added onehot encoding for factors and scaling for numeric columns
mahehsma
parent
8e80949a38
commit
e2b6e45cc6
|
|
@ -2,7 +2,7 @@
|
||||||
"cells": [
|
"cells": [
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 8,
|
"execution_count": 2,
|
||||||
"id": "initial_id",
|
"id": "initial_id",
|
||||||
"metadata": {
|
"metadata": {
|
||||||
"jupyter": {
|
"jupyter": {
|
||||||
|
|
@ -11,12 +11,13 @@
|
||||||
},
|
},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
"import pandas as pd"
|
"import pandas as pd\n",
|
||||||
|
"from sklearn.preprocessing import MinMaxScaler, StandardScaler"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 25,
|
"execution_count": 14,
|
||||||
"id": "67503952-9074-4cdb-9d7e-d9142f7c319c",
|
"id": "67503952-9074-4cdb-9d7e-d9142f7c319c",
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [
|
"outputs": [
|
||||||
|
|
@ -42,128 +43,180 @@
|
||||||
" <tr style=\"text-align: right;\">\n",
|
" <tr style=\"text-align: right;\">\n",
|
||||||
" <th></th>\n",
|
" <th></th>\n",
|
||||||
" <th>age</th>\n",
|
" <th>age</th>\n",
|
||||||
" <th>sex</th>\n",
|
|
||||||
" <th>cp</th>\n",
|
|
||||||
" <th>trestbps</th>\n",
|
" <th>trestbps</th>\n",
|
||||||
" <th>chol</th>\n",
|
" <th>chol</th>\n",
|
||||||
" <th>fbs</th>\n",
|
|
||||||
" <th>restecg</th>\n",
|
|
||||||
" <th>thalach</th>\n",
|
" <th>thalach</th>\n",
|
||||||
" <th>exang</th>\n",
|
|
||||||
" <th>oldpeak</th>\n",
|
" <th>oldpeak</th>\n",
|
||||||
" <th>slope</th>\n",
|
" <th>sex_0</th>\n",
|
||||||
" <th>ca</th>\n",
|
" <th>sex_1</th>\n",
|
||||||
" <th>thal</th>\n",
|
" <th>cp_1</th>\n",
|
||||||
" <th>goal</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",
|
||||||
" </tr>\n",
|
" </tr>\n",
|
||||||
" </thead>\n",
|
" </thead>\n",
|
||||||
" <tbody>\n",
|
" <tbody>\n",
|
||||||
" <tr>\n",
|
" <tr>\n",
|
||||||
" <th>0</th>\n",
|
" <th>0</th>\n",
|
||||||
" <td>63</td>\n",
|
" <td>0.708333</td>\n",
|
||||||
" <td>1</td>\n",
|
" <td>0.481132</td>\n",
|
||||||
" <td>1</td>\n",
|
" <td>0.244292</td>\n",
|
||||||
" <td>145</td>\n",
|
" <td>0.603053</td>\n",
|
||||||
" <td>233</td>\n",
|
" <td>0.370968</td>\n",
|
||||||
" <td>1</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>2</td>\n",
|
" <td>True</td>\n",
|
||||||
" <td>150</td>\n",
|
" <td>True</td>\n",
|
||||||
" <td>0</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>2.3</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>3</td>\n",
|
" <td>...</td>\n",
|
||||||
" <td>0.0</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>6.0</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>0</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",
|
||||||
" </tr>\n",
|
" </tr>\n",
|
||||||
" <tr>\n",
|
" <tr>\n",
|
||||||
" <th>1</th>\n",
|
" <th>1</th>\n",
|
||||||
" <td>67</td>\n",
|
" <td>0.791667</td>\n",
|
||||||
" <td>1</td>\n",
|
" <td>0.622642</td>\n",
|
||||||
" <td>4</td>\n",
|
" <td>0.365297</td>\n",
|
||||||
" <td>160</td>\n",
|
" <td>0.282443</td>\n",
|
||||||
" <td>286</td>\n",
|
" <td>0.241935</td>\n",
|
||||||
" <td>0</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>2</td>\n",
|
" <td>True</td>\n",
|
||||||
" <td>108</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>1</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>1.5</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>2</td>\n",
|
" <td>...</td>\n",
