diff --git a/decision tree classification.ipynb b/decision tree classification.ipynb
index 72186d6..a366e17 100644
--- a/decision tree classification.ipynb	
+++ b/decision tree classification.ipynb	
@@ -24,7 +24,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Constructing a model"
+    "# Constructing a model (algorithm)"
    ]
   },
   {
@@ -309,10 +309,17 @@
     "\n",
     "This dataset became a typical test case for many statistical classification techniques in machine learning such as support vector machines\n",
     "\n",
+    "**Reference**\n",
+    "\n",
+    " R. A. Fisher (1936). \"The use of multiple measurements in taxonomic problems\". Annals of Eugenics. 7 (2): 179–188.\n",
+    " \n",
+    " https://en.wikipedia.org/wiki/Iris_flower_data_set\n",
+    "\n",
     "**Content**\n",
     "\n",
     "The dataset contains a set of 150 records under 5 attributes - Petal Length, Petal Width, Sepal Length, Sepal width and Class(Species).\n",
     "\n",
+    "---\n",
     "So, our objective here is to predict the class that is the specie of the iris flower, given it's features which are:\n",
     "1. sepal_length\n",
     "2. sepal width\n",
@@ -562,7 +569,7 @@
    "source": [
     "## Model visualization\n",
     "\n",
-    "We will use the methon print.tree() to visualize our tree."
+    "We will use the method print.tree() to visualize our tree."
    ]
   },
   {
@@ -598,12 +605,12 @@
    "source": [
     "## Testing the model\n",
     "\n",
-    "We are using the definded method predict() to determine the classes of the Test dataset - those will be stored in the Y_pred which we will than compare to Y_test with the help of sklearn library function called accuracy_score"
+    "We are using definded method predict() to determine the classes of the Test dataset - those will be stored in the Y_pred which we will then compare to Y_test with the help of sklearn library function called accuracy_score"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [
     {
@@ -612,7 +619,7 @@
        "0.9333333333333333"
       ]
      },
-     "execution_count": 32,
+     "execution_count": 41,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -639,6 +646,16 @@
     "Our objective here is to predict if the customer will purchase the iPhone or not given their gender, age and salary."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### About the data \n",
+    "\n",
+    "Despite all the effort I couldn't find the origin of this data thus it shouldn't be used for any other purposes. \n",
+    "The dataset contains a set of 400 records under 4 attributes - Gender, Age, Salary and Class( whether the person made a purchase or not)."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},