{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "1b582ffc-7477-46c3-b5bf-2caf9d028bf2",
   "metadata": {},
   "source": [
    "<a href=\"https://colab.research.google.com/github/GlobalFishingWatch/gfw-api-python-client/blob/develop/notebooks/workflow-guides/workflow-02-analyze-apparent-fishing-effort-argentinian-eez.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "87eddf13-ac9c-45b0-ae10-24eb1620e07e",
   "metadata": {},
   "source": [
    "# Analyze apparent fishing effort in Argentinian EEZ"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d79f0ab4-ab4d-4098-82b0-b6a5c772e101",
   "metadata": {},
   "source": [
    "This guide provides detailed instructions to on how to use the [gfw-api-python-client](https://github.com/GlobalFishingWatch/gfw-api-python-client) to **Analyze apparent fishing effort in [Argentinian EEZ](https://www.marineregions.org/gazetteer.php?p=details&id=8466) region and monitor industrial trawlers** using **[4Wings API](https://globalfishingwatch.org/our-apis/documentation#map-visualization-4wings-api)**, **[Vessels API](https://globalfishingwatch.org/our-apis/documentation#vessels-api)**, and **[Events API](https://globalfishingwatch.org/our-apis/documentation#events-api)**."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7ac25ecf-ffd7-40d7-9ea0-a6514c9fcd85",
   "metadata": {},
   "source": [
    "**Note:** See the [Datasets](https://globalfishingwatch.org/our-apis/documentation#api-dataset), [Data Caveats](https://globalfishingwatch.org/our-apis/documentation#data-caveat), and [Terms of Use](https://globalfishingwatch.org/our-apis/documentation#terms-of-use) pages in the [GFW API documentation](https://globalfishingwatch.org/our-apis/documentation#introduction) for details on GFW data, API licenses, and rate limits."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "71018cec-10c0-4619-9a7d-838a9f43cb15",
   "metadata": {},
   "source": [
    "## Prerequisites"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "996ca24b-99e4-4546-805b-697e4c2eb321",
   "metadata": {},
   "source": [
    "Before using the `gfw-api-python-client`, ensure it is installed (see the [Getting Started](https://globalfishingwatch.github.io/gfw-api-python-client/getting-started.html) guide) and that you have obtained an API access token from the [Global Fishing Watch API portal](https://globalfishingwatch.org/our-apis/tokens)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6be16f6f-19fc-4d19-a0ed-ba370c844fa6",
   "metadata": {},
   "source": [
    "## Installation"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af48cf4e-e24c-47aa-a2c5-64cf87be9c33",
   "metadata": {},
   "source": [
    "The `gfw-api-python-client` can be easily installed using pip:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "88c09924-87d2-4c86-ad60-aed623416193",
   "metadata": {},
   "outputs": [],
   "source": [
    "# %pip install gfw-api-python-client"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eafaa9d1-2143-452c-813c-75b21fd2198c",
   "metadata": {},
   "source": [
    "## Usage"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "420afe1c-ff77-40e2-9a07-7372dc95170c",
   "metadata": {},
   "source": [
    "Import and use `gfw-api-python-client` in your Python codes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "cc98323c-c9e4-401c-8f26-f551968c003a",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "import pandas as pd\n",
    "\n",
    "import gfwapiclient as gfw"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "047ff069-3c87-47fe-bb4a-acb920df2137",
   "metadata": {},
   "outputs": [],
   "source": [
    "try:\n",
    "    from google.colab import userdata\n",
    "\n",
    "    access_token = userdata.get(\"GFW_API_ACCESS_TOKEN\")\n",
    "except Exception:\n",
    "    access_token = os.environ.get(\"GFW_API_ACCESS_TOKEN\")\n",
    "\n",
    "access_token = access_token or \"<PASTE_YOUR_GFW_API_ACCESS_TOKEN_HERE>\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "708e137f-6aa0-461e-b1af-33512a2093fc",
   "metadata": {},
   "outputs": [],
   "source": [
    "gfw_client = gfw.Client(\n",
    "    access_token=access_token,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b08a0e2c-3b9d-4c5e-b3a0-a5663fa32637",
   "metadata": {},
   "source": [
    "## Introduction"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "62fe47aa-ed77-4815-b08d-8c96f2480b04",
   "metadata": {},
   "source": [
    "**Use Case: A Fisheries Enforcement Officer Monitoring Industrial Trawlers**"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5109f67f-aaae-4a7d-9a15-4db740542694",
   "metadata": {},
   "source": [
    "Maria, a fisheries enforcement officer in Argentina, monitors industrial trawlers operating within **[Argentinian Exclusive Economic Zone (EEZ)](https://www.marineregions.org/gazetteer.php?p=details&id=8466)**. His goal is to:\n",
    "\n",
    "1. Analyzing apparent fishing effort for **trawlers** operating in Argentinian EEZ.\n",
    "2. Identifying vessels involved in **apparent trawling activity** and determining their reported **flag states**.\n",
    "3. Checking vessel history, including **potential transshipment** and **port visits**.\n",
    "4. Generating reports to support fisheries enforcement decisions."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b16b1b52-6b68-494a-9d76-ca7a7ab485a0",
   "metadata": {},
   "source": [
    "**APIs Used:**\n",
    "️\n",
    "1. **[4Wings API](https://globalfishingwatch.org/our-apis/documentation#map-visualization-4wings-api)** – Retrieve **apparent fishing effort** data for trawlers.\n",
    "2. **[4Wings API](https://globalfishingwatch.org/our-apis/documentation#map-visualization-4wings-api)** – Group vessels by ID that are involved in **trawling activity**.\n",
    "3. **[Vessels API](https://globalfishingwatch.org/our-apis/documentation#vessels-api)** – Retrieve **vessel identity** & **ownership** details.\n",
    "4. **[Events API](https://globalfishingwatch.org/our-apis/documentation#events-api)** – Fetch **port visits** & **potential transshipment** history. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c93924be-f36e-4f6c-830f-4d06c03d08f7",
   "metadata": {},
   "source": [
    "**Important:** In order to avoid any misinterpretation of **GFW data**, please refer to our official **data caveats** documentations:\n",
    "- [Apparent fishing effort](https://globalfishingwatch.org/dataset-and-code-fishing-effort/) \n",
    "- [Exclusive economic zone boundaries definition](https://globalfishingwatch.org/our-apis/documentation#exclusive-economic-zone-boundaries-definition)\n",
    "- [Vessel ID](https://globalfishingwatch.org/our-apis/documentation#vessel-id)\n",
    "- [Vessel API - Vessel identity information](https://globalfishingwatch.org/our-apis/documentation#vessel-api-vessel-identity-information)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01169672-36d5-4b2b-969d-471070d75f8c",
   "metadata": {},
   "source": [
    "**Important Caveats:**\n",
    "\n",
    "1. The [4Wings API](https://globalfishingwatch.org/our-apis/documentation#map-visualization-4wings-api) only supports **one active report per user at a time**.\n",
    "2. **Sending multiple requests simultaneously** results in a **429 Too Many Requests** error.\n",
    "3. If a report takes over **100 seconds** to generate, it may return a **524 Gateway Timeout** error."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2c1e1858-c328-4719-8f10-40ae5b43ecb0",
   "metadata": {},
   "source": [
    "## Step 0: Identify the Region of Interest (ROI) - Argentinian EEZ"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "88789a27-1e15-44af-ba81-7d07ded02e4b",
   "metadata": {},
   "source": [
