final report - Banana LCA analysis.ipynb

LCAprojectnotebook_JM-DT-FM.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#Import Packages\n",
    "from ocelot import *\n",
    "import pandas as pd\n",
    "from copy import deepcopy\n",
    "import copy\n",
    "import json\n",
    "import numpy as np\n",
    "import math\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#################\n",
    "#DATA Processing#\n",
    "#################"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "#Function to create new regionalised datasets with region-specific production and irrigation values\n",
    "def add_bananas(data):\n",
    "      with open('/home/jm/Documents/PhD_EPFL/events/LCA_summerschool/hands_on/countries.json') as data_file:    \n",
    "        countries = json.load(data_file)\n",
    "   \n",
    "    #Preparing the ecoinvent countries dataset for merging the naming conventions of ecoinvent and FAO\n",
    "    c = countries['Countries']\n",
    "    c = pd.DataFrame(c)\n",
    "    c['name'] = c['name'].str.lower()\n",
    "    c = c[['name', 'shortname']]\n",
    "    \n",
    "    #Preparing the dataset from FAO with the production volume per country - this data was locally stored    path = '/home/jm/Documents/PhD_EPFL/events/LCA_summerschool/group/'\n",
    "    filename = 'fao_bananadata_production.csv'\n",
    "    countries = pd.read_csv((path+filename))\n",
    "    countries['AreaName'] = countries['AreaName'].str.lower()\n",
    "    banana_production = countries[['AreaName', 'Value']]\n",
    "    banana_production.columns = ['name', 'banana_production']\n",
    "    \n",
    "    #Merging the ecoinvent region dataset with FAO's production volume dataset\n",
    "    result = pd.merge(c, banana_production, how='right', on=['name'])\n",
    "    result = result.dropna(subset = ['shortname'])\n",
    "    \n",
    "    #Cutoff of the countries that account for 90% of the production volume\n",
    "    result = result.sort_values(['banana_production'], ascending=[False])\n",
    "    result['proportion_globalproduction'] = result['banana_production']/result['banana_production'].sum()\n",
    "    result['proportion_globalproduction_cumsum'] = result['proportion_globalproduction'].cumsum()\n",
    "    result.index = result['name']\n",
    "    result = result.loc[result['proportion_globalproduction_cumsum'] < 0.9]\n",
    "    \n",
    "    \n",
    "    #Scraping of web data on precipitation\n",
    "    #Creating the headers (not in an easily readable format on the webside, hence easier to not import them)\n",
    "    header = ['name',\n",
    "                'agriculturalland_perclandarea_00_02','agriculturalland_perclandarea_11_13','agriculturalland_percirrigated_11_13',\n",
    "                'avrgannualprecipitation_mm_14',\n",
    "                'landcerealproduction_hat_00_02','landcerealproduction_hat_11_13',\n",
    "                'fertlizerconsumption_percproduction_11_13', 'fertlizerconsumption_kgperha_11_13',\n",
    "                'agriculturalemployment_perctotalempl_00_02','agriculturalemployment_perctotalempl_11_13',\n",
    "                'agriculturalmachinery_tractorpor100sqrkm_00','agriculturalmachinery_tractorpor100sqrkm_09']\n",
    "    \n",
    "    #Scaping the precipitation data from the website\n",
    "    overviewtable = pd.read_html('http://wdi.worldbank.org/table/3.2')\n",
    "    \n",
    "    #Formatting the extracted data and eliminating unecessary information\n",
    "    wbdata = overviewtable[2]\n",
    "    wbdata.columns = header\n",
    "    wbdata = wbdata.replace('..','')\n",
    "    wbdata = wbdata[['name', 'avrgannualprecipitation_mm_14']]\n",
    "    \n",
    "    #Formatting the precipitation data for merging with the production data (naming conventions)\n",
    "    wbdata['name'] = wbdata['name'].str.lower()\n",
    "    wbdata['avrgannualprecipitation_mm_14']=pd.to_numeric(wbdata['avrgannualprecipitation_mm_14'])\n",
    "\n",
    "    #Merging the precipitation dataset with the production volume dataset\n",
    "    input_data = pd.merge(result[['name', 'shortname', 'banana_production']], wbdata, how='left', on=['name'])\n",
    "    input_data = input_data.set_index('shortname')\n",
    "    \n",
    "    #Performing a regression analysis based on a small sample to calculate irrigation need per \n",
    "        #annual precipitation - this data came from literature\n",
    "    rainfall = [2926,2274,3240]\n",
    "    irrigation = [0.106,0.142,0.079]\n",
    "    regression = np.polyfit(rainfall, irrigation, 1)\n",
    "    \n",
    "    #Calculating the irrigation need for each country based on the annual precipitation\n",
    "    #Adding result to the dataset, formatting (adjusting precision to original information)\n",
    "    input_data['irrigation_demand'] = (regression[1] + input_data['avrgannualprecipitation_mm_14']*regression[0])\n",
    "    input_data['irrigation_demand'] = round(input_data['irrigation_demand'], 3)\n",
    "    \n",
    "    #Finding the dataset on bananaproduction in the ecoinvent database\n",
    "    for banana_ds in data:\n",
    "        if banana_ds['name']=='banana production':\n",
    "            break\n",
    "    \n",
    "    #Create a copy of the banana production dataset for each country\n",
    "    for index in input_data.index:\n",
    "        new_ds = copy.deepcopy(banana_ds)\n",
    "        new_ds['location'] = index\n",
    "        \n",
    "        #In each copy, replace the original production volume with the country-specific production volume\n",
    "        for exc in new_ds['exchanges']:\n",
    "            if exc['name']=='banana':\n",
    "                exc['production volume']['amount']= input_data.loc[index]['banana_production']\n",
    "        \n",
    "        #In each copy, replace the original irrigation demand with the country-specific irrigation demand\n",
    "        #Keep the global average for countries with no data on irrigation demand\n",
    "            elif exc['name']=='irrigation':\n",
    "                if math.isnan(input_data.loc[index]['irrigation_demand']):\n",
    "                    print('keeping global irrigation demand')\n",
    "                else:\n",
    "                    exc['amount']= input_data.loc[index]['irrigation_demand']\n",
    "        \n",
    "        #Create a list with the datasets\n",
    "        data.append(copy.deepcopy(new_ds))\n",
    "    return data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#Add the datasets to ocelot database\n",
    "from ocelot.configuration import default_configuration\n",
    "default_configuration.insert(0, add_cool_bananas)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Starting Ocelot model run\n",
      "Using cached ecospold2 data\n",
      "Opening log file at: /home/jm/.local/share/Ocelot/model-runs/c0567b6636114919867fe54f09fe510e/report.log.json\n",
      "Applying transformation add_cool_bananas\n",
      "keeping global irrigation demand\n",
      "Applying transformation variable_names_are_unique\n",
      "Applying transformation ensure_markets_only_have_one_reference_product\n",
      "Applying transformation ensure_markets_dont_consume_their_ref_product\n",
      "Applying transformation fix_specific_ecoinvent_issues\n",
      "Applying transformation replace_implicit_references\n",
      "Applying transformation fix_known_bad_formula_strings\n",
      "Applying transformation lowercase_all_parameters\n",
      "Applying transformation fix_math_formulas\n",
      "Applying transformation replace_reserved_words\n",
      "Applying transformation delete_unparsable_formulas\n",
      "Applying transformation ensure_production_exchanges_have_production_volume\n",
      "Applying transformation add_pv_to_allocatable_byproducts\n",
      "Applying transformation create_pv_parameters\n",
      "Applying transformation remove_consequential_exchanges\n",
      "Applying transformation drop_rp_activity_links\n",
      "Applying transformation drop_zero_amount_activity_links\n",
      "Applying transformation check_activity_link_validity\n",
      "Applying transformation add_hard_linked_production_volumes\n",
      "Applying transformation rename_recyclable_content_exchanges\n",
      "Applying transformation create_recycled_content_datasets\n",
      "Applying transformation flip_non_allocatable_byproducts\n",
      "Applying transformation label_allocation_method\n",
      "Applying transformation economic_allocation\n",
      "Applying transformation constrained_market_allocation\n",
      "Applying transformation recycling_allocation\n",
      "Applying transformation waste_treatment_allocation\n",
      "Applying transformation combined_production_without_products\n",
      "Applying transformation combined_production\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "NameError\n",
      "   5.36e-11* cement+silica_fume*0+ ggbfs*0\n",
      "                     ^^^\n",
      "name 'silica_fume' is not defined\n",
      "NameError\n",
      "   5.36e-11* cement+silica_fume*0+ ggbfs*0\n",
      "                     ^^^\n",
      "name 'silica_fume' is not defined\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Applying transformation combined_production_with_byproducts\n",
