Added necessary comments

Loan-Prediction-main/Loan-Prediction-main/LoanPreds.ipynb

@@ -327,6 +327,14 @@
     "df.Gender.value_counts(dropna=False)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "d0dec656",
+   "metadata": {},
+   "source": [
+    "# Data Visualization"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 9,
@@ -1073,6 +1081,14 @@
     "sns.boxplot(x=\"Loan_Status\", y=\"LoanAmount\", data=df, palette=\"YlOrBr\");\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "2e1578ff",
+   "metadata": {},
+   "source": [
+    "# Data Cleaning"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 27,
@@ -2158,6 +2174,14 @@
     "sns.histplot(data=df, x=\"LoanAmount\", kde=True, ax=axs[1, 0], color='orange');"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "d002f143",
+   "metadata": {},
+   "source": [
+    "# Training"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 39,
@@ -2186,6 +2210,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "#Normalize the data\n",
     "X = MinMaxScaler().fit_transform(X)"
    ]
   },
@@ -2196,6 +2221,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "#Splitting the data\n",
     "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.1, random_state = 48)"
    ]
   },
@@ -2225,6 +2251,7 @@
     }
    ],
    "source": [
+    "#Linear Regression\n",
     "LRclassifier =LogisticRegression()\n",
     "LRclassifier.fit(X_train, y_train)\n",
     "\n",
@@ -2263,6 +2290,7 @@
     }
    ],
    "source": [
+    "#K Nearest Neighbour\n",
     "scoreListknn = []\n",
     "for i in range(1,21):\n",
     "    KNclassifier = KNeighborsClassifier(n_neighbors = i)\n",
@@ -2312,6 +2340,7 @@
     }
    ],
    "source": [
+    "#Support Vector Machine\n",
     "SVCclassifier = SVC(kernel='rbf', max_iter=500)\n",
     "SVCclassifier.fit(X_train, y_train)\n",
     "\n",
@@ -2350,6 +2379,7 @@
     }
    ],
    "source": [
+    "#Decision Tree\n",
     "scoreListDT = []\n",
     "for i in range(2,21):\n",
     "    DTclassifier = DecisionTreeClassifier(max_leaf_nodes=i)\n",
@@ -2390,6 +2420,7 @@
     }
    ],
    "source": [
+    "#Random Forest \n",
     "scoreListRF = []\n",
     "for i in range(2,25):\n",
     "    RFclassifier = RandomForestClassifier(n_estimators = 1000, random_state = 1, max_leaf_nodes=i)\n",
@@ -2412,6 +2443,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "#For Grid Search\n",
     "paramsGB={'n_estimators':[100,200,300,400,500],\n",
     "      'max_depth':[1,2,3,4,5],\n",
     "      'subsample':[0.5,1],\n",
@@ -2512,6 +2544,7 @@
     }
    ],
    "source": [
+    "#Gradient Boosting\n",
     "GBclassifier = GradientBoostingClassifier(subsample=0.5, n_estimators=400, max_depth=4, max_leaf_nodes=10)\n",
     "GBclassifier.fit(X_train, y_train)\n",
     "\n",
@@ -2532,6 +2565,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "#Save all the models for deployment\n",
     "import pickle\n",
     "pickle.dump(LRclassifier, open('model.pkl','wb'))\n",
     "pickle.dump(KNclassifier, open('model2.pkl','wb'))\n",
@@ -2558,7 +2592,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 79,
+   "execution_count": null,
    "id": "9a7dc512-cb24-4faa-9e59-04fcbc74554e",
    "metadata": {},
    "outputs": [
@@ -2622,6 +2656,7 @@
     }
    ],
    "source": [
+    "#Ensemblong the models\n",
     "from sklearn.ensemble import VotingClassifier\n",
     "final_model = VotingClassifier(\n",
     "    estimators=[('lr', model1), ('knn', model2), ('svc', model3),('dt', model4),('rf', model5),('gb', model6)], voting='hard')\n",
@@ -2665,6 +2700,7 @@
     }
    ],
    "source": [
+    "#FInal accuracies\n",
     "print(classification_report(y_test, y_pred))\n",
     "print(confusion_matrix(y_test, y_pred))\n",
     "\n",