    "Before making API requests, Maria must specify the geographic area for analysis using a **Region ID**:"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "75a985b1-3803-48d9-b2f3-f12b29bd29e7",
   "metadata": {},
   "source": [
    "**Options to Define the Region:**\n",
    "\n",
    "1. **Using Region ID** - Each EEZ has a unique ID in the **[public-eez-areas](https://globalfishingwatch.org/our-apis/documentation#regions)** dataset.\n",
    "2. **Custom Geometries** - Users can define a custom area using GeoJSON.\n",
    "   \n",
    "For **[Argentinian EEZ, the region ID is 8466](https://www.marineregions.org/gazetteer.php?p=details&id=8466)** (public-eez-areas dataset)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "35a0691d-b747-48e6-8b02-5c2f54a5d536",
   "metadata": {},
   "source": [
    "## Step 1: Retrieve Apparent Fishing Effort in Argentinian EEZ"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d57cd039-a667-44f7-b785-8d0e50530333",
   "metadata": {},
   "source": [
    "Maria **first queries** the **[4Wings API](https://globalfishingwatch.org/our-apis/documentation#map-visualization-4wings-api)** to get **apparent fishing effort for all vessels**, grouping them by **gear type** in **[Argentinian EEZ](https://www.marineregions.org/gazetteer.php?p=details&id=8466)**. Please [learn more about apparent fishing effort here](https://globalfishingwatch.org/our-apis/documentation#ais-apparent-fishing-effort) and [check its data caveats here](https://globalfishingwatch.org/our-apis/documentation#apparent-fishing-effort)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6229af14-613a-4809-96f5-9cb3d6bd3461",
   "metadata": {},
   "source": [
    "**Filters Used:**\n",
    "\n",
    "1. **[Region ID](https://globalfishingwatch.org/our-apis/documentation#regions)** - 8466 Argentinian EEZ\n",
    "2. **[Date Range](https://globalfishingwatch.org/our-apis/documentation#report-url-parameters-for-both-post-and-get-requests)** - Last 6 Months\n",
    "3. **[Grouped By](https://globalfishingwatch.org/our-apis/documentation#report-url-parameters-for-both-post-and-get-requests)** - Gear Type"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b945aa10-40c3-490a-84e7-89092badd783",
   "metadata": {},
   "source": [
    "**Why This Step?**\n",
    "\n",
    "- Identifies which gear types (e.g., `trawlers`, `squid jiggers` etc.) are most active in the Argentinian EEZ.\n",
    "- Establishes baseline fishing activity trends before narrowing the search to specific vessels."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "62b9b9e5-4170-40d0-9aef-7579beb89bc0",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_1_report_result = await gfw_client.fourwings.create_fishing_effort_report(\n",
    "    spatial_resolution=\"HIGH\",\n",
    "    group_by=\"GEARTYPE\",\n",
    "    temporal_resolution=\"MONTHLY\",\n",
    "    start_date=\"2024-08-01\",\n",
    "    end_date=\"2025-01-31\",\n",
    "    spatial_aggregation=True,\n",
    "    region={\n",
    "        \"dataset\": \"public-eez-areas\",\n",
    "        \"id\": \"8466\",\n",
    "    },\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "4d6190fc-a8fa-4d59-914e-ebae41943381",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_1_report_df = step_1_report_result.df()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "d98ca51f-bb46-4edc-9a61-3e26c56bbcc8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 40 entries, 0 to 39\n",
      "Data columns (total 20 columns):\n",
      " #   Column                   Non-Null Count  Dtype  \n",
      "---  ------                   --------------  -----  \n",
      " 0   date                     40 non-null     object \n",
      " 1   detections               0 non-null      object \n",
      " 2   flag                     0 non-null      object \n",
      " 3   gear_type                40 non-null     object \n",
      " 4   hours                    40 non-null     float64\n",
      " 5   vessel_ids               40 non-null     int64  \n",
      " 6   vessel_id                0 non-null      object \n",
      " 7   vessel_type              0 non-null      object \n",
      " 8   entry_timestamp          0 non-null      object \n",
      " 9   exit_timestamp           0 non-null      object \n",
      " 10  first_transmission_date  0 non-null      object \n",
      " 11  last_transmission_date   0 non-null      object \n",
      " 12  imo                      0 non-null      object \n",
      " 13  mmsi                     0 non-null      object \n",
      " 14  call_sign                0 non-null      object \n",
      " 15  dataset                  0 non-null      object \n",
      " 16  report_dataset           40 non-null     object \n",
      " 17  ship_name                0 non-null      object \n",
      " 18  lat                      0 non-null      object \n",
      " 19  lon                      0 non-null      object \n",
      "dtypes: float64(1), int64(1), object(18)\n",
      "memory usage: 6.4+ KB\n"
     ]
    }
   ],
   "source": [
    "step_1_report_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "ce844c77-6cf0-4648-bdfb-3a72589c0785",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gear_type</th>\n",
       "      <th>hours</th>\n",
       "      <th>vessel_ids</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>pots_and_traps</td>\n",
       "      <td>92.029722</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>inconclusive</td>\n",
       "      <td>215.623889</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>inconclusive</td>\n",
       "      <td>98.155833</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>set_longlines</td>\n",
       "      <td>17.925833</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>other_purse_seines</td>\n",
       "      <td>57.377500</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            gear_type       hours  vessel_ids\n",
       "0      pots_and_traps   92.029722           3\n",
       "1        inconclusive  215.623889           2\n",
       "2        inconclusive   98.155833           2\n",
       "3       set_longlines   17.925833           1\n",
       "4  other_purse_seines   57.377500           1"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_1_report_df[[\"gear_type\", \"hours\", \"vessel_ids\"]].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "45319c2a-e82e-4a9a-8a2d-2ea6d9cdada4",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_1_agg_report_df = (\n",
    "    step_1_report_df.groupby([\"gear_type\"], as_index=False)\n",
    "    .agg(hours=(\"hours\", \"sum\"), vessel_ids=(\"vessel_ids\", \"sum\"))\n",
    "    .sort_values(by=\"hours\", ascending=False)\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "121465c6-65ef-4efa-9d8a-4a0a136564bd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gear_type</th>\n",
       "      <th>hours</th>\n",
       "      <th>vessel_ids</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>trawlers</td>\n",
       "      <td>240642.414444</td>\n",
       "      <td>1315</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>fishing</td>\n",
       "      <td>16023.201389</td>\n",
       "      <td>94</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>squid_jigger</td>\n",
       "      <td>6124.062222</td>\n",
       "      <td>44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>fixed_gear</td>\n",
       "      <td>1948.325556</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>inconclusive</td>\n",
       "      <td>1072.351389</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      gear_type          hours  vessel_ids\n",
       "8      trawlers  240642.414444        1315\n",
       "1       fishing   16023.201389          94\n",
       "7  squid_jigger    6124.062222          44\n",
       "2    fixed_gear    1948.325556          16\n",
