noshot 7.0.0__py3-none-any.whl → 8.0.0__py3-none-any.whl

noshot/data/ML TS XAI/ML/ML 3 (Latest)/3. LDA.ipynb

@@ -0,0 +1,195 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4cb19356",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn import datasets\n",
+    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "import seaborn as sns\n",
+    "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4bfb20c1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "url = \"https://archive.ics.uci.edu/ml/machine-learning-databases/balance-scale/balance-scale.data\"\n",
+    "df = pd.read_csv(url, names=['class name','left-weight','left-distance','right-weight','right-distance'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c52d5405-9da9-40a9-9116-afe433e93046",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1eaf20bd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "feature = ['left-weight','left-distance','right-weight','right-distance']\n",
+    "x = df.loc[:,feature]\n",
+    "y = df.loc[:,'class name']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "73208c45",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x = StandardScaler().fit_transform(x)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0d5df04c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lda = LDA(n_components=2)\n",
+    "x_lda = lda.fit_transform(x, y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e262379f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_lda = pd.DataFrame(data = x_lda, columns = ['LDA1', 'LDA2'])\n",
+    "df_lda['class name'] = y"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7e14b628",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize=(12, 6))\n",
+    "plt.subplot(1, 2, 1)\n",
+    "\n",
+    "for target, color, marker in zip(df['class name'].unique(), ['r', 'g', 'b'], ['o', 's', '^']):\n",
+    "    plt.scatter(x[y == target, 0], x[y == target, 1], c=color, marker=marker, label=target)\n",
+    "\n",
+    "plt.xlabel('Feature 1')\n",
+    "plt.ylabel('Feature 2')\n",
+    "plt.title('Before LDA')\n",
+    "plt.legend()\n",
+    "\n",
+    "plt.subplot(1, 2, 2)\n",
+    "\n",
+    "for target, color, marker in zip(df_lda['class name'].unique(), ['r', 'g', 'b'], ['o', 's', '^']):\n",
+    "    plt.scatter(df_lda[df_lda['class name'] == target]['LDA1'], \n",
+    "                df_lda[df_lda['class name'] == target]['LDA2'], \n",
+    "                c=color, marker=marker, label=target)\n",
+    "\n",
+    "plt.xlabel('LDA1')\n",
+    "plt.ylabel('LDA2')\n",
+    "plt.title('After LDA')\n",
+    "plt.legend()\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "79b009f7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize=(12, 6))\n",
+    "plt.subplot(1, 2, 1)\n",
+    "sns.heatmap(df.corr(numeric_only=True), annot=True, cmap='viridis')\n",
+    "plt.title('Before LDA')\n",
+    "\n",
+    "df_lda = pd.DataFrame(data=x_lda, columns=['LDA1', 'LDA2'])\n",
+    "#df_lda['class name'] = y\n",
+    "plt.subplot(1, 2, 2)\n",
+    "sns.heatmap(df_lda.corr(numeric_only=True), annot=True, cmap='viridis')\n",
+    "plt.title('After LDA')\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "82622933",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = lda.predict(x)  \n",
+    "\n",
+    "cm = confusion_matrix(y, y_pred)\n",
+    "\n",
+    "disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=lda.classes_)\n",
+    "disp.plot()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c5bbcdd2-9bbd-4bb2-91c8-62ed34f225cc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sns.heatmap(cm,annot=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a0135321-d81c-48bc-9c83-8430a3662a0a",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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/ML 3 (Latest)/4. Linear Regression.ipynb

@@ -0,0 +1,267 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "db8a58e5",
+   "metadata": {},
+   "source": [
+    "<h1>Linear Regression</h1>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "de374599",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4dc9e310",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('insurance.csv')\n",
+    "df = df[df['charges'] <= 12000]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7a7f33cd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a19e236b",
+   "metadata": {},
+   "source": [
+    "<h2>Linear Data</h2>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aef9d295",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = np.array(df['age'].iloc[:200])\n",
+    "y = np.array(df['charges'].iloc[:200])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "65c46210",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize = (12,6))\n",
+    "plt.title(\"Age vs Charges Scatterplot\")\n",
+    "plt.xlabel(\"Age\")\n",
+    "plt.ylabel(\"Charges\")\n",
+    "sns.scatterplot(x=X,y=y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5be82cb7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.2, random_state = 0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5d670ad4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = LinearRegression()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "82ece089",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.fit(X_train.reshape(-1,1),y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ca34672b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred_train = model.predict(X_train.reshape(-1,1))\n",
+    "plt.figure(figsize=(12,6))\n",
+    "plt.title(\"Train Set\")\n",
+    "plt.xlabel(\"Age\")\n",
+    "plt.ylabel(\"Charges\")\n",
+    "sns.scatterplot(x=X_train,y=y_train)\n",
+    "sns.lineplot(x=X_train,y=y_pred_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b86971e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = model.predict(X_test.reshape(-1,1))\n",
+    "plt.figure(figsize=(12,6))\n",
+    "plt.title(\"Test Set\")\n",
+    "plt.xlabel(\"Age\")\n",
+    "plt.ylabel(\"Charges\")\n",
+    "sns.scatterplot(x=X_test,y=y_test)\n",
+    "sns.lineplot(x=X_test,y=y_pred)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "07b0706a",
+   "metadata": {},
+   "source": [
+    "<h2>Non Linear Data</h2>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ea4698f7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X=np.array(df['bmi'].iloc[100:300])\n",
+    "y=np.array(df['charges'].iloc[100:300])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1e8db443",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize = (12,6))\n",
+    "plt.title('BMI vs Charges Scatterplot')\n",
+    "plt.xlabel(\"BMI\")\n",
+    "plt.ylabel(\"Charges\")\n",
+    "sns.scatterplot(x=X,y=y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6b7bf657",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.2, random_state = 0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e2e4f730",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = LinearRegression()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "09b3f252",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.fit(X_train.reshape(-1,1),y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4d56b6ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred_train = model.predict(X_train.reshape(-1,1))\n",
+    "plt.figure(figsize=(12,6))\n",
+    "plt.title(\"Train Set\")\n",
+    "plt.xlabel(\"BMI\")\n",
+    "plt.ylabel(\"Charges\")\n",
+    "sns.scatterplot(x=X_train,y=y_train)\n",
+    "sns.lineplot(x=X_train,y=y_pred_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9bff294b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = model.predict(X_test.reshape(-1,1))\n",
+    "plt.figure(figsize=(12,6))\n",
+    "plt.title(\"Test Set\")\n",
+    "plt.xlabel(\"BMI\")\n",
+    "plt.ylabel(\"Charges\")\n",
+    "sns.scatterplot(x=X_test,y=y_test)\n",
+    "sns.lineplot(x=X_test,y=y_pred)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "235253ca-31cb-4ecd-89a5-2f0d71f50d1f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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/ML 3 (Latest)/5. Logistic Regression.ipynb

