noshot 0.3.6__py3-none-any.whl → 0.3.8__py3-none-any.whl

noshot/data/ML TS XAI/ML Lab CIA/1/1.ipynb

@@ -0,0 +1,133 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "31067fce-1168-4c6e-97c2-bfc4fb40904b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "from sklearn.decomposition import PCA\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "from sklearn.metrics import r2_score, mean_squared_error"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "30e4ba93-9e95-4b51-a3e4-89931c193a3a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "file_path = \"airfoil_self_noise.dat\"\n",
+    "columns = [\"Frequency\", \"Angle of Attack\", \"Chord Length\", \"Free-stream Velocity\", \"Suction Side Thickness\", \"Scaled SPL\"]\n",
+    "df = pd.read_csv(file_path, sep=\"\\t\", header=None, names=columns)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c99f7732-9da4-4f2e-8ad2-16722962c435",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.columns = df.columns.str.strip()\n",
+    "X = df.iloc[:, :-1].values  # Features\n",
+    "y = df.iloc[:, -1].values   # Target"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "15940be7-1bdd-497e-81b4-eccd14424881",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "scaler = StandardScaler()\n",
+    "X_scaled = scaler.fit_transform(X)\n",
+    "\n",
+    "pca = PCA(n_components=2)\n",
+    "X_pca = pca.fit_transform(X_scaled)\n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)\n",
+    "X_pca_train, X_pca_test, _, _ = train_test_split(X_pca, y, test_size=0.2, random_state=42)\n",
+    "\n",
+    "lr_original = LinearRegression()\n",
+    "lr_original.fit(X_train, y_train)\n",
+    "y_pred_original = lr_original.predict(X_test)\n",
+    "\n",
+    "lr_pca = LinearRegression()\n",
+    "lr_pca.fit(X_pca_train, y_train)\n",
+    "y_pred_pca = lr_pca.predict(X_pca_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "617f4fdf-6722-4caf-bef3-66240c3cbc0e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(\"R2 Original:\", r2_score(y_test, y_pred_original))\n",
+    "print(\"RMSE Original:\", np.sqrt(mean_squared_error(y_test, y_pred_original)))\n",
+    "print(\"R2 PCA:\", r2_score(y_test, y_pred_pca))\n",
+    "print(\"RMSE PCA:\", np.sqrt(mean_squared_error(y_test, y_pred_pca)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "83ed2bce-0dfe-4bc4-b24b-356113eb6be3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize=(12, 5))\n",
+    "\n",
+    "plt.subplot(1, 2, 1)\n",
+    "sns.scatterplot(x=y_test, y=y_pred_original, alpha=0.5)\n",
+    "plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], '--', color='red')\n",
+    "plt.xlabel(\"Actual\")\n",
+    "plt.ylabel(\"Predicted\")\n",
+    "plt.title(\"Linear Regression on Original Data\")\n",
+    "\n",
+    "plt.subplot(1, 2, 2)\n",
+    "sns.scatterplot(x=y_test, y=y_pred_pca, alpha=0.5)\n",
+    "plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], '--', color='red')\n",
+    "plt.xlabel(\"Actual\")\n",
+    "plt.ylabel(\"Predicted\")\n",
+    "plt.title(\"Linear Regression on PCA-Reduced Data\")\n",
+    "\n",
+    "plt.tight_layout()\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 Lab CIA/2/2.ipynb

