noshot 5.0.0__py3-none-any.whl → 7.0.0__py3-none-any.whl

noshot/data/ML TS XAI/ML/Tamilan Code/2. KNN (Iris Dataset).ipynb

@@ -0,0 +1,156 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f8872206-2c4c-4b9c-a146-4874bed47d58",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "import sklearn\n",
+    "from sklearn import svm\n",
+    "from sklearn.neighbors import KNeighborsClassifier\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn import metrics\n",
+    "from sklearn.preprocessing import StandardScaler"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6784e6b1-ab93-4529-85a0-8be414f00283",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('data/iris.csv')\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7d9be320-b960-49d2-bf0b-d6193332b1f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class_mapper = {0: \"setosa\", 1: \"versicolor\", 2: \"virginica\"}\n",
+    "df['target']  = df['class'].map(class_mapper)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d523f9bd-14d5-42f6-80cc-fe8a8210fa1f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "feature = ['sepal length (cm)','sepal width (cm)','petal length (cm)','petal width (cm)']\n",
+    "x = df.loc[:, feature]\n",
+    "y = df.loc[:, 'target']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f852a9d8-bb7a-49d3-a199-e47738c05a04",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x = StandardScaler().fit_transform(x)\n",
+    "X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.4,\n",
+    "                                                    random_state=4)\n",
+    "print (X_train.shape)\n",
+    "print (X_test.shape)\n",
+    "knn = KNeighborsClassifier(n_neighbors=15)\n",
+    "knn.fit(X_train, y_train)                  "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e57d7cdd-29b8-4235-aea7-9f904a70e9fd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = knn.predict(np.array([5.2, 3.5, 1.1, 0.2]).reshape(1, -1))[0]\n",
+    "print(\"Class Predicted [5.2, 3.5, 1.1, 0.2]:\", y_pred)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b48aeb20-c569-4d0f-900c-82cd9ad92098",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = knn.predict(X_test)\n",
+    "print(\"Accuracy:\", metrics.accuracy_score(y_test, y_pred))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f72df1f8-5075-4d23-b93f-18a91e8fd1e0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cm = metrics.confusion_matrix(y_test, knn.predict(X_test))\n",
+    "metrics.ConfusionMatrixDisplay(cm, display_labels=['setosa','versicolor','virginica']).plot()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4c1df2d9-4e4b-43a1-aaec-d7eee15b716b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn import svm\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "X, y = df.iloc[:, :2].values, df['class'].values\n",
+    "\n",
+    "clf = svm.SVC(kernel='linear').fit(X, y)\n",
+    "\n",
+    "x_min, x_max = X[:,0].min() - 1, X[:,0].max() + 1\n",
+    "y_min, y_max = X[:,1].min() - 1, X[:,1].max() + 1\n",
+    "xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02), np.arange(y_min, y_max, 0.02))\n",
+    "\n",
+    "Z = clf.predict(np.c_[xx.ravel(), yy.ravel()]).reshape(xx.shape)\n",
+    "\n",
+    "plt.figure()\n",
+    "plt.contourf(xx, yy, Z, cmap=plt.cm.coolwarm, alpha=0.8)\n",
+    "plt.scatter(X[:,0], X[:,1], c=y, cmap=plt.cm.coolwarm, s=20, edgecolors='k')\n",
+    "plt.title('Decision surface of linear SVC')\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/Tamilan Code/2. KNN (Sobar-72 Dataset).ipynb