|
||||||
" <td>3.0</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>3.0</td>\n",
|
" <td>True</td>\n",
|
||||||
" <td>2</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",
|
||||||
" </tr>\n",
|
" </tr>\n",
|
||||||
" <tr>\n",
|
" <tr>\n",
|
||||||
" <th>2</th>\n",
|
" <th>2</th>\n",
|
||||||
" <td>67</td>\n",
|
" <td>0.791667</td>\n",
|
||||||
" <td>1</td>\n",
|
" <td>0.245283</td>\n",
|
||||||
" <td>4</td>\n",
|
" <td>0.235160</td>\n",
|
||||||
" <td>120</td>\n",
|
" <td>0.442748</td>\n",
|
||||||
" <td>229</td>\n",
|
" <td>0.419355</td>\n",
|
||||||
" <td>0</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>2</td>\n",
|
" <td>True</td>\n",
|
||||||
" <td>129</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>1</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>2.6</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>2</td>\n",
|
" <td>...</td>\n",
|
||||||
" <td>2.0</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>7.0</td>\n",
|
" <td>True</td>\n",
|
||||||
" <td>1</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",
|
||||||
" </tr>\n",
|
" </tr>\n",
|
||||||
" <tr>\n",
|
" <tr>\n",
|
||||||
" <th>3</th>\n",
|
" <th>3</th>\n",
|
||||||
" <td>37</td>\n",
|
" <td>0.166667</td>\n",
|
||||||
" <td>1</td>\n",
|
" <td>0.339623</td>\n",
|
||||||
" <td>3</td>\n",
|
" <td>0.283105</td>\n",
|
||||||
" <td>130</td>\n",
|
" <td>0.885496</td>\n",
|
||||||
" <td>250</td>\n",
|
" <td>0.564516</td>\n",
|
||||||
" <td>0</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>0</td>\n",
|
" <td>True</td>\n",
|
||||||
" <td>187</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>0</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>3.5</td>\n",
|
" <td>True</td>\n",
|
||||||
" <td>3</td>\n",
|
" <td>...</td>\n",
|
||||||
" <td>0.0</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>3.0</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>0</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",
|
||||||
" </tr>\n",
|
" </tr>\n",
|
||||||
" <tr>\n",
|
" <tr>\n",
|
||||||
" <th>4</th>\n",
|
" <th>4</th>\n",
|
||||||
" <td>41</td>\n",
|
" <td>0.250000</td>\n",
|
||||||
" <td>0</td>\n",
|
" <td>0.339623</td>\n",
|
||||||
" <td>2</td>\n",
|
" <td>0.178082</td>\n",
|
||||||
" <td>130</td>\n",
|
" <td>0.770992</td>\n",
|
||||||
" <td>204</td>\n",
|
" <td>0.225806</td>\n",
|
||||||
" <td>0</td>\n",
|
" <td>True</td>\n",
|
||||||
" <td>2</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>172</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>0</td>\n",
|
" <td>True</td>\n",
|
||||||
" <td>1.4</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>1</td>\n",
|
" <td>...</td>\n",
|
||||||
" <td>0.0</td>\n",
|
" <td>True</td>\n",
|
||||||
" <td>3.0</td>\n",
|
" <td>False</td>\n",
|
||||||
" <td>0</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",
|
||||||
" </tr>\n",
|
" </tr>\n",
|
||||||
" </tbody>\n",
|
" </tbody>\n",
|
||||||
"</table>\n",
|
"</table>\n",
|
||||||
|
"<p>5 rows × 28 columns</p>\n",
|
||||||
"</div>"
|
"</div>"
|
||||||
],
|
],
|
||||||
"text/plain": [
|
"text/plain": [
|
||||||
" age sex cp trestbps chol fbs restecg thalach exang oldpeak slope \\\n",
|
" age trestbps chol thalach oldpeak sex_0 sex_1 cp_1 \\\n",
|
||||||
"0 63 1 1 145 233 1 2 150 0 2.3 3 \n",
|
"0 0.708333 0.481132 0.244292 0.603053 0.370968 False True True \n",
|
