تحلیل و پیش‌بینی تأخیرهای پرواز

هدف و راهنمای انجام

جداسازی آموزش و ارزیابی و سنجش تعمیم مدل

ورودی

train: لیست سطرهای دارای arr_delay؛ test: لیست ویژگی‌های بدون هدف؛ features: ['month', 'day', 'hour', 'distance', 'air_time', 'dep_delay']؛ target: arr_delay

خروجی

result.json شامل predictions با یک مقدار به‌ازای هر سطر test؛ عدد برای رگرسیون و برچسب موجود در train برای دسته‌بندی.

1. request.json شامل train دارای برچسب و test بدون برچسب است؛ فایل CSV محلی برای مطالعه است و در ارزیابی به محیط ارسال نمی‌شود.
2. train را به ویژگی‌ها و target جدا کن؛ داده ارزیابی بیرونی را هرگز برای fit استفاده نکن.
3. برای تمرین، با train_test_split و random_state=42 بخشی از train را نگه دار و مدل را با MAE یا accuracy/F1 بسنج.
4. مدل یا Pipeline را فقط روی داده آموزش fit کن؛ سپس برای تمام سطرهای test پیش‌بینی کن.
5. predictions را به ترتیب test در result.json ذخیره کن؛ امتیاز نهایی را داور روی برچسب‌های خارج محیط محاسبه می‌کند.

تقسیم داده را داور هم مستقل انجام می‌دهد؛ موفقیت صرف اجرای برنامه یا metric چاپ‌شده کافی نیست. random_state=42 را برای بازتولیدپذیری تنظیم کن.

مثال ورودی و خروجی

{
    "input": {
        "train": [
            {
                "month": 1,
                "day": 2,
                "hour": 18,
                "distance": 760,
                "air_time": 127,
                "dep_delay": -1,
                "arr_delay": -16
            },
            {
                "month": 1,
                "day": 1,
                "hour": 16,
                "distance": 199,
                "air_time": 48,
                "dep_delay": 14,
                "arr_delay": 13
            },
            {
                "month": 1,
                "day": 3,
                "hour": 8,
                "distance": 1069,
                "air_time": 165,
                "dep_delay": -1,
                "arr_delay": -4
            },
            {
                "month": 1,
                "day": 3,
                "hour": 8,
                "distance": 1005,
                "air_time": 165,
                "dep_delay": 2,
                "arr_delay": 2
            },
            {
                "month": 1,
                "day": 2,
                "hour": 16,
                "distance": 762,
                "air_time": 130,
                "dep_delay": -2,
                "arr_delay": 26
            },
            {
                "month": 1,
                "day": 2,
                "hour": 18,
                "distance": 419,
                "air_time": 74,
                "dep_delay": -9,
                "arr_delay": -15
            },
            {
                "month": 1,
                "day": 2,
                "hour": 19,
                "distance": 2586,
                "air_time": 320,
                "dep_delay": 17,
                "arr_delay": -33
            },
            {
                "month": 1,
                "day": 2,
                "hour": 6,
                "distance": 719,
                "air_time": 112,
                "dep_delay": 80,
                "arr_delay": 90
            },
            {
                "month": 1,
                "day": 2,
                "hour": 18,
                "distance": 719,
                "air_time": 137,
                "dep_delay": 15,
                "arr_delay": 19
            },
            {
                "month": 1,
                "day": 2,
                "hour": 7,
                "distance": 1400,
                "air_time": 215,
                "dep_delay": 7,
                "arr_delay": 13
            },
            {
                "month": 1,
                "day": 2,
                "hour": 15,
                "distance": 642,
                "air_time": 121,
                "dep_delay": 43,
                "arr_delay": 47
            },
            {
                "month": 1,
                "day": 2,
                "hour": 21,
                "distance": 301,
                "air_time": 63,
                "dep_delay": -4,
                "arr_delay": -10
            },
            {
                "month": 1,
                "day": 1,
                "hour": 17,
                "distance": 1416,
                "air_time": 234,
                "dep_delay": 2,
                "arr_delay": 16
            },
            {
                "month": 1,
                "day": 1,
                "hour": 17,
                "distance": 2402,
                "air_time": 344,
                "dep_delay": 1,
                "arr_delay": -19
            },
            {
                "month": 1,
                "day": 2,
                "hour": 6,
                "distance": 1085,
                "air_time": 157,
                "dep_delay": -1,
                "arr_delay": -1
            },
            {
                "month": 1,
                "day": 2,
                "hour": 12,
                "distance": 719,
                "air_time": 136,
                "dep_delay": -1,
                "arr_delay": -1
            },
            {
                "month": 1,
                "day": 2,
                "hour": 18,
                "distance": 2422,
                "air_time": 325,
                "dep_delay": -5,
                "arr_delay": -51
            },
            {
                "month": 1,
                "day": 2,
                "hour": 16,
                "distance": 1626,
                "air_time": 242,
                "dep_delay": -1,
                "arr_delay": -18
            },
            {
                "month": 1,
                "day": 2,
                "hour": 12,
                "distance": 1183,
                "air_time": 196,
                "dep_delay": -2,
                "arr_delay": 1
            },
            {
                "month": 1,
                "day": 2,
                "hour": 15,
                "distance": 2475,
                "air_time": 341,
                "dep_delay": -5,
                "arr_delay": -23
            },
            {
                "month": 1,
                "day": 2,
                "hour": 9,
                "distance": 266,
                "air_time": 51,
                "dep_delay": -6,
                "arr_delay": -1
            },
            {
                "month": 1,
                "day": 1,
                "hour": 15,
                "distance": 282,
                "air_time": 58,
                "dep_delay": 16,
                "arr_delay": 12
            },
            {
                "month": 1,
                "day": 2,
                "hour": 8,
                "distance": 1020,
                "air_time": 142,
                "dep_delay": 10,
                "arr_delay": -6
            },
            {
                "month": 1,
                "day": 2,
                "hour": 6,
                "distance": 1028,
                "air_time": 146,
                "dep_delay": -6,
                "arr_delay": -10
            },
            {
                "month": 1,
                "day": 2,
                "hour": 18,
                "distance": 1598,
                "air_time": 191,
                "dep_delay": -3,
                "arr_delay": -4
            },
            {
                "month": 1,
                "day": 1,
                "hour": 18,
                "distance": 2422,
                "air_time": 334,
                "dep_delay": -4,
                "arr_delay": -13
            },
            {
                "month": 1,
                "day": 2,
                "hour": 17,
                "distance": 544,
                "air_time": 100,
                "dep_delay": -4,
                "arr_delay": -6
            },
            {
                "month": 1,
                "day": 1,
                "hour": 13,
                "distance": 445,
                "air_time": 86,
                "dep_delay": 40,
                "arr_delay": 46
            },
            {
                "month": 1,
                "day": 2,
                "hour": 7,
                "distance": 733,
                "air_time": 127,
                "dep_delay": 12,
                "arr_delay": 12
            },
            {
                "month": 1,
                "day": 1,
                "hour": 11,
                "distance": 1620,
                "air_time": 256,
                "dep_delay": 13,
                "arr_delay": 34
            },
            {
                "month": 1,
                "day": 1,
                "hour": 13,
                "distance": 569,
                "air_time": 129,
                "dep_delay": 35,
                "arr_delay": 65
            },
            {
                "month": 1,
                "day": 2,
                "hour": 20,
                "distance": 404,
                "air_time": 74,
                "dep_delay": 3,
                "arr_delay": -11
            },
            {
                "month": 1,
                "day": 2,
                "hour": 15,
                "distance": 282,
                "air_time": 51,
                "dep_delay": 128,
                "arr_delay": 141
            },
            {
                "month": 1,
                "day": 2,
                "hour": 7,
                "distance": 445,
                "air_time": 94,
                "dep_delay": -2,
                "arr_delay": 12
            },
            {
                "month": 1,
                "day": 2,
                "hour": 20,
                "distance": 762,
                "air_time": 125,
                "dep_delay": -4,
                "arr_delay": 6
            },
            {
                "month": 1,
                "day": 2,
                "hour": 17,
                "distance": 2446,
                "air_time": 319,
                "dep_delay": -6,
                "arr_delay": -44
            },
            {
                "month": 1,
                "day": 1,
                "hour": 14,
                "distance": 1504,
                "air_time": 252,
                "dep_delay": 1,
                "arr_delay": 17
            },
            {
                "month": 1,
                "day": 2,
                "hour": 7,
                "distance": 2422,
                "air_time": 309,
                "dep_delay": -1,
                "arr_delay": -45
            },
            {
                "month": 1,
                "day": 2,
                "hour": 9,
                "distance": 1023,
                "air_time": 154,
                "dep_delay": 0,
                "arr_delay": 15
            },
            {
                "month": 1,
                "day": 2,
                "hour": 8,
                "distance": 1605,
                "air_time": 242,
                "dep_delay": 1,
                "arr_delay": -11
            }
        ],
        "test": [
            {
                "month": 1,
                "day": 1,
                "hour": 10,
                "distance": 762,
                "air_time": 129,
                "dep_delay": -4
            },
            {
                "month": 1,
                "day": 2,
                "hour": 16,
                "distance": 533,
                "air_time": 102,
                "dep_delay": 168
            },
            {
                "month": 1,
                "day": 1,
                "hour": 15,
                "distance": 483,
                "air_time": 98,
                "dep_delay": -8
            }
        ],
        "features": [
            "month",
            "day",
            "hour",
            "distance",
            "air_time",
            "dep_delay"
        ],
        "target": "arr_delay"
    },
    "output": {
        "predictions": [
            "برچسب یا عدد برای هر سطر test"
        ]
    }
}

معیارهای موفقیت

• MAE حداکثر 15.0
• شکل و تعداد و نوع پیش‌بینی‌ها مطابق ورودی
• ارزیابی روی دو تقسیم تصادفی مستقل؛ برچسب test به کد ارسال نمی‌شود.

کتابخانه‌ها: pandas, scikit-learn, numpy