{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "59d19f73",
   "metadata": {},
   "source": [
    "# Python API Example - Cargo Netbacks\n",
    "\n",
    "This guide is designed to provide an example of how to call the Cargo Netbacks API endpoint, and store the data accordingly.\n",
    "\n",
    "__N.B. This guide is just for Cargo Netbacks data. If you're looking for other API data products (such as Contracts or Freight routes), please refer to their according code example files.__ "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b0a05be4",
   "metadata": {},
   "source": [
    "### Have any questions?\n",
    "\n",
    "If you have any questions regarding our API, or need help accessing specific datasets, please contact us at:\n",
    "\n",
    "__data@sparkcommodities.com__\n",
    "\n",
    "or refer to our API website for more information about this endpoint:\n",
    "https://www.sparkcommodities.com/api/lng-cargo/netbacks.html"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9e00ae34",
   "metadata": {},
   "source": [
    "## 1. Importing Data\n",
    "\n",
    "Here we define the functions that allow us to retrieve the valid credentials to access the Spark API.\n",
    "\n",
    "__This section can remain unchanged for most Spark API users.__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5b30e815",
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import os\n",
    "import sys\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "from base64 import b64encode\n",
    "from urllib.parse import urljoin\n",
    "from io import StringIO\n",
    "import datetime\n",
    "\n",
    "try:\n",
    "    from urllib import request, parse\n",
    "    from urllib.error import HTTPError\n",
    "except ImportError:\n",
    "    raise RuntimeError(\"Python 3 required\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1161e807",
   "metadata": {},
   "outputs": [],
   "source": [
    "API_BASE_URL = \"https://api.sparkcommodities.com\"\n",
    "\n",
    "\n",
    "def retrieve_credentials(file_path=None):\n",
    "    \"\"\"\n",
    "    Find credentials either by reading the client_credentials file or reading\n",
    "    environment variables\n",
    "    \"\"\"\n",
    "    if file_path is None:\n",
    "        client_id = os.getenv(\"SPARK_CLIENT_ID\")\n",
    "        client_secret = os.getenv(\"SPARK_CLIENT_SECRET\")\n",
    "        if not client_id or not client_secret:\n",
    "            raise RuntimeError(\n",
    "                \"SPARK_CLIENT_ID and SPARK_CLIENT_SECRET environment vars required\"\n",
    "            )\n",
    "    else:\n",
    "        # Parse the file\n",
    "        if not os.path.isfile(file_path):\n",
    "            raise RuntimeError(\"The file {} doesn't exist\".format(file_path))\n",
    "\n",
    "        with open(file_path) as fp:\n",
    "            lines = [l.replace(\"\\n\", \"\") for l in fp.readlines()]\n",
    "\n",
    "        if lines[0] in (\"clientId,clientSecret\", \"client_id,client_secret\"):\n",
    "            client_id, client_secret = lines[1].split(\",\")\n",
    "        else:\n",
    "            print(\"First line read: '{}'\".format(lines[0]))\n",
    "            raise RuntimeError(\n",
    "                \"The specified file {} doesn't look like to be a Spark API client \"\n",
    "                \"credentials file\".format(file_path)\n",
    "            )\n",
    "\n",
    "    print(\">>>> Found credentials!\")\n",
    "    \n",
    "    return client_id, client_secret\n",
    "\n",
    "\n",
    "def do_api_post_query(uri, body, headers):\n",
    "    \"\"\"\n",
    "    OAuth2 authentication requires a POST request with client credentials before accessing the API.\n",
    "    This POST request will return an Access Token which will be used for the API GET request.\n",
    "    \"\"\"\n",
    "    url = urljoin(API_BASE_URL, uri)\n",
    "\n",
    "    data = json.dumps(body).encode(\"utf-8\")\n",
    "\n",
    "    # HTTP POST request\n",
    "    req = request.Request(url, data=data, headers=headers)\n",
    "    try:\n",
    "        response = request.urlopen(req)\n",
    "    except HTTPError as e:\n",
    "        print(\"HTTP Error: \", e.code)\n",
    "        print(e.read())\n",
    "        sys.exit(1)\n",
    "\n",
    "    resp_content = response.read()\n",
    "\n",
    "    # The server must return HTTP 201. Raise an error if this is not the case\n",
    "    assert response.status == 201, resp_content\n",
    "\n",
    "    # The server returned a JSON response\n",
    "    content = json.loads(resp_content)\n",
    "\n",
    "    return content\n",
    "\n",
    "\n",
    "def do_api_get_query(uri, access_token, format='json'):\n",
    "    \"\"\"\n",
    "    After receiving an Access Token, we can request information from the API.\n",
    "    Supports both JSON (default) and CSV responses.\n",
    "    \"\"\"\n",
    "    url = urljoin(API_BASE_URL, uri)\n",
    "\n",
    "    if format == 'json':\n",
    "        headers = {\n",
    "            \"Authorization\": \"Bearer {}\".format(access_token),\n",
    "            \"Accept\": \"application/json\",\n",
    "        }\n",
    "    elif format == 'csv':\n",
    "        headers = {\n",
    "            \"Authorization\": \"Bearer {}\".format(access_token),\n",
    "            \"Accept\": \"text/csv\",\n",
    "        }\n",
    "    else:\n",
    "        raise ValueError(\"The format parameter only takes 'csv' or 'json' as inputs\")\n",
    "\n",
    "    print(\"Fetching {}\".format(url))\n",
    "\n",
    "    # HTTP GET request\n",
    "    req = request.Request(url, headers=headers)\n",
    "    try:\n",
    "        response = request.urlopen(req)\n",
    "    except HTTPError as e:\n",
    "        print(\"HTTP Error: \", e.code)\n",
    "        print(e.read())\n",
    "        sys.exit(1)\n",
    "\n",
    "    resp_content = response.read()\n",
    "\n",
    "    # The server must return HTTP 200. Raise an error if this is not the case\n",
    "    assert response.status == 200, resp_content\n",
    "\n",
    "    # Storing response based on requested format\n",
    "    if format == 'json':\n",
    "        content = json.loads(resp_content)\n",
    "    elif format == 'csv':\n",
    "        content = resp_content\n",
    "\n",
    "    return content\n",
    "\n",
    "\n",
    "def get_access_token(client_id, client_secret):\n",
    "\n",
    "    payload = \"{}:{}\".format(client_id, client_secret).encode()\n",
    "    headers = {\n",
    "        \"Authorization\": b64encode(payload).decode(),\n",
    "        \"Accept\": \"application/json\",\n",
    "        \"Content-Type\": \"application/json\",\n",
    "    }\n",
    "    body = {\n",
    "        \"grantType\": \"clientCredentials\",\n",
    "    }\n",
    "\n",
    "    content = do_api_post_query(uri=\"/oauth/token/\", body=body, headers=headers)\n",
    "\n",
    "    print(\n",
    "        \">>>> Successfully fetched an access token {}****, valid {} seconds.\".format(\n",
    "            content[\"accessToken\"][:5], content[\"expiresIn\"]\n",
    "        )\n",
    "    )\n",
    "\n",
    "    return content[\"accessToken\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f40a040b",
   "metadata": {},
   "source": [
    "## N.B. Credentials\n",
    "\n",
    "Here we call the above functions, and input the file path to our credentials.\n",
    "\n",
    "N.B. You must have downloaded your client credentials CSV file before proceeding. Please refer to the API documentation if you have not dowloaded them already.  Instructions for downloading your credentials can be found here:\n",
    "\n",
    "https://www.sparkcommodities.com/api/request/authentication.html\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "eeb3bd88",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Input the path to your client credentials here\n",
    "client_id, client_secret = retrieve_credentials(file_path=\"/tmp/client_credentials.csv\")\n",
    "\n",
    "# Authenticate:\n",
    "access_token = get_access_token(client_id, client_secret)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9c527e40",
   "metadata": {},
   "source": [
    "## Reference Data endpoint\n",
    "\n",
    "This query shows an overview on all available netbacks, showing all available ports and possible routes to/from these destinations (i.e. via Suez, Panama etc.).\n",
    "\n",
    "An example of pulling all available Netbacks data for a specific route (e.g. Netbacks data for Sabine Pass via Suez) is shown later in this script. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fc9904e5",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define the function for listing all netback reference data\n",
    "def list_netbacks(access_token):\n",
    "\n",
    "    content = do_api_get_query(\n",
    "        uri=\"/v1.0/netbacks/reference-data/\", access_token=access_token\n",
    "    )\n",
    "\n",
    "    # retrieve release dates separately\n",
    "    reldates = content[\"data\"][\"staticData\"][\"sparkReleases\"]\n",
    "\n",
    "    # return reference data\n",
    "    refdata_dict = content[\"data\"]\n",
    "\n",
    "    return reldates, refdata_dict\n",
    "\n",
    "# Fetch reference data:\n",
    "reldates, refdata_dict = list_netbacks(access_token)\n",
    "\n",
    "# formatting as a Dataframe\n",
    "available_df = pd.json_normalize(refdata_dict['staticData']['fobPorts'])\n",
    "available_df.head(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2d1bf4c0",
   "metadata": {},
   "source": [
    "## Defining data calling function\n",
    "\n",
    "Details on the available parameters can be found on our API docs website:\n",
    "\n",
    "https://www.sparkcommodities.com/api/lng-cargo/netbacks.html\n",
    "\n",
    "__N.B.:__ This endpoint provides the option to return a JSON or CSV formatted response. Metadata is only available in the JSON format."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "eb563eb4",
   "metadata": {},
   "outputs": [],
   "source": [
    "from io import StringIO\n",
    "\n",
    "def fetch_netback(access_token, fob_port_uuid, release=None, via_point=None, laden=None, ballast=None, start=None, end=None, percent_hire=None, format='json'):\n",
    "    \n",
    "    query_params = \"?fob-port={}\".format(fob_port_uuid)\n",
    "    if release is not None:\n",
    "        query_params += \"&release-date={}\".format(release)\n",
    "    if start is not None:\n",
    "        query_params += \"&start={}\".format(start)\n",
    "    if end is not None:\n",
    "        query_params += \"&end={}\".format(end)\n",
    "    if via_point is not None:\n",
    "        query_params += \"&via-point={}\".format(via_point)\n",
    "    if laden is not None:\n",
    "        query_params += \"&laden-congestion-days={}\".format(laden)\n",
    "    if ballast is not None:\n",
    "        query_params += \"&ballast-congestion-days={}\".format(ballast)\n",
    "    if percent_hire is not None:\n",
    "        query_params += \"&percent-hire={}\".format(percent_hire)\n",
    "    \n",
    "    \n",
    "    content = do_api_get_query(\n",
    "        uri=\"/v1.0/netbacks/{}\".format(query_params),\n",
    "        access_token=access_token, format=format,\n",
    "    )\n",
    "    \n",
    "    if format == 'json':\n",
    "        data = content\n",
    "    elif format == 'csv':\n",
    "        # if there's no data to show, returns raw response (empty string) and \"No Data to Show\" message\n",
    "        if len(content) == 0:\n",
    "            data = content\n",
    "            print('No Data to Show')\n",
    "        else:\n",
    "            data = content.decode('utf-8')\n",
    "            data = pd.read_csv(StringIO(data))  # automatically converting into a Pandas DataFrame when choosing CSV format\n",
    "\n",
    "    return data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "568a2016",
   "metadata": {},
   "source": [
    "### Choosing FOB Port"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "62cfd665",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Select Route\n",
    "tsab = available_df[available_df[\"name\"] == 'Sabine Pass'][\"uuid\"].iloc[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e269bd15",
   "metadata": {},
   "source": [
    "### JSON Response"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "faa16ace",
   "metadata": {},
   "outputs": [],
   "source": [
    "## Calling data in JSON format\n",
    "\n",
    "json_data = fetch_netback(access_token, fob_port_uuid=tsab, via_point='cogh', release='2026-07-06', format='json')\n",
    "json_data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "16fb96d1",
   "metadata": {},
   "source": [
    "### CSV Response\n",
    "\n",
    "Calling the data in CSV format & formatting as a Pandas DataFrame. Here, we also utilise the \"start\" and \"end\" parameters to call a range of historical data in one call."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cde48ff9",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_csv = fetch_netback(access_token, fob_port_uuid=tsab, via_point='cogh', start='2026-01-01', end='2026-06-30', format='csv')\n",
    "df_csv"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eaabce21",
   "metadata": {},
   "source": [
    "## N.B. Historical Data Limits\n",
    "\n",
    "Currently, a maximum of 1 year's worth of historical data can be called at one time due to the size of the data file. \n",
    "\n",
    "If more data points are required, the below code can be used: the function calls the historical data 1 year at a time and combines the data into one Pandas DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3ec7e0db",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "def loop_historical_data(access_token, fob_port_uuid=None, via_point=None, percent_hire=None, start=None, end=None):\n",
    "    \n",
    "    hist_diff = (datetime.datetime.strptime(end, '%Y-%m-%d') - datetime.datetime.strptime(start, '%Y-%m-%d')).days\n",
    "    t = 0\n",
    "\n",
    "    starts = []\n",
    "    ends = []\n",
    "\n",
    "    w = 365\n",
    "\n",
    "    while t < hist_diff:\n",
    "        # initialising dataframe\n",
    "        if t == 0 and hist_diff>w:\n",
    "            diff_end = datetime.datetime.strftime(datetime.datetime.strptime(start, '%Y-%m-%d') + pd.Timedelta(days=w), '%Y-%m-%d')\n",
    "            hist_df = fetch_netback(access_token, fob_port_uuid=fob_port_uuid, via_point=via_point, start=start, end=diff_end, \n",
    "                                    percent_hire=percent_hire, format='csv')\n",
    "\n",
    "            starts.append(start)\n",
    "            ends.append(diff_end)\n",
    "        \n",
    "        elif t==0 and hist_diff<=w:\n",
    "            hist_df = fetch_netback(access_token, fob_port_uuid=fob_port_uuid, via_point=via_point, start=start, end=end, \n",
    "                                    percent_hire=percent_hire, format='csv')\n",
    "\n",
    "        # appending additional historical data\n",
    "        else:\n",
    "            if t < hist_diff-w:\n",
    "                diff_start = datetime.datetime.strftime(datetime.datetime.strptime(start, '%Y-%m-%d') + pd.Timedelta(days=t+1), '%Y-%m-%d')\n",
    "                diff_end = datetime.datetime.strftime(datetime.datetime.strptime(diff_start, '%Y-%m-%d') + pd.Timedelta(days=w), '%Y-%m-%d')\n",
    "                historical_addition = fetch_netback(access_token, fob_port_uuid=fob_port_uuid, via_point=via_point, start=diff_start, end=diff_end, \n",
    "                                    percent_hire=percent_hire, format='csv')\n",
    "                \n",
    "                try:\n",
    "                    hist_df = pd.concat([hist_df,historical_addition])\n",
    "                #exception if hist_df is empty\n",
    "                except:\n",
    "                    hist_df = historical_addition.copy()\n",
    "                starts.append(start)\n",
    "                ends.append(diff_end)\n",
    "            else:\n",
    "                diff_start = datetime.datetime.strftime(datetime.datetime.strptime(start, '%Y-%m-%d') + pd.Timedelta(days=t+1), '%Y-%m-%d')\n",
    "                diff_end = datetime.datetime.strftime(datetime.datetime.strptime(diff_start, '%Y-%m-%d') + pd.Timedelta(days=hist_diff-t), '%Y-%m-%d')\n",
    "\n",
    "                historical_addition = fetch_netback(access_token, fob_port_uuid=fob_port_uuid, via_point=via_point, start=diff_start, end=diff_end, \n",
    "                                    percent_hire=percent_hire, format='csv')\n",
    "\n",
    "                hist_df = pd.concat([hist_df, historical_addition])\n",
    "                starts.append(start)\n",
    "                ends.append(diff_end)\n",
    "        \n",
    "        #looping by year\n",
    "        t += w\n",
    "\n",
    "    for c in list(hist_df.columns)[4:]:\n",
    "        hist_df[c] = pd.to_numeric(hist_df[c])\n",
    "    hist_df['ReleaseDate'] = pd.to_datetime(hist_df['ReleaseDate'])\n",
    "    hist_df['LoadMonthDate'] = pd.to_datetime(hist_df['LoadMonth'])\n",
    "    hist_df['CalMonth'] = hist_df['LoadMonthDate'].dt.strftime('%b%y')\n",
    "\n",
    "    hist_df = hist_df.drop_duplicates()\n",
    "    hist_df = hist_df.sort_values(['ReleaseDate', 'LoadDate'])\n",
    "\n",
    "    return hist_df"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.13.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}