       "3  inconclusive    1072.351389          14"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_1_agg_report_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "449828f2-dda7-422c-8cfb-770ced828ca6",
   "metadata": {},
   "source": [
    "### What We have Learned from Step 1"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e83e24d9-edb1-45d3-af4a-fa60b155ecab",
   "metadata": {},
   "source": [
    "- Multiple **gear types** were potentially detected in Argentinian EEZ.\n",
    "- `Trawlers` appear to be operating, but further **vessel-level investigation** is needed."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6fe5edf3-8e96-4147-8c59-a6bc8982662d",
   "metadata": {},
   "source": [
    "## Step 2: Retrieve Vessel IDs for Trawlers"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4bede3c0-3d01-4661-8b88-467244417d20",
   "metadata": {},
   "source": [
    "Maria refines her **[4Wings API](https://globalfishingwatch.org/our-apis/documentation#map-visualization-4wings-api)** request to group by **vessel ID**, and filtering only for **trawlers** in **[Argentinian EEZ](https://www.marineregions.org/gazetteer.php?p=details&id=8466)**. Please [learn more about apparent fishing effort here](https://globalfishingwatch.org/our-apis/documentation#ais-apparent-fishing-effort) and [check its data caveats here](https://globalfishingwatch.org/our-apis/documentation#apparent-fishing-effort)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2e2e42d9-1b9e-4115-b601-72d0e86ab91d",
   "metadata": {},
   "source": [
    "**Filters Used:**\n",
    "\n",
    "1. **[Region ID](https://globalfishingwatch.org/our-apis/documentation#regions)** - [8466 Argentinian EEZ](https://www.marineregions.org/gazetteer.php?p=details&id=8466)\n",
    "2. **[Date Range](https://globalfishingwatch.org/our-apis/documentation#report-url-parameters-for-both-post-and-get-requests)** - Last 6 Months\n",
    "3. **[Grouped By](https://globalfishingwatch.org/our-apis/documentation#report-url-parameters-for-both-post-and-get-requests)** - Vessel ID\n",
    "4. **[Gear Type](https://globalfishingwatch.org/our-apis/documentation#gear-types-supported)** - Trawlers "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "849f6157-fa79-456f-8974-d294c77a0729",
   "metadata": {},
   "source": [
    "**Why Use group-by=VESSEL_ID?**\n",
    "\n",
    "Grouping by **VESSEL_ID** allows **individual vessel identification** in the response. This is crucial for **tracking vessel activity** and, more importantly, linking each detected vessel to the **[Vessels API](https://globalfishingwatch.org/our-apis/documentation#vessels-api)** in the next step. By structuring the query this way, we can fetch vessel details such as **flag, name, and ownership records** in **Step 3 below**.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "db35d1b2-ba32-4a58-97f3-17059b3de164",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_2_report_result = await gfw_client.fourwings.create_fishing_effort_report(\n",
    "    spatial_resolution=\"HIGH\",\n",
    "    group_by=\"VESSEL_ID\",\n",
    "    temporal_resolution=\"ENTIRE\",\n",
    "    filters=[\"geartype in ('trawlers')\"],\n",
    "    start_date=\"2024-08-01\",\n",
    "    end_date=\"2025-01-31\",\n",
    "    spatial_aggregation=True,\n",
    "    region={\n",
    "        \"dataset\": \"public-eez-areas\",\n",
    "        \"id\": \"8466\",\n",
    "    },\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "301f888e-3b7e-4946-a7aa-496e05b53cbd",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_2_report_df = step_2_report_result.df()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "866f84fb-50c4-47e2-95fa-43fbc06d17cd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 385 entries, 0 to 384\n",
      "Data columns (total 20 columns):\n",
      " #   Column                   Non-Null Count  Dtype              \n",
      "---  ------                   --------------  -----              \n",
      " 0   date                     385 non-null    object             \n",
      " 1   detections               0 non-null      object             \n",
      " 2   flag                     385 non-null    object             \n",
      " 3   gear_type                385 non-null    object             \n",
      " 4   hours                    385 non-null    float64            \n",
      " 5   vessel_ids               0 non-null      object             \n",
      " 6   vessel_id                385 non-null    object             \n",
      " 7   vessel_type              385 non-null    object             \n",
      " 8   entry_timestamp          385 non-null    datetime64[ns, UTC]\n",
      " 9   exit_timestamp           385 non-null    datetime64[ns, UTC]\n",
      " 10  first_transmission_date  385 non-null    datetime64[ns, UTC]\n",
      " 11  last_transmission_date   385 non-null    datetime64[ns, UTC]\n",
      " 12  imo                      385 non-null    object             \n",
      " 13  mmsi                     385 non-null    object             \n",
      " 14  call_sign                385 non-null    object             \n",
      " 15  dataset                  385 non-null    object             \n",
      " 16  report_dataset           385 non-null    object             \n",
      " 17  ship_name                385 non-null    object             \n",
      " 18  lat                      0 non-null      object             \n",
      " 19  lon                      0 non-null      object             \n",
      "dtypes: datetime64[ns, UTC](4), float64(1), object(15)\n",
      "memory usage: 60.3+ KB\n"
     ]
    }
   ],
   "source": [
    "step_2_report_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "82a786a1-c437-430e-aeb5-f61d02a5f900",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>flag</th>\n",
       "      <th>gear_type</th>\n",
       "      <th>hours</th>\n",
       "      <th>mmsi</th>\n",
       "      <th>ship_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ARG</td>\n",
       "      <td>TRAWLERS</td>\n",
       "      <td>714.842500</td>\n",
       "      <td>701000882</td>\n",
       "      <td>FELIX AUGUSTO</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ARG</td>\n",
       "      <td>TRAWLERS</td>\n",
       "      <td>641.522222</td>\n",
       "      <td>701000932</td>\n",
       "      <td>ANTONIO ALVAREZ</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>URY</td>\n",
       "      <td>TRAWLERS</td>\n",
       "      <td>10.023056</td>\n",
       "      <td>770576463</td>\n",
       "      <td>KALATXORI</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ARG</td>\n",
       "      <td>TRAWLERS</td>\n",
       "      <td>326.160833</td>\n",
       "      <td>701079000</td>\n",
       "      <td>ENTRENA UNO</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ARG</td>\n",
       "      <td>TRAWLERS</td>\n",
       "      <td>295.007500</td>\n",
       "      <td>701000820</td>\n",
       "      <td>CORAJE</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  flag gear_type       hours       mmsi        ship_name\n",
       "0  ARG  TRAWLERS  714.842500  701000882    FELIX AUGUSTO\n",
       "1  ARG  TRAWLERS  641.522222  701000932  ANTONIO ALVAREZ\n",
       "2  URY  TRAWLERS   10.023056  770576463        KALATXORI\n",
       "3  ARG  TRAWLERS  326.160833  701079000      ENTRENA UNO\n",
       "4  ARG  TRAWLERS  295.007500  701000820           CORAJE"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_2_report_df[[\"flag\", \"gear_type\", \"hours\", \"mmsi\", \"ship_name\"]].head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "630d95dd-8f82-407f-b223-f55e981e3593",
   "metadata": {},
   "source": [
    "### Explore Vessels Potentially Engaged in Trawling Activity in the Argentinian EEZ"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "984052a3-3920-4fce-8894-4b67af4a8a69",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_2_agg_report_df = (\n",
    "    step_2_report_df.groupby([\"flag\", \"gear_type\", \"mmsi\", \"ship_name\"], as_index=False)\n",
    "    .agg(hours=(\"hours\", \"sum\"))\n",
    "    .sort_values(by=\"hours\", ascending=False)\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "83e4dafb-4491-40c9-9f4d-f4cc1e2b7766",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>flag</th>\n",
       "      <th>gear_type</th>\n",
       "      <th>mmsi</th>\n",
       "      <th>ship_name</th>\n",
       "      <th>hours</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>297</th>\n",
       "      <td>ARG</td>\n",
       "      <td>TRAWLERS</td>\n",
       "      <td>701024000</td>\n",
       "      <td>ATLANTIC SURF III</td>\n",
       "      <td>3151.855278</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>247</th>\n",
       "      <td>ARG</td>\n",
       "      <td>TRAWLERS</td>\n",
       "      <td>701006605</td>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>2270.097500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>ARG</td>\n",
       "      <td>TRAWLERS</td>\n",
       "      <td>701000577</td>\n",
       "      <td>MISS TIDE</td>\n",
       "      <td>2244.895833</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>296</th>\n",
       "      <td>ARG</td>\n",
       "      <td>TRAWLERS</td>\n",
       "      <td>701023000</td>\n",
       "      <td>CAROLINA P</td>\n",
       "      <td>2065.586944</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>301</th>\n",
       "      <td>ARG</td>\n",
       "      <td>TRAWLERS</td>\n",
       "      <td>701037000</td>\n",
       "      <td>DON PEDRO</td>\n",
       "      <td>1807.146111</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    flag gear_type       mmsi          ship_name        hours\n",
       "297  ARG  TRAWLERS  701024000  ATLANTIC SURF III  3151.855278\n",
       "247  ARG  TRAWLERS  701006605          CAPESANTE  2270.097500\n",
       "22   ARG  TRAWLERS  701000577          MISS TIDE  2244.895833\n",
       "296  ARG  TRAWLERS  701023000         CAROLINA P  2065.586944\n",
       "301  ARG  TRAWLERS  701037000          DON PEDRO  1807.146111"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_2_agg_report_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3f948958-ebce-4478-8b17-d6143c38956b",
   "metadata": {},
   "source": [
    "### What We have Learned from Step 2"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d4fb7cba-a577-45fe-88fa-8e5001bb9869",
   "metadata": {},
   "source": [
    "- There are vessels appear to have been engaged in potential trawling activity in Argentinian EEZ over the past 6 months i.e.,:\n",
    "  - `ATLANTIC SURF III (mmsi: 701024000, flag: ARG)`\n",
    "  - `CAPESANTE (mmsi: 701006605, flag: ARG)`\n",
    "- We will retrieve these vessels' `ownership`, `flag history`, and `authorizations` in **Step 3 to validate** them."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "80289282-d160-4901-9bf8-a7996785c898",
   "metadata": {},
   "source": [
    "## Step 3: Retrieve Vessel Details Using the Vessels API"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dcbde755-0e9c-48d9-babe-aaee3179b88d",
   "metadata": {},
   "source": [
    "Maria queries the **[Vessels API](https://globalfishingwatch.org/our-apis/documentation#vessels-api)** to **get detailed vessel identity and ownership records**. Please [learn more about Vessels API here](https://globalfishingwatch.org/our-apis/documentation#vessels-api) and [check its data caveats here](https://globalfishingwatch.org/our-apis/documentation#vessel-api-vessel-identity-information)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ba645e15-f111-48f3-96a4-7e091f27669e",
   "metadata": {},
   "source": [
    "**Filters Used:**\n",
    "\n",
    "1. **Vessel IDs** from [4Wings API](https://globalfishingwatch.org/our-apis/documentation#map-visualization-4wings-api), **Step 2 above**.\n",
    "2. **[Datasets](https://globalfishingwatch.org/our-apis/documentation#api-dataset)** - `public-global-vessel-identity:latest`.\n",
    "3. **[Includes](https://globalfishingwatch.org/our-apis/documentation#get-vessels-by-ids-url-parameters)** - `POTENTIAL_RELATED_SELF_REPORTED_INFO`."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "42a309da-6a56-46a0-aa86-2a148d21d855",
   "metadata": {},
   "source": [
    "**Note:** Vessels may change identifiers over time, such as their `Maritime Mobile Service Identity (MMSI)`,` International Maritime Organization (IMO) number)`, `call sign`, or even their `name`. These changes can occur due to `re-registration`, `changes in ownership`, or other `operational reasons` within the `AIS transponder`. Parameter (`includes = POTENTIAL_RELATED_SELF_REPORTED_INFO`) helps group all **vessel ids** that are **potentially related** as part of the **same physical vessel** based on publicly available registry information."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "24e8452f-7848-4c88-89db-66e4bf182cd1",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_2_vessel_mmsis = list(step_2_agg_report_df[\"mmsi\"].head(n=2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "f25ceec0-3188-4584-bb95-f76c9e0ac578",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['701024000', '701006605']"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_2_vessel_mmsis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "446b506a-a19f-49cd-9110-ed8b9103af8b",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_2_vessel_ids = list(\n",
    "    step_2_report_df[step_2_report_df[\"mmsi\"].isin(step_2_vessel_mmsis)][\n",
    "        \"vessel_id\"\n",
    "    ].unique()\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "6233b1eb-ed4b-4ba9-bce8-faa1ee027dcc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['de8a03acd-dc6c-8e08-2867-24e55ffc0017',\n",
       " '8e930bac5-594b-aa3f-081d-d12668819e1f']"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_2_vessel_ids"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "428889bd-4761-4301-b21e-fbc37eba5622",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_3_vessels_result = await gfw_client.vessels.get_vessels_by_ids(\n",
    "    ids=step_2_vessel_ids,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "c64d68dc-b952-412f-827c-df5236c98bd7",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_3_vessels_df = step_3_vessels_result.df()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "757e6c3c-d0df-4b8f-839d-1e31518d42d7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 2 entries, 0 to 1\n",
      "Data columns (total 7 columns):\n",
      " #   Column                          Non-Null Count  Dtype \n",
      "---  ------                          --------------  ----- \n",
      " 0   dataset                         2 non-null      object\n",
      " 1   registry_info_total_records     2 non-null      int64 \n",
      " 2   registry_info                   2 non-null      object\n",
      " 3   registry_owners                 2 non-null      object\n",
      " 4   registry_public_authorizations  2 non-null      object\n",
      " 5   combined_sources_info           2 non-null      object\n",
      " 6   self_reported_info              2 non-null      object\n",
      "dtypes: int64(1), object(6)\n",
      "memory usage: 244.0+ bytes\n"
     ]
    }
   ],
   "source": [
    "step_3_vessels_df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c2d30f1a-352b-42cb-8ee8-acd67f16103f",
   "metadata": {},
   "source": [
    "**Understanding Vessel Details Response Data**\n",
    "\n",
    "- **registryInfoTotalRecords** – This represents the **number of registry records** found for the vessels.\n",
    "- **registryInfo** – Contains **public registry data**. This data is sourced from official **vessel registries**.\n",
    "- **registryOwners** – Lists the **registered owners** of the vessel based on public sources.\n",
    "- **registryPublicAuthorizations** – Represents known **fishing authorizations** from public sources. Users should verify against national registries and RFMO records for additional context.\n",
    "- **combinedSourcesInfo** – Provides inferred data from multiple sources, including. This is not explicitly reported by vessels but determined through **GFW's classification methods**.\n",
    "- **selfReportedInfo** – Contains **AIS self-reported** data, including `MMSI`, `ship name`, and `flag` as broadcast by the **vessel itself**. Self-reported data may not always align with registry data and should be cross-checked."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "4767e025-e26e-4a61-8971-8f2cc90385cc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>registry_info</th>\n",
       "      <th>registry_owners</th>\n",
       "      <th>self_reported_info</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>[{'id': '2d939efefd3f45788ed103ff0723f564', 's...</td>\n",
       "      <td>[{'name': 'CLEARWATER SEAFOODS', 'flag': 'CAN'...</td>\n",
       "      <td>[{'id': 'de8a03acd-dc6c-8e08-2867-24e55ffc0017...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>[{'id': '45502524c9a150e77869ee647423dba1', 's...</td>\n",
       "      <td>[{'name': 'GLACIAR PESQUERA', 'flag': 'ARG', '...</td>\n",
       "      <td>[{'id': '8e930bac5-594b-aa3f-081d-d12668819e1f...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                       registry_info  \\\n",
       "0  [{'id': '2d939efefd3f45788ed103ff0723f564', 's...   \n",
       "1  [{'id': '45502524c9a150e77869ee647423dba1', 's...   \n",
       "\n",
       "                                     registry_owners  \\\n",
       "0  [{'name': 'CLEARWATER SEAFOODS', 'flag': 'CAN'...   \n",
       "1  [{'name': 'GLACIAR PESQUERA', 'flag': 'ARG', '...   \n",
       "\n",
       "                                  self_reported_info  \n",
       "0  [{'id': 'de8a03acd-dc6c-8e08-2867-24e55ffc0017...  \n",
       "1  [{'id': '8e930bac5-594b-aa3f-081d-d12668819e1f...  "
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_3_vessels_df[[\"registry_info\", \"registry_owners\", \"self_reported_info\"]]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "46760bde-049d-433c-817d-ae63b1c58924",
   "metadata": {},
   "source": [
    "### Explore Vessels Registry Info"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "7efdc6d6-52d8-40bb-9537-e09f242fdb25",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_3_registry_info_df = pd.json_normalize(\n",
    "    step_3_vessels_df[\"registry_info\"].explode()\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "27ab60a9-6496-4406-9ae4-57a7aa97f6fa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ssvid</th>\n",
       "      <th>flag</th>\n",
       "      <th>ship_name</th>\n",
       "      <th>n_ship_name</th>\n",
       "      <th>gear_types</th>\n",
       "      <th>source_code</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>701006605</td>\n",
       "      <td>ARG</td>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>[TRAWLERS]</td>\n",
       "      <td>[GFW-REVIEW, IMO, RESEARCH-PAPER, TMT_OTHER_OF...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>316003980</td>\n",
       "      <td>CAN</td>\n",
       "      <td>ATLANTICLEADER</td>\n",
       "      <td>ATLANTICLEADER</td>\n",
       "      <td>[TRAWLERS]</td>\n",
       "      <td>[IMO, TMT_OTHER_OFFICIAL]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>701024000</td>\n",
       "      <td>ARG</td>\n",
       "      <td>ATLANTIC SURF III</td>\n",
       "      <td>ATLANTICSURF3</td>\n",
       "      <td>[TRAWLERS]</td>\n",
       "      <td>[IMO, TMT_OTHER_OFFICIAL]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       ssvid flag          ship_name     n_ship_name  gear_types  \\\n",
       "0  701006605  ARG          CAPESANTE       CAPESANTE  [TRAWLERS]   \n",
       "1  316003980  CAN     ATLANTICLEADER  ATLANTICLEADER  [TRAWLERS]   \n",
       "2  701024000  ARG  ATLANTIC SURF III   ATLANTICSURF3  [TRAWLERS]   \n",
       "\n",
       "                                         source_code  \n",
       "0  [GFW-REVIEW, IMO, RESEARCH-PAPER, TMT_OTHER_OF...  \n",
       "1                          [IMO, TMT_OTHER_OFFICIAL]  \n",
       "2                          [IMO, TMT_OTHER_OFFICIAL]  "
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_3_registry_info_df[\n",
    "    [\"ssvid\", \"flag\", \"ship_name\", \"n_ship_name\", \"gear_types\", \"source_code\"]\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5787e4ee-69e0-4769-ba05-9a57254c7289",
   "metadata": {},
   "source": [
    "### Explore Registry Owners"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "afe07c2a-81cb-45b3-9e86-c23b4ef67fe9",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_3_registry_owners_df = pd.json_normalize(\n",
    "    step_3_vessels_df[\"registry_owners\"].explode()\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "df7e0b65-0ab0-4722-aaec-3d11c7674b8f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ssvid</th>\n",
       "      <th>flag</th>\n",
       "      <th>name</th>\n",
       "      <th>source_code</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>701006605</td>\n",
       "      <td>CAN</td>\n",
       "      <td>CLEARWATER SEAFOODS</td>\n",
       "      <td>[RESEARCH-PAPER]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>316003980</td>\n",
       "      <td>CAN</td>\n",
       "      <td>CS MANPAR</td>\n",
       "      <td>[TMT_OTHER_OFFICIAL]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>701024000</td>\n",
       "      <td>ARG</td>\n",
       "      <td>GLACIAR PESQUERA</td>\n",
       "      <td>[TMT_OTHER_OFFICIAL]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       ssvid flag                 name           source_code\n",
       "0  701006605  CAN  CLEARWATER SEAFOODS      [RESEARCH-PAPER]\n",
       "1  316003980  CAN            CS MANPAR  [TMT_OTHER_OFFICIAL]\n",
       "2  701024000  ARG     GLACIAR PESQUERA  [TMT_OTHER_OFFICIAL]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_3_registry_owners_df[[\"ssvid\", \"flag\", \"name\", \"source_code\"]]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7a22580f-7c7a-4181-9a80-e37687cc0471",
   "metadata": {},
   "source": [
    "### Explore Vessels Self Reported Info"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "c2fa4bdd-1b51-4b37-abf5-aa18a1cab3e5",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_3_self_reported_info_df = pd.json_normalize(\n",
    "    step_3_vessels_df[\"self_reported_info\"].explode()\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "d1b559c7-4587-4019-a843-181017dd3f07",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ssvid</th>\n",
       "      <th>flag</th>\n",
       "      <th>ship_name</th>\n",
       "      <th>n_ship_name</th>\n",
       "      <th>source_code</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>701006605</td>\n",
       "      <td>ARG</td>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>[AIS]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>316003980</td>\n",
       "      <td>CAN</td>\n",
       "      <td>ATLANTIC LEADER</td>\n",
       "      <td>ATLANTICLEADER</td>\n",
       "      <td>[AIS]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>701024000</td>\n",
       "      <td>ARG</td>\n",
       "      <td>ATLANTIC SURF III</td>\n",