@@ -0,0 +1,215 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "838f3d63-f48d-4003-8a20-767d87d5d63b",
+   "metadata": {
+    "id": "10424106"
+   },
+   "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\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "from sklearn.decomposition import PCA\n",
+    "from sklearn.neighbors import KNeighborsClassifier\n",
+    "from sklearn import metrics\n",
+    "from mlxtend.plotting import plot_decision_regions\n",
+    "from scipy.cluster.hierarchy import dendrogram, linkage\n",
+    "from scipy.spatial import Voronoi, voronoi_plot_2d"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5a30696e-2e04-4ead-90c7-21dbd6b1d75d",
+   "metadata": {
+    "id": "10424106"
+   },
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"data/sobar-72.csv\")\n",
+    "display(df.head())\n",
+    "display(df.info())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "35e3b9f1-f5ed-4dd1-8a4d-aeb7fe77bea2",
+   "metadata": {
+    "id": "10424106"
+   },
+   "outputs": [],
+   "source": [
+    "cols = [\n",
+    "    'behavior_sexualRisk', 'intention_aggregation', 'attitude_consistency',\n",
+    "    'norm_significantPerson', 'perception_vulnerability', 'motivation_strength',\n",
+    "    'socialSupport_emotionality', 'empowerment_knowledge', 'ca_cervix'\n",
+    "]\n",
+    "sns.pairplot(df[cols], hue='ca_cervix')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "09bb4a6d-3807-44cb-b15e-2e6b3ff20d02",
+   "metadata": {
+    "id": "10424106"
+   },
+   "outputs": [],
+   "source": [
+    "X = df.drop(columns=['ca_cervix'])\n",
+    "y = df['ca_cervix']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5a235b36-2136-4924-a6a3-834fde3e541c",
+   "metadata": {
+    "id": "10424106"
+   },
+   "outputs": [],
+   "source": [
+    "X_scaled = StandardScaler().fit_transform(X)\n",
+    "X_pca = PCA(n_components=2).fit_transform(X_scaled)\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_pca, y, test_size=0.4, random_state=4)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7db3c778-fb6f-4509-8598-5df6928058e2",
+   "metadata": {
+    "id": "10424106"
+   },
+   "outputs": [],
+   "source": [
+    "similarities = ['euclidean', 'manhattan', 'minkowski']\n",
+    "for sim in similarities:\n",
+    "    knn = KNeighborsClassifier(n_neighbors=5, metric=sim)\n",
+    "    knn.fit(X_train, y_train)\n",
+    "    y_pred = knn.predict(X_test)\n",
+    "\n",
+    "    plot_decision_regions(X_train, np.array(y_train), clf=knn, legend=2)\n",
+    "    plt.xlabel('X')\n",
+    "    plt.ylabel('Y')\n",
+    "    plt.title(f'KNN with K=5 using {sim.capitalize()} Distance')\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f4fee956-56f9-487d-b1fd-a2c32536fa0f",
+   "metadata": {
+    "id": "10424106"
+   },
+   "outputs": [],
+   "source": [
+    "k_values, accuracies = [], []\n",
+    "for k in range(1, 10):\n",
+    "    knn = KNeighborsClassifier(n_neighbors=k)\n",
+    "    knn.fit(X_train, y_train)\n",
+    "    y_pred = knn.predict(X_test)\n",
+    "    k_values.append(k)\n",
+    "    accuracies.append(metrics.accuracy_score(y_test, y_pred))\n",
+    "\n",
+    "plt.figure(figsize=(4, 2))\n",
+    "plt.plot(k_values, accuracies, marker='o')\n",
+    "plt.title('K Value vs Accuracy')\n",
+    "plt.xlabel('K')\n",
+    "plt.ylabel('Accuracy')\n",
+    "plt.grid()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6ecc3e38-c791-48eb-ad01-a8149a2380ae",
+   "metadata": {
+    "id": "10424106"
+   },
+   "outputs": [],
+   "source": [
+    "plt.scatter(X_test[:, 0], X_test[:, 1], c=y_pred, cmap='coolwarm', edgecolors='k')\n",
+    "plt.title('Test Data Predictions')\n",
+    "plt.grid()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9f40e9af-601f-4b4e-aadc-c3b27d4e4f11",
+   "metadata": {
+    "id": "10424106"
+   },
+   "outputs": [],
+   "source": [
+    "unique_labels = np.unique(y)\n",
+    "label_mapping = {label: i for i, label in enumerate(unique_labels)}\n",
+    "y_mapped = np.array([label_mapping[label] for label in y])\n",
+    "\n",
+    "linked = linkage(X_pca, method='single')\n",
+    "\n",
+    "plt.figure(figsize=(10, 7))\n",
+    "dendrogram(linked, orientation='top', distance_sort='descending', labels=y_mapped, show_leaf_counts=True)\n",
+    "plt.title('Dendrogram for KNN')\n",
+    "plt.xlabel('Data Points')\n",
+    "plt.ylabel('Distance')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5164b3a8-26f4-4855-a551-d5f9790b9975",
+   "metadata": {
+    "id": "10424106"
+   },
+   "outputs": [],
+   "source": [
+    "vor = Voronoi(X_pca)\n",
+    "fig = voronoi_plot_2d(vor, show_vertices=False, line_colors='black', line_width=2, line_alpha=0.6, point_size=10)\n",
+    "\n",
+    "plt.scatter(X_pca[:, 0], X_pca[:, 1], c=y, cmap='viridis', s=50, edgecolors='k')\n",
+    "plt.title('Voronoi Diagram with Target Variable')\n",
+    "plt.xlabel('X')\n",
+    "plt.ylabel('Y')\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": 5
+}

