{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from cw.io import read_cw_data\n",
    "import matplotlib.pylab as plt\n",
    "import numpy as np\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Read and analyse the crowdwater data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total number of cw reading 34415\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/esowc31/anand/CW4Floods/cw/io.py:45: DtypeWarning: Columns (2,3,7,11,16,28,36,38,46,48) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  data = pd.read_csv(file_name)\n"
     ]
    }
   ],
   "source": [
    "cw_data = read_cw_data()\n",
    "print(f\"Total number of cw reading {len(cw_data)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total number of cw reading without NA 7321\n"
     ]
    }
   ],
   "source": [
    "cw_data = cw_data[cw_data.WATER_LEVEL.notna()]\n",
    "print(f\"Total number of cw reading without NA {len(cw_data)}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total number of cw reading without NA and false 7320\n"
     ]
    }
   ],
   "source": [
    "cw_data = cw_data[cw_data.WATER_LEVEL != \"false\" ]\n",
    "print(f\"Total number of cw reading without NA and false {len(cw_data)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "All the columns in cw_data Index(['ID', 'ROOT_ID', 'LATITUDE', 'LONGITUDE', 'CATEGORY', 'IMAGE',\n",
      "       'FLOW_TYPE', 'SNOW_ICE_PRESENT', 'MOISTURE', 'WATER_LEVEL', 'PP_TYPE',\n",
      "       'PP_RIVER_STAGNENT', 'PP_STREAM_OBSERVATION_TIME',\n",
      "       'PP_STREAM_PROPORTIONS', 'PP_SHORE_PLOTSIZE', 'PP_AMOUNT',\n",
      "       'WL_ADVANCED', 'WL_WIDTH', 'WL_DEPTH', 'STREAMTYPE_TYPE',\n",
      "       'STREAMTYPE_DRINK_WATER', 'STREAMTYPE_SWIMMING', 'STREAMTYPE_BUILTIN',\n",
      "       'WL_MATERIAL', 'STREAMTYPE_WATERCOLOR', 'STREAMTYPE_GROUNDVISIBLE',\n",
      "       'STREAMTYPE_ANIMALS', 'STREAMTYPE_POLLUTION', 'STREAMTYPE_DRIESUP',\n",
      "       'STREAMTYPE_NAME', 'WL_METHOD', 'WL_FLOW_VELOCITY', 'WL_DISTANCE',\n",
      "       'WL_TIME_A', 'WL_TIME_B', 'WL_TIME_C', 'WL_DISTANCE_B', 'WL_DISTANCE_C',\n",
      "       'PP_ADVANCED', 'PP_ADV_PET', 'PP_ADV_POSOFT', 'PP_ADV_POHARD',\n",
      "       'PP_ADV_PS', 'PP_ADV_PSE', 'PP_ADV_MULTILAYER', 'PP_ADV_OTHER',\n",
      "       'PP_PLASTIC_REMOVED_CHECK', 'PHYSICAL_SCALE_UNIT',\n",
      "       'PHYSICAL_SCALE_LEVEL', 'DESCRIPTION', 'SPOTTED_AT'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(f\"All the columns in cw_data {cw_data.columns[:]}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1152x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "They are atleast 50 stations with 20 or more readings, \n",
      " this includes the stations on entire globe and not only to europe\n"
     ]
    }
   ],
   "source": [
    "## Sort stations with highest frequency of the data\n",
    "\n",
    "reading_frequency = np.unique(cw_data.ROOT_ID, return_counts = True)\n",
    "sorted_freq = sorted(zip(reading_frequency[1], reading_frequency[0]), reverse=True)\n",
    "tuples = zip(*sorted_freq)\n",
    "freq, station_id = [ list(tuple) for tuple in tuples]\n",
    "\n",
    "# Frequency distribution for 50 stations with highest number of readings\n",
    "fig, (ax1, ax2) = plt.subplots(1,2, figsize = (16, 6))\n",
    "ax1.plot(freq)\n",
    "ax2.plot(np.arange(20, 100), freq[20:100])\n",
    "ax2.axhline(20)\n",
    "plt.grid()\n",
    "plt.show()\n",
    "\n",
    "print(\"They are atleast 50 stations with 20 or more readings, \\n this includes the stations on entire globe and not only to europe\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Most of the values are in the range -1 to +1\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Lets see how are the values distributed\n",
    "fig, ax = plt.subplots(1,1, figsize = (10, 4))\n",
    "plt.hist(cw_data.WATER_LEVEL, bins = 13)\n",
    "\n",
    "print(f\"Most of the values are in the range -1 to +1\")"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "692f5383e91b71d62ecfc91266ec3ccdde3d070cc847d400f4b3a8a0583f7858"
  },
  "kernelspec": {
   "display_name": "Python 3.9.0 ('CW4F')",
   "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": "3.9.0"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}