       "      <td>ATLANTICSURF3</td>\n",
       "      <td>[AIS]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       ssvid flag          ship_name     n_ship_name source_code\n",
       "0  701006605  ARG          CAPESANTE       CAPESANTE       [AIS]\n",
       "1  316003980  CAN    ATLANTIC LEADER  ATLANTICLEADER       [AIS]\n",
       "2  701024000  ARG  ATLANTIC SURF III   ATLANTICSURF3       [AIS]"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_3_self_reported_info_df[\n",
    "    [\"ssvid\", \"flag\", \"ship_name\", \"n_ship_name\", \"source_code\"]\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6a6bcbcd-49a8-4575-9003-d8495deeb2d3",
   "metadata": {},
   "source": [
    "### What We have Learned from Step 3"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "da9c80ea-94d7-4945-8e90-9f5ec4bad8f1",
   "metadata": {},
   "source": [
    "- **Vessel Identity:**\n",
    "  - `ATLANTIC SURF III (mmsi: 701024000, flag: ARG)`- appears to be registered under Argentina (ARG)\n",
    "  - `CAPESANTE (mmsi: 701006605, flag: ARG)` - appears to be registered under Argentina (ARG)\n",
    "- **Ownership & Historical Changes:**\n",
    "  - `ATLANTIC SURF III (mmsi: 701024000, flag: ARG)` - **GLACIAR PESQUERA** appears to be listed as the registered owner.\n",
    "  - `CAPESANTE (mmsi: 701006605, flag: ARG)`- **CLEARWATER SEAFOODS** appears to be listed as the registered owner."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4803ae37-3f96-40dc-8db8-690b51710735",
   "metadata": {},
   "source": [
    "## Step 4: Detect Potential Port Visits, Encounters, or Fishing Events"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "058cc09a-64dc-4913-a90c-cadc7d38439a",
   "metadata": {},
   "source": [
    "Now Maria checks `port visits`, `encounters`, and `fishing events` using the **[Events API](https://globalfishingwatch.org/our-apis/documentation#events-api)**, which allows **monitoring of vessel activities** such as `potential transshipments`, `unauthorized port entries`, or `fishing activity patterns`."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c8ee8f1c-7e5e-487f-ba45-7f7f609ba389",
   "metadata": {},
   "source": [
    "**Filters Used:**\n",
    "\n",
    "1. **Vessel ID** from 4Wings API\n",
    "2. **[Event Types](https://globalfishingwatch.org/our-apis/documentation#events-post-body-parameters)** - Port visits, encounters (potential transshipment), and fishing events.\n",
    "3. **Time Range** - Last 6 months.\n",
    "4. **[Datasets](https://globalfishingwatch.org/our-apis/documentation#api-dataset)**:\n",
    "   - `public-global-port-visits-events::latest` (Port Visits)\n",
    "   - `public-global-encounters-events:latest` (Encounters between vessels)\n",
    "   - `public-global-fishing-events:latest` (Fishing activity)\n",
    "5. **[Encounter Types](https://globalfishingwatch.org/our-apis/documentation#events-post-body-parameters)** - CARRIER-FISHING"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "87c3b592-e431-457c-a5f4-5ce07711d52f",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_4_events_result = await gfw_client.events.get_all_events(\n",
    "    datasets=[\n",
    "        \"public-global-encounters-events:latest\",\n",
    "        \"public-global-fishing-events:latest\",\n",
    "        \"public-global-port-visits-events:latest\",\n",
    "    ],\n",
    "    vessels=step_2_vessel_ids,\n",
    "    types=[\"ENCOUNTER\", \"FISHING\", \"PORT_VISIT\"],\n",
    "    start_date=\"2024-08-01\",\n",
    "    end_date=\"2025-01-31\",\n",
    "    encounter_types=[\"CARRIER-FISHING\"],\n",
    "    sort=\"-start\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "64cb0776-7f0d-481e-be98-da00b448c720",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_4_events_df = step_4_events_result.df()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "4c82d647-3870-4a54-979b-7f586575e5c1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 359 entries, 0 to 358\n",
      "Data columns (total 14 columns):\n",
      " #   Column        Non-Null Count  Dtype              \n",
      "---  ------        --------------  -----              \n",
      " 0   start         359 non-null    datetime64[ns, UTC]\n",
      " 1   end           359 non-null    datetime64[ns, UTC]\n",
      " 2   id            359 non-null    object             \n",
      " 3   type          359 non-null    object             \n",
      " 4   position      359 non-null    object             \n",
      " 5   regions       359 non-null    object             \n",
      " 6   bounding_box  359 non-null    object             \n",
      " 7   distances     359 non-null    object             \n",
      " 8   vessel        359 non-null    object             \n",
      " 9   encounter     0 non-null      object             \n",
      " 10  fishing       351 non-null    object             \n",
      " 11  gap           0 non-null      object             \n",
      " 12  loitering     0 non-null      object             \n",
      " 13  port_visit    8 non-null      object             \n",
      "dtypes: datetime64[ns, UTC](2), object(12)\n",
      "memory usage: 39.4+ KB\n"
     ]
    }
   ],
   "source": [
    "step_4_events_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "17d89920-cda2-497d-9797-1e05a84a0daa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "type\n",
       "fishing       351\n",
       "port_visit      8\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_4_events_df[\"type\"].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1b472de1-8fef-41a1-a76c-057406d86ee1",
   "metadata": {},
   "source": [
    "### Explore Apparent Fishing Events"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "4d360bc4-9762-4ae6-b5b1-1b937e2d2ed0",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_4_fishing_events_df = step_4_events_df[step_4_events_df[\"fishing\"].notna()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "18ff38d6-9442-4742-9dc9-accfb1299e43",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_4_fishing_df = pd.concat(\n",
    "    [\n",
    "        pd.json_normalize(step_4_fishing_events_df[\"vessel\"], sep=\"_\"),\n",
    "        pd.json_normalize(step_4_fishing_events_df[\"fishing\"], sep=\"_\"),\n",
    "    ],\n",
    "    axis=1,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "fc6ebae0-eba2-4a8a-892c-6dfc38822bd7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 351 entries, 0 to 350\n",
      "Data columns (total 12 columns):\n",
      " #   Column                              Non-Null Count  Dtype  \n",
      "---  ------                              --------------  -----  \n",
      " 0   id                                  351 non-null    object \n",
      " 1   name                                351 non-null    object \n",
      " 2   ssvid                               351 non-null    object \n",
      " 3   flag                                351 non-null    object \n",
      " 4   type                                351 non-null    object \n",
      " 5   public_authorizations               351 non-null    object \n",
      " 6   nextPort                            0 non-null      object \n",
      " 7   total_distance_km                   351 non-null    float64\n",
      " 8   average_speed_knots                 351 non-null    float64\n",
      " 9   average_duration_hours              0 non-null      object \n",
      " 10  potential_risk                      351 non-null    bool   \n",
      " 11  vessel_public_authorization_status  351 non-null    object \n",
      "dtypes: bool(1), float64(2), object(9)\n",
      "memory usage: 30.6+ KB\n"
     ]
    }
   ],
   "source": [
    "step_4_fishing_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "8799e988-56a2-41d5-b472-bc83064e1807",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>ssvid</th>\n",
