APIで予測を作成¶

curl -i -X POST "https://example.datarobot.com/predApi/v1.0/deployments/<deploymentId>/predictions" \
    -H "Authorization: Bearer <API key>" -F \
    file=@~/.home/path/to/dataset.csv 

HTTP/1.1 200 OK
Content-Type: application/json
X-DataRobot-Execution-Time: 38
X-DataRobot-Model-Cache-Hit: true

{"data":[...]} 

import json
import requests

data = [
    json.dumps({'Feature1': 42, 'Feature2': 'text value 1'}),
    json.dumps({'Feature1': 60, 'Feature2': 'text value 2'}),
]

api_key = '...'
api_endpoint = '...'

session = requests.Session()
session.headers = {
    'Authorization': 'Bearer {}'.format(api_key),
    'Content-Type': 'text/json',
}

for row in data:
    print(session.post(api_endpoint, data=row).json()) 

a,b,c
1,2,3
7,8,9 

[
  {
    "a": 1,
    "b": 2,
    "c": 3
  },
  {
    "a": 7,
    "b": 8,
    "c": 9
  }
] 

curl -H "Content-Type: application/json" -X POST --data '[{"a": 4, "b": 5, "c": 6}\]' \
    -H "Authorization: Bearer <API key>" \
    https://example.datarobot.com/predApi/v1.0/deployments/<deploymentId>/predictions 

curl -i -X POST "https://example.datarobot.com/predApi/v1.0/deployments/<deploymentId>/predictions" \
    -H "Authorization: Bearer <API key>" -F \
    file=@~/.home/path/to/dataset.csv

HTTP/1.1 200 OK
Date: Fri, 08 Feb 2019 10:00:00 GMT
Content-Type: application/json
Content-Length: 60624
Connection: keep-alive
Server: nginx/1.12.2
X-DataRobot-Execution-Time: 39
X-DataRobot-Model-Cache-Hit: true
Access-Control-Allow-Methods: OPTIONS, POST
Access-Control-Allow-Credentials: true
Access-Control-Expose-Headers: Content-Type,Content-Length,X-DataRobot-Execution-Time,X-DataRobot-Model-Cache-Hit,X-DataRobot-Model-Id,X-DataRobot-Request-Id
Access-Control-Allow-Headers: Content-Type,Authorization,datarobot-key
X-DataRobot-Request-ID: 9e61f97bf07903b8c526f4eb47830a86

{
  "data": [
    {
      "predictionValues": [
        {
          "value": 0.2570950924,
          "label": 1
        },
        {
          "value": 0.7429049076,
          "label": 0
        }
      ],
      "predictionThreshold": 0.5,
      "prediction": 0,
      "rowId": 0
    },
    {
      "predictionValues": [
        {
          "value": 0.7631880558,
          "label": 1
        },
        {
          "value": 0.2368119442,
          "label": 0
        }
      ],
      "predictionThreshold": 0.5,
      "prediction": 1,
      "rowId": 1
    }
  ]
} 

curl  -i -X POST "https://example.datarobot.com/predApi/v1.0/deployments/<deploymentId>/predictions"  --data-binary $'a,b,c\n1,2,3\n7,8,9\n'
    -H "content-type: text/plain" \
    -H "Authorization: Bearer <API key>" \ 

curl -i -X POST "https://example.datarobot.com/predApi/v1.0/deployments/<deploymentId>/predictions?passthroughColumns=Latitude&passthroughColumns=Longitude" \
    -H "Authorization: Bearer <API key>" \
    -H "datarobot-key: <DataRobot key>" -F \
    file=@~/.home/path/to/dataset.csv 

{
  "data": [
    {
      "predictionValues": [
        {
          "value": 0.6856798909,
          "label": 1
        },
        {
          "value": 0.3143201091,
          "label": 0
        }
      ],
      "predictionThreshold": 0.5,
      "prediction": 1,
      "rowId": 0,
      "passthroughValues": {
        "Latitude": -25.433508,
        "Longitude": 22.759397
      }
    },
    {
      "predictionValues": [
        {
          "value": 0.765656753,
          "label": 1
        },
        {
          "value": 0.234343247,
          "label": 0
        }
      ],
      "predictionThreshold": 0.5,
      "prediction": 1,
      "rowId": 1,
      "passthroughValues": {
        "Latitude": 41.051128,
        "Longitude": 14.49598
      }
    }
  ]
} 

