Make all: data+tiny-50M+gguf-scripts+gradio-UI

README.md

@@ -1,21 +1,22 @@
 # Alfa Code - Multimodal Coding GGUF
 
-## 1. Connect to HuggingFace Hub
-1. Token: https://huggingface.co/settings/tokens (read + write) -> copy `hf_xxx`
-2. `copy .env.example .env` then fill `HF_TOKEN=hf_xxx`
-3. Or one-shot:
-  `python scripts/hf_connect.py --token hf_xxx`
+RTX 3050 4GB: use tiny-50M demo. 1B+ needs cloud 8xH100.
 
-Verify: `python scripts/hf_connect.py` -> should print `Logged in as: <you>`
+## 1. Data
+`python scripts/download_data.py --dataset code_small_test --max-rows 500`
+Output: `data/processed/train.jsonl` {modality,prompt,think,answer}
 
-## 2. Get data (best HF sets)
-Public test (no login): `python scripts/download_data.py --dataset code_small_test --max-rows 500`
-Gated large (needs login):
-  `python scripts/hf_connect.py --token hf_xxx`
-  `python scripts/download_data.py --dataset code_pretrain --max-rows 1000 --streaming`
+## 2. Tokenizer + Train
+`python scripts/train_tokenizer.py` -> `tokenizers/alfa-32k.json` (verified 47KB)
+`pip install torch --index-url https://download.pytorch.org/whl/cu121`
+`python scripts/train.py` -> `outputs/tiny-50M`
 
-Output: `data/processed/train.jsonl` with `{modality, prompt, think, answer}`
+## 3. GGUF
+`git clone https://github.com/ggerganov/llama.cpp third_party/llama.cpp`
+`python scripts/convert_to_gguf.py --ckpt outputs/tiny-50M --quant Q4_K_M --out outputs/tiny-50M.gguf`
 
-## 3. Push to Hub
-`python scripts/hf_connect.py --create-repo --repo alfa-code-multimodal`
-`python scripts/hf_connect.py --upload data/processed --repo alfa-code-multimodal`
+## 4. UI (reasoning live->collapsed + image/file/video)
+`python app/ui.py` -> http://127.0.0.1:7860
+
+## 5. Hub sync
+`hf upload mrsandip/Alfa-Code . . --exclude __pycache__ --exclude .venv --commit-message "Update"`

app/ui.py

@@ -0,0 +1,37 @@
+"""Coding AI mode UI: reasoning (live->collapsed) + image + file + video."""
+import time, gradio as gr
+from pathlib import Path
+
+def mock_reason(prompt, image, file, video):
+    steps = []
+    ctx = []
+    if image: ctx.append(f"image: {Path(image).name}")
+    if file: ctx.append(f"file: {Path(file).name if isinstance(file,str) else 'uploaded'}")
+    if video: ctx.append(f"video: {Path(video).name} (4 frames extracted)")
+    header = f"Context: {', '.join(ctx)}\n" if ctx else ""
+    yield "[Thinking...]", f"{header}Understanding: {prompt[:120]}..."
+    time.sleep(0.4)
+    yield "[Planning...]", f"{header}Plan: 1.parse 2.generate 3.verify"
+    time.sleep(0.4)
+    code = f"```python\n# generated for: {prompt[:60]}\ndef solve():\n    return 'todo: wire to outputs/tiny-50M.gguf'\n```"
+    yield "[Coding...]", f"{header}{code}"
+    time.sleep(0.3)
+    yield "[Done]", f"{header}<details><summary>Reasoning (3 steps)</summary>Understand > Plan > Code</details>\n\n{code}"
+
+with gr.Blocks(title="Alfa-Code") as demo:
+    gr.Markdown("# Alfa-Code: reasoning + image + file + video")
+    with gr.Row():
+        with gr.Column(scale=2):
+            chat = gr.Markdown()
+            prompt = gr.Textbox(label="Prompt", placeholder="Describe code task...")
+            with gr.Row():
+                img = gr.Image(label="Image", type="filepath")
+                fil = gr.File(label="File")
+                vid = gr.Video(label="Video")
+            btn = gr.Button("Generate", variant="primary")
+        with gr.Column(scale=1):
+            status = gr.Label(value="Idle", label="Reasoning status")
+    btn.click(fn=mock_reason, inputs=[prompt, img, fil, vid], outputs=[status, chat])
+
+if __name__ == "__main__":
+    demo.launch(server_name="127.0.0.1", server_port=7860)