       "      <th>total_distance_km</th>\n",
       "      <th>average_speed_knots</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ATLANTIC SURF III</td>\n",
       "      <td>701024000</td>\n",
       "      <td>222.721610</td>\n",
       "      <td>4.098386</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ATLANTIC SURF III</td>\n",
       "      <td>701024000</td>\n",
       "      <td>7.905335</td>\n",
       "      <td>4.590909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ATLANTIC SURF III</td>\n",
       "      <td>701024000</td>\n",
       "      <td>2.794681</td>\n",
       "      <td>4.655555</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ATLANTIC SURF III</td>\n",
       "      <td>701024000</td>\n",
       "      <td>2.012392</td>\n",
       "      <td>2.953846</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ATLANTIC SURF III</td>\n",
       "      <td>701024000</td>\n",
       "      <td>3.260040</td>\n",
       "      <td>3.705556</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>346</th>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>701006605</td>\n",
       "      <td>25.568796</td>\n",
       "      <td>4.074561</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>347</th>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>701006605</td>\n",
       "      <td>45.830980</td>\n",
       "      <td>3.771852</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>348</th>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>701006605</td>\n",
       "      <td>74.611830</td>\n",
       "      <td>4.087912</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>349</th>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>701006605</td>\n",
       "      <td>82.607525</td>\n",
       "      <td>3.788187</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>350</th>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>701006605</td>\n",
       "      <td>205.826282</td>\n",
       "      <td>4.136848</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>351 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                  name      ssvid  total_distance_km  average_speed_knots\n",
       "0    ATLANTIC SURF III  701024000         222.721610             4.098386\n",
       "1    ATLANTIC SURF III  701024000           7.905335             4.590909\n",
       "2    ATLANTIC SURF III  701024000           2.794681             4.655555\n",
       "3    ATLANTIC SURF III  701024000           2.012392             2.953846\n",
       "4    ATLANTIC SURF III  701024000           3.260040             3.705556\n",
       "..                 ...        ...                ...                  ...\n",
       "346          CAPESANTE  701006605          25.568796             4.074561\n",
       "347          CAPESANTE  701006605          45.830980             3.771852\n",
       "348          CAPESANTE  701006605          74.611830             4.087912\n",
       "349          CAPESANTE  701006605          82.607525             3.788187\n",
       "350          CAPESANTE  701006605         205.826282             4.136848\n",
       "\n",
       "[351 rows x 4 columns]"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_4_fishing_df[\n",
    "    [\n",
    "        \"name\",\n",
    "        \"ssvid\",\n",
    "        \"total_distance_km\",\n",
    "        \"average_speed_knots\",\n",
    "    ]\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "3659c048-c8bf-463c-a6cb-fc29f818ed77",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ssvid\n",
       "701024000    245\n",
       "701006605    106\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_4_fishing_df[\"ssvid\"].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5da05a04-947e-4f87-b61e-bad015796e5f",
   "metadata": {},
   "source": [
    "### Explore Port Visit Events"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "e806616b-6ed7-4c0c-9bf4-2b4a23de2046",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_4_port_visit_events_df = step_4_events_df[step_4_events_df[\"port_visit\"].notna()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "58a68605-9432-43fe-b8eb-4d0393f95f60",
   "metadata": {},
   "outputs": [],
   "source": [
    "step_4_port_visits_df = pd.concat(\n",
    "    [\n",
    "        pd.json_normalize(step_4_port_visit_events_df[\"vessel\"], sep=\"_\"),\n",
    "        pd.json_normalize(step_4_port_visit_events_df[\"port_visit\"], sep=\"_\"),\n",
    "    ],\n",
    "    axis=1,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "685a746e-8091-4321-b851-79a5f3ca0f81",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 8 entries, 0 to 7\n",
      "Data columns (total 37 columns):\n",
      " #   Column                                         Non-Null Count  Dtype  \n",
      "---  ------                                         --------------  -----  \n",
      " 0   id                                             8 non-null      object \n",
      " 1   name                                           8 non-null      object \n",
      " 2   ssvid                                          8 non-null      object \n",
      " 3   flag                                           8 non-null      object \n",
      " 4   type                                           8 non-null      object \n",
      " 5   public_authorizations                          8 non-null      object \n",
      " 6   nextPort                                       0 non-null      object \n",
      " 7   visit_id                                       8 non-null      object \n",
      " 8   confidence                                     8 non-null      object \n",
      " 9   duration_hrs                                   8 non-null      float64\n",
      " 10  start_anchorage_anchorage_id                   8 non-null      object \n",
      " 11  start_anchorage_at_dock                        8 non-null      bool   \n",
      " 12  start_anchorage_distance_from_shore_km         8 non-null      float64\n",
      " 13  start_anchorage_flag                           8 non-null      object \n",
      " 14  start_anchorage_id                             8 non-null      object \n",
      " 15  start_anchorage_lat                            8 non-null      float64\n",
      " 16  start_anchorage_lon                            8 non-null      float64\n",
      " 17  start_anchorage_name                           8 non-null      object \n",
      " 18  start_anchorage_top_destination                8 non-null      object \n",
      " 19  intermediate_anchorage_anchorage_id            8 non-null      object \n",
      " 20  intermediate_anchorage_at_dock                 8 non-null      bool   \n",
      " 21  intermediate_anchorage_distance_from_shore_km  8 non-null      float64\n",
      " 22  intermediate_anchorage_flag                    8 non-null      object \n",
      " 23  intermediate_anchorage_id                      8 non-null      object \n",
      " 24  intermediate_anchorage_lat                     8 non-null      float64\n",
      " 25  intermediate_anchorage_lon                     8 non-null      float64\n",
      " 26  intermediate_anchorage_name                    8 non-null      object \n",
      " 27  intermediate_anchorage_top_destination         8 non-null      object \n",
      " 28  end_anchorage_anchorage_id                     8 non-null      object \n",
      " 29  end_anchorage_at_dock                          8 non-null      bool   \n",
      " 30  end_anchorage_distance_from_shore_km           8 non-null      float64\n",
      " 31  end_anchorage_flag                             8 non-null      object \n",
      " 32  end_anchorage_id                               8 non-null      object \n",
      " 33  end_anchorage_lat                              8 non-null      float64\n",
      " 34  end_anchorage_lon                              8 non-null      float64\n",
      " 35  end_anchorage_name                             8 non-null      object \n",
      " 36  end_anchorage_top_destination                  8 non-null      object \n",
      "dtypes: bool(3), float64(10), object(24)\n",
      "memory usage: 2.3+ KB\n"
     ]
    }
   ],
   "source": [
    "step_4_port_visits_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "0e77b956-f0f8-4fbd-8a49-0116e4401c12",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>ssvid</th>\n",
       "      <th>confidence</th>\n",
       "      <th>start_anchorage_name</th>\n",
       "      <th>intermediate_anchorage_name</th>\n",
       "      <th>end_anchorage_name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ATLANTIC SURF III</td>\n",
       "      <td>701024000</td>\n",
       "      <td>4</td>\n",
       "      <td>MAR DEL PLATA</td>\n",
       "      <td>MAR DEL PLATA</td>\n",
       "      <td>MAR DEL PLATA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>701006605</td>\n",
       "      <td>4</td>\n",
       "      <td>USHUAIA</td>\n",
       "      <td>USHUAIA</td>\n",
       "      <td>USHUAIA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ATLANTIC SURF III</td>\n",
       "      <td>701024000</td>\n",
       "      <td>4</td>\n",
       "      <td>MAR DEL PLATA</td>\n",
       "      <td>MAR DEL PLATA</td>\n",
       "      <td>MAR DEL PLATA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>701006605</td>\n",
       "      <td>4</td>\n",
       "      <td>USHUAIA</td>\n",
       "      <td>USHUAIA</td>\n",
       "      <td>USHUAIA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ATLANTIC SURF III</td>\n",
       "      <td>701024000</td>\n",
       "      <td>4</td>\n",
       "      <td>MAR DEL PLATA</td>\n",
       "      <td>MAR DEL PLATA</td>\n",
       "      <td>MAR DEL PLATA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>701006605</td>\n",
       "      <td>4</td>\n",
       "      <td>USHUAIA</td>\n",
       "      <td>USHUAIA</td>\n",
       "      <td>USHUAIA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>ATLANTIC SURF III</td>\n",
       "      <td>701024000</td>\n",
       "      <td>4</td>\n",
       "      <td>MAR DEL PLATA</td>\n",
       "      <td>MAR DEL PLATA</td>\n",
       "      <td>MAR DEL PLATA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>CAPESANTE</td>\n",
       "      <td>701006605</td>\n",
       "      <td>4</td>\n",
       "      <td>USHUAIA</td>\n",
       "      <td>USHUAIA</td>\n",
       "      <td>USHUAIA</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                name      ssvid confidence start_anchorage_name  \\\n",
       "0  ATLANTIC SURF III  701024000          4        MAR DEL PLATA   \n",
       "1          CAPESANTE  701006605          4              USHUAIA   \n",
       "2  ATLANTIC SURF III  701024000          4        MAR DEL PLATA   \n",
       "3          CAPESANTE  701006605          4              USHUAIA   \n",
       "4  ATLANTIC SURF III  701024000          4        MAR DEL PLATA   \n",
       "5          CAPESANTE  701006605          4              USHUAIA   \n",
       "6  ATLANTIC SURF III  701024000          4        MAR DEL PLATA   \n",
       "7          CAPESANTE  701006605          4              USHUAIA   \n",
       "\n",
       "  intermediate_anchorage_name end_anchorage_name  \n",
       "0               MAR DEL PLATA      MAR DEL PLATA  \n",
       "1                     USHUAIA            USHUAIA  \n",
       "2               MAR DEL PLATA      MAR DEL PLATA  \n",
       "3                     USHUAIA            USHUAIA  \n",
       "4               MAR DEL PLATA      MAR DEL PLATA  \n",
       "5                     USHUAIA            USHUAIA  \n",
       "6               MAR DEL PLATA      MAR DEL PLATA  \n",
       "7                     USHUAIA            USHUAIA  "
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_4_port_visits_df[\n",
    "    [\n",
    "        \"name\",\n",
    "        \"ssvid\",\n",
    "        \"confidence\",\n",
    "        \"start_anchorage_name\",\n",
    "        \"intermediate_anchorage_name\",\n",
    "        \"end_anchorage_name\",\n",
    "    ]\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "32ee1871-f1c7-4561-9384-5a681293e7e5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ssvid\n",
       "701024000    4\n",
       "701006605    4\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "step_4_port_visits_df[\"ssvid\"].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "61d59d0c-8919-40c4-ac30-bb9ab35a4d53",
   "metadata": {},
   "source": [
    "### What We have learned from  step 4"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4771fe04-5984-4576-b774-a83f104d7194",
   "metadata": {},
   "source": [
    "- **Apparent Fishing Events:**\n",
    "  - `ATLANTIC SURF III (mmsi: 701024000, flag: ARG)`- has been detected in multiple apparent fishing events during the analyzed timeframe (August 2024 – January 2025)\n",
    "  - `CAPESANTE (mmsi: 701006605, flag: ARG)` - has been detected in multiple apparent fishing events during the analyzed timeframe (August 2024 – January 2025)\n",
    "- **Port Visit Events:**\n",
    "  - `ATLANTIC SURF III (mmsi: 701024000, flag: ARG)`- potentially made multiple port visits, including stops at `MAR DEL PLATA`\n",
    "  - `CAPESANTE (mmsi: 701006605, flag: ARG)` - potentially made multiple port visits, including stops at `USHUAIA`\n",
    "- **ENCOUNTER Events:** No explicit **ENCOUNTER** events were returned in the response dataset. Check more details [here](https://globalfishingwatch.org/faqs/what-is-a-vessel-encounter/). You can read more about transshipment behavior from our [report](https://globalfishingwatch.org/wp-content/uploads/GlobalViewOfTransshipment_Aug2017.pdf) or [scientific publication](https://www.frontiersin.org/articles/10.3389/fmars.2018.00240/full)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f0cf3958-fb92-49c0-ba2f-2cfe971bcbc5",
   "metadata": {},
   "source": [
    "**Potential Considerations:**\n",
    "\n",
    "- The vessel's fishing activities appear near the EEZ boundary, requiring further assessment of compliance with national or RFMO regulations.\n",
    "- The absence of matching public authorizations in the RFMO registry does not necessarily indicate illegality, but it suggests that authorities may need to verify through national databases or official sources."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8b951044-6905-4e38-9885-13a98cf3a7cf",
   "metadata": {},
   "source": [
    "### Summary of API Flow"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c8f86731-be44-4b89-8abb-cf2f6693b4c9",
   "metadata": {},
   "source": [
    "1. **[4Wings API](https://globalfishingwatch.org/our-apis/documentation#map-visualization-4wings-api)** - Retrieve apparent fishing effort for **trawlers** within Argentinian EEZ.\n",
    "2. **[Vessels API](https://globalfishingwatch.org/our-apis/documentation#vessels-api)** - Fetch **vessel identity**, **ownership history**, and **public authorizations**.\n",
    "3. **[Events API](https://globalfishingwatch.org/our-apis/documentation#events-api)** - Detect potential **port visits**, **encounters**, and **apparent fishing** events to analyze operational patterns.\n",
    "4. **Assess potential risks** - Compare registry records, AIS data, and inferred vessel activity for enforcement follow-ups.\n",
    "5. **Generate a report** - Provide a structured analysis for relevant authorities."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}