noshot 2.0.0__py3-none-any.whl → 4.0.0__py3-none-any.whl

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
+}

noshot/data/ML TS XAI/ML/Main/8. FeedForward NN (Sobar72 Dataset).ipynb

@@ -0,0 +1,260 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "aYlTWIqe5rL9"
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "import tensorflow as tf\n",
+    "from tensorflow.keras.models import Sequential\n",
+    "from tensorflow.keras.layers import Dense, Flatten\n",
+    "from tensorflow.keras.optimizers import Adam\n",
+    "from tensorflow.keras.losses import SparseCategoricalCrossentropy\n",
+    "from tensorflow.keras.metrics import SparseCategoricalAccuracy\n",
+    "\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 226
+    },
+    "id": "ejG3Obse5smj",
+    "outputId": "85d8cf13-eb83-49f6-e98f-0893fabb1cff"
+   },
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"data/sobar-72.csv\")\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "hLECDj5558Om"
+   },
+   "outputs": [],
+   "source": [
+    "X = df.drop(columns=['ca_cervix'])\n",
+    "y = df['ca_cervix']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "MhA_LTNA5-49"
+   },
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from tensorflow.keras import regularizers\n",
+    "from tensorflow.keras.layers import Dropout"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "rjH4KJqq5_7-"
+   },
+   "outputs": [],
+   "source": [
+    "x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+    "\n",
+    "y_train = tf.keras.utils.to_categorical(y_train, num_classes=2)\n",
+    "y_test = tf.keras.utils.to_categorical(y_test, num_classes=2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "5lQVtYUC6A67"
+   },
+   "outputs": [],
+   "source": [
+    "model = tf.keras.models.Sequential([\n",
+    "    tf.keras.layers.Dense(128, activation='relu', input_shape=(19,),\n",
+    "                         kernel_regularizer=regularizers.l2(0.001)),\n",
+    "    Dropout(0.3),\n",
+    "    tf.keras.layers.Dense(64, activation='relu',\n",
+    "                         kernel_regularizer=regularizers.l2(0.001)),\n",
+    "    Dropout(0.3),\n",
+    "    tf.keras.layers.Dense(units=2, activation='softmax')\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "cgxMgB8q6Cjg"
+   },
+   "outputs": [],
+   "source": [
+    "model.compile(optimizer='adam',\n",
+    "              loss='categorical_crossentropy',\n",
+    "              metrics=['accuracy'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "y71y0yDT6MnK"
+   },
+   "outputs": [],
+   "source": [
+    "early_stopping = tf.keras.callbacks.EarlyStopping(\n",
+    "    monitor='val_loss',\n",
+    "    patience=10,\n",
+    "    restore_best_weights=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "1PZHOQQp6NpP",
+    "outputId": "c1d34cfd-5b74-4f42-aef1-74bbfc6aec95"
+   },
+   "outputs": [],
+   "source": [
+    "history = model.fit(x_train, y_train,\n",
+    "                    epochs=50,\n",
+    "                    batch_size=32,\n",
+    "                    validation_split=0.2,\n",
+    "                    callbacks=[early_stopping],\n",
+    "                    verbose=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 362
+    },
+    "id": "qjhgjajp6O3J",
+    "outputId": "b04cb0d7-bc3f-4991-e5f8-c51698856ab7"
+   },
+   "outputs": [],
+   "source": [
+    "def plot_history(history):\n",
+    "    plt.figure(figsize=(12, 5))\n",
+    "\n",
+    "    # Plot loss\n",
+    "    plt.subplot(1, 2, 1)\n",
+    "    plt.plot(history.history['loss'], label='Training Loss')\n",
+    "    plt.plot(history.history['val_loss'], label='Validation Loss')\n",
+    "    plt.title('Training and Validation Loss')\n",
+    "    plt.xlabel('Epoch')\n",
+    "    plt.ylabel('Loss')\n",
+    "    plt.legend()\n",
+    "\n",
+    "    # Plot accuracy\n",
+    "    plt.subplot(1, 2, 2)\n",
+    "    plt.plot(history.history['accuracy'], label='Training Accuracy')\n",
+    "    plt.plot(history.history['val_accuracy'], label='Validation Accuracy')\n",
+    "    plt.title('Training and Validation Accuracy')\n",
+    "    plt.xlabel('Epoch')\n",
+    "    plt.ylabel('Accuracy')\n",
+    "    plt.legend()\n",
+    "\n",
+    "    plt.tight_layout()\n",
+    "    plt.show()\n",
+    "\n",
+    "plot_history(history)\n",
+    "\n",
+    "loss, accuracy = model.evaluate(x_test, y_test)\n",
+    "print(f'Test accuracy: {accuracy:.4f}')\n",
+    "print(f'Test loss: {loss:.4f}')\n",
+    "\n",
+    "print(f\"Actual: {y_test[1]}, Predicted: {model.predict(x_test[:1])}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 1000
+    },
+    "id": "VaBGSYTs6Qeq",
+    "outputId": "39af0238-9045-412e-cd8b-258fdc133948"
+   },
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import classification_report,confusion_matrix,ConfusionMatrixDisplay,roc_curve, auc, accuracy_score\n",
+    "y_pred=model.predict(x_test)\n",
+    "y_test= [np.argmax(y, axis=None, out=None) for y in y_test]\n",
+    "y_pred= [np.argmax(y, axis=None, out=None) for y in y_pred]\n",
+    "print(\"Feed Forward Classification Report:\")\n",
+    "print(classification_report(y_test, y_pred))\n",
+    "print(f\"Accuracy: {accuracy_score(y_test, y_pred):.2f}\")\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=model.predict(x_test)[:,1]\n",
+    "fpr, tpr, thresholds = roc_curve(y_test, y_pred_proba)\n",
+    "roc_auc = auc(fpr, tpr)\n",
+    "\n",
+    "plt.figure()\n",
+    "plt.plot(fpr, tpr, color='darkorange', lw=2, label='ROC curve (area = %0.2f)' % roc_auc)\n",
+    "plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')\n",
+    "plt.xlim([0.0, 1.0])\n",
+    "plt.ylim([0.0, 1.05])\n",
+    "plt.xlabel('False Positive Rate')\n",
+    "plt.ylabel('True Positive Rate')\n",
+    "plt.title('Receiver Operating Characteristic')\n",
+    "plt.legend(loc=\"lower right\")\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "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": 4
+}