||||||
"1 67 1 4 160 286 0 2 108 1 1.5 2 \n",
|
"1 0.791667 0.622642 0.365297 0.282443 0.241935 False True False \n",
|
||||||
"2 67 1 4 120 229 0 2 129 1 2.6 2 \n",
|
"2 0.791667 0.245283 0.235160 0.442748 0.419355 False True False \n",
|
||||||
"3 37 1 3 130 250 0 0 187 0 3.5 3 \n",
|
"3 0.166667 0.339623 0.283105 0.885496 0.564516 False True False \n",
|
||||||
"4 41 0 2 130 204 0 2 172 0 1.4 1 \n",
|
"4 0.250000 0.339623 0.178082 0.770992 0.225806 True False False \n",
|
||||||
"\n",
|
"\n",
|
||||||
" ca thal goal \n",
|
" cp_2 cp_3 ... slope_1 slope_2 slope_3 thal_3.0 thal_6.0 thal_7.0 \\\n",
|
||||||
"0 0.0 6.0 0 \n",
|
"0 False False ... False False True False True False \n",
|
||||||
"1 3.0 3.0 2 \n",
|
"1 False False ... False True False True False False \n",
|
||||||
"2 2.0 7.0 1 \n",
|
"2 False False ... False True False False False True \n",
|
||||||
"3 0.0 3.0 0 \n",
|
"3 False True ... False False True True False False \n",
|
||||||
"4 0.0 3.0 0 "
|
"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]"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
"execution_count": 25,
|
"execution_count": 14,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"output_type": "execute_result"
|
"output_type": "execute_result"
|
||||||
}
|
}
|
||||||
|
|
@ -171,31 +224,7 @@
|
||||||
"source": [
|
"source": [
|
||||||
"df = pd.read_csv('./data/dataset_cleaned.csv')\n",
|
"df = pd.read_csv('./data/dataset_cleaned.csv')\n",
|
||||||
"df.dropna(inplace=True)\n",
|
"df.dropna(inplace=True)\n",
|
||||||
"df.head()"
|
"\n",
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"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",
|
"# extract all columns except 'goal' --> X\n",
|
||||||
"X = df.loc[:, df.columns != 'goal']\n",
|
"X = df.loc[:, df.columns != 'goal']\n",
|
||||||
"# extract only the column 'goal' --> y\n",
|
"# extract only the column 'goal' --> y\n",
|
||||||
|
|
@ -206,12 +235,24 @@
|
||||||
"y = y.reshape((len(y),1))\n",
|
"y = y.reshape((len(y),1))\n",
|
||||||
"\n",
|
"\n",
|
||||||
"# binarize y\n",
|
"# binarize y\n",
|
||||||
"y[y>0] = 1"
|
"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()"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 91,
|
"execution_count": 18,
|
||||||
"id": "2bbee865-c000-43da-84d9-ce7e04874110",
|
"id": "2bbee865-c000-43da-84d9-ce7e04874110",
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
|
|
@ -221,7 +262,6 @@
|
||||||
" tf.keras.layers.InputLayer(shape=(n_features,)),\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(30, activation='relu'),\n",
|
||||||
" tf.keras.layers.Dense(30, activation='relu'),\n",
|
|
||||||
" tf.keras.layers.Dense(1, activation='sigmoid')\n",
|
" tf.keras.layers.Dense(1, activation='sigmoid')\n",
|
||||||
" ], name='test')\n",
|
" ], name='test')\n",
|
||||||
" model.compile(optimizer=tf.keras.optimizers.Adam(), \n",
|
" model.compile(optimizer=tf.keras.optimizers.Adam(), \n",
|
||||||
|
|
@ -231,7 +271,7 @@
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 97,
|
"execution_count": 20,
|
||||||
"id": "38eb4f87-ca3c-4ecf-a8ca-29422822d933",
|
"id": "38eb4f87-ca3c-4ecf-a8ca-29422822d933",
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [
|
"outputs": [
|
||||||
|
|
@ -239,27 +279,47 @@
|
||||||
"name": "stdout",
|
"name": "stdout",
|
||||||
"output_type": "stream",
|
"output_type": "stream",