configs/tiny-50M.yaml

@@ -0,0 +1,28 @@
+# Tiny demo config - fits RTX 3050 4GB. Scale to 1B+ only on cloud 8xH100.
+model:
+  arch: llama
+  hidden_size: 512
+  num_layers: 8
+  num_heads: 8
+  num_kv_heads: 4
+  intermediate_size: 1376
+  vocab_size: 32000
+  max_seq_len: 2048
+  rope_theta: 10000
+tokenizer:
+  type: bpe
+  vocab_size: 32000
+  train_files: data/processed/train.jsonl
+multimodal:
+  vision_encoder: openai/clip-vit-base-patch32
+  projector_hidden: 512
+  video_frames: 4
+training:
+  batch_size: 2
+  grad_accum: 8
+  lr: 3e-4
+  epochs: 1
+  output_dir: outputs/tiny-50M
+gguf:
+  quant: Q4_K_M
+  out_file: outputs/tiny-50M.gguf

requirements.txt

@@ -4,3 +4,6 @@ transformers>=4.40
 hf_transfer>=0.1
 pyyaml>=6.0
 tqdm>=4.66
+gradio>=5.0
+tokenizers>=0.20
+torch --index-url https://download.pytorch.org/whl/cu121

scripts/convert_to_gguf.py

@@ -0,0 +1,23 @@
+"""Convert HF checkpoint -> GGUF via llama.cpp. Needs: git clone https://github.com/ggerganov/llama.cpp"""
+import subprocess, sys
+from pathlib import Path
+
+def main(ckpt="outputs/tiny-50M", quant="Q4_K_M", out="outputs/tiny-50M.gguf"):
+    conv = Path("third_party/llama.cpp/convert_hf_to_gguf.py")
+    if not conv.exists():
+        print("Clone llama.cpp first: git clone https://github.com/ggerganov/llama.cpp third_party/llama.cpp")
+        sys.exit(1)
+    subprocess.run([sys.executable, str(conv), ckpt, "--outfile", out, "--outtype", "f16"], check=True)
+    quantize = Path("third_party/llama.cpp/build/bin/llama-quantize")
+    if quantize.exists():
+        subprocess.run([str(quantize), out, out.replace(".gguf", f".{quant}.gguf"), quant], check=True)
+    print(f"GGUF ready -> {out}")
+
+if __name__ == "__main__":
+    import argparse
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--ckpt", default="outputs/tiny-50M")
+    ap.add_argument("--quant", default="Q4_K_M")
+    ap.add_argument("--out", default="outputs/tiny-50M.gguf")
+    a = ap.parse_args()
+    main(a.ckpt, a.quant, a.out)

scripts/train.py

@@ -0,0 +1,34 @@
+"""Tiny Llama pretrain demo (CPU/4GB friendly). For 1B+ use cloud + DeepSpeed."""
+import json
+from pathlib import Path
+import torch
+from transformers import LlamaConfig, LlamaForCausalLM, Trainer, TrainingArguments
+from torch.utils.data import Dataset
+
+class JsonlDS(Dataset):
+    def __init__(self, path, tok_len=512):
+        self.rows = [json.loads(l) for l in open(path, encoding="utf-8")]
+        self.tok_len = tok_len
+    def __len__(self): return len(self.rows)
+    def __getitem__(self, i):
+        import random
+        r = self.rows[i]
+        # char-level pseudo-tokenization for demo (real run uses train_tokenizer.py + proper encode)
+        s = (r.get("prompt", "") + "\n" + r.get("think", "") + "\n" + r.get("answer", ""))[:2000]
+        ids = [min(ord(c), 30000) for c in s][:self.tok_len]
+        ids += [0] * (self.tok_len - len(ids))
+        return {"input_ids": torch.tensor(ids, dtype=torch.long), "labels": torch.tensor(ids, dtype=torch.long)}
+
+def main():
+    cfg = LlamaConfig(hidden_size=512, num_hidden_layers=8, num_attention_heads=8,
+                      num_key_value_heads=4, intermediate_size=1376, vocab_size=32000, max_position_embeddings=2048)
+    model = LlamaForCausalLM(cfg)
+    ds = JsonlDS("data/processed/train.jsonl")
+    args = TrainingArguments(output_dir="outputs/tiny-50M", per_device_train_batch_size=2,
+                             num_train_epochs=1, logging_steps=5, save_steps=50, fp16=torch.cuda.is_available())
+    Trainer(model=model, args=args, train_dataset=ds).train()
+    model.save_pretrained("outputs/tiny-50M")
+    print("saved -> outputs/tiny-50M")
+
+if __name__ == "__main__":
+    main()

