Agent trace

Script completed
Wall time 0.1 seconds
Output:

/app
candidate_catalog.parquet 349352 bytes
target_users.parquet 84127 bytes
test_eligible_candidates.npz 7736341 bytes
test_preference_state.parquet 1092329 bytes
train_dislikes.parquet 857213 bytes
train_likes.parquet 5374652 bytes
train_listens.parquet 319183255 bytes
train_undislikes.parquet 155988 bytes
train_unlikes.parquet 1855885 bytes
val_dislikes.parquet 36571 bytes
val_likes.parquet 298484 bytes
val_listens.parquet 9947609 bytes
val_undislikes.parquet 7845 bytes
val_unlikes.parquet 72536 bytes
validation_eligible_candidates.npz 7573821 bytes
validation_preference_state.parquet 1061761 bytes
"""Shared public primitives for Yambda discovery-ranking evaluation.

Both the solver-visible validation evaluator and the private submission judge
import this module from the generated task's ``public`` directory. It owns the
stage-independent contract: reading a ranking, validating its shape, converting
it to per-user rank order, looking up packed candidate eligibility, and
computing graded NDCG@10.

The module deliberately contains no event-derived labels, private artifact
paths, or pass thresholds. Each evaluator supplies its own relevance data and
per-cutoff eligibility checks around these common operations.
"""
from __future__ import annotations

from pathlib import Path

import numpy as np
import pandas as pd


__all__ = [
    "CandidateSet",
    "QUALITY_K",
    "RankingValidationError",
    "REQUIRED_COLUMNS",
    "TOP_N",
    "ndcg_at_k",
    "ranked_items",
    "read_ranking",
    "score_rankings",
    "validate_ranking",
]

TOP_N = 100
QUALITY_K = 10
REQUIRED_COLUMNS = ("uid", "item_id", "rank")


class RankingValidationError(ValueError):
    """Report a ranking-schema or structural-contract violation."""


class CandidateSet:
    """Provide membership lookups over one packed candidate-set archive.

    The archive contains aligned ``uids``, ``item_ids``, and
    ``packed_eligible`` arrays. Candidate column ``c`` is represented by bit
    ``c % 8`` of byte ``c // 8`` using little-endian bit order. Arrays are
    copied into memory so they remain valid after the archive is closed.
    """

    def __init__(self, path: Path):
        """Load an eligibility archive and build ID-to-position indexes.

        Args:
            path: Path to a ``.npz`` archive with the candidate-set schema.
        """
        with np.load(path, allow_pickle=False) as artifact:
            self.uids = artifact["uids"].astype(np.int64, copy=True)
            self.item_ids = artifact["item_ids"].astype(np.int64, copy=True)
            self.packed = artifact["packed_eligible"].astype(np.uint8, copy=True)
        self.uid_row = {int(uid): row for row, uid in enumerate(self.uids)}
        self.item_column = {
            int(item): column for column, item in enumerate(self.item_ids)
        }

    def is_eligible(self, uid: int, item_id: int) -> bool:
        """Return whether ``item_id`` is eligible for ``uid``.

        IDs absent from the target-user or candidate-item arrays are treated as
        ineligible rather than raising an exception.

        Args:
            uid: Target user ID to query.
            item_id: Candidate item ID to query.

        Returns:
            ``True`` only when the corresponding packed eligibility bit is set.
        """
        row = self.uid_row.get(int(uid))
        column = self.item_column.get(int(item_id))
        if row is None or column is None:
            return False
        byte, bit = divmod(column, 8)
        return bool((int(self.packed[row, byte]) >> bit) & 1)


def read_ranking(path: Path) -> pd.DataFrame:
    """Read a parquet or CSV ranking into a pandas frame.

    Args:
        path: Input path. A ``.parquet`` suffix selects parquet; every other
            suffix is interpreted as CSV.

    Returns:
        The ranking frame as loaded by pandas.
    """
    return pd.read_parquet(path) if path.suffix == ".parquet" else pd.read_csv(path)


def validate_ranking(
    frame: pd.DataFrame,
    targets: set[int],
) -> pd.DataFrame:
    """Normalize and validate the stage-independent ranking contract.

    Required values must be finite integers. The user set must exactly match
    ``targets``; every user must have 100 rows, distinct items, and each rank
    from 1 through 100 exactly once. Cutoff-specific candidate eligibility is
    intentionally left to the calling evaluator.

    Args:
        frame: Raw ranking frame. Extra columns are discarded from an internal
            copy; the caller's frame is not modified.
        targets: Exact set of target user IDs the ranking must cover.

    Returns:
        A normalized frame containing only the required ``int64`` columns.

    Raises:
        RankingValidationError: If the ranking violates the shared contract.
    """
    required = list(REQUIRED_COLUMNS)
    if not all(column in frame for column in required):
        raise RankingValidationError(f"submission requires columns {required}")

    normalized = frame[required].copy()
    for column in required:
        numeric = pd.to_numeric(normalized[column], errors="coerce")
        values = numeric.to_numpy(dtype=float)
        if numeric.isna().any() or not np.isfinite(values).all():
            raise RankingValidationError(
                f"submission {column} must be finite numeric values"
            )
        if not np.equal(numeric, np.floor(numeric)).all():
            raise RankingValidationError(
                f"submission {column} must contain integers"
            )
        normalized[column] = numeric.astype(np.int64)

    submitted_users = set(map(int, normalized.uid.unique()))
    if submitted_users != targets:
        raise RankingValidationError(
            f"submission user set mismatch: missing={len(targets - submitted_users)} "
            f"extra={len(submitted_users - targets)}"
        )
    counts = normalized.groupby("uid").size()
    if not (counts == TOP_N).all():
        raise RankingValidationError(
            f"submission must contain exactly {TOP_N} rows for every target user"
        )
    if normalized.duplicated(["uid", "item_id"]).any():
        raise RankingValidationError(
            "submission contains duplicate (uid, item_id) pairs"
        )
    valid_ranks = set(range(1, TOP_N + 1))
    ranks_are_valid = normalized.groupby("uid")["rank"].apply(
        lambda values: set(map(int, values)) == valid_ranks
    )
    if not ranks_are_valid.all():
        raise RankingValidationError(
            f"each user must have every rank from 1 through {TOP_N} exactly once"
        )
    return normalized


def ranked_items(frame: pd.DataFrame) -> dict[int, list[int]]:
    """Convert a validated ranking frame to ordered items keyed by user.

    Args:
        frame: Frame that has passed :func:`validate_ranking`.

    Returns:
        A ``uid -> item IDs`` mapping ordered by ascending rank.
    """
    ordered = frame.sort_values(["uid", "rank"])
    return {
        int(uid): list(map(int, values))
        for uid, values in ordered.groupby("uid").item_id
    }


def ndcg_at_k(ranked: list[int], gold: dict[int, int], k: int) -> float:
    """Compute graded normalized discounted cumulative gain at ``k``.

    Relevance gain is ``2**grade - 1`` and the discount at one-based rank
    ``r`` is ``1 / log2(r + 1)``. Items absent from ``gold`` have grade zero.

    Args:
        ranked: Item IDs in predicted rank order.
        gold: Mapping from relevant item IDs to integer relevance grades.
        k: Maximum number of predicted positions to score.

    Returns:
        For a valid duplicate-free ranking, NDCG in ``[0, 1]``; returns
        ``0.0`` when the ideal gain is zero.
    """
    gains = np.asarray([gold.get(item, 0) for item in ranked[:k]], dtype=np.float64)
    discounts = 1.0 / np.log2(np.arange(2, len(gains) + 2))
    dcg = float(np.sum((np.power(2.0, gains) - 1.0) * discounts))
    ideal = np.asarray(sorted(gold.values(), reverse=True)[:k], dtype=np.float64)
    ideal_discounts = 1.0 / np.log2(np.arange(2, len(ideal) + 2))
    idcg = float(np.sum((np.power(2.0, ideal) - 1.0) * ideal_discounts))
    return dcg / idcg if idcg else 0.0


def score_rankings(
    ranked: dict[int, list[int]],
    graded: dict[int, dict[int, int]],
) -> dict[str, float | int]:
    """Aggregate per-user NDCG@10 over users with relevance labels.

    Args:
        ranked: Ranked item IDs for every target user.
        graded: Relevant item grades keyed by user and item.

    Returns:
        The six-decimal ``quality_ndcg@10`` value and number of scored users.
    """
    quality = float(
        np.mean(
            [
                ndcg_at_k(ranked[uid], gold, QUALITY_K)
                for uid, gold in graded.items()
            ]
        )
    )
    return {
        "quality_ndcg@10": round(quality, 6),
        "quality_users": len(graded),
    }
#!/usr/bin/env python3
"""Score a validation-stage ranking against public discovery labels.

``build_task.py`` publishes this module with the solver-visible task files. It
loads target users, validation eligibility, and validation-window events from
the adjacent ``data`` directory, then evaluates one ranking supplied on the
command line. Stage-independent mechanics come from the adjacent public
``ranking_evaluation.py`` module. The builder installs the same checked-in
module in the private judge, so public and private scoring mechanics cannot
drift. A relevant candidate receives grade 3 for an organic like or grade 1 for
an organic listen with at least 80 percent completion; a like takes precedence
when both events exist.

Before scoring, the ranking must contain exactly 100 distinct eligible items
for every target user, with integer-valued ``uid``, ``item_id``, and ``rank``
columns and ranks 1 through 100 exactly once per user. Extra columns are
ignored. Quality is graded NDCG@10, averaged only over users who have at least
one eligible relevant item in the validation window.

The evaluator prints a JSON object containing the model path and scores. It
does not apply the task's pass threshold; its purpose is model development and
selection. The private judge applies the threshold to the final submission.

Usage::

    python evaluate_public.py <validation-ranking.parquet|csv>
"""
from __future__ import annotations

import json
import sys
from pathlib import Path

import pandas as pd

from ranking_evaluation import (
    CandidateSet,
    RankingValidationError,
    ranked_items,
    read_ranking,
    score_rankings,
    validate_ranking,
)


HERE = Path(__file__).resolve().parent
DATA = HERE / "data"
LISTEN_STRONG = 80


def validation_truth(
    eligibility: CandidateSet, targets: set[int]
) -> dict[int, dict[int, int]]:
    """Build cutoff-correct graded relevance from public validation events.

    Only target-user events for eligible candidates are retained. Organic
    listens completed to at least 80 percent receive grade 1, and organic likes
    receive grade 3. Repeated user-item events are collapsed, and processing
    likes second ensures that grade 3 wins over grade 1.

    Args:
        eligibility: Validation-cutoff candidate membership service.
        targets: Complete set of target user IDs.

    Returns:
        A nested ``uid -> item_id -> grade`` mapping. Users without an eligible
        relevant event are omitted.
    """
    listens = pd.read_parquet(DATA / "val_listens.parquet")
    likes = pd.read_parquet(DATA / "val_likes.parquet")
    strong = listens[
        listens.uid.isin(targets)
        & (listens.is_organic == 1)
        & (listens.played_ratio_pct >= LISTEN_STRONG)
    ][["uid", "item_id"]].drop_duplicates()
    organic_likes = likes[
        likes.uid.isin(targets) & (likes.is_organic == 1)
    ][["uid", "item_id"]].drop_duplicates()

    graded: dict[int, dict[int, int]] = {}
    for raw_uid, raw_item in strong.itertuples(index=False, name=None):
        uid, item = int(raw_uid), int(raw_item)
        if eligibility.is_eligible(uid, item):
            graded.setdefault(uid, {})[item] = 1
    for raw_uid, raw_item in organic_likes.itertuples(index=False, name=None):
        uid, item = int(raw_uid), int(raw_item)
        if eligibility.is_eligible(uid, item):
            graded.setdefault(uid, {})[item] = 3
    return graded


def load_submission(
    path: Path, eligibility: CandidateSet, targets: set[int]
) -> dict[int, list[int]]:
    """Load and validate a public validation ranking.

