Created using Colab_Class2

ModelTrainer.ipynb

@@ -0,0 +1,127 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyNXuzwVU1r7VkwSe9K3urmL",
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/Saeidhoseinipour/100Data/blob/main/ModelTrainer.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "DjzHGr01XPn5"
+      },
+      "outputs": [],
+      "source": [
+        "from sklearn.model_selection import train_test_split\n",
+        "from sklearn.linear_model import LogisticRegression, LinearRegression\n",
+        "from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor\n",
+        "from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor\n",
+        "from sklearn.cluster import KMeans\n",
+        "from sklearn.decomposition import PCA\n",
+        "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix, mean_squared_error, silhouette_score\n",
+        "\n",
+        "class ModelTrainer:\n",
+        "    def __init__(self, datasets):\n",
+        "        \"\"\"\n",
+        "        Initialize the class with cleaned datasets.\n",
+        "        :param datasets: Dictionary of cleaned datasets from BioinformaticsDatasetCleaner.\n",
+        "        \"\"\"\n",
+        "        self.datasets = datasets\n",
+        "\n",
+        "    def train_model(self, dataset_name, target_column):\n",
+        "        \"\"\"\n",
+        "        Train a machine learning model based on the dataset type.\n",
+        "        :param dataset_name: Name of the dataset.\n",
+        "        :param target_column: Name of the target column.\n",
+        "        \"\"\"\n",
+        "        if dataset_name in self.datasets:\n",
+        "            dataset = self.datasets[dataset_name]['data']\n",
+        "            dataset_type = self.datasets[dataset_name]['type']\n",
+        "\n",
+        "            # Split data into features and target\n",
+        "            X = dataset.drop(columns=[target_column])\n",
+        "            y = dataset[target_column]\n",
+        "\n",
+        "            # Split into training and testing sets\n",
+        "            X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+        "\n",
+        "            # Train a model based on dataset type\n",
+        "            if dataset_type == 'quantitative':\n",
+        "                # Regression model for quantitative data\n",
+        "                model = RandomForestRegressor()\n",
+        "                model.fit(X_train, y_train)\n",
+        "                y_pred = model.predict(X_test)\n",
+        "\n",
+        "                # Evaluate regression model\n",
+        "                mse = mean_squared_error(y_test, y_pred)\n",
+        "                print(f\"Mean Squared Error for {dataset_name}: {mse:.2f}\")\n",
+        "\n",
+        "            elif dataset_type == 'qualitative':\n",
+        "                # Classification model for qualitative data\n",
+        "                model = RandomForestClassifier()\n",
+        "                model.fit(X_train, y_train)\n",
+        "                y_pred = model.predict(X_test)\n",
+        "\n",
+        "                # Evaluate classification model\n",
+        "                accuracy = accuracy_score(y_test, y_pred)\n",
+        "                print(f\"Model Accuracy for {dataset_name}: {accuracy:.2f}\")\n",
+        "                print(\"Classification Report:\\n\", classification_report(y_test, y_pred))\n",
+        "                print(\"Confusion Matrix:\\n\", confusion_matrix(y_test, y_pred))\n",
+        "\n",
+        "            elif dataset_type == 'unsupervised':\n",
+        "                # Clustering model for unsupervised data\n",
+        "                model = KMeans(n_clusters=3)\n",
+        "                model.fit(X)\n",
+        "                labels = model.labels_\n",
+        "\n",
+        "                # Evaluate clustering model\n",
+        "                silhouette = silhouette_score(X, labels)\n",
+        "                print(f\"Silhouette Score for {dataset_name}: {silhouette:.2f}\")\n",
+        "\n",
+        "            else:\n",
+        "                raise ValueError(f\"No model defined for {dataset_type} data.\")\n",
+        "\n",
+        "            return model, X_test, y_test\n",
+        "        else:\n",
+        "            raise KeyError(f\"Dataset {dataset_name} not found.\")\n",
+        "\n",
+        "    def apply_pca(self, dataset_name, n_components=2):\n",
+        "        \"\"\"\n",
+        "        Apply PCA for dimensionality reduction.\n",
+        "        :param dataset_name: Name of the dataset.\n",
+        "        :param n_components: Number of components for PCA.\n",
+        "        \"\"\"\n",
+        "        if dataset_name in self.datasets:\n",
+        "            dataset = self.datasets[dataset_name]['data']\n",
+        "            pca = PCA(n_components=n_components)\n",
+        "            transformed_data = pca.fit_transform(dataset)\n",
+        "            print(f\"PCA applied to {dataset_name}. Transformed data shape: {transformed_data.shape}\")\n",
+        "            return transformed_data\n",
+        "        else:\n",
+        "            raise KeyError(f\"Dataset {dataset_name} not found.\")"
+      ]
+    }
+  ]
+}