From 3f13b45bbfdac1c296cc272ccfdb3e0dbbaea39d Mon Sep 17 00:00:00 2001
From: SaurabhIndi <116150732+SaurabhIndi@users.noreply.github.com>
Date: Wed, 9 Oct 2024 15:42:00 +0530
Subject: [PATCH] Ensemble Method with Validation code

---
 Stock_Price_Prediction.ipynb | 89 +++++++++++++++++++++++++++++++++---
 1 file changed, 83 insertions(+), 6 deletions(-)

diff --git a/Stock_Price_Prediction.ipynb b/Stock_Price_Prediction.ipynb
index 6113649..ab9c593 100644
--- a/Stock_Price_Prediction.ipynb
+++ b/Stock_Price_Prediction.ipynb
@@ -276,7 +276,6 @@
        "</table>\n",
        "</div>"
       ],
-
       "text/plain": [
        "        Open       High        Low      Close      Volume\n",
        "0  18.691147  18.978922  18.540184  18.823240  43733533.0\n",
@@ -284,7 +283,6 @@
        "2  18.327892  18.568489  17.643839  17.738192  68296318.0\n",
        "3  17.502312  17.832542  17.223972  17.676863  86073880.0\n",
        "4  17.738192  17.785366  17.459852  17.577793  76613039.0"
-
       ]
      },
      "execution_count": 30,
@@ -438,11 +436,9 @@
    },
    "outputs": [
     {
-
      "data": {
       "text/plain": [
        "(1415,)"
-
       ]
      },
      "execution_count": 46,
@@ -4382,7 +4378,6 @@
    },
    "outputs": [
     {
-
      "name": "stdout",
      "output_type": "stream",
      "text": [
@@ -4483,7 +4478,6 @@
       "MAPE: 0.0126215060590655\n",
       "\n"
      ]
-
     }
    ],
    "source": [
@@ -4679,6 +4673,89 @@
     "metrics_catboost = train_and_evaluate_model(model_catboost, X_train, X_test, y_train, y_test)\n",
     "print(\"CatBoost Metrics:\", metrics_catboost)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Ensemble method using random forest and AdaBoost"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.ensemble import RandomForestRegressor, AdaBoostRegressor\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.metrics import mean_squared_error\n",
+    "\n",
+    "# Assuming you have your features (X) and target variable (y)\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+    "\n",
+    "# Create individual models\n",
+    "rf_model = RandomForestRegressor(n_estimators=100, random_state=42)\n",
+    "adaboost_model = AdaBoostRegressor(n_estimators=100, random_state=42)\n",
+    "\n",
+    "# Train the models\n",
+    "rf_model.fit(X_train, y_train)\n",
+    "adaboost_model.fit(X_train, y_train)\n",
+    "\n",
+    "# Make predictions\n",
+    "rf_predictions = rf_model.predict(X_test)\n",
+    "adaboost_predictions = adaboost_model.predict(X_test)\n",
+    "\n",
+    "# Combine predictions (simple averaging)\n",
+    "ensemble_predictions = (rf_predictions + adaboost_predictions) / 2\n",
+    "\n",
+    "# Evaluate the ensemble model\n",
+    "ensemble_mse = mean_squared_error(y_test, ensemble_predictions)\n",
+    "print(\"Ensemble MSE:\", ensemble_mse)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Validation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import accuracy_score, mean_squared_error, mean_absolute_error\n",
+    "\n",
+    "# Assuming we have the true labels (y_test) and the ensemble predictions (ensemble_predictions)\n",
+    "\n",
+    "# Calculate accuracy\n",
+    "accuracy = accuracy_score(y_test, ensemble_predictions.round())\n",
+    "print(\"Accuracy:\", accuracy)\n",
+    "\n",
+    "# Calculate RMSE\n",
+    "rmse = mean_squared_error(y_test, ensemble_predictions, squared=False)\n",
+    "print(\"RMSE:\", rmse)\n",
+    "\n",
+    "# Calculate MAE\n",
+    "mae = mean_absolute_error(y_test, ensemble_predictions)\n",
+    "print(\"MAE:\", mae)\n",
+    "\n",
+    "# Other relevant metrics\n",
+    "# For example, if your target variable is categorical:\n",
+    "# precision = precision_score(y_test, ensemble_predictions.round())\n",
+    "# recall = recall_score(y_test, ensemble_predictions.round())\n",
+    "# f1_score = f1_score(y_test, ensemble_predictions.round())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {