diff --git a/data_preprocessing_template.ipynb b/data_preprocessing_template.ipynb
new file mode 100644
index 0000000000000..120ddbec57118
--- /dev/null
+++ b/data_preprocessing_template.ipynb
@@ -0,0 +1,100 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/Abcxyzcmnl2006/leetcode/blob/main/data_preprocessing_template.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "WOw8yMd1VlnD"
+      },
+      "source": [
+        "# Data Preprocessing Template"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "NvUGC8QQV6bV"
+      },
+      "source": [
+        "## Importing the libraries"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "wfFEXZC0WS-V"
+      },
+      "source": [
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt\n",
+        "import pandas as pd"
+      ],
+      "execution_count": 2,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fhYaZ-ENV_c5"
+      },
+      "source": [
+        "## Importing the dataset"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "aqHTg9bxWT_u"
+      },
+      "source": [
+        "dataset = pd.read_csv('Data.csv')\n",
+        "X = dataset.iloc[:, :-1].values\n",
+        "y = dataset.iloc[:, -1].values"
+      ],
+      "execution_count": 3,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3abSxRqvWEIB"
+      },
+      "source": [
+        "## Splitting the dataset into the Training set and Test set"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "hm48sif-WWsh"
+      },
+      "source": [
+        "from sklearn.model_selection import train_test_split\n",
+        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)"
+      ],
+      "execution_count": 5,
+      "outputs": []
+    }
+  ]
+}
\ No newline at end of file