@@ -0,0 +1,104 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cef03733-f76d-4c75-9570-43d8b4d946d8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\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\n",
+    "\n",
+    "# Load the wine dataset\n",
+    "wine = datasets.load_wine()\n",
+    "\n",
+    "# Features and target\n",
+    "X = wine.data\n",
+    "Y = wine.target\n",
+    "\n",
+    "# Split the dataset\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.30, random_state=7)\n",
+    "\n",
+    "# Initialize and train Logistic Regression model\n",
+    "log_reg_model = linear_model.LogisticRegression(max_iter=5000)  # Increase max_iter to avoid convergence warning\n",
+    "log_reg_model.fit(X_train, y_train)\n",
+    "\n",
+    "# Model evaluation\n",
+    "score = log_reg_model.score(X_test, y_test)\n",
+    "print(\"The score for the Logistic Regression Model is:\", score)\n",
+    "\n",
+    "# Confusion Matrix\n",
+    "cm = confusion_matrix(y_test, log_reg_model.predict(X_test))\n",
+    "print(\"Confusion Matrix:\\n\", cm)\n",
+    "\n",
+    "# ------------------------------\n",
+    "# Visualization with only 2 features\n",
+    "# ------------------------------\n",
+    "\n",
+    "# Use only the first two features for visualization\n",
+    "X_vis = X[:, :2]\n",
+    "\n",
+    "# Train again on 2 features\n",
+    "log_reg_model.fit(X_vis, Y)\n",
+    "\n",
+    "# Set mesh grid limits\n",
+    "x_min, x_max = X_vis[:, 0].min() - 0.5, X_vis[:, 0].max() + 0.5\n",
+    "y_min, y_max = X_vis[:, 1].min() - 0.5, X_vis[:, 1].max() + 0.5\n",
+    "xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.01),\n",
+    "                     np.arange(y_min, y_max, 0.01))\n",
+    "\n",
+    "# Predict over mesh\n",
+    "Z = log_reg_model.predict(np.c_[xx.ravel(), yy.ravel()])\n",
+    "Z = Z.reshape(xx.shape)\n",
+    "\n",
+    "# Plot\n",
+    "plt.figure(figsize=(8, 6))\n",
+    "plt.pcolormesh(xx, yy, Z, cmap=plt.cm.Paired, shading='auto')\n",
+    "\n",
+    "# Scatter plot\n",
+    "plt.scatter(X_vis[:, 0], X_vis[:, 1], c=Y, edgecolors='k', cmap=plt.cm.Paired)\n",
+    "plt.xlabel(wine.feature_names[0])\n",
+    "plt.ylabel(wine.feature_names[1])\n",
+    "plt.title('Logistic Regression Decision Boundary (Wine Dataset)')\n",
+    "plt.xlim(xx.min(), xx.max())\n",
+    "plt.ylim(yy.min(), yy.max())\n",
+    "plt.xticks(())\n",
+    "plt.yticks(())\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9b026574-d96c-455d-af8f-8fa02e942a85",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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/ML 3 (Latest)/6. Bayesian Classifier.ipynb

@@ -0,0 +1,109 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f7327c24-ed64-4b50-9eb9-42f1ca544cd6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "from sklearn import datasets\n",
+    "from sklearn.metrics import confusion_matrix\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.naive_bayes import GaussianNB\n",
+    "\n",
+    "# Load dataset\n",
+    "win = datasets.load_wine()\n",
+    "X = win.data\n",
+    "y = win.target\n",
+    "\n",
+    "# Train-test split\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)\n",
+    "\n",
+    "# Train model\n",
+    "gnb = GaussianNB().fit(X_train, y_train)\n",
+    "gnb_predictions = gnb.predict(X_test)\n",
+    "\n",
+    "# Confusion matrix\n",
+    "cm = confusion_matrix(y_test, gnb_predictions)\n",
+    "#labels = win.target_names\n",
+    "\n",
+    "# Plot\n",
+    "plt.figure(figsize=(8, 6))\n",
+    "sns.heatmap(cm, annot=True, fmt=\"d\", cmap=\"Blues\",\n",
+    "            xticklabels=[0,1,2], yticklabels=[0,1,2])\n",
+    "plt.xlabel(\"Predicted Label\")\n",
+    "plt.ylabel(\"True Label\")\n",
+    "plt.title(\"Confusion Matrix for Gaussian Naive Bayes (Wine Dataset)\")\n",
+    "plt.tight_layout()\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "219554ad-622f-4428-aa10-35f5b6bbafcb",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "import sklearn.naive_bayes\n",
+    "help(sklearn.naive_bayes)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "abdd3ed0-02f1-4d10-b280-563984c82cab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sklearn.naive_bayes\n",
+    "print(dir(sklearn.naive_bayes))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f5f672f9-a0f5-4fe0-8a79-c6368858311a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import inspect\n",
+    "inspect.getmembers(sklearn.naive_bayes, inspect.isclass) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "28f73c18-b901-405e-88c7-9a7c606b6633",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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
+}