@@ -0,0 +1,139 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0c44baad-6341-4743-ae5d-502ce6647dfc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "from sklearn.decomposition import PCA\n",
+    "from sklearn.neighbors import KNeighborsClassifier\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "from sklearn.metrics import accuracy_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "328266f0-f099-47a9-b146-0a1df89d5b47",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d4ad00b9-b339-4af3-9fdc-aada76a5eac5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "file_path = \"pop_failures.dat\"\n",
+    "df = pd.read_table(file_path, sep=\"\\s+\")\n",
+    "print(\"Dataset Shape:\", df.shape)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8bf01bf7-e86b-43dc-8787-d4d50afc5f56",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b21b1c88-35e1-477a-9c8c-469ff2cb49ea",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.dropna(inplace = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3f459656-d365-4d6c-9a2a-63f021d3d27e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = df.iloc[:, 2:20].values\n",
+    "y = df.iloc[:, 20].values\n",
+    "\n",
+    "scaler = StandardScaler()\n",
+    "X_scaled = scaler.fit_transform(X)\n",
+    "\n",
+    "pca = PCA(n_components=2)\n",
+    "X_pca = pca.fit_transform(X_scaled)\n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)\n",
+    "X_pca_train, X_pca_test, _, _ = train_test_split(X_pca, y, test_size=0.2, random_state=42)\n",
+    "\n",
+    "k_values = range(1, 21)\n",
+    "accuracies_original = []\n",
+    "accuracies_pca = []\n",
+    "\n",
+    "for k in k_values:\n",
+    "    knn = KNeighborsClassifier(n_neighbors=k)\n",
+    "    knn.fit(X_train, y_train)\n",
+    "    y_pred_original = knn.predict(X_test)\n",
+    "    accuracies_original.append(accuracy_score(y_test, y_pred_original))\n",
+    "    \n",
+    "    knn.fit(X_pca_train, y_train)\n",
+    "    y_pred_pca = knn.predict(X_pca_test)\n",
+    "    accuracies_pca.append(accuracy_score(y_test, y_pred_pca))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f4ff07e6-a4af-433b-b9fe-f9134dea12e1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize=(10, 5))\n",
+    "plt.plot(k_values, accuracies_original, label='KNN without PCA', marker='o')\n",
+    "plt.plot(k_values, accuracies_pca, label='KNN with PCA', marker='s')\n",
+    "plt.xlabel(\"K Value\")\n",
+    "plt.ylabel(\"Accuracy\")\n",
+    "plt.title(\"KNN Accuracy Comparison with and without PCA\")\n",
+    "plt.legend()\n",
+    "plt.grid()\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 Lab CIA/3/3.ipynb

@@ -0,0 +1,130 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5bd9b810-1eef-4f1c-8b46-86e8e8f013d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.decomposition import PCA\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "from sklearn.metrics import r2_score, mean_squared_error"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "733faa11-400f-4160-8292-e8bd90948264",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "file_path = \"go_track_tracks.csv\"\n",
+    "df = pd.read_csv(file_path)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bd1254cc-242c-439b-9baf-8c0b08daf597",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.select_dtypes(include=[np.number]).dropna()\n",
+    "\n",
+    "X = df.iloc[:, :-1].values  # Features\n",
+    "y = df.iloc[:, -1].values   # Target\n",
+    "\n",
+    "scaler = StandardScaler()\n",
+    "X_scaled = scaler.fit_transform(X)\n",
+    "\n",
+    "pca = PCA(n_components=2)\n",
+    "X_pca = pca.fit_transform(X_scaled)\n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)\n",
+    "X_pca_train, X_pca_test, _, _ = train_test_split(X_pca, y, test_size=0.2, random_state=42)\n",
+    "\n",
+    "lr_original = LinearRegression()\n",
+    "lr_original.fit(X_train, y_train)\n",
+    "y_pred_original = lr_original.predict(X_test)\n",
+    "\n",
+    "lr_pca = LinearRegression()\n",
+    "lr_pca.fit(X_pca_train, y_train)\n",
+    "y_pred_pca = lr_pca.predict(X_pca_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e0116213-f55e-4512-95a0-e1983bddcd30",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "r2_original = r2_score(y_test, y_pred_original)\n",
+    "rmse_original = np.sqrt(mean_squared_error(y_test, y_pred_original))\n",
+    "\n",
+    "r2_pca = r2_score(y_test, y_pred_pca)\n",
+    "rmse_pca = np.sqrt(mean_squared_error(y_test, y_pred_pca))\n",
+    "\n",
+    "print(\"R2 Original:\", r2_original)\n",
+    "print(\"RMSE Original:\", rmse_original)\n",
+    "print(\"R2 PCA:\", r2_pca)\n",
+    "print(\"RMSE PCA:\", rmse_pca)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ba2a1ef3-1554-4164-9966-3bc59fdb69e3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize=(10, 5))\n",
+    "\n",
+    "plt.subplot(1, 2, 1)\n",
+    "plt.scatter(y_test, y_pred_original, alpha=0.5)\n",
+    "plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], '--', color='red')\n",
+    "plt.xlabel(\"Actual\")\n",
+    "plt.ylabel(\"Predicted\")\n",
+    "plt.title(\"Linear Regression on Original Data\")\n",
+    "\n",
+    "plt.subplot(1, 2, 2)\n",
+    "plt.scatter(y_test, y_pred_pca, alpha=0.5)\n",
+    "plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], '--', color='red')\n",
+    "plt.xlabel(\"Actual\")\n",
+    "plt.ylabel(\"Predicted\")\n",
+    "plt.title(\"Linear Regression on PCA-Reduced Data\")\n",
+    "\n",
+    "plt.tight_layout()\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 Lab CIA/4/4.ipynb