scripts/train_tokenizer.py

@@ -0,0 +1,27 @@
+"""Train BPE tokenizer on data/processed/train.jsonl -> tokenizers/alfa-32k.json"""
+import json
+from pathlib import Path
+from tokenizers import Tokenizer, models, trainers, pre_tokenizers, decoders
+
+DATA = Path("data/processed/train.jsonl")
+OUT = Path("tokenizers/alfa-32k.json")
+
+def texts():
+    for line in open(DATA, encoding="utf-8"):
+        o = json.loads(line)
+        yield o.get("prompt", "") + "\n" + o.get("answer", "")
+
+def main(vocab_size=32000):
+    assert DATA.exists(), f"missing {DATA}, run download_data.py first"
+    tok = Tokenizer(models.BPE())
+    tok.pre_tokenizer = pre_tokenizers.ByteLevel(add_prefix_space=False)
+    tok.decoder = decoders.ByteLevel()
+    trainer = trainers.BpeTrainer(vocab_size=vocab_size,
+        special_tokens=["<s>", "</s>", "<unk>", "<pad>", "<think>", "<image>", "<video>", "<file>", "<code>"])
+    tok.train_from_iterator(texts(), trainer=trainer, length=20000)
+    OUT.parent.mkdir(parents=True, exist_ok=True)
+    tok.save(str(OUT))
+    print(f"saved -> {OUT}")
+
+if __name__ == "__main__":
+    main()

tokenizers/alfa-32k.json

@@ -0,0 +1,3536 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "</s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 4,
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 5,
+      "content": "<image>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 6,
+      "content": "<video>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 7,
+      "content": "<file>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 8,
+      "content": "<code>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": null,
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<s>": 0,
+      "</s>": 1,
+      "<unk>": 2,
+      "<pad>": 3,
+      "<think>": 4,
+      "<image>": 5,
+      "<video>": 6,
+      "<file>": 7,
+      "<code>": 8,
+      "\"": 9,
+      "#": 10,
+      "'": 11,
+      "(": 12,
+      ")": 13,
+      "*": 14,
+      "+": 15,
+      ",": 16,
+      "-": 17,
+      ".": 18,
+      "/": 19,
+      "0": 20,
+      "1": 21,
+      "2": 22,
+      "3": 23,
+      "4": 24,
+      "5": 25,
+      "6": 26,
+      "9": 27,
+      ":": 28,
+      ";": 29,
+      "<": 30,
+      "=": 31,
+      ">": 32,
+      "A": 33,
+      "B": 34,
+      "C": 35,
+      "D": 36,
+      "E": 37,
+      "F": 38,
+      "G": 39,
+      "I": 40,
+      "J": 41,
+      "L": 42,
+      "M": 43,
+      "N": 44,
+      "O": 45,
+      "P": 46,
+      "Q": 47,
+      "R": 48,
+      "S": 49,
+      "T": 50,
+      "U": 51,
+      "V": 52,
+      "W": 53,
+      "X": 54,
+      "Y": 55,
+      "[": 56,
+      "]": 57,
+      "_": 58,
+      "a": 59,
+      "b": 60,
+      "c": 61,
+      "d": 62,
+      "e": 63,
+      "f": 64,
+      "g": 65,
+      "h": 66,
+      "i": 67,
+      "j": 68,
+      "k": 69,
+      "l": 70,
+      "m": 71,
+      "n": 72,
+      "o": 73,
+      "p": 74,
+      "q": 75,
+      "r": 76,
+      "s": 77,
+      "t": 78,
+      "u": 79,
+      "v": 80,
+      "w": 81,
+      "x": 82,
+      "y": 83,
+      "z": 84,
+      "{": 85,
+      "}": 86,
+      "ĉ": 87,
+      "Ċ": 88,
+      "Ġ": 89,
+      "ĠĠ": 90,
+      "in": 91,
+      "ĠĠĠĠ": 92,
+      "int": 93,
+      "st": 94,
+      "Ġ=": 95,
+      "oint": 96,
+      "le": 97,
+      "ĠĠĠ": 98,
+      "Ġa": 99,
+      "ĠĊ": 100,
+      "th": 101,
+      "oints": 102,
+      "or": 103,
+      "Ġp": 104,
+      "Ġc": 105,
+      "rr": 106,
+      "Ġi": 107,
+      "ĠĠĠĠĠĠĠ": 108,
+      "ĊĠ": 109,
+      "lo": 110,
+      "on": 111,
+      "se": 112,
+      "ai": 113,
+      ");": 114,
+      "Points": 115,
+      "ou": 116,
+      "Ġm": 117,
+      "//": 118,
+      "Ġ[": 119,
+      "Ġr": 120,
+      "de": 121,
+      "ist": 122,
+      "tPoints": 123,
+      "Ġf": 124,
+      "Ġt": 125,
+      "Ġth": 126,
+      "lose": 127,
+      "losest": 128,
+      "air": 129,
+      "],": 130,
+      "an": 131,
+      "at": 132,
+      "et": 133,
+      "Ġarr": 134,
+      "Ġthe": 135,
+      "er": 136,
+      "Ġ{": 137,
+      "Ġclosest": 138,
+      "ct": 139,
+      "ort": 140,
+      "Pair": 141,
+      "ay": 142,
+      "Ġ(": 143,
+      "Ġ//": 144,
+      "ĠĊĠĠĠĠĠĠĠ": 145,
+      "Ġpoints": 146,
+      "Dist": 147,
+      "en": 148,
+      "gh": 149,
+      "igh": 150,
+      "rint": 151,
+      "Ġb": 152,
+      "Ġd": 153,
+      "Ġn": 154,
+      "Ġo": 155,
+      "ing": 156,
+      "ĠĠĠĠĠĠĠĠĠĠĠ": 157,
+      "lef": 158,
+      "let": 159,
+      "em": 160,
+      "re": 161,
+      "Ġ2": 162,
+      "onst": 163,
+      "Ġmin": 164,
+      "Ġrigh": 165,
+      "ĠclosestPair": 166,
+      "ce": 167,
+      "om": 168,
+      "ra": 169,
+      "rn": 170,
+      "ĊĠĠĠ": 171,
+      "Ġg": 172,
+      "Ġs": 173,
+      "Ġ}": 174,
+      "Ġan": 175,
+      "oun": 176,
+      "out": 177,
+      "leftPoints": 178,
+      "ĠrightPoints": 179,
+      "li": 180,
+      "ok": 181,
