Merge pull request #305 from sof202/main

Intro to Machine Learning proof read

Author: liamjberrisford

individual_modules/introduction_to_machine_learning/1_linear_regression.ipynb

@@ -838,8 +838,8 @@
     "plt.plot(x, y_pred, color=\"orange\", label=\"Closed form predictions\")\n",
     "\n",
     "# Draw vertical lines from each point to the line\n",
-    "for i in range(len(x)):\n",
-    "    plt.plot([x[i], x[i]], [y[i], y_pred[i]], color='black', linestyle='dashed')\n",
+    "for i, x_i in enumerate(x):\n",
+    "    plt.plot([x_i, x_i], [y[i], y_pred[i]], color='black', linestyle='dashed')\n",
     "\n",
     "plt.title(\"Linear Regression with closed-form predictions\")\n",
     "plt.legend()\n",
@@ -1495,7 +1495,7 @@
    "source": [
     "## Multiple regression with synthetic data\n",
     "\n",
-    "As before, we can generate some random data, but this time, for two dependent variables. We will need to combine the feature variables to create a single vector for the model training stage."
+    "As before, we can generate some random data, but this time, for two independent variables. We will need to combine the feature variables to create a single vector for the model training stage."
    ]
   },
   {

individual_modules/introduction_to_machine_learning/2_model_selection.ipynb

@@ -152,8 +152,8 @@
     }
    ],
    "source": [
-    "plt.scatter(X_train[:, 0], X_train[:, 1], label=\"X_train\")\n",
-    "plt.scatter(X_test[:, 0], X_test[:, 1], label=\"X_test\")\n",
+    "plt.scatter(X_train[:, 0], X_train[:, 1], label=\"X_train\", edgecolors='k')\n",
+    "plt.scatter(X_test[:, 0], X_test[:, 1], label=\"X_test\", edgecolors='k')\n",
     "plt.xlabel('Feature 1')\n",
     "plt.ylabel('Feature 2')\n",
     "plt.title('Dataset split into train (80%) and test (20%)')\n",
@@ -666,7 +666,7 @@
     }
    ],
    "source": [
-    "plt.scatter(X_test[:, 0], X_test[:, 1], label=\"X_test\")\n",
+    "plt.scatter(X_test[:, 0], X_test[:, 1], label=\"X_test\", edgecolors='k')\n",
     "plt.xlabel('Feature 1')\n",
     "plt.ylabel('Feature 2')\n",
     "plt.title('Test dataset')\n",
@@ -703,15 +703,14 @@
     "plt.xlabel('Feature 1')\n",
     "plt.ylabel('Feature 2')\n",
     "plt.title('Test dataset coloured by model prediction')\n",
-    "plt.legend()\n",
     "plt.show()"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "* Which points were incorrectly classified? We know that ~5% of 1000 were."
+    "* Which points were incorrectly classified? We know that ~5% of 200 were."
    ]
   },
   {