
"avg_accuracy = sum(accuracies) / len(accuracies)\n",
2024-06-07 09:51:06 +02:00
"print(f'Avg accuracy {avg_accuracy:.3%}')"
2024-06-05 11:20:55 +02:00
]
2024-06-05 13:12:53 +02:00
},
{
"cell_type": "code",
2024-06-07 09:51:06 +02:00
"execution_count": 5,
2024-06-05 13:12:53 +02:00
"id": "95215693-47c9-4202-92f5-efbc65bc32c9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-06-07 09:51:06 +02:00
"Training 5 folds\n",
"Fold 0\n",
"\tTrain samples:\t237\tTest samples:\t60\n"
2024-06-05 13:12:53 +02:00
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\maxwi\\anaconda3\\Lib\\site-packages\\sklearn\\cluster\\_kmeans.py:1382: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-06-07 09:51:06 +02:00
"\tAccuracy 58.333%\n",
"\n",
"Fold 1\n",
"\tTrain samples:\t237\tTest samples:\t60\n"
2024-06-05 13:12:53 +02:00
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\maxwi\\anaconda3\\Lib\\site-packages\\sklearn\\cluster\\_kmeans.py:1382: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-06-07 09:51:06 +02:00
"\tAccuracy 50.000%\n",
"\n",
"Fold 2\n",
"\tTrain samples:\t238\tTest samples:\t59\n"
2024-06-05 13:12:53 +02:00
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\maxwi\\anaconda3\\Lib\\site-packages\\sklearn\\cluster\\_kmeans.py:1382: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-06-07 09:51:06 +02:00
"\tAccuracy 55.932%\n",
"\n",
"Fold 3\n",
"\tTrain samples:\t238\tTest samples:\t59\n"
2024-06-05 13:12:53 +02:00
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\maxwi\\anaconda3\\Lib\\site-packages\\sklearn\\cluster\\_kmeans.py:1382: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-06-07 09:51:06 +02:00
"\tAccuracy 57.627%\n",
"\n",
"Fold 4\n",
"\tTrain samples:\t238\tTest samples:\t59\n"
2024-06-05 13:12:53 +02:00
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\maxwi\\anaconda3\\Lib\\site-packages\\sklearn\\cluster\\_kmeans.py:1382: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-06-07 09:51:06 +02:00
"\tAccuracy 52.542%\n",
"\n",
"Avg accuracy 54.887%\n"
2024-06-05 13:12:53 +02:00
]
}
],
"source": [
"from sklearn.cluster import KMeans\n",
"\n",
2024-06-07 09:36:01 +02:00
"use_pca = True\n",
2024-06-05 13:12:53 +02:00
"# number of components extracted from the pca\n",
"n_features = 10\n",
"\n",
"k_folds = 5\n",
"\n",
"# used to split the dataset into k folds\n",
"kf = KFold(n_splits=k_folds)\n",
"\n",
"accuracies = []\n",
2024-06-07 09:51:06 +02:00
"print(f'Training {k_folds} folds')\n",
2024-06-05 13:12:53 +02:00
"for i, (train_idx, test_idx) in enumerate(kf.split(X[numeric_columns])):\n",
"\n",
2024-06-07 09:51:06 +02:00
" print(f'Fold {i}')\n",
" \n",
2024-06-05 13:12:53 +02:00
" # 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",
2024-06-07 09:51:06 +02:00
" print(f'\\tTrain samples:\\t{len(X_train)}\\tTest samples:\\t{len(X_test)}')\n",
2024-06-05 13:12:53 +02:00
"\n",
2024-06-07 09:36:01 +02:00
" if use_pca:\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",
2024-06-05 13:12:53 +02:00
"\n",
2024-06-07 09:36:01 +02:00
" model = KMeans(n_clusters=2, n_init=10)\n",
2024-06-05 13:12:53 +02:00
" model.fit(X_train)\n",
"\n",
2024-06-07 09:36:01 +02:00