+      "ook": 182,
+      "Ġ-": 183,
+      "Ġ0": 184,
+      "Ġ<": 185,
+      "ĠM": 186,
+      "Ġj": 187,
+      "Ġin": 188,
+      "Ġto": 189,
+      "Ġof": 190,
+      "];": 191,
+      "am": 192,
+      "ath": 193,
+      "gth": 194,
+      "id": 195,
+      "ion": 196,
+      "ngth": 197,
+      "ode": 198,
+      "pam": 199,
+      "um": 200,
+      "urn": 201,
+      "length": 202,
+      "ĠĊĠĠĠ": 203,
+      "ĠĊĠĠĠĠĠĠĠĠĠĠĠ": 204,
+      "Ġconst": 205,
+      "rray": 206,
+      "Ġret": 207,
+      "ance": 208,
+      "Ġget": 209,
+      "ount": 210,
+      "Ġreturn": 211,
+      "++": 212,
+      "Array": 213,
+      "])": 214,
+      "di": 215,
+      "for": 216,
+      "im": 217,
+      "it": 218,
+      "iv": 219,
+      "la": 220,
+      "print": 221,
+      "rom": 222,
+      "spam": 223,
+      "ve": 224,
+      "Ġ1": 225,
+      "ĠC": 226,
+      "ĠS": 227,
+      "Ġint": 228,
+      "Ġlet": 229,
+      "inde": 230,
+      "Ġab": 231,
+      "ĠĊĠĠ": 232,
+      "Ġis": 233,
+      "Ġfor": 234,
+      "Ġbook": 235,
+      "Ġdist": 236,
+      "redi": 237,
+      "ĠMath": 238,
+      "odel": 239,
+      "index": 240,
+      "redict": 241,
+      "')": 242,
+      "',": 243,
+      "('": 244,
+      "Sort": 245,
+      "Th": 246,
+      "]);": 247,
+      "]];": 248,
+      "al": 249,
+      "arr": 250,
+      "eat": 251,
+      "is": 252,
+      "ot": 253,
+      "points": 254,
+      "ry": 255,
+      "ul": 256,
+      "ut": 257,
+      "Ġ'": 258,
+      "Ġ4": 259,
+      "Ġe": 260,
+      "Ġv": 261,
+      "Ġw": 262,
+      "Ġy": 263,
+      "Ġem": 264,
+      "ori": 265,
+      "Ġpair": 266,
+      "Ġprint": 267,
+      "ail": 268,
+      "Ġ[-": 269,
+      "Ġarray": 270,
+      "Ġminim": 271,
+      "++)": 272,
+      "ĠCount": 273,
+      "Ġabout": 274,
+      "'),": 275,
+      "Ġemail": 276,
+      "Ġminimum": 277,
+      "RO": 278,
+      "[])": 279,
+      "ap": 280,
+      "bra": 281,
+      "const": 282,
+      "dle": 283,
+      "ed": 284,
+      "ew": 285,
+      "ge": 286,
+      "min": 287,
+      "men": 288,
+      "oid": 289,
+      "point": 290,
+      "port": 291,
+      "predict": 292,
+      "qu": 293,
+      "ran": 294,
+      "sort": 295,
+      "un": 296,
+      "wo": 297,
+      "xt": 298,
+      "yst": 299,
+      "ĊĠĠĠĠ": 300,
+      "ĊĠĠĠĠĠĠĠ": 301,
+      "ĊĊĠ": 302,
+      "Ġor": 303,
+      "Ġli": 304,
+      "ĠArray": 305,
+      "ind": 306,
+      "ĠĠĠĠĠĠĠĠ": 307,
+      "Ġ=>": 308,
+      "lemen": 309,
+      "ĠĊĠ": 310,
+      "Ġpoint": 311,
+      "Ġif": 312,
+      "Ġmodel": 313,
+      "Ġ[[": 314,
+      "Ġtwo": 315,
+      "ange": 316,
+      "ata": 317,
+      "ate": 318,
+      "ers": 319,
+      "Distance": 320,
+      "end": 321,
+      "Ġob": 322,
+      "ĠminDist": 323,
+      "iddle": 324,
+      "ĠgetDistance": 325,
+      "ĠSyst": 326,
+      "ĠĊĠĠĊĠĠĠ": 327,
+      "Ġdistance": 328,
+      "This": 329,
+      "Ġelemen": 330,
+      "Ġvoid": 331,
+      "brary": 332,
+      "quer": 333,
+      "rans": 334,
+      "ĊĠĠĠĠĠ": 335,
+      "Ġlibrary": 336,
+      "ĠArraySort": 337,
+      "ĠSystem": 338,
+      "Ġelement": 339,
+      "\");": 340,
+      "()": 341,
+      "();": 342,
+      "):": 343,
+      "BY": 344,
+      "Book": 345,
+      "CT": 346,
+      "Closest": 347,
+      "Cre": 348,
+      "DE": 349,
+      "EL": 350,
+      "ECT": 351,
+      "FRO": 352,
+      "ID": 353,
+      "Ja": 354,
+      "NB": 355,
+      "Out": 356,
+      "SEL": 357,
+      "Tit": 358,
+      "Ve": 359,
+      "ab": 360,
+      "ase": 361,
+      "arn": 362,
+      "bers": 363,
+      "ch": 364,
+      "cv": 365,
+      "count": 366,
+      "cul": 367,
+      "est": 368,
+      "een": 369,
+      "ext": 370,
+      "fit": 371,
+      "from": 372,
+      "feat": 373,
+      "gori": 374,
+      "ide": 375,
+      "ial": 376,