{
    "data": [
        {
            "rowId": 0,
            "prediction": "In the field of biology, there have been some exciting new discoveries made through research conducted on the International Space Station (ISS). Here are three examples:\n\n1. Understanding Plant Root Orientation: Scientists have been studying the growth and development of plants in microgravity. They found that plants grown in space exhibit different root orientation compared to those grown on Earth. This discovery helps us understand how plants adapt and respond to the absence of gravity. This knowledge can be applied to improve agricultural practices and develop innovative techniques for growing plants in challenging environments on Earth.\n\n2. Tissue Damage and Repair: One fascinating area of research on the ISS involves studying how living organisms respond to injuries in space. Scientists have investigated tissue damage and repair mechanisms in various organisms, including humans. By studying the healing processes in microgravity, researchers gained insights into how wounds heal differently in space compared to on Earth. This knowledge has implications for developing new therapies and treatments for wound healing and tissue regeneration.\n\n3. Bubbles, Lightning, and Fire Dynamics: The ISS provides a unique laboratory environment for studying the behavior of bubbles, lightning, and fire in microgravity. Scientists have conducted experiments to understand how these phenomena behave differently without the influence of gravity. These studies have practical applications, such as improving combustion processes, enhancing fire safety measures, and developing more efficient cooling systems.\n\nThese are just a few examples of the exciting discoveries that have been made in the field of biology through research conducted on the ISS. The microgravity environment of space offers a unique perspective and enables researchers to uncover new insights into the workings of living organisms and their interactions with the environment.",
            "predictionValues": [
                {
                    "label": "resultText",
                    "value": "In the field of biology, there have been some exciting new discoveries made through research conducted on the International Space Station (ISS). Here are three examples:\n\n1. Understanding Plant Root Orientation: Scientists have been studying the growth and development of plants in microgravity. They found that plants grown in space exhibit different root orientation compared to those grown on Earth. This discovery helps us understand how plants adapt and respond to the absence of gravity. This knowledge can be applied to improve agricultural practices and develop innovative techniques for growing plants in challenging environments on Earth.\n\n2. Tissue Damage and Repair: One fascinating area of research on the ISS involves studying how living organisms respond to injuries in space. Scientists have investigated tissue damage and repair mechanisms in various organisms, including humans. By studying the healing processes in microgravity, researchers gained insights into how wounds heal differently in space compared to on Earth. This knowledge has implications for developing new therapies and treatments for wound healing and tissue regeneration.\n\n3. Bubbles, Lightning, and Fire Dynamics: The ISS provides a unique laboratory environment for studying the behavior of bubbles, lightning, and fire in microgravity. Scientists have conducted experiments to understand how these phenomena behave differently without the influence of gravity. These studies have practical applications, such as improving combustion processes, enhancing fire safety measures, and developing more efficient cooling systems.\n\nThese are just a few examples of the exciting discoveries that have been made in the field of biology through research conducted on the ISS. The microgravity environment of space offers a unique perspective and enables researchers to uncover new insights into the workings of living organisms and their interactions with the environment."
                }
            ],
            "deploymentApprovalStatus": "APPROVED",
            "extraModelOutput": {
                "CITATION_CONTENT_8": "3\nthe research study is received by others and how the \nknowledge is disseminated through citations in other \njournals. For example, six ISS studies have been \npublished in Nature, represented as a small node in the \ngraph. Network analysis shows that findings published \nin Nature are likely to be cited by other similar leading \njournals such as Science and Astrophysical Journal \nLetters (represented in bright yellow links) as well as \nspecialized journals such as Physical Review D and New \nJournal of Physics (represented in a yellow-green link). \nSix publications in Nature led to 512 citations according \nto VOSviewer\u2019s network map (version 1.6.11), an \nincrease of over 8,000% from publication to citation. \nFor comparison purposes, 6 publications in a small \njournal like American Journal of Botany led to 185 \ncitations and 107 publications in Acta Astronautica, \na popular journal among ISS scientists, led to 1,050 \ncitations (Figure 3, panel B). This count of 1,050",
                "CITATION_CONTENT_9": "Introduction\n4\nFigure 3. Count of publications reported in journals ranked in the top 100 according to global standards of Clarivate. A total of 567 top-tier publications \nthrough the end of FY-23 are shown by year and research category.\nIn this year\u2019s edition of the Annual Highlights of Results, we report findings from a \nwide range of topics in biology and biotechnology, physics, human research, Earth and \nspace science, and technology development \u2013 including investigations about plant root \norientation, tissue damage and repair, bubbles, lightning, fire dynamics, neutron stars, \ncosmic ray nuclei, imaging technology improvements, brain and vascular health, solar \npanel materials, grain flow, as well as satellite and robot control. \nThe findings highlighted here are only a small sample representative of the research \nconducted by the participating space agencies \u2013 ASI (Agenzia Spaziale Italiana), CSA \n(Canadian Space Agency), ESA (European Space Agency), JAXA (Japanese Aerospace",
                "CITATION_PAGE_3": 4,
                "CITATION_PAGE_8": 6,
                "CITATION_CONTENT_5": "23\nPUBLICATION HIGHLIGHTS: \nEARTH AND SPACE SCIENCE\nThe ISS laboratories enable scientific experiments in the biological sciences \nthat explore the complex responses of living organisms to the microgravity \nenvironment. The lab facilities support the exploration of biological systems \nranging from microorganisms and cellular biology to integrated functions \nof multicellular plants and animals. Several recent biological sciences \nexperiments have facilitated new technology developments that allow \ngrowth and maintenance of living cells, tissues, and organisms.\nThe Alpha Magnetic \nSpectrometer-02 (AMS-02) is \na state-of-the-art particle \nphysics detector constructed, \ntested, and operated by an \ninternational team composed \nof 60 institutes from \n16 countries and organized \nunder the United States \nDepartment of Energy (DOE) sponsorship. \nThe AMS-02 uses the unique environment of \nspace to advance knowledge of the universe \nand lead to the understanding of the universe\u2019s",
                "CITATION_SOURCE_5": "Space_Station_Annual_Highlights/iss_2017_highlights.pdf",
                "CITATION_CONTENT_3": "Introduction\n2\nExtensive international collaboration in the \nunique environment of LEO as well as procedural \nimprovements to assist researchers in the collection \nof data from the ISS have produced promising \nresults in the areas of protein crystal growth, tissue \nregeneration, vaccine and drug development, 3D \nprinting, and fiber optics, among many others. In \nthis year\u2019s edition of the Annual Highlights of Results, \nwe report findings from a wide range of topics in \nbiotechnology, physics, human research, Earth \nand space science, and technology development \n\u2013 including investigations about human retinal cells, \nbacterial resistance, black hole detection, space \nanemia, brain health, Bose-Einstein condensates, \nparticle self-assembly, RNA extraction technology, \nand more. The findings highlighted here represent \nonly a sample of the work ISS has contributed to \nsociety during the past 12 months.\nAs of Oct. 1, 2022, we have identified a total of 3,679",
                "CITATION_SOURCE_8": "Space_Station_Annual_Highlights/iss_2021_highlights.pdf",
                "CITATION_PAGE_7": 8,
                "CITATION_PAGE_6": 8,
                "CITATION_PAGE_2": 4,
                "CITATION_CONTENT_7": "Biology and Biotechnology Earth and Space Science Educational and Cultural Activities\nHuman Research Physical Science Technology Development and Demonstration",
                "CITATION_SOURCE_9": "Space_Station_Annual_Highlights/iss_2023_highlights.pdf",
                "datarobot_latency": 3.1466632366,
                "blocked_resultText": false,
                "CITATION_SOURCE_2": "Space_Station_Annual_Highlights/iss_2023_highlights.pdf",
                "CITATION_SOURCE_6": "Space_Station_Annual_Highlights/iss_2021_highlights.pdf",
                "CITATION_SOURCE_7": "Space_Station_Annual_Highlights/iss_2023_highlights.pdf",
                "datarobot_confidence_score": 0.6524822695,
                "CITATION_PAGE_9": 7,
                "CITATION_CONTENT_4": "Molecular Life Sciences. 2021 October 29; DOI: \n10.1007/s00018-021-03989-2.\nFigure 7. Immunoflourescent images of human retinal \ncells in different conditions. Image adopted from \nCialdai, Cellular and Molecular Life Sciences.\nThe ISS laboratory provides a platform for investigations in the biological sciences that \nexplores the complex responses of living organisms to the microgravity environment. Lab \nfacilities support the exploration of biological systems, from microorganisms and cellular \nbiology to the integrated functions of multicellular plants and animals.",
                "CITATION_SOURCE_1": "Space_Station_Annual_Highlights/iss_2023_highlights.pdf",
                "CITATION_SOURCE_0": "Space_Station_Annual_Highlights/iss_2018_highlights.pdf",
                "CITATION_SOURCE_3": "Space_Station_Annual_Highlights/iss_2022_highlights.pdf",
                "CITATION_PAGE_5": 26,
                "CITATION_PAGE_0": 7,
                "CITATION_PAGE_1": 11,
                "LLM_BLUEPRINT_ID": "662ba0062ade64c4fc4c1a1f",
                "CITATION_PAGE_4": 9,
                "datarobot_token_count": 320,
                "CITATION_CONTENT_0": "more effectively in space by addressing \nsuch topics as understanding radiation effects on \ncrew health, combating bone and muscle loss, \nimproving designs of systems that handle fluids \nin microgravity, and determining how to maintain \nenvironmental control efficiently. \nResults from the ISS provide new \ncontributions to the body of scientific \nknowledge in the physical sciences, life \nsciences, and Earth and space sciences \nto advance scientific discoveries in multi\u0002disciplinary ways. \nISS science results have Earth-based \napplications, including understanding our \nclimate, contributing to the treatment of \ndisease, improving existing materials, and inspiring \nthe future generation of scientists, clinicians, \ntechnologists, engineers, mathematicians, artists, \nand explorers.\nBENEFITS\nFOR HUMANITY\nDISCOVERY\nFigure 4. A heat map of all of the countries whose authors have cited scientific results publications from ISS Research through October 1, 2018.\nEXPLORATION",
                "CITATION_SOURCE_4": "Space_Station_Annual_Highlights/iss_2022_highlights.pdf",
                "CITATION_CONTENT_2": "capabilities (i.e., facilities), and data delivery are critical to the effective operation \nof scientific projects for accurate results to be shared with the scientific community, \nsponsors, legislators, and the public. \nOver 3,700 investigations have operated since Expedition 1, with more than 250 active \nresearch facilities, the participation of more than 100 countries, the work of more than \n5,000 researchers, and over 4,000 publications. The growth in research (Figure 1) and \ninternational collaboration (Figure 2) has prompted the publication of over 560 research \narticles in top-tier scientific journals with about 75 percent of those groundbreaking studies \noccurring since 2018 (Figure 3). \nBibliometric analyses conducted through VOSviewer1\n measure the impact of space station \nresearch by quantifying and visualizing networks of journals, citations, subject areas, and \ncollaboration between authors, countries, or organizations. Using bibliometrics, a broad",
                "CITATION_CONTENT_1": "technologists, engineers, mathematicians, artists, and explorers.\nEXPLORATION\nDISCOVERY\nBENEFITS\nFOR HUMANITY",
                "CITATION_CONTENT_6": "control efficiently. \nResults from the ISS provide new \ncontributions to the body of scientific \nknowledge in the physical sciences, life \nsciences, and Earth and space sciences \nto advance scientific discoveries in multi\u0002disciplinary ways. \nISS science results have Earth-based \napplications, including understanding our \nclimate, contributing to the treatment of \ndisease, improving existing materials, and \ninspiring the future generation of scientists, \nclinicians, technologists, engineers, \nmathematicians, artists and explorers.\nBENEFITS\nFOR HUMANITY\nDISCOVERY\nEXPLORATION"
            }
        },
    ]
} 

