noshot 1.0.0__py3-none-any.whl → 3.0.0__py3-none-any.whl

noshot/data/ML TS XAI/ML/Main/4. Linear Regression (Machine Dataset).ipynb

@@ -0,0 +1,115 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2d42ca1a-531d-4d5b-aee4-a489d5033d1b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "from sklearn.metrics import r2_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f81220bc-5415-4b02-b2fd-fd5a8ff8c97a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('data/machine-data.csv')\n",
+    "print(\"Shape:\", df.shape)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "958f3a04-3ae7-442b-a6e7-9134b9c5aeb3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x = df.iloc[:,3:4].values\n",
+    "y = df.iloc[:,8].values\n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 0)\n",
+    "regressor = LinearRegression()\n",
+    "regressor.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5b15fa5c-5c78-436b-8f33-4f431c797788",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = regressor.predict(X_test)\n",
+    "y_pred_train = regressor.predict(X_train)\n",
+    "print(\"Model Score: \", regressor.score(X_test, y_test))\n",
+    "print(\"R2 Score: \", r2_score(y_test, y_pred))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b044ea95-014e-466b-b036-8ba9f96e3910",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.scatter(X_train, y_train, color = 'red')\n",
+    "plt.plot(X_train, regressor.predict(X_train), color = 'blue')\n",
+    "plt.title('Y vs X (Training set)')\n",
+    "plt.xlabel('X')\n",
+    "plt.ylabel('Y')\n",
+    "plt.show()\n",
+    "plt.scatter(X_test, y_test, color = 'red')\n",
+    "plt.plot(X_train, regressor.predict(X_train), color = 'blue')\n",
+    "plt.title('Y vs X (Test set)')\n",
+    "plt.xlabel('X')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "33c64414-d432-439e-a976-d28a9b4c3f2a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_future_expereince = [[2],[4]]\n",
+    "print(\"Prediction :\", regressor.predict(X_future_expereince))\n",
+    "plt.scatter(X_future_expereince, regressor.predict(X_future_expereince), color = 'red')\n",
+    "plt.plot(X_train, regressor.predict(X_train), color = 'blue')\n",
+    "plt.title('Y vs X (Test set)')\n",
+    "plt.xlabel('X')\n",
+    "plt.ylabel('Y')\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/4. Linear Regression (Real Estate Dataset).ipynb

@@ -0,0 +1,159 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4e998aac",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.model_selection import train_test_split"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7fef393a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=pd.read_excel(\"data/real-estate.xlsx\")\n",
+    "print(\"Shape:\", df.shape)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "18f866b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c238436e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sns.pairplot(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "480aa3b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "corr = df.corr()\n",
+    "sns.heatmap(corr)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7fe55d8d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def lin_reg(colX):\n",
+    "    X = df[colX].values\n",
+    "    y = df['Y house price of unit area'].values\n",
+    "\n",
+    "    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+    "\n",
+    "    N = len(X_train)\n",
+    "    sum_x = np.sum(X_train)\n",
+    "    sum_y = np.sum(y_train)\n",
+    "    sum_xy = np.sum(X_train * y_train)\n",
+    "    sum_x2 = np.sum(X_train ** 2)\n",
+    "\n",
+    "    beta1 = (N * sum_xy - sum_x * sum_y) / (N * sum_x2 - sum_x ** 2)\n",
+    "    beta0 = (sum_y - beta1 * sum_x) / N\n",
+    "\n",
+    "    y_pred_train = beta1 * X_train + beta0\n",
+    "    y_pred_test = beta1 * X_test + beta0\n",
+    "\n",
+    "    plt.scatter(X_train, y_train, color='blue', label='Training Data Points')\n",
+    "    plt.plot(X_train, y_pred_train, color='red', label='Regression Line (Training)')\n",
+    "    plt.xlabel(colX)\n",
+    "    plt.ylabel('Y house price of unit area')\n",
+    "    plt.title(f'Linear Regression: {colX} vs Y (Training Set)')\n",
+    "    plt.legend()\n",
+    "    plt.show()\n",
+    "\n",
+    "    plt.scatter(X_test, y_test, color='blue', label='Test Data Points')\n",
+    "    plt.plot(X_test, y_pred_test, color='red', label='Regression Line (Test)')\n",
+    "    plt.xlabel(colX)\n",
+    "    plt.ylabel('Y house price of unit area')\n",
+    "    plt.title(f'Linear Regression: {colX} vs Y (Test Set)')\n",
+    "    plt.legend()\n",
+    "    plt.show()\n",
+    "\n",
+    "    mse_train = np.mean((y_train - y_pred_train) ** 2)\n",
+    "    mse_test = np.mean((y_test - y_pred_test) ** 2)\n",
+    "    print(f\"Mean Squared Error (MSE) for Training Set: {mse_train}\")\n",
+    "    print(f\"Mean Squared Error (MSE) for Test Set: {mse_test}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8d80579a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lin_reg('X3 distance to the nearest MRT station')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6b162be8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lin_reg('X5 latitude')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7b576d0a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lin_reg('X6 longitude')"
+   ]
+  }
+ ],
+ "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/{XAI/XAI 2/Exp-3 (EDA-loan).ipynb → ML/Main/5. Logistic Regression (Magic04 Dataset).ipynb }