+      "kle": 377,
+      "ln": 378,
+      "lgori": 379,
+      "model": 380,
+      "mport": 381,
+      "not": 382,
+      "op": 383,
+      "ow": 384,
+      "ove": 385,
+      "put": 386,
+      "pend": 387,
+      "pow": 388,
+      "ro": 389,
+      "ss": 390,
+      "sli": 391,
+      "ts": 392,
+      "tin": 393,
+      "trans": 394,
+      "ub": 395,
+      "ure": 396,
+      "va": 397,
+      "ween": 398,
+      "xDist": 399,
+      "zer": 400,
+      "ĊĠĠ": 401,
+      "ĊĠĠĠĠĠĠĠĠĠĠĠ": 402,
+      "ĊĠĊĠ": 403,
+      "Ġ+": 404,
+      "Ġ3": 405,
+      "Ġ5": 406,
+      "Ġ6": 407,
+      "ĠA": 408,
+      "Ġlo": 409,
+      "Ġse": 410,
+      "ĠleftPoints": 411,
+      "Ġun": 412,
+      "ĠBY": 413,
+      "ĠJa": 414,
+      "Ġalgori": 415,
+      "ĠĊĠĠĠĠĠĠĠĠ": 416,
+      "thm": 417,
+      "Ġpredict": 418,
+      "Ġcon": 419,
+      "Ġcal": 420,
+      "Ġimport": 421,
+      "one": 422,
+      "our": 423,
+      "Ġmiddle": 424,
+      "Ġrange": 425,
+      "Ġfrom": 426,
+      "Ġfeat": 427,
+      "Ġfind": 428,
+      "Ġtem": 429,
+      "Ġtest": 430,
+      "Ġthat": 431,
+      "etween": 432,
+      "ction": 433,
+      "ctori": 434,
+      "Ġbetween": 435,
+      "Ġdiv": 436,
+      "Ġdata": 437,
+      "Ġnum": 438,
+      "Ġnew": 439,
+      "left": 440,
+      "omial": 441,
+      "rain": 442,
+      "Ġgiv": 443,
+      "Ġsort": 444,
+      "Ġskle": 445,
+      "Ġand": 446,
+      "ound": 447,
+      "ĠMul": 448,
+      "ĠgetClosest": 449,
+      "form": 450,
+      "lab": 451,
+      "lass": 452,
+      "println": 453,
+      "vect": 454,
+      "ĠbookID": 455,
+      "ĠbookTit": 456,
+      "Ġwh": 457,
+      "ĠCountVe": 458,
+      "append": 459,
+      "prediction": 460,
+      "sorted": 461,
+      "ĠlibraryBook": 462,
+      "Create": 463,
+      "FROM": 464,
+      "Output": 465,
+      "SELECT": 466,
+      "abs": 467,
+      "slice": 468,
+      "tinomial": 469,
+      "transform": 470,
+      "ĊĠĠĊĠ": 471,
+      "Ġunsorted": 472,
+      "ĠJava": 473,
+      "Ġalgorithm": 474,
+      "Ġconquer": 475,
+      "Ġcalcul": 476,
+      "Ġtemp": 477,
+      "ctorizer": 478,
+      "Ġdivide": 479,
+      "Ġnumbers": 480,
+      "Ġgiven": 481,
+      "Ġsklearn": 482,
+      "ĠMultinomial": 483,
+      "ĠgetClosestPair": 484,
+      "ĠbookTitle": 485,
+      "ĠCountVectorizer": 486,
+      "ĠMultinomialNB": 487,
+      "\"])": 488,
+      "']": 489,
+      "(\"": 490,
+      "(*": 491,
+      "([": 492,
+      "));": 493,
+      "10": 494,
+      "Ch": 495,
+      "Dr": 496,
+      "Eu": 497,
+      "Find": 498,
+      "GRO": 499,
+      "IM": 500,
+      "IT": 501,
+      "LIM": 502,
+      "Math": 503,
+      "NT": 504,
+      "OR": 505,
+      "OU": 506,
+      "On": 507,
+      "Print": 508,
+      "QL": 509,
+      "SC": 510,
+      "Sc": 511,
+      "St": 512,
+      "Train": 513,
+      "UP": 514,
+      "We": 515,
+      "Wr": 516,
+      "['": 517,
+      "[]": 518,
+      "]]": 519,
+      "ad": 520,
+      "ain": 521,
+      "ale": 522,
+      "array": 523,
+      "ary": 524,
+      "ach": 525,
+      "bin": 526,
+      "bay": 527,
+      "con": 528,
+      "closest": 529,
+      "cli": 530,
+      "cend": 531,
+      "ccount": 532,
+      "class": 533,
+      "dist": 534,
+      "data": 535,
+      "es": 536,
+      "eth": 537,
+      "flo": 538,
+      "fer": 539,
+      "gs": 540,
+      "gra": 541,
+      "ic": 542,
+      "ip": 543,
+      "ir": 544,
+      "ith": 545,
+      "ich": 546,
+      "lt": 547,
+      "llo": 548,
+      "mm": 549,
+      "middle": 550,
+      "nai": 551,
+      "ost": 552,
+      "ole": 553,
+      "ollo": 554,
+      "pp": 555,
+      "qr": 556,
+      "righ": 557,
+      "ring": 558,
+      "rgs": 559,
+      "rip": 560,
+      "scend": 561,
+      "sole": 562,
+      "sqr": 563,
+      "text": 564,