" if use_pca:\n",
" X_test = pca.transform(X_test)\n",
" \n",
2024-06-05 13:12:53 +02:00
" y_pred = model.predict(X_test)\n",
"\n",
" # calculate the accuracy of the train data for the current fold\n",
" accuracy1 = sum(y_pred == y_test)[0] / len(y_pred)\n",
" accuracy2 = sum(y_pred != y_test)[0] / len(y_pred)\n",
" accuracy = max(accuracy1, accuracy2)\n",
" accuracies.append(accuracy)\n",
2024-06-07 09:51:06 +02:00
" print(f'\\tAccuracy {accuracy:.3%}')\n",
" print()\n",
2024-06-05 13:12:53 +02:00
"\n",
"# calculate the average accuracy over all folds\n",
"avg_accuracy = sum(accuracies) / len(accuracies)\n",
2024-06-07 09:51:06 +02:00
"print(f'Avg accuracy {avg_accuracy:.3%}')"
2024-06-05 13:12:53 +02:00
]
},
{
"cell_type": "code",
2024-06-07 09:51:06 +02:00
"execution_count": 6,
2024-06-05 13:12:53 +02:00
"id": "880302e4-82c1-47b9-9fe3-cb3567511639",
"metadata": {},
2024-06-07 09:36:01 +02:00
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-06-07 09:51:06 +02:00
"Training 5 folds\n",
"Fold 0\n",
"\tTrain samples:\t237\tTest samples:\t60\n",
"\tAccuracy 85.000%\n",
"\n",
"Fold 1\n",
"\tTrain samples:\t237\tTest samples:\t60\n",
"\tAccuracy 90.000%\n",
"\n",
"Fold 2\n",
"\tTrain samples:\t238\tTest samples:\t59\n",
"\tAccuracy 84.746%\n",
"\n",
"Fold 3\n",
"\tTrain samples:\t238\tTest samples:\t59\n",
"\tAccuracy 76.271%\n",
"\n",
"Fold 4\n",
"\tTrain samples:\t238\tTest samples:\t59\n",
"\tAccuracy 77.966%\n",
"\n",
"Avg accuracy 82.797%\n"
2024-06-07 09:36:01 +02:00
]
}
],
"source": [
"from sklearn.ensemble import RandomForestClassifier\n",
"\n",
"use_pca = True\n",
"# number of components extracted from the pca\n",
"n_features = 10\n",
"\n",
"k_folds = 5\n",
"\n",
"# used to split the dataset into k folds\n",
"kf = KFold(n_splits=k_folds)\n",
"\n",
"accuracies = []\n",
2024-06-07 09:51:06 +02:00
"print(f'Training {k_folds} folds')\n",
2024-06-07 09:36:01 +02:00
"for i, (train_idx, test_idx) in enumerate(kf.split(X[numeric_columns])):\n",
2024-06-07 09:51:06 +02:00
" print(f'Fold {i}')\n",
2024-06-07 09:36:01 +02:00
"\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",
" y_train, y_test = y_train[:, 0], y_test[:, 0]\n",
"\n",
2024-06-07 09:51:06 +02:00
" print(f'\\tTrain samples:\\t{len(X_train)}\\tTest samples:\\t{len(X_test)}')\n",
2024-06-07 09:36:01 +02:00
"\n",
" if use_pca:\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",
" model = RandomForestClassifier(max_depth=2, random_state=0)\n",
" model.fit(X_train, y_train)\n",
"\n",
" if use_pca:\n",
" X_test = pca.transform(X_test)\n",
" \n",
" y_pred = model.predict(X_test)\n",
"\n",
" # calculate the accuracy of the train data for the current fold\n",
" accuracy = sum(y_pred == y_test) / len(y_pred)\n",
" accuracies.append(accuracy)\n",
2024-06-07 09:51:06 +02:00
" print(f'\\tAccuracy {accuracy:.3%}')\n",
" print()\n",
2024-06-07 09:36:01 +02:00
"\n",
"# calculate the average accuracy over all folds\n",
"avg_accuracy = sum(accuracies) / len(accuracies)\n",
2024-06-07 09:51:06 +02:00
"print(f'Avg accuracy {avg_accuracy:.3%}')"
2024-06-07 09:36:01 +02:00
]
2024-06-05 11:20:55 +02:00
}
],
"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
}
