noshot 1.0.0__py3-none-any.whl → 2.0.0__py3-none-any.whl

noshot/data/ML TS XAI/XAI/XAI 1/deepchecksframeworks.ipynb

@@ -1,100 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/",
-     "height": 1000,
-     "resources": {
-      "http://localhost:8080/jupyterlab-plotly.js": {
-       "data": "",
-       "headers": [
-        [
-         "content-length",
-         "0"
-        ]
-       ],
-       "ok": false,
-       "status": 404,
-       "status_text": ""
-      }
-     }
-    },
-    "id": "mJC5pjBETXIW",
-    "outputId": "2d1d08a1-9acb-4a24-bb57-83c35a4f62d6"
-   },
-   "outputs": [],
-   "source": [
-    "import pandas as pd\n",
-    "from sklearn.model_selection import train_test_split\n",
-    "!pip install deepchecks\n",
-    "from deepchecks.tabular import Dataset\n",
-    "from deepchecks.suites import data_integrity, train_test_validation\n",
-    "\n",
-    "# Load the dataset manually (replace with the actual path)\n",
-    "file_path = \"adult.csv\"  # Update this with your dataset file path\n",
-    "column_names = [\n",
-    "    'age', 'workclass', 'fnlwgt', 'education', 'education-num', 'marital-status',\n",
-    "    'occupation', 'relationship', 'race', 'sex', 'capital-gain', 'capital-loss',\n",
-    "    'hours-per-week', 'native-country', 'income'\n",
-    "]\n",
-    "\n",
-    "# Read CSV file\n",
-    "df = pd.read_csv(file_path, names=column_names, skipinitialspace=True)\n",
-    "\n",
-    "# Convert categorical features to string (if needed)\n",
-    "cat_features = ['workclass', 'education', 'marital-status', 'occupation',\n",
-    "                'relationship', 'race', 'sex', 'native-country']\n",
-    "\n",
-    "df[cat_features] = df[cat_features].astype(str)\n",
-    "\n",
-    "# Separate features and labels\n",
-    "X = df.drop(columns=['income'])\n",
-    "y = df['income']\n",
-    "\n",
-    "# Split into train and test sets\n",
-    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
-    "\n",
-    "# Create Deepchecks Dataset objects\n",
-    "train_ds = Dataset(X_train, label=y_train, cat_features=cat_features)\n",
-    "test_ds = Dataset(X_test, label=y_test, cat_features=cat_features)\n",
-    "\n",
-    "# Run Data Integrity Suite\n",
-    "integrity_suite = data_integrity()\n",
-    "integrity_result = integrity_suite.run(train_ds)\n",
-    "integrity_result.show()\n",
-    "\n",
-    "# Run Train-Test Validation Suite\n",
-    "validation_suite = train_test_validation()\n",
-    "validation_result = validation_suite.run(train_ds, test_ds)\n",
-    "validation_result.show()\n"
-   ]
-  }
- ],
- "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
-}

noshot/data/ML TS XAI/XAI/XAI 1/deepexplainers (mnist).ipynb

@@ -1,90 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/",
-     "height": 1000
-    },
-    "id": "hGTdvcVMiIrP",
-    "outputId": "4581c094-26c9-4b7c-d4e3-7c69d8a81713"
-   },
-   "outputs": [],
-   "source": [
-    "import shap\n",
-    "import tensorflow as tf\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "\n",
-    "# Load a sample dataset (for demonstration, using MNIST)\n",
-    "from tensorflow.keras.datasets import mnist\n",
-    "from tensorflow.keras.models import Sequential\n",
-    "from tensorflow.keras.layers import Dense, Flatten\n",
-    "\n",
-    "# Load MNIST dataset\n",
-    "(x_train, y_train), (x_test, y_test) = mnist.load_data()\n",
-    "\n",
-    "# Normalize pixel values to 0-1\n",
-    "x_train, x_test = x_train / 255.0, x_test / 255.0\n",
-    "\n",
-    "# Build a simple neural network\n",
-    "model = Sequential([\n",
-    "    Flatten(input_shape=(28, 28)),\n",
-    "    Dense(128, activation='relu'),\n",
-    "    Dense(10, activation='softmax')\n",
-    "])\n",
-    "\n",
-    "# Compile the model\n",
-    "model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n",
-    "\n",
-    "# Train the model (using fewer epochs for quick results)\n",
-    "model.fit(x_train, y_train, epochs=3, batch_size=128, validation_data=(x_test, y_test))\n",
-    "\n",
-    "# Select background data for SHAP explanations\n",
-    "background = x_train[np.random.choice(x_train.shape[0], 100, replace=False)]\n",
-    "\n",
-    "# ✅ Initialize SHAP DeepExplainer\n",
-    "explainer = shap.DeepExplainer(model, background)\n",
-    "\n",
-    "# Select a few test samples\n",
-    "X_test_sample = x_test[:10]\n",
-    "\n",
-    "# ✅ Compute SHAP values\n",
-    "shap_values = explainer.shap_values(X_test_sample)\n",
-    "\n",
-    "# ✅ Visualize SHAP values for an image\n",
-    "# Plot the SHAP values for class 0 (change index to see for other classes)\n",
-    "index = 0  # Change this to visualize different images\n",
-    "\n",
-    "plt.figure(figsize=(8, 4))\n",
-    "shap.image_plot(shap_values, X_test_sample)\n"
-   ]
-  }
- ],
- "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
-}

