Upload option_b_entity_resolution.ipynb with huggingface_hub
Browse files- option_b_entity_resolution.ipynb +1076 -0
option_b_entity_resolution.ipynb
ADDED
|
@@ -0,0 +1,1076 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "markdown",
|
| 5 |
+
"id": "494afa14",
|
| 6 |
+
"metadata": {},
|
| 7 |
+
"source": [
|
| 8 |
+
"# Option B \u2014 Hybrid Multi-View Blocking + Bi-Encoder Neural Embeddings\n",
|
| 9 |
+
"### Business Entity Resolution \u2014 Amazon ML Challenge 2026\n",
|
| 10 |
+
"\n",
|
| 11 |
+
"This notebook implements the complete, production-ready Option B pipeline:\n",
|
| 12 |
+
"1. **Universal Fast Transliteration & Accent Stripping** (Phonetic Indic table + NFKD + unidecode before key extraction)\n",
|
| 13 |
+
"2. **DuckDB Multi-View Blocking**:\n",
|
| 14 |
+
" - Both Source 2 and Source 3 targets combined into one index\n",
|
| 15 |
+
" - Target keys and frequency caps indexed **once** per country (not re-run in inner loops)\n",
|
| 16 |
+
" - S1 batched to avoid memory bottlenecks\n",
|
| 17 |
+
" - Top-K candidate pairs filtering per entity\n",
|
| 18 |
+
"3. **Mandatory Blocking Recall Ceiling Check**:\n",
|
| 19 |
+
" - Accurately checks recall on ground truth to ensure zero candidate loss\n",
|
| 20 |
+
"4. **Deduplicated Bi-Encoder Embeddings (Qwen3-Embedding-0.6B)**:\n",
|
| 21 |
+
" - One embedding per **unique** entity (not per pair)\n",
|
| 22 |
+
" - Multi-GPU DataParallel support (e.g. 2x T4 on Kaggle)\n",
|
| 23 |
+
" - Persistent `EntityEmbedder` class available for both train and test phases\n",
|
| 24 |
+
"5. **LightGBM Reranker with In-Fold-Only Metric Evaluation**:\n",
|
| 25 |
+
" - `macro_f05` evaluates **only** the entities in the current validation fold (fixing CV skew)\n",
|
| 26 |
+
" - Per-country threshold sweeps (France gets its own operating point)\n",
|
| 27 |
+
"6. **End-to-End Test Set Inference**:\n",
|
| 28 |
+
" - Full test blocking, embedding, feature extraction, and prediction\n",
|
| 29 |
+
"7. **1:Many Target-Exclusivity Resolution**:\n",
|
| 30 |
+
" - Each Target entity is assigned to at most one S1 (highest probability >= threshold)\n",
|
| 31 |
+
" - Each S1 can match to multiple targets (across S2 and S3)\n",
|
| 32 |
+
"8. **Submission Generation & Official Validation**:\n",
|
| 33 |
+
" - Exports `matching_results.tsv` and `candidate_pairs.tsv`\n",
|
| 34 |
+
" - Validates format with `utils/validate_submission.py`\n"
|
| 35 |
+
]
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"cell_type": "code",
|
| 39 |
+
"id": "fc4d836b",
|
| 40 |
+
"metadata": {},
|
| 41 |
+
"source": [
|
| 42 |
+
"import os\n",
|
| 43 |
+
"import sys\n",
|
| 44 |
+
"import time\n",
|
| 45 |
+
"import json\n",
|
| 46 |
+
"import gc\n",
|
| 47 |
+
"import re\n",
|
| 48 |
+
"import unicodedata\n",
|
| 49 |
+
"from pathlib import Path\n",
|
| 50 |
+
"from collections import defaultdict\n",
|
| 51 |
+
"\n",
|
| 52 |
+
"import numpy as np\n",
|
| 53 |
+
"import pandas as pd\n",
|
| 54 |
+
"import duckdb\n",
|
| 55 |
+
"import torch\n",
|
| 56 |
+
"import torch.nn as nn\n",
|
| 57 |
+
"import torch.nn.functional as F\n",
|
| 58 |
+
"\n",
|
| 59 |
+
"# ---- Data Directory Auto-Discovery ----\n",
|
| 60 |
+
"# Checks Kaggle paths, standard local paths, or relative paths\n",
|
| 61 |
+
"POSSIBLE_DATA_DIRS = [\n",
|
| 62 |
+
" Path(\"/kaggle/input/amazon-ml-challenge-2026\"),\n",
|
| 63 |
+
" Path(\"/kaggle/input/amazon-ml\"),\n",
|
| 64 |
+
" Path(\"/kaggle/input/datasets/arghasaha1905/amazon-ml\"),\n",
|
| 65 |
+
" Path(\"/kaggle/input/student-resource\"),\n",
|
| 66 |
+
" Path(\"dataset\"),\n",
|
| 67 |
+
" Path(\".\"),\n",
|
| 68 |
+
"]\n",
|
| 69 |
+
"\n",
|
| 70 |
+
"DATA_DIR = None\n",
|
| 71 |
+
"for p in POSSIBLE_DATA_DIRS:\n",
|
| 72 |
+
" if p.exists() and (\n",
|
| 73 |
+
" (p / \"train_source1.tsv\").exists() or\n",
|
| 74 |
+
" (p / \"train\" / \"train_source1.tsv\").exists() or\n",
|
| 75 |
+
" (p / \"test_source1.tsv\").exists() or\n",
|
| 76 |
+
" (p / \"test\" / \"test_source1.tsv\").exists()\n",
|
| 77 |
+
" ):\n",
|
| 78 |
+
" DATA_DIR = p\n",
|
| 79 |
+
" break\n",
|
| 80 |
+
"\n",
|
| 81 |
+
"if DATA_DIR is None:\n",
|
| 82 |
+
" DATA_DIR = Path(\"/kaggle/input/amazon-ml-challenge-2026\")\n",
|
| 83 |
+
"\n",
|
| 84 |
+
"print(f\"Detected DATA_DIR: {DATA_DIR}\")\n",
|
| 85 |
+
"\n",
|
| 86 |
+
"# ---- Output & Cache Directories ----\n",
|
| 87 |
+
"if Path(\"/kaggle/working\").exists():\n",
|
| 88 |
+
" OUTPUT_DIR = Path(\"/kaggle/working/output\")\n",
|
| 89 |
+
" CACHE_DIR = Path(\"/kaggle/working/cache\")\n",
|
| 90 |
+
"else:\n",
|
| 91 |
+
" OUTPUT_DIR = Path(\"output\")\n",
|
| 92 |
+
" CACHE_DIR = Path(\"cache\")\n",
|
| 93 |
+
"\n",
|
| 94 |
+
"OUTPUT_DIR.mkdir(parents=True, exist_ok=True)\n",
|
| 95 |
+
"CACHE_DIR.mkdir(parents=True, exist_ok=True)\n",
|
| 96 |
+
"\n",
|
| 97 |
+
"# ---- Run Configuration ----\n",
|
| 98 |
+
"# Set SAMPLE_MODE = True to test on a fast sample (20k per country) first.\n",
|
| 99 |
+
"# Set SAMPLE_MODE = False for the full 2.2M train + 1.73M test run.\n",
|
| 100 |
+
"SAMPLE_MODE = True\n",
|
| 101 |
+
"SAMPLE_N_PER_COUNTRY = 20_000\n",
|
| 102 |
+
"TOP_K_CANDIDATES = 35\n",
|
| 103 |
+
"FREQ_CAP_DEFAULT = 500\n",
|
| 104 |
+
"FREQ_CAP_FRANCE = 1000\n",
|
| 105 |
+
"\n",
|
| 106 |
+
"# ---- Hardware & GPU Check ----\n",
|
| 107 |
+
"n_gpus = torch.cuda.device_count()\n",
|
| 108 |
+
"print(f\"CUDA available: {torch.cuda.is_available()} | GPU count: {n_gpus}\")\n",
|
| 109 |
+
"for i in range(n_gpus):\n",
|
| 110 |
+
" props = torch.cuda.get_device_properties(i)\n",
|
| 111 |
+
" print(f\" GPU {i}: {props.name} | {props.total_memory / 1e9:.1f} GB\")\n",
|
| 112 |
+
"\n",
|
| 113 |
+
"device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
|
| 114 |
+
"print(f\"Using primary device: {device}\")\n"
|
| 115 |
+
],
|
| 116 |
+
"execution_count": null,
|
| 117 |
+
"outputs": []
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"cell_type": "markdown",
|
| 121 |
+
"id": "6025bbce",
|
| 122 |
+
"metadata": {},
|
| 123 |
+
"source": [
|
| 124 |
+
"## 1. High-Performance Text Normalization & Transliteration\n",
|
| 125 |
+
"Indic scripts (Devanagari, Tamil, Telugu, Bengali, Kannada, Malayalam, etc.) and French diacritics\n",
|
| 126 |
+
"must be mapped phonetically into Latin characters **before** generating blocking keys.\n",
|
| 127 |
+
"We use a precompiled C-level `str.translate` lookup table with NFKD normalization, ensuring\n",
|
| 128 |
+
"sub-microsecond execution per entity with zero empty-string wipes.\n"
|
| 129 |
+
]
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"cell_type": "code",
|
| 133 |
+
"id": "faa1babb",
|
| 134 |
+
"metadata": {},
|
| 135 |
+
"source": [
|
| 136 |
+
"try:\n",
|
| 137 |
+
" from unidecode import unidecode\n",
|
| 138 |
+
"except ImportError:\n",
|
| 139 |
+
" import subprocess\n",
|
| 140 |
+
" subprocess.run([sys.executable, \"-m\", \"pip\", \"install\", \"unidecode\", \"-q\"])\n",
|
| 141 |
+
" from unidecode import unidecode\n",
|
| 142 |
+
"\n",
|
| 143 |
+
"# Universal Indic & European phonetic transliteration map\n",
|
| 144 |
+
"DEV_PHONETICS = {\n",
|
| 145 |
+
" 0x05:'a',0x06:'a',0x07:'i',0x08:'i',0x09:'u',0x0A:'u',0x0B:'ri',0x0E:'e',0x0F:'e',0x10:'ai',0x12:'o',0x13:'o',0x14:'au',\n",
|
| 146 |
+
" 0x15:'k',0x16:'kh',0x17:'g',0x18:'gh',0x19:'n',0x1A:'ch',0x1B:'chh',0x1C:'j',0x1D:'jh',0x1E:'n',\n",
|
| 147 |
+
" 0x1F:'t',0x20:'th',0x21:'d',0x22:'dh',0x23:'n',0x24:'t',0x25:'th',0x26:'d',0x27:'dh',0x28:'n',\n",
|
| 148 |
+
" 0x2A:'p',0x2B:'ph',0x2C:'b',0x2D:'bh',0x2E:'m',0x2F:'y',0x30:'r',0x31:'r',0x32:'l',0x33:'l',0x35:'v',\n",
|
| 149 |
+
" 0x36:'sh',0x37:'sh',0x38:'s',0x39:'h',0x3E:'a',0x3F:'i',0x40:'i',0x41:'u',0x42:'u',0x43:'ri',\n",
|
| 150 |
+
" 0x46:'e',0x47:'e',0x48:'ai',0x4A:'o',0x4B:'o',0x4C:'au',0x4D:'',0x02:'n',0x01:'n',0x03:'h'\n",
|
| 151 |
+
"}\n",
|
| 152 |
+
"TRANSLIT_MAP = {chr(base+off): lat for base in (0x0900,0x0980,0x0A00,0x0A80,0x0B00,0x0B80,0x0C00,0x0C80,0x0D00) for off, lat in DEV_PHONETICS.items()}\n",
|
| 153 |
+
"TRANSLIT_MAP.update({\n",
|
| 154 |
+
" '\u00e9':'e','\u00e8':'e','\u00ea':'e','\u00eb':'e','\u00e0':'a','\u00e2':'a','\u00e4':'a','\u00f4':'o','\u00f6':'o',\n",
|
| 155 |
+
" '\u00ee':'i','\u00ef':'i','\u00f9':'u','\u00fb':'u','\u00fc':'u','\u00e7':'c','\u00f1':'n','\u00c9':'e','\u00c8':'e','\u00ca':'e','\u00cb':'e',\n",
|
| 156 |
+
" '\u00c0':'a','\u00c2':'a','\u00c4':'a','\u00d4':'o','\u00d6':'o','\u00ce':'i','\u00cf':'i','\u00d9':'u','\u00db':'u','\u00dc':'u','\u00c7':'c','\u00d1':'n',\n",
|
| 157 |
+
" '\u00ab':'','\u00bb':'','\u2019':\"'\",'\u201c':'\"','\u201d':'\"'\n",
|
| 158 |
+
"})\n",
|
| 159 |
+
"TRANSLIT_TABLE = str.maketrans(TRANSLIT_MAP)\n",
|
| 160 |
+
"\n",
|
| 161 |
+
"_WS_RE = re.compile(r\"\\s+\")\n",
|
| 162 |
+
"_NONALNUM_RE = re.compile(r\"[^a-z0-9\\s]\")\n",
|
| 163 |
+
"_DOMAIN_RE = re.compile(r\"^(https?://)?(www\\.)?\", re.IGNORECASE)\n",
|
| 164 |
+
"_TLD_RE = re.compile(r\"\\.(com|in|org|net|co|io|fr)$\", re.IGNORECASE)\n",
|
| 165 |
+
"SUFFIX_RE = re.compile(r\"\\b(pvt|ltd|limited|private|inc|incorporated|llc|corp|corporation|co|company|enterprises|services|solutions|group|sarl|sas|sasu|eurl|sci|association|fils)\\b\", re.I)\n",
|
| 166 |
+
"\n",
|
| 167 |
+
"def clean_and_translit(text):\n",
|
| 168 |
+
" \"\"\"Fast transliteration: C-table translation + NFKD + unidecode fallback + clean whitespace.\"\"\"\n",
|
| 169 |
+
" if text is None or (isinstance(text, float) and np.isnan(text)):\n",
|
| 170 |
+
" return \"\"\n",
|
| 171 |
+
" s = str(text).translate(TRANSLIT_TABLE)\n",
|
| 172 |
+
" s = unicodedata.normalize(\"NFKD\", s)\n",
|
| 173 |
+
" s = \"\".join(c for c in s if not unicodedata.combining(c))\n",
|
| 174 |
+
" # fallback for any exotic scripts not in base table\n",
|
| 175 |
+
" if any(ord(c) > 127 for c in s):\n",
|
| 176 |
+
" s = unidecode(s)\n",
|
| 177 |
+
" s = s.lower()\n",
|
| 178 |
+
" s = _DOMAIN_RE.sub(\"\", s)\n",
|
| 179 |
+
" s = _TLD_RE.sub(\"\", s)\n",
|
| 180 |
+
" s = _NONALNUM_RE.sub(\" \", s)\n",
|
| 181 |
+
" return _WS_RE.sub(\" \", s).strip()\n",
|
| 182 |
+
"\n",
|
| 183 |
+
"def strip_legal_suffixes(name_clean):\n",
|
| 184 |
+
" return SUFFIX_RE.sub(\" \", name_clean).strip()\n",
|
| 185 |
+
"\n",
|
| 186 |
+
"def compact_alnum(s):\n",
|
| 187 |
+
" return _NONALNUM_RE.sub(\"\", s).replace(\" \", \"\")\n",
|
| 188 |
+
"\n",
|
| 189 |
+
"# Verification against known Indian and French test entities\n",
|
| 190 |
+
"_tests = [\n",
|
| 191 |
+
" (\"\u0930\u093f\u092f\u0932 \u0915\u0902\u0938\u0932\u094d\u091f\u0947\u0902\u091f\u094d\u0938 \u092a\u094d\u0930\u093e\u0907\u0935\u0947\u091f \u0932\u093f\u092e\u093f\u091f\u0947\u0921\", \"real\"),\n",
|
| 192 |
+
" (\"Physical Th\u00e9rapy Care\", \"physical\"),\n",
|
| 193 |
+
" (\"\u0baa\u0bbe\u0bb2\u0bbe\u0b9c\u0bbf \u0b95\u0bcb\u0bb2\u0bcd\u0b9f\u0bc1 \u0b95\u0bc7\u0bb0\u0bcd\", \"balaji\"),\n",
|
| 194 |
+
"]\n",
|
| 195 |
+
"for raw, expect_prefix in _tests:\n",
|
| 196 |
+
" out = clean_and_translit(raw)\n",
|
| 197 |
+
" print(f\"{raw!r:45s} -> {out!r}\")\n",
|
| 198 |
+
" assert out != \"\", f\"Transliteration produced an EMPTY string for: {raw!r}\"\n",
|
| 199 |
+
" if expect_prefix:\n",
|
| 200 |
+
" assert out.startswith(expect_prefix), f\"Expected prefix {expect_prefix!r}, got {out!r}\"\n"
|
| 201 |
+
],
|
| 202 |
+
"execution_count": null,
|
| 203 |
+
"outputs": []
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"cell_type": "markdown",
|
| 207 |
+
"id": "51550e1d",
|
| 208 |
+
"metadata": {},
|
| 209 |
+
"source": [
|
| 210 |
+
"## 2. Load Dataset\n",
|
| 211 |
+
"Locates and loads `source1`, `source2`, `source3`, and `ground_truth`.\n",
|
| 212 |
+
"In `SAMPLE_MODE = True`, it takes a balanced per-country sample to enable sub-2-minute prototyping.\n"
|
| 213 |
+
]
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"cell_type": "code",
|
| 217 |
+
"id": "79917e97",
|
| 218 |
+
"metadata": {},
|
| 219 |
+
"source": [
|
| 220 |
+
"def find_file(filename):\n",
|
| 221 |
+
" \"\"\"Finds a dataset file whether in flat structure or train/test subfolders.\"\"\"\n",
|
| 222 |
+
" candidates = [\n",
|
| 223 |
+
" DATA_DIR / filename,\n",
|
| 224 |
+
" DATA_DIR / \"train\" / filename,\n",
|
| 225 |
+
" DATA_DIR / \"test\" / filename,\n",
|
| 226 |
+
" ]\n",
|
| 227 |
+
" for c in candidates:\n",
|
| 228 |
+
" if c.exists():\n",
|
| 229 |
+
" return c\n",
|
| 230 |
+
" raise FileNotFoundError(f\"Could not locate {filename} in {DATA_DIR}\")\n",
|
| 231 |
+
"\n",
|
| 232 |
+
"def load_tsv(filename):\n",
|
| 233 |
+
" path = find_file(filename)\n",
|
| 234 |
+
" df = pd.read_csv(path, sep=\"\\t\", dtype=str, keep_default_na=False)\n",
|
| 235 |
+
" print(f\"Loaded {filename}: {len(df):,} rows, cols={list(df.columns)}\")\n",
|
| 236 |
+
" return df\n",
|
| 237 |
+
"\n",
|
| 238 |
+
"train_s1 = load_tsv(\"train_source1.tsv\")\n",
|
| 239 |
+
"train_s2 = load_tsv(\"train_source2.tsv\")\n",
|
| 240 |
+
"train_s3 = load_tsv(\"train_source3.tsv\")\n",
|
| 241 |
+
"train_gt = load_tsv(\"train_ground_truth.tsv\")\n",
|
| 242 |
+
"\n",
|
| 243 |
+
"for df in [train_s1, train_s2, train_s3]:\n",
|
| 244 |
+
" assert df[\"entity_id\"].is_unique, \"Duplicate entity_id found!\"\n",
|
| 245 |
+
"\n",
|
| 246 |
+
"if SAMPLE_MODE:\n",
|
| 247 |
+
" print(f\"\\n[SAMPLE_MODE active] Sampling {SAMPLE_N_PER_COUNTRY:,} entities per country from train_s1...\")\n",
|
| 248 |
+
" train_s1 = (train_s1.groupby(\"country\", group_keys=False)\n",
|
| 249 |
+
" .apply(lambda g: g.sample(min(SAMPLE_N_PER_COUNTRY, len(g)), random_state=42))\n",
|
| 250 |
+
" .reset_index(drop=True))\n",
|
| 251 |
+
" keep_ids = set(train_s1[\"entity_id\"])\n",
|
| 252 |
+
" train_gt = train_gt[train_gt[\"source1_entity_id\"].isin(keep_ids)].reset_index(drop=True)\n",
|
| 253 |
+
" print(f\"train_s1 sampled to: {len(train_s1):,} rows\")\n"
|
| 254 |
+
],
|
| 255 |
+
"execution_count": null,
|
| 256 |
+
"outputs": []
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"cell_type": "markdown",
|
| 260 |
+
"id": "656c196c",
|
| 261 |
+
"metadata": {},
|
| 262 |
+
"source": [
|
| 263 |
+
"## 3. Pre-Normalize Name and Address Fields\n",
|
| 264 |
+
"Adds `name_clean`, `name_root`, `addr_clean`, `name_compact`, `house_no`, and `postal`.\n",
|
| 265 |
+
"Only normalizes required tables, preserving memory.\n"
|
| 266 |
+
]
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"cell_type": "code",
|
| 270 |
+
"id": "69261b0f",
|
| 271 |
+
"metadata": {},
|
| 272 |
+
"source": [
|
| 273 |
+
"def add_normalized_columns(df):\n",
|
| 274 |
+
" \"\"\"Vectorized / batch text normalization for high speed and minimal memory.\"\"\"\n",
|
| 275 |
+
" df = df.copy()\n",
|
| 276 |
+
" names = df[\"business_name\"].tolist()\n",
|
| 277 |
+
" addrs = df[\"business_address\"].tolist()\n",
|
| 278 |
+
"\n",
|
| 279 |
+
" clean_names = [clean_and_translit(n) for n in names]\n",
|
| 280 |
+
" clean_addrs = [clean_and_translit(a) for a in addrs]\n",
|
| 281 |
+
"\n",
|
| 282 |
+
" df[\"name_clean\"] = clean_names\n",
|
| 283 |
+
" df[\"name_root\"] = [strip_legal_suffixes(n) for n in clean_names]\n",
|
| 284 |
+
" df[\"addr_clean\"] = clean_addrs\n",
|
| 285 |
+
" df[\"name_compact\"] = [compact_alnum(n) for n in clean_names]\n",
|
| 286 |
+
"\n",
|
| 287 |
+
" df[\"house_no\"] = df[\"addr_clean\"].str.extract(r\"(\\d{1,6})\", expand=False).fillna(\"\")\n",
|
| 288 |
+
" df[\"postal\"] = df[\"addr_clean\"].str.extract(r\"(\\d{5,6})(?!.*\\d{5,6})\", expand=False).fillna(\"\")\n",
|
| 289 |
+
" return df\n",
|
| 290 |
+
"\n",
|
| 291 |
+
"print(\"Normalizing train_s1...\")\n",
|
| 292 |
+
"train_s1 = add_normalized_columns(train_s1)\n",
|
| 293 |
+
"\n",
|
| 294 |
+
"empty_name_frac = (train_s1[\"name_clean\"] == \"\").mean()\n",
|
| 295 |
+
"assert empty_name_frac < 0.01, \"Error: Transliteration produced excessive empty strings!\"\n"
|
| 296 |
+
],
|
| 297 |
+
"execution_count": null,
|
| 298 |
+
"outputs": []
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"cell_type": "markdown",
|
| 302 |
+
"id": "8a2f4922",
|
| 303 |
+
"metadata": {},
|
| 304 |
+
"source": [
|
| 305 |
+
"## 4. Multi-View DuckDB Blocking (Fixed & Optimized)\n",
|
| 306 |
+
"Key fixes implemented:\n",
|
| 307 |
+
"- **Combined Targets**: Both Source 2 and Source 3 targets are registered together into `targets_tmp` (eliminating the bug where Source 2 was overwritten).\n",
|
| 308 |
+
"- **Index-Once Architecture**: Target keys and frequency caps are generated **once per country**, completely removing the 17x redundant inner loop computation.\n",
|
| 309 |
+
"- **Top-K Candidate Selection**: Keeps Top-K (35) candidates per S1 entity.\n"
|
| 310 |
+
]
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"cell_type": "code",
|
| 314 |
+
"id": "e2984698",
|
| 315 |
+
"metadata": {},
|
| 316 |
+
"source": [
|
| 317 |
+
"con = duckdb.connect()\n",
|
| 318 |
+
"con.execute(\"PRAGMA threads=8;\")\n",
|
| 319 |
+
"con.execute(\"PRAGMA max_memory='12GB';\")\n",
|
| 320 |
+
"con.execute(f\"PRAGMA temp_directory='{CACHE_DIR}/duckdb_spill';\")\n",
|
| 321 |
+
"\n",
|
| 322 |
+
"def generate_keys_sql(alias):\n",
|
| 323 |
+
" return f\"\"\"\n",
|
| 324 |
+
" SELECT entity_id, 'p5:' || substr(name_compact, 1, 5) AS key FROM {alias} WHERE length(name_compact) >= 5\n",
|
| 325 |
+
" UNION ALL\n",
|
| 326 |
+
" SELECT entity_id, 'nt:' || tok AS key\n",
|
| 327 |
+
" FROM (SELECT entity_id, unnest(string_split(name_clean, ' ')) AS tok FROM {alias})\n",
|
| 328 |
+
" WHERE length(tok) >= 3\n",
|
| 329 |
+
" UNION ALL\n",
|
| 330 |
+
" SELECT entity_id, 'nb:' || toks[1] || '_' || toks[2] AS key\n",
|
| 331 |
+
" FROM (SELECT entity_id, string_split(name_clean, ' ') AS toks FROM {alias})\n",
|
| 332 |
+
" WHERE len(toks) >= 2 AND length(toks[1]) >= 3 AND length(toks[2]) >= 3\n",
|
| 333 |
+
" UNION ALL\n",
|
| 334 |
+
" SELECT entity_id, 'np:' || substr(toks[1],1,3) || '_' || substr(toks[2],1,3) AS key\n",
|
| 335 |
+
" FROM (SELECT entity_id, string_split(name_clean, ' ') AS toks FROM {alias})\n",
|
| 336 |
+
" WHERE len(toks) >= 2 AND length(toks[1]) >= 3 AND length(toks[2]) >= 3\n",
|
| 337 |
+
" UNION ALL\n",
|
| 338 |
+
" SELECT entity_id, 'addr_toks:' || tok AS key\n",
|
| 339 |
+
" FROM (SELECT entity_id, unnest(string_split(addr_clean, ' ')) AS tok FROM {alias})\n",
|
| 340 |
+
" WHERE length(tok) >= 4\n",
|
| 341 |
+
" UNION ALL\n",
|
| 342 |
+
" SELECT entity_id, 'pn:' || postal || '_' || substr(name_compact,1,3) AS key\n",
|
| 343 |
+
" FROM {alias} WHERE postal != '' AND length(name_compact) >= 3\n",
|
| 344 |
+
" UNION ALL\n",
|
| 345 |
+
" SELECT entity_id, 'hn:' || house_no || '_' || substr(name_compact,1,3) AS key\n",
|
| 346 |
+
" FROM {alias} WHERE house_no != '' AND length(name_compact) >= 3\n",
|
| 347 |
+
" UNION ALL\n",
|
| 348 |
+
" SELECT entity_id, 'ht:' || house_no || '_' || toks[1] AS key\n",
|
| 349 |
+
" FROM (SELECT entity_id, house_no, string_split(name_clean, ' ') AS toks FROM {alias})\n",
|
| 350 |
+
" WHERE house_no != '' AND len(toks) >= 1 AND length(toks[1]) >= 3\n",
|
| 351 |
+
" \"\"\"\n",
|
| 352 |
+
"\n",
|
| 353 |
+
"def run_blocking_for_country(s1_country_df, targets_country_df, country, freq_cap, top_k, batch_size=50_000):\n",
|
| 354 |
+
" \"\"\"Extracts target keys ONCE, then streams S1 batches for candidate joining.\"\"\"\n",
|
| 355 |
+
" if len(s1_country_df) == 0:\n",
|
| 356 |
+
" return pd.DataFrame(columns=[\"s1_id\", \"target_id\", \"key_hits\"])\n",
|
| 357 |
+
"\n",
|
| 358 |
+
" t_start = time.time()\n",
|
| 359 |
+
" print(f\"\\n--- [Blocking {country}] S1: {len(s1_country_df):,}, Combined Targets: {len(targets_country_df):,} ---\")\n",
|
| 360 |
+
" \n",
|
| 361 |
+
" con.register(\"targets_country\", targets_country_df)\n",
|
| 362 |
+
" tgt_sql = generate_keys_sql(\"targets_country\")\n",
|
| 363 |
+
" con.execute(f\"CREATE OR REPLACE TEMP TABLE target_keys AS {tgt_sql}\")\n",
|
| 364 |
+
" \n",
|
| 365 |
+
" # Calculate key frequencies once\n",
|
| 366 |
+
" con.execute(f\"\"\"\n",
|
| 367 |
+
" CREATE OR REPLACE TEMP TABLE key_freq AS\n",
|
| 368 |
+
" SELECT key, count(*) AS n FROM target_keys GROUP BY key\n",
|
| 369 |
+
" \"\"\")\n",
|
| 370 |
+
" con.execute(f\"\"\"\n",
|
| 371 |
+
" CREATE OR REPLACE TEMP TABLE filtered_target_keys AS\n",
|
| 372 |
+
" SELECT t.entity_id, t.key\n",
|
| 373 |
+
" FROM target_keys t\n",
|
| 374 |
+
" JOIN key_freq f ON t.key = f.key AND f.n <= {freq_cap}\n",
|
| 375 |
+
" \"\"\")\n",
|
| 376 |
+
" con.execute(\"CREATE INDEX IF NOT EXISTS ftk_idx ON filtered_target_keys(key);\")\n",
|
| 377 |
+
"\n",
|
| 378 |
+
" n_batches = (len(s1_country_df) + batch_size - 1) // batch_size\n",
|
| 379 |
+
" candidates_list = []\n",
|
| 380 |
+
"\n",
|
| 381 |
+
" for b in range(n_batches):\n",
|
| 382 |
+
" s1_batch = s1_country_df.iloc[b * batch_size : (b + 1) * batch_size]\n",
|
| 383 |
+
" con.register(\"s1_batch\", s1_batch)\n",
|
| 384 |
+
" s1_sql = generate_keys_sql(\"s1_batch\")\n",
|
| 385 |
+
" con.execute(f\"CREATE OR REPLACE TEMP TABLE s1_batch_keys AS {s1_sql}\")\n",
|
| 386 |
+
"\n",
|
| 387 |
+
" joined = con.execute(f\"\"\"\n",
|
| 388 |
+
" WITH pair_hits AS (\n",
|
| 389 |
+
" SELECT s.entity_id AS s1_id, t.entity_id AS target_id, count(*) AS key_hits\n",
|
| 390 |
+
" FROM s1_batch_keys s\n",
|
| 391 |
+
" JOIN filtered_target_keys t ON s.key = t.key\n",
|
| 392 |
+
" GROUP BY 1, 2\n",
|
| 393 |
+
" ),\n",
|
| 394 |
+
" ranked AS (\n",
|
| 395 |
+
" SELECT s1_id, target_id, key_hits,\n",
|
| 396 |
+
" row_number() OVER(PARTITION BY s1_id ORDER BY key_hits DESC, target_id) AS rank\n",
|
| 397 |
+
" FROM pair_hits\n",
|
| 398 |
+
" )\n",
|
| 399 |
+
" SELECT s1_id, target_id, key_hits\n",
|
| 400 |
+
" FROM ranked\n",
|
| 401 |
+
" WHERE rank <= {top_k};\n",
|
| 402 |
+
" \"\"\").fetchdf()\n",
|
| 403 |
+
"\n",
|
| 404 |
+
" con.unregister(\"s1_batch\")\n",
|
| 405 |
+
" candidates_list.append(joined)\n",
|
| 406 |
+
" print(f\" Batch {b+1}/{n_batches}: {len(s1_batch):,} S1 -> {len(joined):,} candidate pairs\")\n",
|
| 407 |
+
"\n",
|
| 408 |
+
" con.unregister(\"targets_country\")\n",
|
| 409 |
+
" result = pd.concat(candidates_list, ignore_index=True) if candidates_list else pd.DataFrame(columns=[\"s1_id\", \"target_id\", \"key_hits\"])\n",
|
| 410 |
+
" print(f\"Country {country} finished in {time.time()-t_start:.1f}s. Total candidate pairs: {len(result):,}\")\n",
|
| 411 |
+
" return result\n"
|
| 412 |
+
],
|
| 413 |
+
"execution_count": null,
|
| 414 |
+
"outputs": []
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"cell_type": "markdown",
|
| 418 |
+
"id": "c4385c2d",
|
| 419 |
+
"metadata": {},
|
| 420 |
+
"source": [
|
| 421 |
+
"## 4.1 Run Blocking on Training Set\n",
|
| 422 |
+
"We normalize S2 and S3 per-country on demand to ensure lean memory usage.\n"
|
| 423 |
+
]
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"cell_type": "code",
|
| 427 |
+
"id": "ec3db4dc",
|
| 428 |
+
"metadata": {},
|
| 429 |
+
"source": [
|
| 430 |
+
"countries = train_s1[\"country\"].unique().tolist()\n",
|
| 431 |
+
"candidate_frames = []\n",
|
| 432 |
+
"\n",
|
| 433 |
+
"for ctry in countries:\n",
|
| 434 |
+
" cap = FREQ_CAP_FRANCE if ctry == \"France\" else FREQ_CAP_DEFAULT\n",
|
| 435 |
+
" \n",
|
| 436 |
+
" # Filter S2 and S3 for this country and normalize on demand\n",
|
| 437 |
+
" s1_c = train_s1[train_s1[\"country\"] == ctry]\n",
|
| 438 |
+
" s2_c = add_normalized_columns(train_s2[train_s2[\"country\"] == ctry])\n",
|
| 439 |
+
" s3_c = add_normalized_columns(train_s3[train_s3[\"country\"] == ctry])\n",
|
| 440 |
+
" targets_c = pd.concat([s2_c, s3_c], ignore_index=True)\n",
|
| 441 |
+
"\n",
|
| 442 |
+
" cands = run_blocking_for_country(s1_c, targets_c, ctry, cap, TOP_K_CANDIDATES)\n",
|
| 443 |
+
" candidate_frames.append(cands)\n",
|
| 444 |
+
" del s2_c, s3_c, targets_c\n",
|
| 445 |
+
" gc.collect()\n",
|
| 446 |
+
"\n",
|
| 447 |
+
"candidate_pairs = pd.concat(candidate_frames, ignore_index=True)\n",
|
| 448 |
+
"print(f\"\\n>>> Total Training Candidate Pairs Generated: {len(candidate_pairs):,} <<<\")\n"
|
| 449 |
+
],
|
| 450 |
+
"execution_count": null,
|
| 451 |
+
"outputs": []
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"cell_type": "markdown",
|
| 455 |
+
"id": "56b67ec4",
|
| 456 |
+
"metadata": {},
|
| 457 |
+
"source": [
|
| 458 |
+
"## 5. Mandatory Blocking Recall Ceiling Diagnostic\n",
|
| 459 |
+
"Verifies the true candidate recall ceiling before model training.\n",
|
| 460 |
+
"Any silent failure in blocking will be detected here immediately.\n"
|
| 461 |
+
]
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"cell_type": "code",
|
| 465 |
+
"id": "84946a80",
|
| 466 |
+
"metadata": {},
|
| 467 |
+
"source": [
|
| 468 |
+
"def measure_blocking_recall(candidate_df, gt_df):\n",
|
| 469 |
+
" gt_pairs = set()\n",
|
| 470 |
+
" for _, row in gt_df.iterrows():\n",
|
| 471 |
+
" s1 = row[\"source1_entity_id\"]\n",
|
| 472 |
+
" matched = str(row.get(\"matched_entity_ids\", \"\") or \"\").strip()\n",
|
| 473 |
+
" if matched and matched != \"nan\":\n",
|
| 474 |
+
" for tid in matched.split(\",\"):\n",
|
| 475 |
+
" tid_clean = tid.strip()\n",
|
| 476 |
+
" if tid_clean:\n",
|
| 477 |
+
" gt_pairs.add((s1, tid_clean))\n",
|
| 478 |
+
"\n",
|
| 479 |
+
" cand_set = set(zip(candidate_df[\"s1_id\"], candidate_df[\"target_id\"]))\n",
|
| 480 |
+
" recalled = gt_pairs & cand_set\n",
|
| 481 |
+
"\n",
|
| 482 |
+
" recall = len(recalled) / len(gt_pairs) if gt_pairs else 0.0\n",
|
| 483 |
+
" print(f\"True entity pairs in Ground Truth : {len(gt_pairs):,}\")\n",
|
| 484 |
+
" print(f\"True entity pairs captured by blocking : {len(recalled):,}\")\n",
|
| 485 |
+
" print(f\"BLOCKING RECALL CEILING: {recall:.4%}\")\n",
|
| 486 |
+
" return recall, gt_pairs\n",
|
| 487 |
+
"\n",
|
| 488 |
+
"recall_ceiling, gt_pairs_all = measure_blocking_recall(candidate_pairs, train_gt)\n",
|
| 489 |
+
"assert recall_ceiling >= 0.85, f\"Recall ceiling {recall_ceiling:.2%} is below 85%! Check blocking rules.\"\n",
|
| 490 |
+
"print(\"SUCCESS: Blocking recall check passed!\")\n"
|
| 491 |
+
],
|
| 492 |
+
"execution_count": null,
|
| 493 |
+
"outputs": []
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"cell_type": "markdown",
|
| 497 |
+
"id": "d66d92ba",
|
| 498 |
+
"metadata": {},
|
| 499 |
+
"source": [
|
| 500 |
+
"## 6. Bi-Encoder Neural Embeddings (`Qwen3-Embedding-0.6B`)\n",
|
| 501 |
+
"To fit within Kaggle execution limits:\n",
|
| 502 |
+
"1. **Deduplication to Unique Entities**: Each entity is embedded only **once** and cached by ID.\n",
|
| 503 |
+
"2. **Matryoshka Truncation**: Truncated to 256 dimensions for fast dot-product cosine similarity.\n",
|
| 504 |
+
"3. **Multi-GPU Parallelism**: Automatically leverages `torch.nn.DataParallel` when 2x GPUs are available.\n"
|
| 505 |
+
]
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"cell_type": "code",
|
| 509 |
+
"id": "a88c001c",
|
| 510 |
+
"metadata": {},
|
| 511 |
+
"source": [
|
| 512 |
+
"from transformers import AutoTokenizer, AutoModel\n",
|
| 513 |
+
"\n",
|
| 514 |
+
"class EntityEmbedder:\n",
|
| 515 |
+
" def __init__(self, model_name=\"Qwen/Qwen3-Embedding-0.6B\", embed_dim=256, max_len=64):\n",
|
| 516 |
+
" self.model_name = model_name\n",
|
| 517 |
+
" self.embed_dim = embed_dim\n",
|
| 518 |
+
" self.max_len = max_len\n",
|
| 519 |
+
" self.embed_cache = {}\n",
|
| 520 |
+
" \n",
|
| 521 |
+
" print(f\"Loading tokenizer and model: {model_name}...\")\n",
|
| 522 |
+
" self.tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)\n",
|
| 523 |
+
" self.model = AutoModel.from_pretrained(model_name, torch_dtype=torch.float16, trust_remote_code=True)\n",
|
| 524 |
+
" \n",
|
| 525 |
+
" if torch.cuda.device_count() > 1:\n",
|
| 526 |
+
" print(f\"Using DataParallel across {torch.cuda.device_count()} GPUs\")\n",
|
| 527 |
+
" self.model = nn.DataParallel(self.model)\n",
|
| 528 |
+
" \n",
|
| 529 |
+
" self.model = self.model.to(device).eval()\n",
|
| 530 |
+
" print(\"Embedder ready.\")\n",
|
| 531 |
+
"\n",
|
| 532 |
+
" def format_record(self, name, addr, country):\n",
|
| 533 |
+
" return f\"Business name: {name} | Address: {addr} | Country: {country}\"\n",
|
| 534 |
+
"\n",
|
| 535 |
+
" @torch.inference_mode()\n",
|
| 536 |
+
" def embed_entities(self, df_entities, batch_size=256 if torch.cuda.device_count() >= 2 else 64):\n",
|
| 537 |
+
" \"\"\"Embeds unique entities that are not already present in the cache.\"\"\"\n",
|
| 538 |
+
" new_entities = df_entities[~df_entities[\"entity_id\"].isin(self.embed_cache)].drop_duplicates(subset=\"entity_id\")\n",
|
| 539 |
+
" if len(new_entities) == 0:\n",
|
| 540 |
+
" return\n",
|
| 541 |
+
"\n",
|
| 542 |
+
" texts = [self.format_record(r.name_clean, r.addr_clean, r.country) for r in new_entities.itertuples()]\n",
|
| 543 |
+
" e_ids = new_entities[\"entity_id\"].tolist()\n",
|
| 544 |
+
" \n",
|
| 545 |
+
" print(f\"Embedding {len(texts):,} new unique entities...\")\n",
|
| 546 |
+
" t0 = time.time()\n",
|
| 547 |
+
" \n",
|
| 548 |
+
" for i in range(0, len(texts), batch_size):\n",
|
| 549 |
+
" b_texts = texts[i : i + batch_size]\n",
|
| 550 |
+
" b_ids = e_ids[i : i + batch_size]\n",
|
| 551 |
+
" \n",
|
| 552 |
+
" enc = self.tokenizer(b_texts, padding=True, truncation=True, max_length=self.max_len, return_tensors=\"pt\").to(device)\n",
|
| 553 |
+
" out = self.model(**enc)\n",
|
| 554 |
+
" last_hidden = out.last_hidden_state if hasattr(out, \"last_hidden_state\") else out[0]\n",
|
| 555 |
+
" mask = enc[\"attention_mask\"].unsqueeze(-1).float()\n",
|
| 556 |
+
" pooled = (last_hidden * mask).sum(1) / mask.sum(1).clamp(min=1e-9)\n",
|
| 557 |
+
" pooled = pooled[:, :self.embed_dim]\n",
|
| 558 |
+
" pooled = F.normalize(pooled, p=2, dim=1)\n",
|
| 559 |
+
" \n",
|
| 560 |
+
" vecs = pooled.float().cpu().numpy()\n",
|
| 561 |
+
" for eid, v in zip(b_ids, vecs):\n",
|
| 562 |
+
" self.embed_cache[eid] = v\n",
|
| 563 |
+
"\n",
|
| 564 |
+
" if (i // batch_size) % 100 == 0 and i > 0:\n",
|
| 565 |
+
" rate = i / max(time.time() - t0, 1e-9)\n",
|
| 566 |
+
" print(f\" Progress: {i:,}/{len(texts):,} ({rate:.0f} entities/s)\")\n",
|
| 567 |
+
" \n",
|
| 568 |
+
" print(f\"Completed in {time.time()-t0:.1f}s. Total cached entities: {len(self.embed_cache):,}\")\n",
|
| 569 |
+
"\n",
|
| 570 |
+
" def compute_cosine_similarity(self, s1_ids, target_ids):\n",
|
| 571 |
+
" \"\"\"Fast dot product lookup between cached L2-normalized embeddings.\"\"\"\n",
|
| 572 |
+
" s1_vecs = np.stack([self.embed_cache[i] for i in s1_ids])\n",
|
| 573 |
+
" tgt_vecs = np.stack([self.embed_cache[i] for i in target_ids])\n",
|
| 574 |
+
" return (s1_vecs * tgt_vecs).sum(axis=1)\n",
|
| 575 |
+
"\n",
|
| 576 |
+
"embedder = EntityEmbedder()\n"
|
| 577 |
+
],
|
| 578 |
+
"execution_count": null,
|
| 579 |
+
"outputs": []
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"cell_type": "markdown",
|
| 583 |
+
"id": "8e504ee9",
|
| 584 |
+
"metadata": {},
|
| 585 |
+
"source": [
|
| 586 |
+
"## 7. Fast Feature Extraction\n",
|
| 587 |
+
"Combines lexical similarity signals (RapidFuzz), structural signals (House/Postal match),\n",
|
| 588 |
+
"blocking frequency (`key_hits`), and the neural semantic similarity (`qwen_cosine_sim`).\n",
|
| 589 |
+
"Processed in batches to guarantee zero OOM risk.\n"
|
| 590 |
+
]
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"cell_type": "code",
|
| 594 |
+
"id": "da83c2f1",
|
| 595 |
+
"metadata": {},
|
| 596 |
+
"source": [
|
| 597 |
+
"from rapidfuzz import fuzz\n",
|
| 598 |
+
"\n",
|
| 599 |
+
"def extract_features_batched(candidate_df, s1_lookup_df, target_lookup_df, embedder, batch_size=100_000):\n",
|
| 600 |
+
" \"\"\"Extracts features in chunks to prevent large intermediate DataFrame allocations.\"\"\"\n",
|
| 601 |
+
" s1_dict = s1_lookup_df.set_index(\"entity_id\")[[\"name_clean\", \"name_root\", \"addr_clean\", \"house_no\", \"postal\", \"country\"]].to_dict(\"index\")\n",
|
| 602 |
+
" tgt_dict = target_lookup_df.set_index(\"entity_id\")[[\"name_clean\", \"name_root\", \"addr_clean\", \"house_no\", \"postal\", \"country\"]].to_dict(\"index\")\n",
|
| 603 |
+
"\n",
|
| 604 |
+
" # Prepare embedding universe\n",
|
| 605 |
+
" needed_eids = list(set(candidate_df[\"s1_id\"]) | set(candidate_df[\"target_id\"]))\n",
|
| 606 |
+
" missing_eids = [eid for eid in needed_eids if eid not in embedder.embed_cache]\n",
|
| 607 |
+
" if missing_eids:\n",
|
| 608 |
+
" records = []\n",
|
| 609 |
+
" for eid in missing_eids:\n",
|
| 610 |
+
" row = s1_dict.get(eid) or tgt_dict.get(eid)\n",
|
| 611 |
+
" if row:\n",
|
| 612 |
+
" records.append({\"entity_id\": eid, \"name_clean\": row[\"name_clean\"], \"addr_clean\": row[\"addr_clean\"], \"country\": row[\"country\"]})\n",
|
| 613 |
+
" if records:\n",
|
| 614 |
+
" embedder.embed_entities(pd.DataFrame(records))\n",
|
| 615 |
+
"\n",
|
| 616 |
+
" feature_chunks = []\n",
|
| 617 |
+
" n_chunks = (len(candidate_df) + batch_size - 1) // batch_size\n",
|
| 618 |
+
" print(f\"Extracting features for {len(candidate_df):,} pairs in {n_chunks} chunks...\")\n",
|
| 619 |
+
"\n",
|
| 620 |
+
" for i in range(n_chunks):\n",
|
| 621 |
+
" chunk = candidate_df.iloc[i * batch_size : (i + 1) * batch_size]\n",
|
| 622 |
+
" s1_ids = chunk[\"s1_id\"].tolist()\n",
|
| 623 |
+
" tgt_ids = chunk[\"target_id\"].tolist()\n",
|
| 624 |
+
"\n",
|
| 625 |
+
" qwen_sim = embedder.compute_cosine_similarity(s1_ids, tgt_ids)\n",
|
| 626 |
+
"\n",
|
| 627 |
+
" name_ratios, name_tsorts, name_tsets, name_partials, root_ratios = [], [], [], [], []\n",
|
| 628 |
+
" addr_ratios, addr_tsorts, addr_tsets, addr_partials = [], [], [], []\n",
|
| 629 |
+
" house_matches, postal_matches, postal_conflicts = [], [], []\n",
|
| 630 |
+
"\n",
|
| 631 |
+
" for s, t in zip(s1_ids, tgt_ids):\n",
|
| 632 |
+
" s_row = s1_dict[s]\n",
|
| 633 |
+
" t_row = tgt_dict[t]\n",
|
| 634 |
+
"\n",
|
| 635 |
+
" sn, tn = s_row[\"name_clean\"], t_row[\"name_clean\"]\n",
|
| 636 |
+
" sa, ta = s_row[\"addr_clean\"], t_row[\"addr_clean\"]\n",
|
| 637 |
+
" sr, tr = s_row[\"name_root\"], t_row[\"name_root\"]\n",
|
| 638 |
+
"\n",
|
| 639 |
+
" name_ratios.append(fuzz.ratio(sn, tn))\n",
|
| 640 |
+
" name_tsorts.append(fuzz.token_sort_ratio(sn, tn))\n",
|
| 641 |
+
" name_tsets.append(fuzz.token_set_ratio(sn, tn))\n",
|
| 642 |
+
" name_partials.append(fuzz.partial_ratio(sn, tn))\n",
|
| 643 |
+
" root_ratios.append(fuzz.ratio(sr, tr))\n",
|
| 644 |
+
"\n",
|
| 645 |
+
" addr_ratios.append(fuzz.ratio(sa, ta))\n",
|
| 646 |
+
" addr_tsorts.append(fuzz.token_sort_ratio(sa, ta))\n",
|
| 647 |
+
" addr_tsets.append(fuzz.token_set_ratio(sa, ta))\n",
|
| 648 |
+
" addr_partials.append(fuzz.partial_ratio(sa, ta))\n",
|
| 649 |
+
"\n",
|
| 650 |
+
" sh, th = s_row[\"house_no\"], t_row[\"house_no\"]\n",
|
| 651 |
+
" sp, tp = s_row[\"postal\"], t_row[\"postal\"]\n",
|
| 652 |
+
"\n",
|
| 653 |
+
" house_matches.append(1 if (sh and th and sh == th) else 0)\n",
|
| 654 |
+
" postal_matches.append(1 if (sp and tp and sp == tp) else 0)\n",
|
| 655 |
+
" postal_conflicts.append(1 if (sp and tp and sp != tp) else 0)\n",
|
| 656 |
+
"\n",
|
| 657 |
+
" df_chunk = pd.DataFrame({\n",
|
| 658 |
+
" \"s1_id\": s1_ids,\n",
|
| 659 |
+
" \"target_id\": tgt_ids,\n",
|
| 660 |
+
" \"key_hits\": chunk[\"key_hits\"].values,\n",
|
| 661 |
+
" \"qwen_cosine_sim\": qwen_sim,\n",
|
| 662 |
+
" \"name_ratio\": name_ratios,\n",
|
| 663 |
+
" \"name_tsort\": name_tsorts,\n",
|
| 664 |
+
" \"name_tset\": name_tsets,\n",
|
| 665 |
+
" \"name_partial\": name_partials,\n",
|
| 666 |
+
" \"root_ratio\": root_ratios,\n",
|
| 667 |
+
" \"addr_ratio\": addr_ratios,\n",
|
| 668 |
+
" \"addr_tsort\": addr_tsorts,\n",
|
| 669 |
+
" \"addr_tset\": addr_tsets,\n",
|
| 670 |
+
" \"addr_partial\": addr_partials,\n",
|
| 671 |
+
" \"house_match\": house_matches,\n",
|
| 672 |
+
" \"postal_match\": postal_matches,\n",
|
| 673 |
+
" \"postal_conflict\": postal_conflicts,\n",
|
| 674 |
+
" })\n",
|
| 675 |
+
" feature_chunks.append(df_chunk)\n",
|
| 676 |
+
"\n",
|
| 677 |
+
" return pd.concat(feature_chunks, ignore_index=True)\n",
|
| 678 |
+
"\n",
|
| 679 |
+
"# Prepare combined target reference\n",
|
| 680 |
+
"targets_all_norm = pd.concat([\n",
|
| 681 |
+
" add_normalized_columns(train_s2[train_s2[\"entity_id\"].isin(set(candidate_pairs[\"target_id\"]))]),\n",
|
| 682 |
+
" add_normalized_columns(train_s3[train_s3[\"entity_id\"].isin(set(candidate_pairs[\"target_id\"]))]),\n",
|
| 683 |
+
"], ignore_index=True).drop_duplicates(subset=\"entity_id\")\n",
|
| 684 |
+
"\n",
|
| 685 |
+
"training_features = extract_features_batched(candidate_pairs, train_s1, targets_all_norm, embedder)\n",
|
| 686 |
+
"print(\"Extracted training features shape:\", training_features.shape)\n"
|
| 687 |
+
],
|
| 688 |
+
"execution_count": null,
|
| 689 |
+
"outputs": []
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"cell_type": "markdown",
|
| 693 |
+
"id": "52e4f748",
|
| 694 |
+
"metadata": {},
|
| 695 |
+
"source": [
|
| 696 |
+
"## 8. LightGBM Classifier & Corrected Cross-Validation\n",
|
| 697 |
+
"Key Fix: `macro_f05` evaluates **only** the entities present in the current validation fold / country,\n",
|
| 698 |
+
"eliminating the 5x score suppression bug.\n"
|
| 699 |
+
]
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"cell_type": "code",
|
| 703 |
+
"id": "a4b8b502",
|
| 704 |
+
"metadata": {},
|
| 705 |
+
"source": [
|
| 706 |
+
"import lightgbm as lgb\n",
|
| 707 |
+
"from sklearn.model_selection import GroupKFold\n",
|
| 708 |
+
"\n",
|
| 709 |
+
"# Build labels\n",
|
| 710 |
+
"gt_lookup = defaultdict(set)\n",
|
| 711 |
+
"for _, row in train_gt.iterrows():\n",
|
| 712 |
+
" s1 = row[\"source1_entity_id\"]\n",
|
| 713 |
+
" m = str(row.get(\"matched_entity_ids\", \"\") or \"\").strip()\n",
|
| 714 |
+
" if m and m != \"nan\":\n",
|
| 715 |
+
" for t in m.split(\",\"):\n",
|
| 716 |
+
" gt_lookup[s1].add(t.strip())\n",
|
| 717 |
+
"\n",
|
| 718 |
+
"training_features[\"label\"] = [\n",
|
| 719 |
+
" 1 if t in gt_lookup[s] else 0\n",
|
| 720 |
+
" for s, t in zip(training_features[\"s1_id\"], training_features[\"target_id\"])\n",
|
| 721 |
+
"]\n",
|
| 722 |
+
"\n",
|
| 723 |
+
"FEATURE_COLS = [c for c in training_features.columns if c not in (\"s1_id\", \"target_id\", \"label\")]\n",
|
| 724 |
+
"X = training_features[FEATURE_COLS].astype(float)\n",
|
| 725 |
+
"y = training_features[\"label\"].values\n",
|
| 726 |
+
"groups = training_features[\"s1_id\"].values\n",
|
| 727 |
+
"\n",
|
| 728 |
+
"n_pos, n_neg = (y == 1).sum(), (y == 0).sum()\n",
|
| 729 |
+
"scale_pos_weight = n_neg / max(n_pos, 1)\n",
|
| 730 |
+
"print(f\"Positives: {n_pos:,} | Negatives: {n_neg:,} | scale_pos_weight: {scale_pos_weight:.2f}\")\n",
|
| 731 |
+
"\n",
|
| 732 |
+
"def evaluate_macro_f05(eval_s1_ids, cand_s1_ids, cand_target_ids, probs, threshold, gt_map):\n",
|
| 733 |
+
" \"\"\"Accurately computes Macro F0.5 strictly for the specified eval_s1_ids.\"\"\"\n",
|
| 734 |
+
" preds = defaultdict(set)\n",
|
| 735 |
+
" for s, t, p in zip(cand_s1_ids, cand_target_ids, probs):\n",
|
| 736 |
+
" if p >= threshold:\n",
|
| 737 |
+
" preds[s].add(t)\n",
|
| 738 |
+
"\n",
|
| 739 |
+
" scores = []\n",
|
| 740 |
+
" for s in eval_s1_ids:\n",
|
| 741 |
+
" pred_set = preds.get(s, set())\n",
|
| 742 |
+
" true_set = gt_map.get(s, set())\n",
|
| 743 |
+
" if not pred_set and not true_set:\n",
|
| 744 |
+
" scores.append(1.0)\n",
|
| 745 |
+
" continue\n",
|
| 746 |
+
" tp = len(pred_set & true_set)\n",
|
| 747 |
+
" prec = tp / len(pred_set) if pred_set else 0.0\n",
|
| 748 |
+
" rec = tp / len(true_set) if true_set else 0.0\n",
|
| 749 |
+
" if (0.25 * prec + rec) > 0:\n",
|
| 750 |
+
" f05 = (1.25 * prec * rec) / (0.25 * prec + rec)\n",
|
| 751 |
+
" else:\n",
|
| 752 |
+
" f05 = 0.0\n",
|
| 753 |
+
" scores.append(f05)\n",
|
| 754 |
+
" return float(np.mean(scores))\n",
|
| 755 |
+
"\n",
|
| 756 |
+
"gkf = GroupKFold(n_splits=5)\n",
|
| 757 |
+
"oof_pred = np.zeros(len(X))\n",
|
| 758 |
+
"fold_scores = []\n",
|
| 759 |
+
"\n",
|
| 760 |
+
"for fold, (train_idx, val_idx) in enumerate(gkf.split(X, y, groups)):\n",
|
| 761 |
+
" train_set = lgb.Dataset(X.iloc[train_idx], label=y[train_idx])\n",
|
| 762 |
+
" val_set = lgb.Dataset(X.iloc[val_idx], label=y[val_idx])\n",
|
| 763 |
+
" \n",
|
| 764 |
+
" params = dict(\n",
|
| 765 |
+
" objective=\"binary\",\n",
|
| 766 |
+
" metric=\"binary_logloss\",\n",
|
| 767 |
+
" scale_pos_weight=scale_pos_weight,\n",
|
| 768 |
+
" num_leaves=63,\n",
|
| 769 |
+
" learning_rate=0.05,\n",
|
| 770 |
+
" n_estimators=500,\n",
|
| 771 |
+
" n_jobs=-1,\n",
|
| 772 |
+
" verbosity=-1\n",
|
| 773 |
+
" )\n",
|
| 774 |
+
" booster = lgb.train(\n",
|
| 775 |
+
" params, train_set, valid_sets=[val_set],\n",
|
| 776 |
+
" callbacks=[lgb.early_stopping(30, verbose=False)]\n",
|
| 777 |
+
" )\n",
|
| 778 |
+
" val_probs = booster.predict(X.iloc[val_idx])\n",
|
| 779 |
+
" oof_pred[val_idx] = val_probs\n",
|
| 780 |
+
"\n",
|
| 781 |
+
" val_s1 = set(groups[val_idx])\n",
|
| 782 |
+