+      "use": 565,
+      "ula": 566,
+      "wing": 567,
+      "wap": 568,
+      "yth": 569,
+      "yDist": 570,
+      "};": 571,
+      "Ġ\"": 572,
+      "Ġ*": 573,
+      "Ġ/": 574,
+      "Ġst": 575,
+      "Ġde": 576,
+      "Ġout": 577,
+      "Ġ++": 578,
+      "Ġquer": 579,
+      "Ġ\");": 580,
+      "ĠDE": 581,
+      "ĠxDist": 582,
+      "Ġone": 583,
+      "Ġour": 584,
+      "Ġleft": 585,
+      "Ġlab": 586,
+      "ĠFROM": 587,
+      "ĠOutput": 588,
+      "ĠDr": 589,
+      "ĠEu": 590,
+      "ĠFind": 591,
+      "ĠOn": 592,
+      "ĠPrint": 593,
+      "Ġuse": 594,
+      "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 595,
+      "ĠĠĠĠĊĠĠĠĠĠĠĠĠĠĠĠ": 596,
+      "Ġaccount": 597,
+      "Ġapp": 598,
+      "Ġargs": 599,
+      "ĠĊĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 600,
+      "Ġprom": 601,
+      "Ġpop": 602,
+      "Ġpro": 603,
+      "Ġpub": 604,
+      "Ġpyth": 605,
+      "Ġcv": 606,
+      "Ġcom": 607,
+      "Ġcode": 608,
+      "Ġcase": 609,
+      "Ġclass": 610,
+      "Ġit": 611,
+      "Ġits": 612,
+      "log": 613,
+      "Ġmove": 614,
+      "Ġmone": 615,
+      "Ġmain": 616,
+      "Ġmost": 617,
+      "Ġ[]": 618,
+      "Ġ[],": 619,
+      "Ġ[('": 620,
+      "der": 621,
+      "dean": 622,
+      "Ġfew": 623,
+      "Ġfun": 624,
+      "Ġfound": 625,
+      "Ġfir": 626,
+      "Ġfollo": 627,
+      "Ġtrans": 628,
+      "Ġtrain": 629,
+      "ant": 630,
+      "ating": 631,
+      "atic": 632,
+      "ere": 633,
+      "ĠclosestPoints": 634,
+      "cting": 635,
+      "Ġby": 636,
+      "Ġbase": 637,
+      "Ġbound": 638,
+      "Ġdis": 639,
+      "Ġnot": 640,
+      "Ġnlt": 641,
+      "Ġright": 642,
+      "raction": 643,
+      "racting": 644,
+      "Ġso": 645,
+      "��spam": 646,
+      "Ġsub": 647,
+      "Ġsale": 648,
+      "lic": 649,
+      "Ġ<=": 650,
+      "Ġreturns": 651,
+      "import": 652,
+      "ite": 653,
+      "iver": 654,
+      "printArray": 655,
+      "Ġ10": 656,
+      "Ġ11": 657,
+      "ĠCOU": 658,
+      "ĠSQL": 659,
+      "ĠSwap": 660,
+      "Ġabove": 661,
+      "ĠĊĠĠĊĠĠĠĠĠĠĠ": 662,
+      "ĠĊĠĠĊĠĠĠĠĠĠĠĠĠĠĠ": 663,
+      "Ġbooks": 664,
+      "Sorted": 665,
+      "There": 666,
+      "otion": 667,
+      "Ġext": 668,
+      "Ġvers": 669,
+      "Ġwith": 670,
+      "Ġwant": 671,
+      "ĠyDist": 672,
+      "Ġyour": 673,
+      "Ġprints": 674,
+      "ĠprintArray": 675,
+      "Ġorder": 676,
+      "Ġ[[-": 677,
+      "DER": 678,
+      "extraction": 679,
+      "feature": 680,
+      "roach": 681,
+      "ures": 682,
+      "ĠAI": 683,
+      "ĠAS": 684,
+      "Ġloop": 685,
+      "Ġload": 686,
+      "Ġset": 687,
+      "Ġsets": 688,
+      "ĠĊĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 689,
+      "ĠĊĠĠĠĠĠĠĠĠĠĠĠĠĊĠĠĠĠĠĠĠĠĠĠĠ": 690,
+      "Ġpredicting": 691,
+      "Ġfeatures": 692,
+      "Ġtesting": 693,
+      "Ġsorts": 694,
+      "Ġwheth": 695,
+      "Ġwhich": 696,
+      "ĠJavaSc": 697,
+      "Ġcalculate": 698,
+      "Ġcalculating": 699,
+      "\"]))": 700,
+      "(*)": 701,
+      "([\"": 702,
+      "Change": 703,
+      "GROUP": 704,
+      "LIMIT": 705,
+      "ORDER": 706,
+      "String": 707,
+      "Write": 708,
+      "bine": 709,
+      "bayes": 710,
+      "console": 711,
+      "closestPoints": 712,
+      "clidean": 713,
+      "floor": 714,
+      "gramm": 715,
+      "naive": 716,
+      "right": 717,
+      "ript": 718,
+      "scending": 719,
+      "sqrt": 720,
+      "ular": 721,
+      "Ġstatic": 722,
+      "Ġdescending": 723,
+      "Ġquery": 724,
+      "ĠDESC": 725,
+      "ĠDriver": 726,
+      "ĠEuclidean": 727,
+      "ĠOne": 728,
+      "ĠPrints": 729,
+      "Ġuses": 730,
+      "Ġapproach": 731,
+      "Ġpromotion": 732,
+      "Ġpopular": 733,
+      "Ġprogramm": 734,
+      "Ġpublic": 735,
+      "Ġpython": 736,
