dati_idrometro

dati_idrometro.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Download data\n",
    "\n",
    "Data are available at [UFFICIO DIGHE](https://www.floods.it/public/DatiStoriciDown.php?Argomento=Trento%20Ponte%20S%20Lorenzo&Corpo=fiume%20Adige)  whith  [CC BY 4.0](http://creativecommons.org/licenses/by/4.0/) license and with attribuition to \"Dati della rete di monitoraggio dell'Ufficio Dighe – Servizio Prevenzione rischi della Provincia Autonoma di Trento\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "years = range(1994,2020)\n",
    "data_dir = './data'\n",
    "file_str = data_dir + '/portate_san_lorenzo_{}.zip'\n",
    "url = 'https://www.floods.it/public/DatiStoriciBis/DSdownloadBis.php?Arg=Trento%20Ponte%20S%20Lorenzo&Type=Portate&Anno={}'\n",
    "\n",
    "import urllib.request\n",
    "import os\n",
    "import zipfile\n",
    "\n",
    "if not os.path.exists(data_dir):\n",
    "    os.makedirs(data_dir)\n",
    "\n",
    "for year in years:\n",
    "    f = file_str.format(year)\n",
    "    urllib.request.urlretrieve(url.format(year), f)\n",
    "    with zipfile.ZipFile(f, \"r\") as zip_ref:\n",
    "        zip_ref.extractall(data_dir)\n",
    "  \n",
    "\n",
    "\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2001\n",
      "(55, 2)\n",
      "2014\n",
      "(31, 2)\n",
      "1997\n",
      "(202, 2)\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import re\n",
    "\n",
    "\n",
    "y= '2000'\n",
    "for root, dirs, files in os.walk(data_dir):\n",
    "    for file in files:\n",
    "        if \".csv\" in file:\n",
    "            df = pd.read_csv(root+'/'+file, skiprows=6)\n",
    "            df.columns = ['data', 'portata']\n",
    "            y = re.findall(r'\\d+',  root)[0]\n",
    "            df = df[(df.portata > 750) & (df.data > y+'-06-01') & (df.data < y+'-08-31') ]\n",
    "            if df.shape[0] > 0:\n",
    "                print(y)\n",
    "                print(df.shape)\n",
    "\n",
    "        #append the file name to the list\n",
    "\t\t#print(os.path.join(root,file))\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}

dati_idrometro.py

#!/usr/bin/env python
# coding: utf-8

# ## Download data
# 
# Data are available at [UFFICIO DIGHE](https://www.floods.it/public/DatiStoriciDown.php?Argomento=Trento%20Ponte%20S%20Lorenzo&Corpo=fiume%20Adige)  whith  [CC BY 4.0](http://creativecommons.org/licenses/by/4.0/) license and with attribuition to "Dati della rete di monitoraggio dell'Ufficio Dighe – Servizio Prevenzione rischi della Provincia Autonoma di Trento"

# In[36]:


years = range(1994,2020)
data_dir = './data'
file_str = data_dir + '/portate_san_lorenzo_{}.zip'
url = 'https://www.floods.it/public/DatiStoriciBis/DSdownloadBis.php?Arg=Trento%20Ponte%20S%20Lorenzo&Type=Portate&Anno={}'

import urllib.request
import os
import zipfile

if not os.path.exists(data_dir):
    os.makedirs(data_dir)

for year in years:
    f = file_str.format(year)
    urllib.request.urlretrieve(url.format(year), f)
    with zipfile.ZipFile(f, "r") as zip_ref:
        zip_ref.extractall(data_dir)
  


    


# In[37]:


import pandas as pd
import re


y= '2000'
for root, dirs, files in os.walk(data_dir):
    for file in files:
        if ".csv" in file:
            df = pd.read_csv(root+'/'+file, skiprows=6)
            df.columns = ['data', 'portata']
            y = re.findall(r'\d+',  root)[0]
            df = df[(df.portata > 750) & (df.data > y+'-06-01') & (df.data < y+'-08-31') ]
            if df.shape[0] > 0:
                print(y)
                print(df.shape)

        #append the file name to the list
		#print(os.path.join(root,file))
    


# In[ ]: