Changed SMOTE by SMOTETomek

gen_train_data/gen_train_data.ipynb

@@ -17,7 +17,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -25,13 +25,13 @@
     "import pandas as pd\n",
     "import numpy as np\n",
     "from sklearn.model_selection import train_test_split\n",
-    "from imblearn.over_sampling import SMOTE\n",
+    "from imblearn.combine import SMOTETomek\n",
     "from imblearn.under_sampling import TomekLinks"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -42,7 +42,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -79,7 +79,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -90,7 +90,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -103,7 +103,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -116,19 +116,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# OVERSAMPLING: SMOTE\n",
-    "smote = SMOTE()\n",
-    "X_train_over_pre, y_train_over_pre = smote.fit_resample(X_train_pre, y_train_pre)\n",
-    "X_train_over_post, y_train_over_post = smote.fit_resample(X_train_post, y_train_post)"
+    "# OVERSAMPLED training data\n",
+    "smote_tomek = SMOTETomek()\n",
+    "X_train_over_pre, y_train_over_pre = smote_tomek.fit_resample(X_train_pre, y_train_pre)\n",
+    "X_train_over_post, y_train_over_post = smote_tomek.fit_resample(X_train_post, y_train_post)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -141,7 +141,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -153,7 +153,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [