Add titles to TOC and placeholder tutorial NBs

lboegner · Jul 29, 2023 · c7a950a · c7a950a
1 parent 95f9c09
commit c7a950a
Show file tree

Hide file tree

Showing 16 changed files with 995 additions and 12 deletions.
diff --git a/docs/TutorialNotebookExample.ipynb → docs/00_Sig53DatasetTutorial.ipynb b/docs/TutorialNotebookExample.ipynb → docs/00_Sig53DatasetTutorial.ipynb
@@ -7,23 +7,21 @@
     "tags": []
    },
    "source": [
-    "## Tutorial Notebook Example\n",
+    "## Sig53 Dataset\n",
     "\n",
-    "last updated: 2023-07-23\n",
+    "last updated: 2023-07-29\n",
     "\n",
-    "This is a test notebook to show how we can include examples and tutorials as non-executed jupyter notebooks that get built during our documentation building on readthedocs. This way, we can still include code and code output to show the capabilities of TorchSig.\n",
-    "\n",
-    "This is just a template for how to do this and should be replaced :)"
+    "TODO: This notebook is just a placeholder for now."
    ]
   },
   {
    "cell_type": "markdown",
    "id": "d2d7597b-7f82-4493-b3b1-d4ef7b9c24b8",
    "metadata": {},
    "source": [
-    "### Generate Complex Sinusoid Example Data\n",
+    "### Modulation Family Background\n",
     "\n",
-    "TODO: Explain steps in tutorial in more detail"
+    "TODO: Describe and plot the modulation families present in Sig53. Should resemble Figure 3 from [Large Scale Radio Frequency Signal Classification](https://arxiv.org/pdf/2207.09918.pdf)."
    ]
   },
   {
@@ -33,6 +31,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "#TODO: Replace this code block\n",
     "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
     "\n",
@@ -53,9 +52,9 @@
    "id": "2e3151e0-813b-4c07-bc86-72c72f92f6ee",
    "metadata": {},
    "source": [
-    "### Apply TorchSig Transform\n",
+    "### Instantiate the Sig53 Dataset\n",
     "\n",
-    "TODO: Explain steps in tutorial in more detail"
+    "TODO: Explain details of the Sig53 dataset and show code on how to instantiate the datasets."
    ]
   },
   {
@@ -65,6 +64,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "#TODO: Replace this code block\n",
+    "\n",
     "from torchsig.transforms import AddNoise\n",
     "\n",
     "t = AddNoise(noise_power_db=-20)\n",

diff --git a/docs/01_WidebandSig53DatasetTutorial.ipynb b/docs/01_WidebandSig53DatasetTutorial.ipynb
@@ -0,0 +1,114 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ff639336-c092-4882-b08e-78f8b82f741e",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## WidebandSig53 Dataset\n",
+    "\n",
+    "last updated: 2023-07-29\n",
+    "\n",
+    "TODO: This notebook is just a placeholder for now."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d2d7597b-7f82-4493-b3b1-d4ef7b9c24b8",
+   "metadata": {},
+   "source": [
+    "### Dataset Background\n",
+    "\n",
+    "TODO: Describe and plot a few examples from WidebandSig53 (via the `WidebandModulations` class such that we are not asking sphinx to generate the full dataset). Should resemble Figure 1 from [Large Scale Wideband Radio Frequency Signal Detection & Recognition](https://arxiv.org/pdf/2211.10335.pdf)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7888b4a8-0b66-4d29-bf40-6bce2b83a288",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#TODO: Replace this code block\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
+    "num_samples = 4096\n",
+    "x = np.exp(2j * np.pi * 2.0 / num_samples * np.arange(num_samples))\n",
+    "\n",
+    "plt.figure()\n",
+    "plt.plot(x.real, c='b')\n",
+    "plt.plot(x.imag, c='r')\n",
+    "plt.title('Test plot')\n",
+    "plt.xlabel('samples')\n",
+    "plt.ylabel('amplitude')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2e3151e0-813b-4c07-bc86-72c72f92f6ee",
+   "metadata": {},
+   "source": [
+    "### Instantiate the WidebandSig53 Dataset\n",
+    "\n",
+    "TODO: Explain details of the WidebandSig53 dataset and show code on how to instantiate the datasets."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "462b7078-f064-4a2b-ba18-8c8b320e35ef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#TODO: Replace this code block\n",
+    "\n",
+    "from torchsig.transforms import AddNoise\n",
+    "\n",
+    "t = AddNoise(noise_power_db=-20)\n",
+    "\n",
+    "y = t(x)\n",
+    "\n",
+    "plt.figure()\n",
+    "plt.plot(y.real, c='b')\n",
+    "plt.plot(y.imag, c='r')\n",
+    "plt.title('Test plot')\n",
+    "plt.xlabel('samples')\n",
+    "plt.ylabel('amplitude')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b2166e37-6a60-4088-9c60-d2bb62d7834b",
+   "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": "3.8.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/docs/02_RadioMLDatasetTutorial.ipynb b/docs/02_RadioMLDatasetTutorial.ipynb
@@ -0,0 +1,80 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ff639336-c092-4882-b08e-78f8b82f741e",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## RadioML Dataset\n",
+    "\n",
+    "last updated: 2023-07-29\n",
+    "\n",
+    "TODO: This notebook is just a placeholder for now."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d2d7597b-7f82-4493-b3b1-d4ef7b9c24b8",
+   "metadata": {},
+   "source": [
+    "### Dataset Background\n",
+    "\n",
+    "TODO: Describe and plot a few examples from RadioML"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7888b4a8-0b66-4d29-bf40-6bce2b83a288",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#TODO: Replace this code block\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
+    "num_samples = 4096\n",
+    "x = np.exp(2j * np.pi * 2.0 / num_samples * np.arange(num_samples))\n",
+    "\n",
+    "plt.figure()\n",
+    "plt.plot(x.real, c='b')\n",
+    "plt.plot(x.imag, c='r')\n",
+    "plt.title('Test plot')\n",
+    "plt.xlabel('samples')\n",
+    "plt.ylabel('amplitude')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b2166e37-6a60-4088-9c60-d2bb62d7834b",
+   "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": "3.8.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/docs/03_DataTransformTutorial.ipynb b/docs/03_DataTransformTutorial.ipynb
@@ -0,0 +1,114 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ff639336-c092-4882-b08e-78f8b82f741e",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Data Transforms\n",
+    "\n",
+    "last updated: 2023-07-29\n",
+    "\n",
+    "TODO: This notebook is just a placeholder for now."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d2d7597b-7f82-4493-b3b1-d4ef7b9c24b8",
+   "metadata": {},
+   "source": [
+    "### Data Transform Background\n",
+    "\n",
+    "TODO: Define data transforms to be static or feature extraction methods. List transforms included."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7888b4a8-0b66-4d29-bf40-6bce2b83a288",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#TODO: Replace this code block\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
+    "num_samples = 4096\n",
+    "x = np.exp(2j * np.pi * 2.0 / num_samples * np.arange(num_samples))\n",
+    "\n",
+    "plt.figure()\n",
+    "plt.plot(x.real, c='b')\n",
+    "plt.plot(x.imag, c='r')\n",
+    "plt.title('Test plot')\n",
+    "plt.xlabel('samples')\n",
+    "plt.ylabel('amplitude')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2e3151e0-813b-4c07-bc86-72c72f92f6ee",
+   "metadata": {},
+   "source": [
+    "### Feature Transforms\n",
+    "\n",
+    "TODO: Walk through each feature transform with plots"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "462b7078-f064-4a2b-ba18-8c8b320e35ef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#TODO: Replace this code block\n",
+    "\n",
+    "from torchsig.transforms import AddNoise\n",
+    "\n",
+    "t = AddNoise(noise_power_db=-20)\n",
+    "\n",
+    "y = t(x)\n",
+    "\n",
+    "plt.figure()\n",
+    "plt.plot(y.real, c='b')\n",
+    "plt.plot(y.imag, c='r')\n",
+    "plt.title('Test plot')\n",
+    "plt.xlabel('samples')\n",
+    "plt.ylabel('amplitude')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b2166e37-6a60-4088-9c60-d2bb62d7834b",
+   "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": "3.8.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}