noshot 2.0.0__py3-none-any.whl → 3.0.0__py3-none-any.whl

noshot/data/ML TS XAI/ML/Main/6. Naive Bayes Classifier (Agaricus Lepiota Dataset).ipynb

@@ -0,0 +1,153 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5bafc01f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.naive_bayes import GaussianNB\n",
+    "from sklearn.metrics import accuracy_score, roc_curve, auc\n",
+    "from sklearn.metrics import classification_report, confusion_matrix, ConfusionMatrixDisplay\n",
+    "from sklearn.preprocessing import LabelEncoder"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6ef7990c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"data/agaricus-lepiota.data\", header=None)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a5e91b36",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = df.drop(columns=[0])\n",
+    "X"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "eb58da4a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for col in X.columns: \n",
+    "    X[col] = LabelEncoder().fit_transform(X[col])\n",
+    "X"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a4a1e805",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y = df[0]\n",
+    "y = LabelEncoder().fit_transform(y)\n",
+    "y"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "114a44f5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42, stratify=y)\n",
+    "nb = GaussianNB()\n",
+    "nb.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "79e3ed49",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = nb.predict(X_test)\n",
+    "print(f\"Accuracy : {accuracy_score(y_test,y_pred)}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f377d0cc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "report = classification_report(y_test,y_pred)\n",
+    "print(report)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e42690dc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cm = confusion_matrix(y_test,y_pred)\n",
+    "ConfusionMatrixDisplay(cm).plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bd35e7f4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred_proba = nb.predict_proba(X_test)[:,1]\n",
+    "fpr, tpr, thresholds = roc_curve(y_test, y_pred_proba) \n",
+    "roc_auc = auc(fpr, tpr)\n",
+    "\n",
+    "plt.plot(fpr, tpr, label='ROC curve (area = %0.2f)' % roc_auc)\n",
+    "plt.plot([0, 1], [0, 1], 'k--', label='No Skill')\n",
+    "plt.xlabel('False Positive Rate')\n",
+    "plt.ylabel('True Positive Rate')\n",
+    "plt.title('ROC Curve for Breast Cancer Classification')\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

noshot/data/ML TS XAI/ML/Main/6. Naive Bayes Classifier (Wine Dataset).ipynb

@@ -0,0 +1,89 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "939c616d-2779-4e21-adcf-1d070898d65b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn import datasets\n",
+    "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.naive_bayes import GaussianNB\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "17720a0d-e788-4b1d-b2b2-a542f6b824a2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "wine = pd.read_csv('data/wine-dataset.csv')\n",
+    "print(wine.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a050923e-4382-4ff7-93bf-446b117c0ef5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = wine.iloc[:, :13]\n",
+    "X.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9f1a4355-718e-40ed-b892-3e3d03c4ef3c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y = wine.iloc[:, 13]\n",
+    "y"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dd3f31ef-c0d2-48dd-9fb7-338c10f9fbf9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state = 0)\n",
+    "\n",
+    "gnb = GaussianNB().fit(X_train, y_train)\n",
+    "gnb_predictions = gnb.predict(X_test)\n",
+    "accuracy = gnb.score(X_test, y_test)\n",
+    "accuracy\n",
+    "cm = confusion_matrix(y_test, gnb_predictions)\n",
+    "ConfusionMatrixDisplay(cm).plot()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

noshot/data/ML TS XAI/ML/Main/7. SVM (Rice Dataset).ipynb

@@ -0,0 +1,208 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "30043339",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "from sklearn.decomposition import PCA\n",
+    "from sklearn import svm\n",
+    "from sklearn.svm import SVC\n",
+    "from scipy.io import arff"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "74c26fca",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = arff.loadarff(\"data/rice.arff\")\n",
+    "df = pd.DataFrame(data[0])\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "51439c01",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "03e7a5d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['Class'].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cf14dcf8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['Class'] = df['Class'].map({b'Cammeo':0, b'Osmancik':1})\n",
+    "df['Class'].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dba18b10",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "246346b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = df.drop(columns=['Class'])\n",
+    "y = df['Class']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d182a204",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = PCA(n_components=2).fit_transform(X)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f8e67728",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "99facee4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.scatter(X[:,0], X[:,1], c=y, edgecolor=\"black\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "23da86fe-1c5d-4f57-ab29-a2bb6b060783",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "903cccff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "models=[\n",
+    "    SVC(kernel='linear', C=1, degree=5, gamma=\"auto\", probability=True),\n",
+    "    SVC(kernel='rbf', C=1, gamma='scale', probability=True),\n",
+    "    SVC(kernel='poly', C=1, degree=5, gamma=\"auto\", probability=True)\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ff7b81e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.preprocessing import StandardScaler\n",
+    "from sklearn.pipeline import make_pipeline\n",
+    "from sklearn.metrics import classification_report,confusion_matrix,ConfusionMatrixDisplay\n",
+    "from sklearn.metrics import roc_curve, auc\n",
+    "from mlxtend.plotting import plot_decision_regions\n",
+    "\n",
+    "for model in models:\n",
+    "    nonlinear_svm = make_pipeline(StandardScaler(), model)\n",
+    "    nonlinear_svm.fit(X_train, y_train)\n",
+    "    y_pred = nonlinear_svm.predict(X_test)\n",
+    "    print(\"SVM Classification Report:\")\n",
+    "    print(classification_report(y_test, y_pred))\n",
+    "    print(f\"Accuracy: {accuracy_score(y_test, y_pred):.2f}\")\n",
+    "    plot_decision_regions(X=X_train, \n",
+    "                          y=y_train.values,\n",
+    "                          clf=nonlinear_svm, \n",
+    "                          legend=2)\n",
+    "\n",
+    "    plt.title('SVM Decision Region Boundary', size=16)\n",
+    "    plt.show()\n",
+    "    conf=confusion_matrix(y_test,y_pred)\n",
+    "    ConfusionMatrixDisplay(conf,display_labels=[0,1]).plot(cmap='Blues')\n",
+    "    plt.show()\n",
+    "    y_pred_proba=nonlinear_svm.predict_proba(X_test)[:,1]\n",
+    "    fpr, tpr, thresholds = roc_curve(y_test, y_pred_proba) \n",
+    "    roc_auc = auc(fpr, tpr)\n",
+    "    \n",
+    "    plt.plot(fpr, tpr, label='ROC curve (area = %0.2f)' % roc_auc)\n",
+    "    plt.plot([0, 1], [0, 1], 'k--', label='No Skill')\n",
+    "    plt.xlabel('False Positive Rate')\n",
+    "    plt.ylabel('True Positive Rate')\n",
+    "    plt.title('ROC Curve for Rice Classification')\n",
+    "    plt.legend()\n",
+    "    plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}