vdavez/long_tail_elements.ipynb

## long_tail_elements.ipynb
{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "The long tail of shared federal data elements ",
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Fnif23V9im4r",
        "colab_type": "text"
      },
      "source": [
        "# The long tail of federal form elements\n",
        "\n",
        "Examining the distribution of shared data elements across forms.\n",
        "\n",
        "Data source: https://repository.usaspending.gov/cder_library/authorized/report/common"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9pd7t9tLhLrT",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import xml.etree.ElementTree as et\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "\n",
        "# Data downloaded from https://repository.usaspending.gov/cder_library/authorized/report/common\n",
        "with open('/content/CDER_Library_DataElements_202001261038.xml','r') as fp:\n",
        "  tree = et.parse(fp)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UPgQy_j5hWx4",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "outputId": "c92f9cab-f3d8-42f0-c84b-fc912a39e5c5"
      },
      "source": [
        "# Examining the number of data elements total\n",
        "d = tree.getroot()\n",
        "print(f\"There are {len(d)} data elements that appear on 2 or more forms.\")"
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "There are 4278 data elements that appear on 2 or more forms.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "kTcd8flAiU62",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Creating a list of the number of times that each element appears on a form\n",
        "common_list = [len(elem.findall(\".//form\")) for elem in d]"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "yjmVRygFkIUp",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 297
        },
        "outputId": "5309bea9-fdca-4c67-bc2e-3938e77099c0"
      },
      "source": [
        "# Plotting the histogram\n",
        "# Note: I chose to plot the histogram *and* the log of the histogram to demonstrate that the long tail has some texture\n",
        "fig, axs = plt.subplots(ncols=2)\n",
        "sns.distplot(common_list, hist=True, hist_kws={\"range\":(1.5,19.5),\"log\":False}, kde=False, norm_hist=False, axlabel=\"Number shared forms\", ax=axs[0])\n",
        "sns.distplot(common_list, hist=True, hist_kws={\"range\":(1.5,19.5),\"log\":True}, kde=False, norm_hist=False, axlabel=\"Log of number of shared forms\", ax=axs[1])"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7fe7085f4cc0>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 4
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYAAAAEGCAYAAABsLkJ6AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngJlZSTkBmJmVlBOAmVlJ/X8Kc9Ciy1ziHgAAAABJRU5ErkJggg==\n",
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    }
  ]
}
	{
	"nbformat": 4,
	"nbformat_minor": 0,
	"metadata": {
	"colab": {
	"name": "The long tail of shared federal data elements ",
	"provenance": []
	},
	"kernelspec": {
	"name": "python3",
	"display_name": "Python 3"
	}
	},
	"cells": [
	{
	"cell_type": "markdown",
	"metadata": {
	"id": "Fnif23V9im4r",
	"colab_type": "text"
	},
	"source": [
	"# The long tail of federal form elements\n",
	"\n",
	"Examining the distribution of shared data elements across forms.\n",
	"\n",
	"Data source: https://repository.usaspending.gov/cder_library/authorized/report/common"
	]
	},
	{
	"cell_type": "code",
	"metadata": {
	"id": "9pd7t9tLhLrT",
	"colab_type": "code",
	"colab": {}
	},
	"source": [
	"import xml.etree.ElementTree as et\n",
	"import matplotlib.pyplot as plt\n",
	"import seaborn as sns\n",
	"\n",
	"# Data downloaded from https://repository.usaspending.gov/cder_library/authorized/report/common\n",
	"with open('/content/CDER_Library_DataElements_202001261038.xml','r') as fp:\n",
	" tree = et.parse(fp)"
	],
	"execution_count": 0,
	"outputs": []
	},
	{
	"cell_type": "code",
	"metadata": {
	"id": "UPgQy_j5hWx4",
	"colab_type": "code",
	"colab": {
	"base_uri": "https://localhost:8080/",
	"height": 35
	},
	"outputId": "c92f9cab-f3d8-42f0-c84b-fc912a39e5c5"
	},
	"source": [
	"# Examining the number of data elements total\n",
	"d = tree.getroot()\n",
	"print(f\"There are {len(d)} data elements that appear on 2 or more forms.\")"
	],
	"execution_count": 2,
	"outputs": [
	{
	"output_type": "stream",
	"text": [
	"There are 4278 data elements that appear on 2 or more forms.\n"
	],
	"name": "stdout"
	}
	]
	},
	{
	"cell_type": "code",
	"metadata": {
	"id": "kTcd8flAiU62",
	"colab_type": "code",
	"colab": {}
	},
	"source": [
	"# Creating a list of the number of times that each element appears on a form\n",
	"common_list = [len(elem.findall(\".//form\")) for elem in d]"
	],
	"execution_count": 0,
	"outputs": []
	},
	{
	"cell_type": "code",
	"metadata": {
	"id": "yjmVRygFkIUp",
	"colab_type": "code",
	"colab": {
	"base_uri": "https://localhost:8080/",
	"height": 297
	},
	"outputId": "5309bea9-fdca-4c67-bc2e-3938e77099c0"
	},
	"source": [
	"# Plotting the histogram\n",
	"# Note: I chose to plot the histogram and the log of the histogram to demonstrate that the long tail has some texture\n",
	"fig, axs = plt.subplots(ncols=2)\n",
	"sns.distplot(common_list, hist=True, hist_kws={\"range\":(1.5,19.5),\"log\":False}, kde=False, norm_hist=False, axlabel=\"Number shared forms\", ax=axs[0])\n",
	"sns.distplot(common_list, hist=True, hist_kws={\"range\":(1.5,19.5),\"log\":True}, kde=False, norm_hist=False, axlabel=\"Log of number of shared forms\", ax=axs[1])"
	],
	"execution_count": 4,
	"outputs": [
	{
	"output_type": "execute_result",
	"data": {
	"text/plain": [
	"<matplotlib.axes._subplots.AxesSubplot at 0x7fe7085f4cc0>"
	]
	},
	"metadata": {
	"tags": []
	},
	"execution_count": 4
	},
	{
	"output_type": "display_data",
	"data": {
	"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYAAAAEGCAYAAABsLkJ6AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngJlZSTkBmJmVlBOAmVlJ/X8Kc9Ciy1ziHgAAAABJRU5ErkJggg==\n",
	"text/plain": [
	"<Figure size 432x288 with 2 Axes>"
	]
	},
	"metadata": {
	"tags": []
	}
	}
	]
	}
	]
	}