noshot/data/ML TS XAI/XAI/XAI 1/guidedbackpropagation.ipynb

@@ -1,203 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/",
-     "height": 406
-    },
-    "id": "t71r0zijG0_7",
-    "outputId": "e772d9a6-eaf7-4363-b00a-4e46913ae149"
-   },
-   "outputs": [],
-   "source": [
-    "import torch\n",
-    "import torch.nn as nn\n",
-    "from torchvision import models, transforms\n",
-    "from PIL import Image\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "\n",
-    "\n",
-    "# Custom Guided Backpropagation ReLU\n",
-    "class GuidedBackpropReLU(nn.Module):\n",
-    "    def forward(self, input):\n",
-    "        return torch.relu(input)\n",
-    "\n",
-    "    def backward(self, grad_output):\n",
-    "        grad_input = torch.clamp(grad_output, min=0.0)\n",
-    "        return grad_input\n",
-    "\n",
-    "\n",
-    "# Replace ReLU with GuidedBackpropReLU\n",
-    "def replace_relu_with_guided(model):\n",
-    "    for name, module in model.named_children():\n",
-    "        if isinstance(module, nn.ReLU):\n",
-    "            setattr(model, name, GuidedBackpropReLU())\n",
-    "        else:\n",
-    "            replace_relu_with_guided(module)\n",
-    "\n",
-    "\n",
-    "# Preprocess the input image\n",
-    "def preprocess_image(image_path):\n",
-    "    preprocess = transforms.Compose([\n",
-    "        transforms.Resize((224, 224)),\n",
-    "        transforms.ToTensor(),\n",
-    "        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),\n",
-    "    ])\n",
-    "    image = Image.open(image_path).convert('RGB')\n",
-    "    return preprocess(image).unsqueeze(0)  # Add batch dimension\n",
-    "\n",
-    "\n",
-    "# Guided Backpropagation function\n",
-    "def guided_backpropagation(model, input_image, target_class):\n",
-    "    model.eval()  # Set model to evaluation mode\n",
-    "    input_image.requires_grad = True  # Enable gradient computation for input\n",
-    "\n",
-    "    replace_relu_with_guided(model)  # Replace all ReLU activations\n",
-    "\n",
-    "    output = model(input_image)  # Forward pass\n",
-    "    loss = output[0, target_class]  # Target class loss\n",
-    "    model.zero_grad()  # Zero out gradients\n",
-    "    loss.backward()  # Backward pass\n",
-    "\n",
-    "    return input_image.grad.data  # Return gradients w.r.t. input image\n",
-    "\n",
-    "\n",
-    "# Visualize the gradients\n",
-    "def visualize_gradients(gradients):\n",
-    "    gradients = gradients[0].cpu().numpy()  # Remove batch dimension\n",
-    "    gradients = np.moveaxis(gradients, 0, -1)  # Rearrange channels to last dimension\n",
-    "    gradients = (gradients - gradients.min()) / (gradients.max() - gradients.min())  # Normalize\n",
-    "    plt.imshow(gradients)\n",
-    "    plt.axis('off')\n",
-    "    plt.show()\n",
-    "\n",
-    "\n",
-    "# Main script\n",
-    "if __name__ == \"__main__\":\n",
-    "    # Load a pretrained model\n",
-    "    model = models.vgg16(pretrained=True)\n",
-    "\n",
-    "    # Load and preprocess the input image\n",
-    "    image_path = \"/content/g2.jpeg\"  # Replace with the path to your image\n",
-    "    input_image = preprocess_image(image_path)\n",
-    "\n",
-    "    # Define target class (e.g., 'bull mastiff' class in ImageNet)\n",
-    "    target_class = 243\n",
-    "\n",
-    "    # Move to device (CPU/GPU)\n",
-    "    device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
-    "    model = model.to(device)\n",
-    "    input_image = input_image.to(device)\n",
-    "\n",
-    "    # Perform Guided Backpropagation\n",
-    "    gradients = guided_backpropagation(model, input_image, target_class)\n",
-    "\n",
-    "    # Visualize the gradients\n",
-    "    visualize_gradients(gradients)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "id": "x5z8OBtLIqWh"
-   },
-   "outputs": [],
-   "source": [
-    "gradients = (gradients - gradients.min()) / (gradients.max() - gradients.min())  # Normalize\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "tIlhZt2SIt8S",
-    "outputId": "d22fdb34-f725-41d1-9117-5a8456daddbc"
-   },
-   "outputs": [],
-   "source": [
-    "print(\"Gradient shape:\", gradients.shape)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "PxPrybk2JQdQ",
-    "outputId": "f3e1ed74-8b5b-476c-e70e-f682a528d2a1"
-   },
-   "outputs": [],
-   "source": [
-    "output = model(input_image)\n",
-    "print(\"Model output:\", output)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "id": "hOjkXsMrJZF3",
-    "outputId": "65173d32-1016-4616-dfd4-3cb6cc858615"
-   },
-   "outputs": [],
-   "source": [
-    "gradients = guided_backpropagation(model, input_image, target_class)\n",
-    "print(\"Gradients shape:\", gradients.shape)  # Should be [1, 3, 224, 224] for a single image\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/",
-     "height": 434
-    },
-    "id": "dXeuco_bJd8h",
-    "outputId": "f7bef501-ada9-4afb-8531-c069bd1d417a"
-   },
-   "outputs": [],
-   "source": [
-    "plt.imshow(gradients[0].cpu().numpy()[0], cmap='hot')  # Display the first channel's gradients\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
-}