curl -i -X POST "https://example.datarobot.com/predApi/v1.0/deployments/<deploymentId>/predictions" \
    -H "Authorization: Bearer <API key>" -F \
    file=@~/.home/path/to/dataset.csv  

HTTP/1.1 200 OK
Content-Type: application/json
X-DataRobot-Execution-Time: 1405
X-DataRobot-Model-Cache-Hit: false

{
  "data": [
    {
      "seriesId": 1,
      "forecastPoint": "2018-01-09T00:00:00Z",
      "rowId": 365,
      "timestamp": "2018-01-10T00:00:00.000000Z",
      "predictionValues": [
        {
          "value": 45180.4041874386,
          "label": "target (actual)"
        }
      ],
      "forecastDistance": 1,
      "prediction": 45180.4041874386
    },
    {
      "seriesId": 1,
      "forecastPoint": "2018-01-09T00:00:00Z",
      "rowId": 366,
      "timestamp": "2018-01-11T00:00:00.000000Z",
      "predictionValues": [
        {
          "value": 47742.9432499386,
          "label": "target (actual)"
        }
      ],
      "forecastDistance": 2,
      "prediction": 47742.9432499386
    },
    {
      "seriesId": 1,
      "forecastPoint": "2018-01-09T00:00:00Z",
      "rowId": 367,
      "timestamp": "2018-01-12T00:00:00.000000Z",
      "predictionValues": [
        {
          "value": 46394.5698978878,
          "label": "target (actual)"
        }
      ],
      "forecastDistance": 3,
      "prediction": 46394.5698978878
    },
    {
      "seriesId": 2,
      "forecastPoint": "2018-01-09T00:00:00Z",
      "rowId": 697,
      "timestamp": "2018-01-10T00:00:00.000000Z",
      "predictionValues": [
        {
          "value": 39794.833199375,
          "label": "target (actual)"
        }
      ]
    }
  ]
} 

curl -i -X POST "https://example.datarobot.com/predApi/v1.0/deployments/<deploymentId>/predictions?forecastPoint=1961-01-01T00:00:00?relaxKnownInAdvanceFeaturesCheck=true" \
    -H "Authorization: Bearer <API key>" -F \
    file=@~/.home/path/to/dataset.csv 

curl -i -X POST "https://example.datarobot.com/predApi/v1.0/deployments/<deploymentId>/predictionExplanations" \
    -H "Authorization: Bearer <API key>" -F \
    file=@~/.home/path/to/dataset.csv 