@@ -0,0 +1,141 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8b01d639-7417-4a71-a735-d519043691ac",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.decomposition import PCA\n",
+    "from sklearn.neighbors import KNeighborsClassifier\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import StandardScaler, LabelEncoder\n",
+    "from sklearn.metrics import accuracy_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "03cbb0a7-0a95-4e08-94a9-028c664ecbe1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "file_path = \"Wilt.csv\"\n",
+    "df = pd.read_csv(file_path)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0a4961c3-0fea-401b-a7f0-5f6fd0eb9e69",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y = df.iloc[:, 0]\n",
+    "X = df.iloc[:, 1:]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d6699a1a-5436-40d7-84b9-f2c3d5e87850",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if y.dtype == 'object':\n",
+    "    class_mapping = {label: idx for idx, label in enumerate(y.unique())}\n",
+    "    y = y.map(class_mapping)\n",
+    "\n",
+    "scaler = StandardScaler()\n",
+    "X_scaled = scaler.fit_transform(X)\n",
+    "\n",
+    "pca = PCA(n_components=2)\n",
+    "X_pca = pca.fit_transform(X_scaled)\n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)\n",
+    "X_pca_train, X_pca_test, _, _ = train_test_split(X_pca, y, test_size=0.2, random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0c6c271e-3725-4472-b082-a96aa9850ec6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "knn_original = KNeighborsClassifier(n_neighbors=5)\n",
+    "knn_original.fit(X_train, y_train)\n",
+    "y_pred_original = knn_original.predict(X_test)\n",
+    "accuracy_original = accuracy_score(y_test, y_pred_original)\n",
+    "\n",
+    "knn_pca = KNeighborsClassifier(n_neighbors=5)\n",
+    "knn_pca.fit(X_pca_train, y_train)\n",
+    "y_pred_pca = knn_pca.predict(X_pca_test)\n",
+    "accuracy_pca = accuracy_score(y_test, y_pred_pca)\n",
+    "\n",
+    "print(\"Accuracy without PCA:\", accuracy_original)\n",
+    "print(\"Accuracy with PCA:\", accuracy_pca)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5b129aaa-8fba-4dac-a4be-e94c277d40ae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize=(6, 4))\n",
+    "plt.scatter(X_pca[:, 0], X_pca[:, 1], c=y, cmap='coolwarm', alpha=0.5)\n",
+    "plt.xlabel(\"Principal Component 1\")\n",
+    "plt.ylabel(\"Principal Component 2\")\n",
+    "plt.title(\"PCA Visualization of Wilt Dataset\")\n",
+    "plt.colorbar(label=\"Class\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a4b9dcf0-d091-4ece-9651-e84932fb1eba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "labels = ['Without PCA', 'With PCA']\n",
+    "accuracies = [accuracy_original, accuracy_pca]\n",
+    "plt.figure(figsize=(6, 4))\n",
+    "plt.bar(labels, accuracies, color=['blue', 'orange'])\n",
+    "plt.xlabel(\"Model\")\n",
+    "plt.ylabel(\"Accuracy\")\n",
+    "plt.title(\"KNN Classification Accuracy Comparison\")\n",
+    "plt.ylim(0, 1)\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
+}