      "Applying transformation delete_allocation_method\n",
      "Applying transformation drop_rp_activity_links\n",
      "Applying transformation label_reference_product\n",
      "Applying transformation delete_allowed_zero_pv_market_datsets\n",
      "Applying transformation assign_fake_pv_to_confidential_datasets\n",
      "Applying transformation relabel_global_to_row\n",
      "Applying transformation add_unique_codes\n",
      "Applying transformation actualize_activity_links\n",
      "Applying transformation add_recycled_content_suppliers_to_markets\n",
      "Applying transformation add_suppliers_to_markets\n",
      "Applying transformation update_market_production_volumes\n",
      "Applying transformation add_suppliers_to_markets\n",
      "Applying transformation update_market_production_volumes\n",
      "Applying transformation allocate_suppliers\n",
      "Skipping zero total PV with multiple inputs:\n",
      "\tmarket for waste newspaper/waste newspaper (GLO, 3 suppliers)\n",
      "Applying transformation link_consumers_to_regional_markets\n",
      "Applying transformation link_consumers_to_recycled_content_activities\n",
      "Applying transformation link_consumers_to_global_markets\n",
      "Applying transformation add_reference_product_codes\n",
      "Applying transformation log_and_delete_unlinked_exchanges\n",
      "Saving final results\n"
     ]
    }
   ],
   "source": [
    "fp, data = system_model('/home/jm/Documents/PhD_EPFL/events/LCA_summerschool/'\n",
    "                        'ecoinvent_3.2_modified_for_ocelot_summer_school')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "################\n",
    "#Data Uploading#\n",
    "################"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Creating default biosphere\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Writing activities to SQLite3 database:\n",
      "0%                          100%\n",
      "[###                           ] | ETA: 00:00:01"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Applying strategy: normalize_units\n",
      "Applying strategy: drop_unspecified_subcategories\n",
      "Applied 2 strategies in 0.01 seconds\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[##############################] | ETA: 00:00:00\n",
      "Total time elapsed: 00:00:01\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Title: Writing activities to SQLite3 database:\n",
      "  Started: 09/08/2016 22:28:34\n",
      "  Finished: 09/08/2016 22:28:35\n",
      "  Total time elapsed: 00:00:01\n",
      "  CPU %: 70.80\n",
      "  Memory %: 12.81\n",
      "Created database: biosphere3\n",
      "Creating default LCIA methods\n",
      "\n",
      "Applying strategy: normalize_units\n",
      "Applying strategy: set_biosphere_type\n",
      "Applying strategy: drop_unspecified_subcategories\n",
      "Applying strategy: link_iterable_by_fields\n",
      "Applied 4 strategies in 1.02 seconds\n",
      "Wrote 665 LCIA methods with 169551 characterization factors\n",
      "Creating core data migrations\n",
      "\n"
     ]
    }
   ],
   "source": [
    "#Setup brightway2\n",
    "from brightway2 import *\n",
    "projects.set_current(\"bananas2\")\n",
    "bw2setup()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Creating database `ecoinvent gone bananas` in project `bananas2`\n",
      "Applying strategy: normalize_units\n",
      "Applying strategy: drop_unspecified_subcategories\n",
      "Applying strategy: strip_biosphere_exc_locations\n",
      "Applied 3 strategies in 0.38 seconds\n",
      "Applying strategy: link_iterable_by_fields\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Writing activities to SQLite3 database:\n",
      "0%                          100%\n",
      "[                              ]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "13292 datasets\n",
      "319917 exchanges\n",
      "0 unlinked exchanges\n",
      "  \n",
      "Writing database\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[##############################] | ETA: 00:00:00\n",
      "Total time elapsed: 00:01:24\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Title: Writing activities to SQLite3 database:\n",
      "  Started: 09/08/2016 22:29:37\n",
      "  Finished: 09/08/2016 22:31:01\n",
      "  Total time elapsed: 00:01:24\n",
      "  CPU %: 62.00\n",
      "  Memory %: 13.03\n",
      "Created database: ecoinvent gone bananas\n"
     ]
    }
   ],
   "source": [
    "#Import the new databsae\n",
    "from ocelot.io.brightway2 import *\n",
    "db = import_into_brightway2(data, \"ecoinvent gone bananas\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}