noshot/data/ML TS XAI/ML/Tamilan Code/3. LDA (Balance Scale Dataset).ipynb

@@ -0,0 +1,78 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "96ac04a5-6577-4da4-8454-3b10535351f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b1ffa4dc-488f-4238-877b-5cbd6fb48e4e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cols = ['class name','left-weight','left-distance','right-weight','right-distance']\n",
+    "df = pd.read_table('data/balance-scale.txt', delimiter = \",\", names=cols)\n",
+    "print(\"Shape:\", df.shape)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "069bba36-4187-48e4-bc5b-d1443c1ee87c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "features = ['left-weight','left-distance','right-weight','right-distance']\n",
+    "x = df.loc[:,features]\n",
+    "y = df.loc[:,'class name']\n",
+    "lda = LDA(n_components=2)\n",
+    "lda_X = lda.fit(x,y).transform(x)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "66c2b6ac-6163-4f36-ae6b-3a9e32e578ce",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.scatter(lda_X[y == 'L', 0], lda_X[y == 'L', 1], s=50, c='orange', label='L')\n",
+    "plt.scatter(lda_X[y == 'B', 0], lda_X[y == 'B', 1], s=50, c='blue', label='B')\n",
+    "plt.scatter(lda_X[y == 'R', 0], lda_X[y == 'R', 1], s=50, c='green', label='R')\n",
+    "plt.title('LDA plot for cmc DataSet')"
+   ]
+  }
+ ],
+ "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/Tamilan Code/3. LDA (NPHA Doctor Visits Dataset).ipynb

@@ -0,0 +1,114 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "68f40eda",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "066999b2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(r\"data\\doctor-visits.csv\")\n",
+    "print(\"Shape:\", df.shape)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "839d6a31",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7d105e4c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = df.drop(columns=['Number of Doctors Visited'])\n",
+    "Y = df['Number of Doctors Visited']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "05dc3f49-79f4-4862-91e8-89aab4ae2b2f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn import metrics\n",
+    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.4, random_state=4)\n",
+    "\n",
+    "lda = LinearDiscriminantAnalysis(n_components=2)\n",
+    "X_train = lda.fit_transform(X_train, y_train)\n",
+    "X_test = lda.fit_transform(X_test,y_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9e25c024-8dd8-40da-b755-1ed36dfc197c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lda.fit(X_train,y_train)\n",
+    "y_pred=lda.predict(X_test)\n",
+    "print (\"Accuracy:\",metrics.accuracy_score(y_test, y_pred))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7f0537a8-6820-4859-a3f5-f24096dfa66b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap='viridis')\n",
+    "plt.title('LDA Dimensionality Reduction')\n",
+    "plt.xlabel('LDA Component 1')\n",
+    "plt.ylabel('LDA Component 2')\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/Tamilan Code/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
+}