File size: 6,494 Bytes
e7919f8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 | """
Manara-Annotate: Arabic Dataset Fetching & Cataloging Script
Phase 2 — Identify and fetch public Arabic/GCC dialect datasets
"""
import os
import json
import csv
from pathlib import Path
from datasets import load_dataset
DATA_DIR = Path("/home/ubuntu/manara-annotate/data/raw")
DATA_DIR.mkdir(parents=True, exist_ok=True)
catalog = []
# ─────────────────────────────────────────────
# 1. ArSarcasm-v2 (Arabic Sarcasm Detection)
# ─────────────────────────────────────────────
print("=" * 60)
print("[1/3] Fetching ArSarcasm-v2 ...")
try:
ds_sarcasm = load_dataset("iabufarha/ar_sarcasm", trust_remote_code=True)
train_split = ds_sarcasm["train"]
test_split = ds_sarcasm["test"]
# Save samples
sarcasm_path = DATA_DIR / "arsarcasm_train.jsonl"
with open(sarcasm_path, "w", encoding="utf-8") as f:
for row in train_split:
f.write(json.dumps(row, ensure_ascii=False) + "\n")
sarcasm_test_path = DATA_DIR / "arsarcasm_test.jsonl"
with open(sarcasm_test_path, "w", encoding="utf-8") as f:
for row in test_split:
f.write(json.dumps(row, ensure_ascii=False) + "\n")
# Show sample
print(f" Train samples : {len(train_split)}")
print(f" Test samples : {len(test_split)}")
print(f" Columns : {train_split.column_names}")
print(f" Sample row : {train_split[0]}")
catalog.append({
"name": "ArSarcasm-v1",
"hf_id": "iabufarha/ar_sarcasm",
"task": "Sarcasm Detection / Sentiment",
"language": "Arabic (MSA + Dialectal)",
"train_size": len(train_split),
"test_size": len(test_split),
"columns": train_split.column_names,
"local_path": str(sarcasm_path),
"relevance": "Primary seed for sarcasm + sentiment labeling tasks"
})
print(" [OK] ArSarcasm saved.")
except Exception as e:
print(f" [ERROR] ArSarcasm: {e}")
# ─────────────────────────────────────────────
# 2. QADI — Arabic Dialect Identification
# ─────────────────────────────────────────────
print("\n[2/3] Fetching QADI (Arabic Dialect Identification) ...")
try:
ds_qadi = load_dataset("qcri/qadi", trust_remote_code=True)
qadi_split = ds_qadi["train"]
qadi_path = DATA_DIR / "qadi_train.jsonl"
with open(qadi_path, "w", encoding="utf-8") as f:
for row in qadi_split:
f.write(json.dumps(row, ensure_ascii=False) + "\n")
print(f" Train samples : {len(qadi_split)}")
print(f" Columns : {qadi_split.column_names}")
print(f" Sample row : {qadi_split[0]}")
catalog.append({
"name": "QADI",
"hf_id": "qcri/qadi",
"task": "Dialect Identification (18 country-level Arabic dialects)",
"language": "Arabic Dialectal (incl. Kuwaiti/Gulf)",
"train_size": len(qadi_split),
"test_size": 0,
"columns": qadi_split.column_names,
"local_path": str(qadi_path),
"relevance": "Primary seed for Kuwaiti vs MSA dialect detection"
})
print(" [OK] QADI saved.")
except Exception as e:
print(f" [ERROR] QADI: {e}")
# Fallback: try alternative dataset ID
try:
ds_qadi = load_dataset("arbml/qadi", trust_remote_code=True)
qadi_split = list(ds_qadi.values())[0]
qadi_path = DATA_DIR / "qadi_train.jsonl"
with open(qadi_path, "w", encoding="utf-8") as f:
for row in qadi_split:
f.write(json.dumps(row, ensure_ascii=False) + "\n")
print(f" [OK] QADI (arbml) saved. Samples: {len(qadi_split)}")
catalog.append({
"name": "QADI (arbml)",
"hf_id": "arbml/qadi",
"task": "Dialect Identification",
"language": "Arabic Dialectal",
"train_size": len(qadi_split),
"test_size": 0,
"columns": list(qadi_split.features.keys()) if hasattr(qadi_split, 'features') else [],
"local_path": str(qadi_path),
"relevance": "Dialect detection seed data"
})
except Exception as e2:
print(f" [ERROR] QADI fallback: {e2}")
# ─────────────────────────────────────────────
# 3. Arabic Sentiment (ASTD / LABR / SemEval)
# ─────────────────────────────────────────────
print("\n[3/3] Fetching Arabic Sentiment / NER datasets ...")
try:
ds_sent = load_dataset("arbml/ASTD", trust_remote_code=True)
sent_split = list(ds_sent.values())[0]
sent_path = DATA_DIR / "astd_sentiment.jsonl"
with open(sent_path, "w", encoding="utf-8") as f:
for row in sent_split:
f.write(json.dumps(row, ensure_ascii=False) + "\n")
print(f" Samples : {len(sent_split)}")
print(f" Columns : {sent_split.column_names}")
print(f" Sample : {sent_split[0]}")
catalog.append({
"name": "ASTD (Arabic Sentiment Tweets Dataset)",
"hf_id": "arbml/ASTD",
"task": "Sentiment Analysis",
"language": "Arabic (MSA + Egyptian/Gulf)",
"train_size": len(sent_split),
"test_size": 0,
"columns": sent_split.column_names,
"local_path": str(sent_path),
"relevance": "Sentiment nuance labeling; Khaleeji sarcasm baseline"
})
print(" [OK] ASTD saved.")
except Exception as e:
print(f" [ERROR] ASTD: {e}")
# ─────────────────────────────────────────────
# Save catalog
# ─────────────────────────────────────────────
catalog_path = DATA_DIR / "dataset_catalog.json"
with open(catalog_path, "w", encoding="utf-8") as f:
json.dump(catalog, f, ensure_ascii=False, indent=2)
print("\n" + "=" * 60)
print(f"Dataset catalog saved to: {catalog_path}")
print(f"Total datasets cataloged: {len(catalog)}")
for d in catalog:
print(f" - {d['name']}: {d.get('train_size', '?')} train samples | Task: {d['task']}")
|