HTTP/1.1 200 OK
Content-Type: application/json
X-DataRobot-Execution-Time: 841
X-DataRobot-Model-Cache-Hit: true

{
  "data": [
    {
      "predictionValues": [
        {
          "value": 0.6634830442,
          "label": 1
        },
        {
          "value": 0.3365169558,
          "label": 0
        }
      ],
      "prediction": 1,
      "rowId": 0,
      "predictionExplanations": [
        {
          "featureValue": 49,
          "strength": 0.6194461777,
          "feature": "driver_age",
          "qualitativeStrength": "+++",
          "label": 1
        },
        {
          "featureValue": 1,
          "strength": 0.3501610895,
          "feature": "territory",
          "qualitativeStrength": "++",
          "label": 1
        },
        {
          "featureValue": "M",
          "strength": -0.171075409,
          "feature": "gender",
          "qualitativeStrength": "--",
          "label": 1
        }
      ]
    },
    {
      "predictionValues": [
        {
          "value": 0.3565584672,
          "label": 1
        },
        {
          "value": 0.6434415328,
          "label": 0
        }
      ],
      "prediction": 0,
      "rowId": 1,
      "predictionExplanations": []
    }
  ]
} 

curl -i -X POST "https://example.datarobot.com/predApi/v1.0/deployments/<deploymentId>/predictionExplanations?maxExplanations=2&thresholdLow=0.2&thresholdHigh=0.5"
    -H "Authorization: Bearer <API key>" -F \
    file=@~/.home/path/to/dataset.csv 

{
  "data": [
    {
      "predictionValues": [
        {
          "value": 122.8034057617,
          "label": "length"
        }
      ],
      "prediction": 122.8034057617,
      "rowId": 99,
      "humility": [
        {
          "ruleId": "5ebad4735f11b33a38ff3e0d",
          "triggered": true,
          "ruleName": "Uncertain Prediction Trigger"
        }
      ]
    }
  ]
} 

480 Error: {"message":"Humility ReturnError action triggered."} 

{
  "data": [
    {
      "predictionValues": [
        {
          "value": 122.8034057617,
          "label": "length"
        }
      ],
      "prediction": 5220,
      "rowId": 99,
      "humility": [
        {
          "ruleId": "5ebad4735f11b33a38ff3e0d",
          "triggered": true,
          "ruleName": "Uncertain Prediction Trigger"
        }
      ]
    }
  ]
} 

curl -H "Content-Type: application/json" -X POST --data '' \
    -H "Authorization: Bearer <API key>" \
    https://example.datarobot.com/predApi/v1.0/deployments/<deploymentId>

HTTP/1.1 400 BAD REQUEST
Date: Fri, 08 Feb 2019 11:00:00 GMT
Content-Type: application/json
Content-Length: 53
Connection: keep-alive
Server: nginx/1.12.2
X-DataRobot-Execution-Time: 332
X-DataRobot-Request-ID: fad6a0b62c1ff30db74c6359648d12fd

{
  "message": "The requested URL was not found on the server.  If you entered the URL manually, please check your spelling and try again."
} 

import requests
import urllib3

# create a transport adapter that will automatically retry GET/POST/HEAD requests on failures up to 3 times
adapter = requests.adapters.HTTPAdapter(
    max_retries=urllib3.Retry(
        total=3,
        method_whitelist=frozenset(['GET', 'POST', 'HEAD'])
    )
)

# create a Session (a pool of connections) and make it use the given adapter for HTTP and HTTPS requests
session = requests.Session()
session.mount('http://', adapter)
session.mount('https://', adapter)

# execute a prediction request that will be retried on transport failures, if needed
api_token = '<your api token>'
dr_key = '<your datarobot key>'
response = session.post(
    'https://example.datarobot.com/predApi/v1.0/deployments/<deploymentId>/predictions',
    headers={
        'Authorization': 'Bearer %s' % api_token,
        'DataRobot-Key': dr_key,
        'Content-Type': 'text/csv',
    },
    data='<your scoring data>',
)

print(response.content)