    Files ending in ``.parquet`` are read as parquet; every other suffix is
    read as CSV. The required columns must be integer-valued, cover exactly the
    target-user set, contain 100 rows and ranks 1 through 100 per user, avoid
    duplicate user-item pairs, and contain only cutoff-eligible items.

    Args:
        path: Ranking file to read.
        eligibility: Validation-cutoff candidate membership service.
        targets: Exact set of users the ranking must cover.

    Returns:
        A ``uid -> ranked item IDs`` mapping ordered by ascending rank.

    Raises:
        ValueError: If the ranking violates the required schema or invariants.
    """
    frame = validate_ranking(read_ranking(path), targets)
    if not all(
        eligibility.is_eligible(uid, item)
        for uid, item in frame[["uid", "item_id"]].itertuples(index=False, name=None)
    ):
        raise RankingValidationError(
            "submission contains an item rejected by eligibility service"
        )
    return ranked_items(frame)


def score(
    ranked: dict[int, list[int]],
    graded: dict[int, dict[int, int]],
) -> dict[str, float | int]:
    """Aggregate per-user NDCG@10 over users with public relevance labels.

    Args:
        ranked: Ranked item IDs for every target user.
        graded: Eligible validation relevance keyed by user and item.

    Returns:
        The six-decimal ``quality_ndcg@10`` value and number of scored users.
    """
    return score_rankings(ranked, graded)


def main() -> None:
    """Run the public evaluator CLI and print its JSON score report."""
    targets_frame = pd.read_parquet(DATA / "target_users.parquet")
    targets = set(targets_frame.uid.astype(int))
    eligibility = CandidateSet(DATA / "validation_eligible_candidates.npz")
    graded = validation_truth(eligibility, targets)

    if len(sys.argv) != 2:
        raise SystemExit(
            "usage: evaluate_public.py <validation-ranking.parquet|csv>"
        )
    path = Path(sys.argv[1])
    ranked = load_submission(path, eligibility, targets)
    print(json.dumps({"model": str(path), "scores": score(ranked, graded)}, indent=2))


if __name__ == "__main__":
    main()
# Exact distribution inventory for the Yambda two-tower task family.
#
# This is an input to `uv pip sync`, not a list of minimum requirements. A
# conforming task environment contains exactly these third-party Python
# distributions and no others. Python itself is pinned by task.toml and both
# Harbor image Dockerfiles.
attrs==26.1.0
bleach==6.4.0
certifi==2026.7.22
chardet==7.6.0
charset-normalizer==3.5.1
fastjsonschema==2.22.2
filelock==3.32.3
fsspec==2026.7.0
idna==3.18
Jinja2==3.1.6
joblib==1.5.3
jsonschema==4.26.0
jsonschema-specifications==2025.9.1
jupyter-core==5.9.1
jupytext==1.19.5
kaggle==2.2.4
kagglesdk==0.1.37
markdown-it-py==4.2.0
MarkupSafe==3.0.3
mdit-py-plugins==0.6.1
mdurl==0.1.2
mpmath==1.3.0
nbformat==5.11.1
networkx==3.6.1
numpy==2.2.6
packaging==26.3
pandas==2.3.3
pillow==12.3.0
pip==26.0.1
platformdirs==4.11.3
protobuf==7.35.1
pyarrow==18.1.0
python-dateutil==2.9.0.post0
python-dotenv==1.2.3
python-slugify==8.0.4
pytz==2026.3.post1
PyYAML==6.0.3
referencing==0.37.0
reportlab==4.2.5
requests==2.34.2
rpds-py==2026.6.3
scikit-learn==1.7.2
scipy==1.15.3
setuptools==84.0.0
six==1.17.0
sympy==1.14.0
text-unidecode==1.3
threadpoolctl==3.6.0
torch==2.8.0
tqdm==4.70.0
traitlets==5.16.1
typing-extensions==4.16.0
tzdata==2026.3
urllib3==2.7.0
webencodings==0.6.1
Architecture:                            x86_64
CPU op-mode(s):                          32-bit, 64-bit
Address sizes:                           48 bits physical, 48 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  8
On-line CPU(s) list:                     0-7
Vendor ID:                               AuthenticAMD
Model name:                              AMD EPYC 7R13 Processor
CPU family:                              25
Model:                                   1
Thread(s) per core:                      2
Core(s) per socket:                      4
Socket(s):                               1
Stepping:                                1
BogoMIPS:                                5299.99
Flags:                                   fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru wbnoinvd arat npt nrip_save vaes vpclmulqdq rdpid
Hypervisor vendor:                       KVM
Virtualization type:                     full
L1d cache:                               128 KiB (4 instances)
L1i cache:                               128 KiB (4 instances)
L2 cache:                                2 MiB (4 instances)
L3 cache:                                16 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-7
/bin/sh: 1: free: not found

Script completed
Wall time 0.1 seconds
Output:

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
ModuleNotFoundError: No module named 'pandas'

Script completed
Wall time 0.1 seconds
Output:

/usr/local/bin/python
/usr/local/bin/python3
total 36
dr-xr-xr-x 1 root root 4096 Aug 31 18:22 .
drwxr-xr-x 1 root root 4096 Aug 31 18:25 ..
-r--r--r-- 1 root root    0 Aug 31 18:08 .keep
dr-xr-xr-x 1 root root 4096 Aug 31 18:09 data
-r--r--r-- 1 root root 5774 Aug 31 18:08 evaluate_public.py
-r--r--r-- 1 root root 8265 Aug 31 18:08 ranking_evaluation.py
-r--r--r-- 1 root root 1295 Aug 31 18:08 requirements.txt
CODEX_CI=1
CODEX_HOME=/tmp/codex-home
CODEX_THREAD_ID=01a05911-6d99-7d43-bf68-29aef44477b3
COLORTERM=
GH_PAGER=cat
GIT_PAGER=cat
GPG_KEY=7169605F62C751356D054A26A821E680E5FA6305
HOME=/home/agent
HOSTNAME=aec47db0eab4
LANG=C.UTF-8
LC_ALL=C.UTF-8
LC_CTYPE=C.UTF-8
NO_COLOR=1
PAGER=cat
PATH=/opt/codex-home/packages/standalone/releases/0.147.0-x86_64-unknown-linux-musl/codex-path:/usr/local/bin:/usr/bin:/bin:/usr/local/games:/usr/games
PWD=/app
PYTHONDONTWRITEBYTECODE=1
PYTHONNOUSERSITE=1
PYTHON_SHA256=c08bc65a81971c1dd5783182826503369466c7e67374d1646519adf05207b684
PYTHON_VERSION=3.12.13
SHLVL=1
TERM=dumb
_=/usr/local/bin/codex

Script completed
Wall time 1.2 seconds
Output:

Package Version
------- -------
pip     25.0.1
/opt/task-venv/lib/python3.12/site-packages
/usr/local/lib/python3.12/site-packages
/usr/local/bin/python3.12-config
/usr/local/bin/python3.12

Script completed
Wall time 4.0 seconds
Output:

total 124
dr-xr-xr-x 1 root root 4096 Aug 31 18:22 .
dr-xr-xr-x 1 root root 4096 Aug 31 18:22 ..
-r--r--r-- 1 root root 9033 Aug 31 18:22 Activate.ps1
-r--r--r-- 1 root root 2158 Aug 31 18:22 activate
-r--r--r-- 1 root root  920 Aug 31 18:22 activate.csh
-r--r--r-- 1 root root 2195 Aug 31 18:22 activate.fish
-r-xr-xr-x 1 root root  302 Aug 31 18:22 chardetect
-r-xr-xr-x 1 root root  304 Aug 31 18:22 dotenv
-r-xr-xr-x 1 root root  308 Aug 31 18:22 f2py
-r-xr-xr-x 1 root root  299 Aug 31 18:22 idna
-r-xr-xr-x 1 root root  297 Aug 31 18:22 isympy
-r-xr-xr-x 1 root root  305 Aug 31 18:22 jsonschema
-r-xr-xr-x 1 root root  311 Aug 31 18:22 jupyter
-r-xr-xr-x 1 root root  311 Aug 31 18:22 jupyter-migrate
-r-xr-xr-x 1 root root  316 Aug 31 18:22 jupyter-troubleshoot
-r-xr-xr-x 1 root root  344 Aug 31 18:22 jupyter-trust
-r-xr-xr-x 1 root root  311 Aug 31 18:22 jupytext
-r-xr-xr-x 1 root root  315 Aug 31 18:22 jupytext-config
-r-xr-xr-x 1 root root  301 Aug 31 18:22 kaggle
-r-xr-xr-x 1 root root  312 Aug 31 18:22 markdown-it
-r-xr-xr-x 1 root root  325 Aug 31 18:22 normalizer
-r-xr-xr-x 1 root root  308 Aug 31 18:22 numpy-config
-r-xr-xr-x 1 root root  313 Aug 31 18:22 pip
-r-xr-xr-x 1 root root  313 Aug 31 18:22 pip3
-r-xr-xr-x 1 root root  313 Aug 31 18:22 pip3.12
lrwxrwxrwx 1 root root   21 Aug 31 18:22 python -> /usr/local/bin/python
lrwxrwxrwx 1 root root    6 Aug 31 18:22 python3 -> python
lrwxrwxrwx 1 root root    6 Aug 31 18:22 python3.12 -> python
-r-xr-xr-x 1 root root  307 Aug 31 18:22 slugify
-r-xr-xr-x 1 root root  321 Aug 31 18:22 torchfrtrace
-r-xr-xr-x 1 root root  312 Aug 31 18:22 torchrun
-r-xr-xr-x 1 root root  299 Aug 31 18:22 tqdm
2.3.3 2.8.0+cpu 18.1.0 2.2.6

Script completed
Wall time 3.1 seconds
Output:


 candidate_catalog.parquet rows 30000 cols ['item_id', 'positive_listens', 'organic_positive_listens', 'popularity_rank'] dtypes {'item_id': 'uint32', 'positive_listens': 'int64', 'organic_positive_listens': 'uint64', 'popularity_rank': 'int32'}
[{'item_id': 5862961, 'positive_listens': 26615, 'organic_positive_listens': 20620, 'popularity_rank': 1}, {'item_id': 6901374, 'positive_listens': 25536, 'organic_positive_listens': 17347, 'popularity_rank': 2}]

 target_users.parquet rows 8456 cols ['uid', 'recent_positive_listens', 'history_positive_listens'] dtypes {'uid': 'uint32', 'recent_positive_listens': 'float64', 'history_positive_listens': 'int64'}
[{'uid': 100, 'recent_positive_listens': 844.0, 'history_positive_listens': 2604}, {'uid': 200, 'recent_positive_listens': 50.0, 'history_positive_listens': 286}]

 test_preference_state.parquet rows 484776 cols ['uid', 'item_id', 'state'] dtypes {'uid': 'uint32', 'item_id': 'uint32', 'state': 'object'}
[{'uid': 100, 'item_id': 410868, 'state': 'liked'}, {'uid': 100, 'item_id': 732449, 'state': 'liked'}]

 train_dislikes.parquet rows 101075 cols ['uid', 'timestamp', 'item_id', 'is_organic'] dtypes {'uid': 'uint32', 'timestamp': 'uint32', 'item_id': 'uint32', 'is_organic': 'uint8'}
[{'uid': 100, 'timestamp': 3087560, 'item_id': 9170134, 'is_organic': 1}, {'uid': 100, 'timestamp': 3936560, 'item_id': 8661238, 'is_organic': 1}]