|
||||||
"text": [
|
"text": [
|
||||||
"Training fold 0 for 5 epochs\n",
|
"Training fold 0 for 20 epochs\n",
|
||||||
"Train samples:\t237\n",
|
"Train samples:\t267\n",
|
||||||
"Test samples:\t60\n",
|
"Test samples:\t30\n",
|
||||||
"Accuracy of fold 0: 0.6166666666666667\n",
|
"Accuracy of fold 0: 0.8666666666666667\n",
|
||||||
"Training fold 1 for 5 epochs\n",
|
"Training fold 1 for 20 epochs\n",
|
||||||
"Train samples:\t237\n",
|
"Train samples:\t267\n",
|
||||||
"Test samples:\t60\n",
|
"Test samples:\t30\n",
|
||||||
"Accuracy of fold 1: 0.75\n",
|
"Accuracy of fold 1: 0.8666666666666667\n",
|
||||||
"Training fold 2 for 5 epochs\n",
|
"Training fold 2 for 20 epochs\n",
|
||||||
"Train samples:\t238\n",
|
"Train samples:\t267\n",
|
||||||
"Test samples:\t59\n",
|
"Test samples:\t30\n",
|
||||||
"Accuracy of fold 2: 0.6949152542372882\n",
|
"Accuracy of fold 2: 0.8666666666666667\n",
|
||||||
"Training fold 3 for 5 epochs\n",
|
"Training fold 3 for 20 epochs\n",
|
||||||
"Train samples:\t238\n",
|
"Train samples:\t267\n",
|
||||||
"Test samples:\t59\n",
|
"Test samples:\t30\n",
|
||||||
"Accuracy of fold 3: 0.7457627118644068\n",
|
"Accuracy of fold 3: 0.9333333333333333\n",
|
||||||
"Training fold 4 for 5 epochs\n",
|
"Training fold 4 for 20 epochs\n",
|
||||||
"Train samples:\t238\n",
|
"Train samples:\t267\n",
|
||||||
"Test samples:\t59\n",
|
"Test samples:\t30\n",
|
||||||
"Accuracy of fold 4: 0.6610169491525424\n",
|
"Accuracy of fold 4: 0.8666666666666667\n",
|
||||||
"Avg accuracy 0.6936723163841808\n"
|
"Training fold 5 for 20 epochs\n",
|
||||||
|
"Train samples:\t267\n",
|
||||||
|
"Test samples:\t30\n",
|
||||||
|
"Accuracy of fold 5: 0.8333333333333334\n",
|
||||||
|
"Training fold 6 for 20 epochs\n",
|
||||||
|
"Train samples:\t267\n",
|
||||||
|
"Test samples:\t30\n",
|
||||||
|
"Accuracy of fold 6: 0.8666666666666667\n",
|
||||||
|
"Training fold 7 for 20 epochs\n",
|
||||||
|
"Train samples:\t268\n",
|
||||||
|
"Test samples:\t29\n",
|
||||||
|
"Accuracy of fold 7: 0.896551724137931\n",
|
||||||
|
"Training fold 8 for 20 epochs\n",
|
||||||
|
"Train samples:\t268\n",
|
||||||
|
"Test samples:\t29\n",
|
||||||
|
"Accuracy of fold 8: 0.7931034482758621\n",
|
||||||
|
"Training fold 9 for 20 epochs\n",
|
||||||
|
"Train samples:\t268\n",
|
||||||
|
"Test samples:\t29\n",
|
||||||
|
"Accuracy of fold 9: 0.7931034482758621\n",
|
||||||
|
"Avg accuracy 0.8582758620689654\n"
|
||||||
]
|
]
|
||||||
}
|
}
|
||||||
],
|
],
|
||||||
|
|
@ -269,12 +329,13 @@
|
||||||
"import tensorflow as tf\n",
|
"import tensorflow as tf\n",
|
||||||
"\n",
|
"\n",
|
||||||
"# number of components extracted from the pca\n",
|
"# number of components extracted from the pca\n",
|
||||||
"n_features = 5 \n",
|
"n_features = 8\n",
|
||||||
"\n",
|
"\n",
|
||||||
"epochs = 5\n",
|
"epochs = 20\n",
|
||||||
|
"k_folds = 10\n",
|
||||||
"\n",
|
"\n",
|
||||||
"# used to split the dataset into k folds\n",
|
"# used to split the dataset into k folds\n",
|
||||||
"kf = KFold(n_splits=5)\n",
|
"kf = KFold(n_splits=k_folds)\n",
|
||||||
"\n",
|
"\n",
|
||||||
"accuracies = []\n",
|
"accuracies = []\n",
|
||||||
"for i, (train_idx, test_idx) in enumerate(kf.split(X)):\n",
|
"for i, (train_idx, test_idx) in enumerate(kf.split(X)):\n",
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue