Check USGS realtime streamflow using Python.

check_usgs_realtime.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Untitled1.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyMu8mkhEDPlau2X7jStmEEX",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/knu2xs/191e1847b53aa1ca371d48e5fc7e8dba/untitled1.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "YZp4k6JnXnFl"
      },
      "source": [
        "from dateutil.parser import parse\n",
        "from math import floor\n",
        "\n",
        "import requests"
      ],
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "F4JjiIUeXUv8"
      },
      "source": [
        "class DictObj:\n",
        "    def __init__(self, in_dict):\n",
        "        for key, val in in_dict.items():\n",
        "            if isinstance(val, (list, tuple)):\n",
        "               setattr(self, key, [DictObj(x) if isinstance(x, dict) else x for x in val])\n",
        "            else:\n",
        "               setattr(self, key, DictObj(val) if isinstance(val, dict) else val)\n"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bg0vHtHZlQ68"
      },
      "source": [
        "def print_time_since_observation(obs_dt):\n",
        "\n",
        "  dt = parse(obs_dt)\n",
        "  td = dt.now(tz=dt.tzinfo) - dt\n",
        "\n",
        "  hr = floor(td.seconds / 60 / 60)\n",
        "  min = floor(td.seconds / 60 % 60)\n",
        "  sec = floor(td.seconds / 60 / 60 % 60 * 100)\n",
        "\n",
        "  print(f'Time Since Last Observation - {hr:02d}:{min:02d}:{sec:02d}')\n",
        "\n",
        "  return td"
      ],
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "hZXQtU5Ehgo6"
      },
      "source": [
        "url = 'https://waterservices.usgs.gov/nwis/iv/'\n",
        "\n",
        "class Gauge:\n",
        "\n",
        "  def __init__(self, station_code:str='12080010'):\n",
        "\n",
        "    self.station_code = station_code\n",
        "      \n",
        "    self.params = {\n",
        "        'format': 'json',\n",
        "        'sites': self.station_code,\n",
        "        'parameterCd': '00060',\n",
        "        'period': 'P30D',\n",
        "        'siteStatus': 'all'\n",
        "    }\n",
        "\n",
        "    self.response = None\n",
        "\n",
        "  def get_current_observation_list(self)->list:\n",
        "    res = requests.get(url, params=self.params)\n",
        "    self.response = res\n",
        "    res_json = res.json()\n",
        "    obs_ts = res_json['value']['timeSeries']\n",
        "    assert len(obs_ts), 'No data in TimeSeries, please check gauge.response.json() to diagnose.'\n",
        "    obs_lst = obs_ts[0]['values'][0]['value']\n",
        "    return obs_lst"
      ],
      "execution_count": 77,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eBiVxOdWqXo3"
      },
      "source": [
        "gauge = Gauge()"
      ],
      "execution_count": 78,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "19wtCgBTyQNQ"
      },
      "source": [
        "import pandas as pd\n",
        "\n",
        "obs_df = pd.DataFrame(gauge.get_current_observation_list())\n",
        "\n",
        "obs_df.value = obs_df.value.astype('int64')"
      ],
      "execution_count": 79,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 282
        },
        "id": "UOuo0jtEzrc4",
        "outputId": "a7a3595d-097b-4dcb-b1a6-99efac45faed"
      },
      "source": [
        "obs_df.plot()"
      ],
      "execution_count": 80,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7f1e6c2cced0>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 80
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "xLooaMDwz90L"
      },
      "source": [
        "from scipy.ndimage import gaussian_filter"
      ],
      "execution_count": 81,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 282
        },
        "id": "QZ7ukOiF__ZB",
        "outputId": "f8d04ff0-333c-414b-da2a-328c66788c37"
      },
      "source": [
        "pd.Series(gaussian_filter(obs_df.value, sigma=2)).plot()"
      ],
      "execution_count": 82,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7f1e6c284b50>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 82
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rd2YA_XpAIV3"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}