 train_likes.parquet rows 814831 cols ['uid', 'timestamp', 'item_id', 'is_organic'] dtypes {'uid': 'uint32', 'timestamp': 'uint32', 'item_id': 'uint32', 'is_organic': 'uint8'}
[{'uid': 100, 'timestamp': 44755, 'item_id': 732449, 'is_organic': 1}, {'uid': 100, 'timestamp': 1155860, 'item_id': 6568592, 'is_organic': 0}]

 train_listens.parquet rows 43484159 cols ['uid', 'timestamp', 'item_id', 'is_organic', 'played_ratio_pct', 'track_length_seconds'] dtypes {'uid': 'uint32', 'timestamp': 'uint32', 'item_id': 'uint32', 'is_organic': 'uint8', 'played_ratio_pct': 'uint16', 'track_length_seconds': 'uint32'}
[{'uid': 100, 'timestamp': 39420, 'item_id': 8326270, 'is_organic': 0, 'played_ratio_pct': 100, 'track_length_seconds': 170}, {'uid': 100, 'timestamp': 39420, 'item_id': 1441281, 'is_organic': 0, 'played_ratio_pct': 100, 'track_length_seconds': 105}]

 train_undislikes.parquet rows 19960 cols ['uid', 'timestamp', 'item_id', 'is_organic'] dtypes {'uid': 'uint32', 'timestamp': 'uint32', 'item_id': 'uint32', 'is_organic': 'uint8'}
[{'uid': 100, 'timestamp': 7895900, 'item_id': 9170134, 'is_organic': 1}, {'uid': 100, 'timestamp': 7895900, 'item_id': 5038504, 'is_organic': 1}]

 train_unlikes.parquet rows 292665 cols ['uid', 'timestamp', 'item_id', 'is_organic'] dtypes {'uid': 'uint32', 'timestamp': 'uint32', 'item_id': 'uint32', 'is_organic': 'uint8'}
[{'uid': 100, 'timestamp': 3087555, 'item_id': 5038504, 'is_organic': 1}, {'uid': 100, 'timestamp': 3087555, 'item_id': 9170134, 'is_organic': 1}]

 val_dislikes.parquet rows 3563 cols ['uid', 'timestamp', 'item_id', 'is_organic'] dtypes {'uid': 'uint32', 'timestamp': 'uint32', 'item_id': 'uint32', 'is_organic': 'uint8'}
[{'uid': 1600, 'timestamp': 25163525, 'item_id': 6747257, 'is_organic': 0}, {'uid': 1900, 'timestamp': 24877510, 'item_id': 5832822, 'is_organic': 1}]

 val_likes.parquet rows 37795 cols ['uid', 'timestamp', 'item_id', 'is_organic'] dtypes {'uid': 'uint32', 'timestamp': 'uint32', 'item_id': 'uint32', 'is_organic': 'uint8'}
[{'uid': 100, 'timestamp': 25249855, 'item_id': 3526521, 'is_organic': 1}, {'uid': 300, 'timestamp': 25046245, 'item_id': 4867327, 'is_organic': 1}]

 val_listens.parquet rows 1501697 cols ['uid', 'timestamp', 'item_id', 'is_organic', 'played_ratio_pct', 'track_length_seconds'] dtypes {'uid': 'uint32', 'timestamp': 'uint32', 'item_id': 'uint32', 'is_organic': 'uint8', 'played_ratio_pct': 'uint16', 'track_length_seconds': 'uint32'}
[{'uid': 100, 'timestamp': 24943430, 'item_id': 9321269, 'is_organic': 0, 'played_ratio_pct': 100, 'track_length_seconds': 195}, {'uid': 100, 'timestamp': 24943605, 'item_id': 5452713, 'is_organic': 0, 'played_ratio_pct': 100, 'track_length_seconds': 175}]

 val_undislikes.parquet rows 606 cols ['uid', 'timestamp', 'item_id', 'is_organic'] dtypes {'uid': 'uint32', 'timestamp': 'uint32', 'item_id': 'uint32', 'is_organic': 'uint8'}
[{'uid': 900, 'timestamp': 25364045, 'item_id': 6092542, 'is_organic': 1}, {'uid': 900, 'timestamp': 25364045, 'item_id': 6501913, 'is_organic': 1}]

 val_unlikes.parquet rows 9346 cols ['uid', 'timestamp', 'item_id', 'is_organic'] dtypes {'uid': 'uint32', 'timestamp': 'uint32', 'item_id': 'uint32', 'is_organic': 'uint8'}
[{'uid': 1100, 'timestamp': 24861880, 'item_id': 6901050, 'is_organic': 1}, {'uid': 1100, 'timestamp': 24861880, 'item_id': 5421761, 'is_organic': 1}]

 validation_preference_state.parquet rows 469124 cols ['uid', 'item_id', 'state'] dtypes {'uid': 'uint32', 'item_id': 'uint32', 'state': 'object'}
[{'uid': 100, 'item_id': 410868, 'state': 'liked'}, {'uid': 100, 'item_id': 732449, 'state': 'liked'}]

 test_eligible_candidates.npz {'uids': ((8456,), 'uint32'), 'item_ids': ((30000,), 'uint32'), 'packed_eligible': ((8456, 3750), 'uint8')} eligible [24552.0, 28657.0, 29220.0, 29619.25, 30000.0]

 validation_eligible_candidates.npz {'uids': ((8456,), 'uint32'), 'item_ids': ((30000,), 'uint32'), 'packed_eligible': ((8456, 3750), 'uint8')} eligible [24657.0, 28682.75, 29242.0, 29644.0, 30000.0]

Script completed
Wall time 0.5 seconds
Output:

MemTotal:       15988980 kB
MemFree:         2066596 kB
MemAvailable:   14973136 kB
Buffers:          227940 kB
Cached:         12387292 kB
SwapCached:            0 kB
Active:           514536 kB
Inactive:       12386704 kB
Active(anon):     312460 kB
Inactive(anon):        0 kB
Active(file):     202076 kB
Inactive(file): 12386704 kB
rowgroups 42
0 1048576 [('uid', 100, 26500), ('timestamp', 15, 24786690), ('item_id', 206, 9390541)]
1 1048576 [('uid', 26500, 50300), ('timestamp', 185, 24786725), ('item_id', 105, 9390541)]
41 492543 [('uid', 989500, 1000000), ('timestamp', 20, 24786690), ('item_id', 50, 9390508)]

Script completed
Wall time 7.4 seconds
Output:

{}
raw strong 255608 users 6325 likes 17195 users 2714
{
  "model": "/app/solution/validation_popularity.parquet",
  "scores": {
    "quality_ndcg@10": 0.01071,
    "quality_users": 4263
  }
}

Script completed
Wall time 2.5 seconds
Output:

train_listens catalog rows 31249613 secs 0.49226999282836914
users 9217 target rows 31062540 organic 15619474
>=50 20056329 >=80 organic 8699160
train_likes catalog rows 554824 secs 0.015738248825073242
users 7901 target rows 472889 organic 301527

Script running with cell ID 10
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.3 seconds
Output:

{"session_id":63356,"output":"/app/solution/global_baselines.py:45: RuntimeWarning: overflow encountered in exp\n  \"organic_30d\": np.bincount(ii[strong], weights=np.exp(-(CUTOFF-ts[strong])/(30*86400)), minlength=len(items)),\n/app/solution/global_baselines.py:47: RuntimeWarning: overflow encountered in exp\n  \"positive_30d\": np.bincount(ii[ratio>=50], weights=np.exp(-(CUTOFF-ts[ratio>=50])/(30*86400)), minlength=len(items)),\norganic_all 19362.0 29974\norganic_30d inf 29974\norganic_90d 6.761620250105525e+243 29974\npositive_30d inf 30000\nlikes_all 565.0 27464\nlikes_90d 2.022302271801164e+242 27464\n{   \"model\": \"/app/solution/validation_organic_all.parquet\",   \"scores\": {     \"quality_ndcg@10\": 0.010551,     \"quality_users\": 4263   } } \n{   \"model\": \"/app/solution/validation_organic_30d.parquet\",   \"scores\": {     \"quality_ndcg@10\": 0.01071,     \"quality_users\": 4263   } } \n"}

Script running with cell ID 11
Wall time 11.0 seconds
Output:

Script completed
Wall time 15.4 seconds
Output:

{"session_id":44323,"output":"organic_all     \"quality_ndcg@10\": 0.010551,\n    \"quality_users\": 4263\norganic_30d     \"quality_ndcg@10\": 0.016254,\n    \"quality_users\": 4263\norganic_90d     \"quality_ndcg@10\": 0.015031,\n    \"quality_users\": 4263\npositive_30d "}

Script completed
Wall time 9.6 seconds
Output:

organic_all {'quality_ndcg@10': 0.010551, 'quality_users': 4263}
organic_30d {'quality_ndcg@10': 0.016254, 'quality_users': 4263}
organic_90d {'quality_ndcg@10': 0.015031, 'quality_users': 4263}
positive_30d {'quality_ndcg@10': 0.018115, 'quality_users': 4263}
likes_all {'quality_ndcg@10': 0.012054, 'quality_users': 4263}
likes_90d {'quality_ndcg@10': 0.016093, 'quality_users': 4263}

Script completed
Wall time 0.0 seconds
Output:

{}
{}

Script running with cell ID 14
Wall time 11.0 seconds
Output:

Script completed
Wall time 14.5 seconds
Output:

Warning: truncated output (original token count: 5212)
Total output lines: 1

{"session_id":59049,"output":"Warning: truncated output (original token count: 378261)\n... 464466 bytes omitted ...\n\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in …212 tokens truncated…numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast\r\n  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h[\"last\"].to_numpy(), 0) / (90 * DAY))\r\n{\"stage\": \"validation\", \"users\": 8456, \"items\": 30000, \"history_shape\": [8456, 192], \"positive_pairs\": 2581120}\r\n/app/solution/train_ranker.py:215: UserWarning: Converting a tensor with requires_grad=True to a scalar may lead to unexpected behavior.\r\nConsider using tensor.detach() first. (Triggered internally at /pytorch/torch/csrc/autograd/generated/python_variable_methods.cpp:835.)\r\n  print(json.dumps({\"epoch\": epoch + 1, \"steps\": steps_per_epoch, \"loss\": round(float(np.mean(losses)), 5), \"scale\": round(float(model.logit_scale.exp()), 3)}), flush=True)\r\n{\"epoch\": 1, \"steps\": 20, \"loss\": NaN, \"scale\": NaN}\r\n{\"epoch\": 10, \"steps\": 20, \"loss\": NaN, \"scale\": NaN}\r\n"}

Script completed
Wall time 0.0 seconds
Output:

{}
/bin/sh: 1: ps: not found
  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h["last"].to_numpy(), 0) / (90 * DAY))
/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast
  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h["last"].to_numpy(), 0) / (90 * DAY))
/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast
  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h["last"].to_numpy(), 0) / (90 * DAY))
/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast
  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h["last"].to_numpy(), 0) / (90 * DAY))
/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast
  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h["last"].to_numpy(), 0) / (90 * DAY))
/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast
  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h["last"].to_numpy(), 0) / (90 * DAY))
/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast
  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h["last"].to_numpy(), 0) / (90 * DAY))
/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast
  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h["last"].to_numpy(), 0) / (90 * DAY))
/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast
  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h["last"].to_numpy(), 0) / (90 * DAY))
/app/solution/train_ranker.py:162: RuntimeWarning: overflow encountered in cast
  hist_features[row, :k, 0] = np.exp(-np.maximum(cutoff - h["last"].to_numpy(), 0) / (90 * DAY))
{"stage": "validation", "users": 8456, "items": 30000, "history_shape": [8456, 192], "positive_pairs": 2581120}
/app/solution/train_ranker.py:215: UserWarning: Converting a tensor with requires_grad=True to a scalar may lead to unexpected behavior.
Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/csrc/autograd/generated/python_variable_methods.cpp:835.)
  print(json.dumps({"epoch": epoch + 1, "steps": steps_per_epoch, "loss": round(float(np.mean(losses)), 5), "scale": round(float(model.logit_scale.exp()), 3)}), flush=True)
{"epoch": 1, "steps": 20, "loss": NaN, "scale": NaN}
{"epoch": 10, "steps": 20, "loss": NaN, "scale": NaN}
{"epoch": 20, "steps": 20, "loss": NaN, "scale": NaN}
{"epoch": 30, "steps": 20, "loss": NaN, "scale": NaN}
{"epoch": 40, "steps": 20, "loss": NaN, "scale": NaN}
{"epoch": 50, "steps": 20, "loss": NaN, "scale": NaN}
wrote /app/solution/validation_twotower_b0p0.parquet /app/solution/validation_twotower_b0p5.parquet /app/solution/validation_twotower_b1p0.parquet /app/solution/validation_twotower_b2p0.parquet /app/solution/validation_twotower_b4p0.parquet /app/solution/validation_twotower_b8p0.parquet

Script running with cell ID 16
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.8 seconds
Output:

{"session_id":81193,"output":"{\"stage\": \"validation\", \"users\": 8456, \"items\": 30000, \"history_shape\": [8456, 192], \"positive_pairs\": 2581120}\r\n{\"epoch\": 1, \"steps\": 20, \"loss\": 6.25228, \"scale\": 9.694}\r\n{\"epoch\": 10, \"steps\": 20, \"loss\": 5.77807, \"scale\": 9.64}\r\n"}

Script completed
Wall time 0.1 seconds
Output:

{"stage": "validation", "users": 8456, "items": 30000, "history_shape": [8456, 192], "positive_pairs": 2581120}
{"epoch": 1, "steps": 20, "loss": 6.25228, "scale": 9.694}
{"epoch": 10, "steps": 20, "loss": 5.77807, "scale": 9.64}
{"epoch": 20, "steps": 20, "loss": 5.44374, "scale": 10.042}
-rw-r--r-- 1 agent agent 11603723 Aug 31 18:37 /app/solution/model_validation.pt
-rw-r--r-- 1 agent agent   935917 Aug 31 18:37 /app/solution/validation_twotower_b4p0.parquet

Script completed
Wall time 9.9 seconds
Output:

{"epoch": 20, "steps": 20, "loss": 5.44374, "scale": 10.042}
{"epoch": 30, "steps": 20, "loss": 5.24213, "scale": 10.871}
{"epoch": 40, "steps": 20, "loss": 5.03169, "scale": 12.086}
{"epoch": 50, "steps": 20, "loss": 4.88639, "scale": 13.506}
{"epoch": 60, "steps": 20, "loss": 4.75961, "scale": 14.766}
wrote /app/solution/validation_twotower_b0p0.parquet /app/solution/validation_twotower_b0p5.parquet /app/solution/validation_twotower_b1p0.parquet /app/solution/validation_twotower_b2p0.parquet /app/solution/validation_twotower_b4p0.parquet /app/solution/validation_twotower_b8p0.parquet

Script completed
Wall time 10.1 seconds
Output:

0p0 {'quality_ndcg@10': 0.018098, 'quality_users': 4263}
0p5 {'quality_ndcg@10': 0.018276, 'quality_users': 4263}
1p0 {'quality_ndcg@10': 0.018673, 'quality_users': 4263}
2p0 {'quality_ndcg@10': 0.018985, 'quality_users': 4263}
4p0 {'quality_ndcg@10': 0.019669, 'quality_users': 4263}
8p0 {'quality_ndcg@10': 0.020561, 'quality_users': 4263}

Script running with cell ID 20
Wall time 11.0 seconds
Output:

Script completed
Wall time 8.7 seconds
Output:

['/app/solution/validation_twotower_b12p0.parquet', '/app/solution/validation_twotower_b16p0.parquet', '/app/solution/validation_twotower_b24p0.parquet', '/app/solution/validation_twotower_b32p0.parquet', '/app/solution/validation_twotower_b48p0.parquet']

Script completed
Wall time 9.8 seconds
Output:

8p0 0.020561
12p0 0.022408
16p0 0.023008
24p0 0.021857
32p0 0.018982
48p0 0.013646

Script running with cell ID 22
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.1 seconds
Output:

{"session_id":91115,"output":"{\"stage\": \"validation\", \"users\": 8456, \"items\": 30000, \"history_shape\": [8456, 256], \"positive_pairs\": 2581120}\r\n{\"epoch\": 1, \"steps\": 20, \"loss\": 6.13319, \"scale\": 9.703}\r\n{\"epoch\": 10, \"steps\": 20, \"loss\": 5.73095, \"scale\": 9.728}\r\n"}

Script running with cell ID 23
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.3 seconds
Output:

{"epoch": 20, "steps": 20, "loss": 5.37465, "scale": 10.325}
{"epoch": 30, "steps": 20, "loss": 5.10861, "scale": 11.656}
{"epoch": 40, "steps": 20, "loss": 4.92659, "scale": 13.179}
{"epoch": 50, "steps": 20, "loss": 4.80621, "scale": 14.687}
{"epoch": 60, "steps": 20, "loss": 4.69788, "scale": 15.984}

Script running with cell ID 24
Wall time 11.0 seconds
Output:

Script completed
Wall time 12.5 seconds
Output:

{"epoch": 70, "steps": 20, "loss": 4.61173, "scale": 17.14}
{"epoch": 80, "steps": 20, "loss": 4.53815, "scale": 18.363}
{"epoch": 90, "steps": 20, "loss": 4.46672, "scale": 19.416}
{"epoch": 100, "steps": 20, "loss": 4.43057, "scale": 20.331}
wrote /app/solution/validation_twotower_b0p0.parquet /app/solution/validation_twotower_b0p5.parquet /app/solution/validation_twotower_b1p0.parquet /app/solution/validation_twotower_b2p0.parquet /app/solution/validation_twotower_b4p0.parquet /app/solution/validation_twotower_b8p0.parquet

Script running with cell ID 25
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.7 seconds
Output:

{"session_id":69575,"output":"v2 0p0 0.018098\r\nv2 0p5 0.01826\r\nv2 1p0 0.018462\r\nv2 2p0 0.01867\r\nv2 4p0 0.019384\r\nv2 8p0 0.02\r\n"}

Script completed
Wall time 5.0 seconds
Output:

v2 12p0 0.021024
v2 16p0 0.02193
v2 20p0 0.022919
v2 24p0 0.02255
v2 32p0 0.020324

Script running with cell ID 27
Wall time 11.0 seconds
Output:

Script completed
Wall time 10.2 seconds
Output:

{}

Script completed
Wall time 1.5 seconds
Output:

Traceback (most recent call last):
  File "<stdin>", line 4, in <module>
ImportError: cannot import name 'ndcg_at_k' from 'evaluate_public' (/task/evaluate_public.py)

Script running with cell ID 29
Wall time 11.0 seconds
Output:

Script completed
Wall time 1.3 seconds
Output:

8 0.020561
10 0.021684
12 0.022408
14 0.022909
16 0.023008
18 0.022803
20 0.022458
22 0.022016
24 0.021857
quartile 0 n 1066 [(8, 0.02919), (10, 0.02946), (12, 0.03011), (14, 0.0294), (16, 0.02909), (18, 0.02883), (20, 0.0285), (22, 0.02751), (24, 0.02622)]
quartile 1 n 1066 [(8, 0.0201), (10, 0.02159), (12, 0.02229), (14, 0.02398), (16, 0.02397), (18, 0.02453), (20, 0.02431), (22, 0.0249), (24, 0.02488)]
quartile 2 n 1065 [(8, 0.01717), (10, 0.01826), (12, 0.01914), (14, 0.01926), (16, 0.01967), (18, 0.01913), (20, 0.01907), (22, 0.01908), (24, 0.01913)]
quartile 3 n 1066 [(8, 0.01577), (10, 0.01742), (12, 0.01809), (14, 0.01899), (16, 0.0193), (18, 0.01872), (20, 0.01795), (22, 0.01658), (24, 0.01719)]

Script running with cell ID 30
Wall time 11.0 seconds
Output:

Script completed
Wall time 0.0 seconds
Output:

0 828 12 0.033136 [(10, 0.0327), (12, 0.03314), (14, 0.03231), (16, 0.03136), (18, 0.03018), (20, 0.02909), (22, 0.02836), (24, 0.02701)]
1 998 22 0.028831 [(10, 0.02387), (12, 0.02512), (14, 0.02653), (16, 0.02721), (18, 0.02829), (20, 0.02881), (22, 0.02883), (24, 0.02854)]
2 1159 14 0.017816 [(10, 0.01716), (12, 0.0173), (14, 0.01782), (16, 0.01748), (18, 0.01729), (20, 0.01712), (22, 0.0171), (24, 0.0172)]
3 1278 16 0.019327 [(10, 0.01694), (12, 0.01797), (14, 0.01861), (16, 0.01933), (18, 0.01873), (20, 0.01805), (22, 0.01704), (24, 0.01752)]
adaptive {'quality_ndcg@10': 0.023823, 'quality_users': 4263} {0: 12, 1: 22, 2: 14, 3: 16}

Script completed
Wall time 0.0 seconds
Output:

{}
{}

Script running with cell ID 32
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.5 seconds
Output:

{"session_id":35858,"output":"{\"stage\": \"final\", \"users\": 8456, \"items\": 30000, \"history_shape\": [8456, 192], \"positive_pairs\": 2661891}\r\n{\"epoch\": 1, \"steps\": 21, \"loss\": 6.2371, \"scale\": 9.688}\r\n{\"epoch\": 10, \"steps\": 21, \"loss\": 5.78441, \"scale\": 9.625}\r\n"}

Script running with cell ID 33
Wall time 11.0 seconds
Output:

Script completed
Wall time 6.9 seconds
Output:

{"epoch": 20, "steps": 21, "loss": 5.43837, "scale": 10.033}
{"epoch": 30, "steps": 21, "loss": 5.20693, "scale": 10.922}
{"epoch": 40, "steps": 21, "loss": 5.01833, "scale": 12.108}
{"epoch": 50, "steps": 21, "loss": 4.92044, "scale": 13.381}
{"epoch": 60, "steps": 21, "loss": 4.79246, "scale": 14.798}
wrote /app/solution/submission.parquet

Script completed
Wall time 6.1 seconds
Output:

{}
{
  "model": "/app/solution/validation.parquet",
  "scores": {
    "quality_ndcg@10": 0.023823,
    "quality_users": 4263
  }
}
{'rows': 845600, 'users': 8456, 'min_rank': 1, 'max_rank': 100, 'ineligible': 0, 'duplicate_pairs': 0, 'dtypes': {'uid': 'int64', 'item_id': 'int64', 'rank': 'int64'}}
-rw-r--r-- 1 agent agent 2.1K Aug 31 18:48 /app/solution/README.md
-rw-r--r-- 1 agent agent  12M Aug 31 18:47 /app/solution/model_final.pt
-rw-r--r-- 1 agent agent 1.6M Aug 31 18:47 /app/solution/submission.parquet
-rw-r--r-- 1 agent agent  15K Aug 31 18:46 /app/solution/train_ranker.py
-rw-r--r-- 1 agent agent 1.6M Aug 31 18:48 /app/solution/validation.parquet

Script completed
Wall time 0.0 seconds
Output:

{}