" f05 = evaluate_macro_f05(val_s1, groups[val_idx], training_features[\"target_id\"].values[val_idx], val_probs, 0.50, gt_lookup)\n",
|
| 783 |
+
" fold_scores.append(f05)\n",
|
| 784 |
+
" print(f\"Fold {fold+1}: Macro F0.5 @ 0.50 = {f05:.4f}\")\n",
|
| 785 |
+
"\n",
|
| 786 |
+
"print(f\"\\n>>> 5-Fold Mean Macro F0.5: {np.mean(fold_scores):.4f} +/- {np.std(fold_scores):.4f} <<<\")\n"
|
| 787 |
+
],
|
| 788 |
+
"execution_count": null,
|
| 789 |
+
"outputs": []
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"cell_type": "markdown",
|
| 793 |
+
"id": "3e8638ca",
|
| 794 |
+
"metadata": {},
|
| 795 |
+
"source": [
|
| 796 |
+
"## 9. Per-Country Threshold Sweeping\n",
|
| 797 |
+
"Optimizes decision thresholds individually for France, US, and India on the OOF predictions.\n"
|
| 798 |
+
]
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"cell_type": "code",
|
| 802 |
+
"id": "455def1b",
|
| 803 |
+
"metadata": {},
|
| 804 |
+
"source": [
|
| 805 |
+
"s1_country_map = train_s1.set_index(\"entity_id\")[\"country\"].to_dict()\n",
|
| 806 |
+
"candidate_countries = np.array([s1_country_map[s] for s in groups])\n",
|
| 807 |
+
"\n",
|
| 808 |
+
"per_country_threshold = {}\n",
|
| 809 |
+
"for ctry in np.unique(candidate_countries):\n",
|
| 810 |
+
" mask = candidate_countries == ctry\n",
|
| 811 |
+
" ctry_s1 = set(groups[mask])\n",
|
| 812 |
+
" \n",
|
| 813 |
+
" best_t, best_score = 0.50, -1.0\n",
|
| 814 |
+
" for t in np.arange(0.30, 0.951, 0.02):\n",
|
| 815 |
+
" score = evaluate_macro_f05(\n",
|
| 816 |
+
" ctry_s1,\n",
|
| 817 |
+
" groups[mask],\n",
|
| 818 |
+
" training_features[\"target_id\"].values[mask],\n",
|
| 819 |
+
" oof_pred[mask],\n",
|
| 820 |
+
" t,\n",
|
| 821 |
+
" gt_lookup\n",
|
| 822 |
+
" )\n",
|
| 823 |
+
" if score > best_score:\n",
|
| 824 |
+
" best_score, best_t = score, t\n",
|
| 825 |
+
" \n",
|
| 826 |
+
" per_country_threshold[ctry] = round(float(best_t), 2)\n",
|
| 827 |
+
" print(f\"Country [{ctry}]: Optimal Threshold = {best_t:.2f} (Macro F0.5 = {best_score:.4f})\")\n",
|
| 828 |
+
"\n",
|
| 829 |
+
"per_country_threshold[\"__default__\"] = 0.50\n",
|
| 830 |
+
"print(\"\\nConfigured Decision Thresholds:\", per_country_threshold)\n"
|
| 831 |
+
],
|
| 832 |
+
"execution_count": null,
|
| 833 |
+
"outputs": []
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"cell_type": "markdown",
|
| 837 |
+
"id": "806a7056",
|
| 838 |
+
"metadata": {},
|
| 839 |
+
"source": [
|
| 840 |
+
"## 10. Final Model Training & Artifact Persistence\n"
|
| 841 |
+
]
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"cell_type": "code",
|
| 845 |
+
"id": "f3f967cb",
|
| 846 |
+
"metadata": {},
|
| 847 |
+
"source": [
|
| 848 |
+
"full_train_set = lgb.Dataset(X, label=y)\n",
|
| 849 |
+
"final_params = dict(\n",
|
| 850 |
+
" objective=\"binary\",\n",
|
| 851 |
+
" metric=\"binary_logloss\",\n",
|
| 852 |
+
" scale_pos_weight=scale_pos_weight,\n",
|
| 853 |
+
" num_leaves=63,\n",
|
| 854 |
+
" learning_rate=0.05,\n",
|
| 855 |
+
" n_estimators=500,\n",
|
| 856 |
+
" n_jobs=-1,\n",
|
| 857 |
+
" verbosity=-1\n",
|
| 858 |
+
")\n",
|
| 859 |
+
"final_model = lgb.train(final_params, full_train_set)\n",
|
| 860 |
+
"final_model.save_model(str(CACHE_DIR / \"model.lgb\"))\n",
|
| 861 |
+
"\n",
|
| 862 |
+
"with open(CACHE_DIR / \"model_meta.json\", \"w\") as f:\n",
|
| 863 |
+
" json.dump({\n",
|
| 864 |
+
" \"feature_cols\": FEATURE_COLS,\n",
|
| 865 |
+
" \"per_country_threshold\": per_country_threshold,\n",
|
| 866 |
+
" \"scale_pos_weight\": float(scale_pos_weight)\n",
|
| 867 |
+
" }, f, indent=2)\n",
|
| 868 |
+
"\n",
|
| 869 |
+
"print(\"Saved final model and metadata to\", CACHE_DIR)\n"
|
| 870 |
+
],
|
| 871 |
+
"execution_count": null,
|
| 872 |
+
"outputs": []
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"cell_type": "markdown",
|
| 876 |
+
"id": "6d3e876d",
|
| 877 |
+
"metadata": {},
|
| 878 |
+
"source": [
|
| 879 |
+
"## 11. Full End-to-End Test Set Inference\n",
|
| 880 |
+
"Executes multi-view blocking, Qwen bi-encoder neural embeddings, and feature extraction\n",
|
| 881 |
+
"across `test_source1`, `test_source2`, and `test_source3`.\n"
|
| 882 |
+
]
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"cell_type": "code",
|
| 886 |
+
"id": "a35939da",
|
| 887 |
+
"metadata": {},
|
| 888 |
+
"source": [
|
| 889 |
+
"print(\"Loading test tables...\")\n",
|
| 890 |
+
"test_s1 = load_tsv(\"test_source1.tsv\")\n",
|
| 891 |
+
"test_s2 = load_tsv(\"test_source2.tsv\")\n",
|
| 892 |
+
"test_s3 = load_tsv(\"test_source3.tsv\")\n",
|
| 893 |
+
"\n",
|
| 894 |
+
"print(\"Normalizing test_s1...\")\n",
|
| 895 |
+
"test_s1 = add_normalized_columns(test_s1)\n",
|
| 896 |
+
"\n",
|
| 897 |
+
"test_candidate_frames = []\n",
|
| 898 |
+
"for ctry in test_s1[\"country\"].unique():\n",
|
| 899 |
+
" cap = FREQ_CAP_FRANCE if ctry == \"France\" else FREQ_CAP_DEFAULT\n",
|
| 900 |
+
" s1_c = test_s1[test_s1[\"country\"] == ctry]\n",
|
| 901 |
+
" s2_c = add_normalized_columns(test_s2[test_s2[\"country\"] == ctry])\n",
|
| 902 |
+
" s3_c = add_normalized_columns(test_s3[test_s3[\"country\"] == ctry])\n",
|
| 903 |
+
" targets_c = pd.concat([s2_c, s3_c], ignore_index=True)\n",
|
| 904 |
+
"\n",
|
| 905 |
+
" cands = run_blocking_for_country(s1_c, targets_c, ctry, cap, TOP_K_CANDIDATES)\n",
|
| 906 |
+
" test_candidate_frames.append(cands)\n",
|
| 907 |
+
" del s2_c, s3_c, targets_c\n",
|
| 908 |
+
" gc.collect()\n",
|
| 909 |
+
"\n",
|
| 910 |
+
"test_candidate_pairs = pd.concat(test_candidate_frames, ignore_index=True)\n",
|
| 911 |
+
"print(f\"\\nTotal Test Candidate Pairs: {len(test_candidate_pairs):,}\")\n",
|
| 912 |
+
"\n",
|
| 913 |
+
"# Prepare test targets reference\n",
|
| 914 |
+
"test_needed_targets = set(test_candidate_pairs[\"target_id\"])\n",
|
| 915 |
+
"test_targets_all = pd.concat([\n",
|
| 916 |
+
" add_normalized_columns(test_s2[test_s2[\"entity_id\"].isin(test_needed_targets)]),\n",
|
| 917 |
+
" add_normalized_columns(test_s3[test_s3[\"entity_id\"].isin(test_needed_targets)])\n",
|
| 918 |
+
"], ignore_index=True).drop_duplicates(subset=\"entity_id\")\n",
|
| 919 |
+
"\n",
|
| 920 |
+
"test_features = extract_features_batched(test_candidate_pairs, test_s1, test_targets_all, embedder)\n",
|
| 921 |
+
"\n",
|
| 922 |
+
"# Predict probabilities\n",
|
| 923 |
+
"test_probs = final_model.predict(test_features[FEATURE_COLS].astype(float))\n",
|
| 924 |
+
"test_features[\"prob\"] = test_probs\n",
|
| 925 |
+
"\n",
|
| 926 |
+
"# Apply per-country threshold\n",
|
| 927 |
+
"test_s1_ctry = test_s1.set_index(\"entity_id\")[\"country\"].to_dict()\n",
|
| 928 |
+
"test_features[\"country\"] = test_features[\"s1_id\"].map(test_s1_ctry)\n",
|
| 929 |
+
"test_features[\"threshold\"] = test_features[\"country\"].map(lambda c: per_country_threshold.get(c, per_country_threshold[\"__default__\"]))\n",
|
| 930 |
+
"test_features[\"above_threshold\"] = test_features[\"prob\"] >= test_features[\"threshold\"]\n",
|
| 931 |
+
"\n",
|
| 932 |
+
"n_above = test_features[\"above_threshold\"].sum()\n",
|
| 933 |
+
"print(f\"Candidate pairs above confidence threshold: {n_above:,} ({n_above/len(test_features):.1%})\")\n"
|
| 934 |
+
],
|
| 935 |
+
"execution_count": null,
|
| 936 |
+
"outputs": []
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"cell_type": "markdown",
|
| 940 |
+
"id": "909a5f79",
|
| 941 |
+
"metadata": {},
|
| 942 |
+
"source": [
|
| 943 |
+
"## 12. 1:Many Target-Exclusivity Resolution (Fixed)\n",
|
| 944 |
+
"**Ground Truth Rule**:\n",
|
| 945 |
+
"- Each Target entity belongs to **at most one** S1 entity.\n",
|
| 946 |
+
"- Each S1 entity can belong to **multiple** Target entities (across S2 and S3).\n",
|
| 947 |
+
"\n",
|
| 948 |
+
"We sort candidate pairs above threshold by confidence probability descending, and retain the\n",
|
| 949 |
+
"single highest-confidence S1 entity for every matched target.\n"
|
| 950 |
+
]
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"cell_type": "code",
|
| 954 |
+
"id": "42a24012",
|
| 955 |
+
"metadata": {},
|
| 956 |
+
"source": [
|
| 957 |
+
"candidates_above = test_features[test_features[\"above_threshold\"]][[\"s1_id\", \"target_id\", \"prob\"]]\n",
|
| 958 |
+
"\n",
|
| 959 |
+
"# Resolve 1:Many target exclusivity\n",
|
| 960 |
+
"resolved = (candidates_above\n",
|
| 961 |
+
" .sort_values(\"prob\", ascending=False)\n",
|
| 962 |
+
" .drop_duplicates(subset=[\"target_id\"]))\n",
|
| 963 |
+
"\n",
|
| 964 |
+
"print(f\"Resolved {len(resolved):,} matching links across {resolved['s1_id'].nunique():,} unique S1 entities.\")\n"
|
| 965 |
+
],
|
| 966 |
+
"execution_count": null,
|
| 967 |
+
"outputs": []
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"cell_type": "markdown",
|
| 971 |
+
"id": "3cde9178",
|
| 972 |
+
"metadata": {},
|
| 973 |
+
"source": [
|
| 974 |
+
"## 13. Build Official Submission Files\n",
|
| 975 |
+
"Generates `matching_results.tsv` and `candidate_pairs.tsv` following the exact challenge schema:\n",
|
| 976 |
+
"- Every `test_source1` entity is represented exactly once in `matching_results.tsv`.\n",
|
| 977 |
+
"- Candidate pairs are exported in `candidate_pairs.tsv`.\n"
|
| 978 |
+
]
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"cell_type": "code",
|
| 982 |
+
"id": "38fcf2db",
|
| 983 |
+
"metadata": {},
|
| 984 |
+
"source": [
|
| 985 |
+
"# Build matches map: S1 -> comma-separated sorted targets\n",
|
| 986 |
+
"matches_by_s1 = resolved.groupby(\"s1_id\")[\"target_id\"].apply(lambda ids: \",\".join(sorted(ids))).to_dict()\n",
|
| 987 |
+
"\n",
|
| 988 |
+
"all_test_s1_ids = test_s1[\"entity_id\"].tolist()\n",
|
| 989 |
+
"matching_results = pd.DataFrame({\n",
|
| 990 |
+
" \"source1_entity_id\": all_test_s1_ids,\n",
|
| 991 |
+
" \"matched_entity_ids\": [matches_by_s1.get(sid, \"\") for sid in all_test_s1_ids]\n",
|
| 992 |
+
"})\n",
|
| 993 |
+
"\n",
|
| 994 |
+
"n_singletons = (matching_results[\"matched_entity_ids\"] == \"\").sum()\n",
|
| 995 |
+
"n_matched = len(matching_results) - n_singletons\n",
|
| 996 |
+
"print(f\"Test Entities: {len(matching_results):,}\")\n",
|
| 997 |
+
"print(f\" Singletons (no match): {n_singletons:,} ({n_singletons/len(matching_results):.1%})\")\n",
|
| 998 |
+
"print(f\" Matched Entities : {n_matched:,} ({n_matched/len(matching_results):.1%})\")\n",
|
| 999 |
+
"\n",
|
| 1000 |
+
"assert len(matching_results) == len(all_test_s1_ids), \"Row count mismatch!\"\n",
|
| 1001 |
+
"assert matching_results[\"source1_entity_id\"].is_unique, \"Duplicate S1 rows detected!\"\n",
|
| 1002 |
+
"\n",
|
| 1003 |
+
"# Export matching results\n",
|
| 1004 |
+
"out_match_path = OUTPUT_DIR / \"matching_results.tsv\"\n",
|
| 1005 |
+
"matching_results.to_csv(out_match_path, sep=\"\\t\", index=False)\n",
|
| 1006 |
+
"print(\"Wrote matching_results.tsv to:\", out_match_path)\n",
|
| 1007 |
+
"\n",
|
| 1008 |
+
"# Export candidate pairs\n",
|
| 1009 |
+
"out_cand_path = OUTPUT_DIR / \"candidate_pairs.tsv\"\n",
|
| 1010 |
+
"cand_export = test_candidate_pairs[[\"s1_id\", \"target_id\"]].rename(\n",
|
| 1011 |
+
" columns={\"s1_id\": \"source1_entity_id\", \"target_id\": \"matched_entity_id\"}\n",
|
| 1012 |
+
")\n",
|
| 1013 |
+
"cand_export.to_csv(out_cand_path, sep=\"\\t\", index=False)\n",
|
| 1014 |
+
"print(\"Wrote candidate_pairs.tsv to:\", out_cand_path)\n"
|
| 1015 |
+
],
|
| 1016 |
+
"execution_count": null,
|
| 1017 |
+
"outputs": []
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"cell_type": "markdown",
|
| 1021 |
+
"id": "52a6c3fc",
|
| 1022 |
+
"metadata": {},
|
| 1023 |
+
"source": [
|
| 1024 |
+
"## 14. Run Submission Validator\n",
|
| 1025 |
+
"Executes `utils/validate_submission.py` to confirm total compliance with the competition specification.\n"
|
| 1026 |
+
]
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"cell_type": "code",
|
| 1030 |
+
"id": "bc2c9715",
|
| 1031 |
+
"metadata": {},
|
| 1032 |
+
"source": [
|
| 1033 |
+
"import subprocess\n",
|
| 1034 |
+
"\n",
|
| 1035 |
+
"validator_script = None\n",
|
| 1036 |
+
"for cand in [Path(\"utils/validate_submission.py\"), DATA_DIR / \"utils\" / \"validate_submission.py\"]:\n",
|
| 1037 |
+
" if cand.exists():\n",
|
| 1038 |
+
" validator_script = cand\n",
|
| 1039 |
+
" break\n",
|
| 1040 |
+
"\n",
|
| 1041 |
+
"if validator_script:\n",
|
| 1042 |
+
" test_dir_arg = DATA_DIR if (DATA_DIR / \"test_source1.tsv\").exists() else (DATA_DIR / \"test\")\n",
|
| 1043 |
+
" print(f\"Running official validator using {validator_script}...\")\n",
|
| 1044 |
+
" res = subprocess.run([\n",
|
| 1045 |
+
" sys.executable, str(validator_script),\n",
|
| 1046 |
+
" \"--output_dir\", str(OUTPUT_DIR),\n",
|
| 1047 |
+
" \"--test_dir\", str(test_dir_arg)\n",
|
| 1048 |
+
" ], capture_output=True, text=True)\n",
|
| 1049 |
+
" print(res.stdout)\n",
|
| 1050 |
+
" if res.stderr:\n",
|
| 1051 |
+
" print(res.stderr)\n",
|
| 1052 |
+
" if res.returncode == 0:\n",
|
| 1053 |
+
" print(\"\\n>>> SUBMISSION FULLY VALIDATED AND READY TO SUBMIT! <<<\")\n",
|
| 1054 |
+
" else:\n",
|
| 1055 |
+
" print(\"Validator returned non-zero code. Inspect messages above.\")\n",
|
| 1056 |
+
"else:\n",
|
| 1057 |
+
" print(\"validate_submission.py not found in local path \u2014 verify output files manually.\")\n"
|
| 1058 |
+
],
|
| 1059 |
+
"execution_count": null,
|
| 1060 |
+
"outputs": []
|
| 1061 |
+
}
|
| 1062 |
+
],
|
| 1063 |
+
"metadata": {
|
| 1064 |
+
"kernelspec": {
|
| 1065 |
+
"display_name": "Python 3",
|
| 1066 |
+
"language": "python",
|
| 1067 |
+
"name": "python3"
|
| 1068 |
+
},
|
| 1069 |
+
"language_info": {
|
| 1070 |
+
"name": "python",
|
| 1071 |
+
"version": "3.10"
|
| 1072 |
+
}
|
| 1073 |
+
},
|
| 1074 |
+
"nbformat": 4,
|
| 1075 |
+
"nbformat_minor": 5
|
| 1076 |
+
}
|