@@ -3,198 +3,177 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ccf7df96",
+   "id": "5bafc01f",
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd \n",
-    "import numpy as np\n",
+    "import pandas as pd\n",
     "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns"
+    "import seaborn as sns\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LogisticRegression\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 MinMaxScaler\n",
+    "from sklearn.decomposition import PCA"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "05fcafeb",
+   "id": "6ef7990c",
    "metadata": {},
    "outputs": [],
    "source": [
-    "auto=pd.read_csv(\"loan_data.csv\")\n",
-    "auto.reset_index(inplace=True)\n",
-    "auto"
+    "df = pd.read_csv('data/magic04.data', header=None)\n",
+    "df.head()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "774d8ecf",
+   "id": "1f1065b5",
    "metadata": {},
    "outputs": [],
    "source": [
-    "auto.head()"
+    "df[10] = df[10].map({'g':0,'h':1})"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "66bef117",
+   "id": "5f228790",
    "metadata": {},
    "outputs": [],
    "source": [
-    "auto.tail()"
+    "sns.pairplot(df, hue=10)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d12303ac",
+   "id": "a5e91b36",
    "metadata": {},
    "outputs": [],
    "source": [
-    "auto.info()"
+    "X = df.drop(columns=[10])\n",
+    "X"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "13ca9a52",
+   "id": "dcbc168e",
    "metadata": {},
    "outputs": [],
    "source": [
-    "auto.nunique()"
+    "X = MinMaxScaler().fit_transform(X)\n",
+    "X"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "406b67f4",
+   "id": "a4a1e805",
    "metadata": {},
    "outputs": [],
    "source": [
-    "auto.isnull()"
+    "y = df[10]\n",
+    "y"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "eaa5f031",
+   "id": "7edc3c7f",
    "metadata": {},
    "outputs": [],
    "source": [
-    "auto.describe()"
+    "y.value_counts()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "214537c9",
+   "id": "243c084d",
    "metadata": {},
    "outputs": [],
    "source": [
-    "data = auto.drop(['index'], axis = 1)\n",
-    "data"
+    "lr = LogisticRegression(max_iter=10000, random_state=0)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9e22f6d6",
+   "id": "92615b1f",
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(auto.purpose.unique())"
+    "X_train, X_test, y_train, y_test=train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "95a9706b",
+   "id": "114a44f5",
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(auto.purpose.nunique())"
+    "lr.fit(X_train,y_train)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "0c895e16",
+   "id": "79e3ed49",
    "metadata": {},
    "outputs": [],
    "source": [
-    "au=auto.head(50)\n",
-    "au"
+    "y_pred = lr.predict(X_test)\n",
+    "print(f\"Accuracy : {accuracy_score(y_test,y_pred)}\")"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ff300c7a",
+   "id": "f377d0cc",
    "metadata": {},
    "outputs": [],
    "source": [
-    "plt.title(\"INSTALLMENT BASED ON ANNUAL INCOME\")\n",
-    "plt.xlabel(\"log.annual.inc\")\n",
-    "plt.ylabel(\"installment\")\n",
-    "plt.plot(au['log.annual.inc'],au['installment'],color=\"blue\")\n",
-    "plt.show(10,20)"
+    "report = classification_report(y_test,y_pred)\n",
+    "print(report)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f53a7f1d",
+   "id": "e42690dc",
    "metadata": {},
    "outputs": [],
    "source": [
-    "plt.title(\"INSTALLMENT BASED ON ANNUAL INCOME\")\n",
-    "plt.xlabel(\"log.annual.inc\")\n",
-    "plt.ylabel(\"installment\")\n",
-    "plt.bar(au['log.annual.inc'],au['installment'],color=\"green\")\n",
-    "plt.show()\n"
+    "cm = confusion_matrix(y_test,y_pred)\n",
+    "ConfusionMatrixDisplay(cm).plot()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f0625d78",
+   "id": "bd35e7f4",
    "metadata": {},
    "outputs": [],
    "source": [
-    "sns.pairplot(au)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "88d11bbd",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "plt.hist(au['installment'],bins=10,color='cyan')\n",
+    "y_pred_proba = lr.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()"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "bfc6edb5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "plt.figure(figsize=(12, 7))\n",
-    "sns.heatmap(au.corr(), annot = True, vmin = -1, vmax = 1)\n",
-    "plt.show()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "adc44fdc-323a-4b9f-9ec2-1227ef925241",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

noshot/data/ML TS XAI/ML/Main/5. Logistic Regression (Wine Dataset).ipynb

@@ -0,0 +1,112 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0fcc8bb7-4d22-4d3b-b58a-302bb24f8f2e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import itertools\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn import linear_model,datasets\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n",
+    "\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d28e507b-fb15-4058-a161-656859a27c65",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "wine = pd.read_csv('data/wine-dataset.csv')\n",
+    "print(\"Shape:\", wine.shape)\n",
+    "wine.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c4e953da-6941-43f2-a9ce-aab907876d45",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "wine.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9ee44a66-dc4a-4c79-9dab-eec60669dd8b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = wine.iloc[:, :13]\n",
+    "y = wine.iloc[:, 13]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bd9d60dd-8272-46b4-8335-69d9751ed0c7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train,X_test,y_train,y_test = train_test_split(X, y, test_size=0.30, random_state=7)\n",
+    "\n",
+    "log_reg_model = linear_model.LogisticRegression()\n",
+    "log_reg_model.fit(X_train,y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7c8fca42-c8d8-4334-9cc4-da4f5e1b0a1e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "log_reg_base_score = log_reg_model.score(X_test,y_test)\n",
+    "print(\"The score for the Logistic Regression Model is : \", log_reg_base_score)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "61bbb23e-cb29-41ae-9ea3-82e8d465c7f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cm = confusion_matrix(y_test, log_reg_model.predict(X_test))\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
+}