+      "Ġcombine": 737,
+      "Ġmoney": 738,
+      "Ġfewer": 739,
+      "Ġfunction": 740,
+      "Ġfirst": 741,
+      "Ġfollowing": 742,
+      "Ġtransfer": 743,
+      "Ġtraining": 744,
+      "Ġboundary": 745,
+      "Ġdiscount": 746,
+      "Ġnltk": 747,
+      "Ġsubarray": 748,
+      "ĠCOUNT": 749,
+      "Ġextracting": 750,
+      "Ġversion": 751,
+      "Ġloading": 752,
+      "Ġwhether": 753,
+      "ĠJavaScript": 754,
+      "Ġprogramming": 755
+    },
+    "merges": [
+      [
+        "Ġ",
+        "Ġ"
+      ],
+      [
+        "i",
+        "n"
+      ],
+      [
+        "ĠĠ",
+        "ĠĠ"
+      ],
+      [
+        "in",
+        "t"
+      ],
+      [
+        "s",
+        "t"
+      ],
+      [
+        "Ġ",
+        "="
+      ],
+      [
+        "o",
+        "int"
+      ],
+      [
+        "l",
+        "e"
+      ],
+      [
+        "ĠĠ",
+        "Ġ"
+      ],
+      [
+        "Ġ",
+        "a"
+      ],
+      [
+        "Ġ",
+        "Ċ"
+      ],
+      [
+        "t",
+        "h"
+      ],
+      [
+        "oint",
+        "s"
+      ],
+      [
+        "o",
+        "r"
+      ],
+      [
+        "Ġ",
+        "p"
+      ],
+      [
+        "Ġ",
+        "c"
+      ],
+      [
+        "r",
+        "r"
+      ],
+      [
+        "Ġ",
+        "i"
+      ],
+      [
+        "ĠĠĠĠ",
+        "ĠĠĠ"
+      ],
+      [
+        "Ċ",
+        "Ġ"
+      ],
+      [
+        "l",
+        "o"
+      ],
+      [
+        "o",
+        "n"
+      ],
+      [
+        "s",
+        "e"
+      ],
+      [
+        "a",
+        "i"
+      ],
+      [
+        ")",
+        ";"
+      ],
+      [
+        "P",
+        "oints"
+      ],
+      [
+        "o",
+        "u"
+      ],
+      [
+        "Ġ",
+        "m"
+      ],
+      [
+        "/",
+        "/"
+      ],
+      [
+        "Ġ",
+        "["
+      ],
+      [
+        "Ġ",
+        "r"
+      ],
+      [
+        "d",
+        "e"
+      ],
+      [
+        "i",
+        "st"
+      ],
+      [
+        "t",
+        "Points"
+      ],
+      [
+        "Ġ",
+        "f"
+      ],
+      [
+        "Ġ",
+        "t"
+      ],
+      [
+        "Ġ",
+        "th"
+      ],
+      [
+        "lo",
+        "se"
+      ],
+      [
+        "lose",
+        "st"
+      ],
+      [
+        "ai",
+        "r"
+      ],
+      [
+        "]",
+        ","
+      ],
+      [
+        "a",
+        "n"
+      ],
+      [
+        "a",
+        "t"
+      ],
+      [
+        "e",
+        "t"
+      ],
+      [
+        "Ġa",
+        "rr"
+      ],
+      [
+        "Ġth",
+        "e"
+      ],
+      [
+        "e",
+        "r"
+      ],
+      [
+        "Ġ",
+        "{"
+      ],
+      [
+        "Ġc",
+        "losest"
+      ],
+      [
+        "c",
+        "t"
+      ],
+      [
+        "or",
+        "t"
+      ],
+      [
+        "P",
+        "air"
+      ],
+      [
+        "a",
+        "y"
+      ],
+      [
+        "Ġ",
+        "("
+      ],
+      [
+        "Ġ",
+        "//"
+      ],
+      [
+        "ĠĊ",
+        "ĠĠĠĠĠĠĠ"
+      ],
+      [
+        "Ġp",
+        "oints"
+      ],
+      [
+        "D",
+        "ist"
+      ],
+      [
+        "e",
+        "n"
+      ],
+      [
+        "g",
+        "h"
+      ],
+      [
+        "i",
+        "gh"
+      ],
+      [
+        "r",
+        "int"
+      ],
+      [
+        "Ġ",
+        "b"
+      ],
+      [
+        "Ġ",
+        "d"
+      ],
+      [
+        "Ġ",
+        "n"
+      ],
+      [
+        "Ġ",
+        "o"
+      ],
+      [
+        "in",
+        "g"
+      ],
+      [
+        "ĠĠĠĠ",
+        "ĠĠĠĠĠĠĠ"
+      ],
+      [
+        "le",
+        "f"
+      ],
+      [
+        "le",
+        "t"
+      ],
+      [
+        "e",
+        "m"
+      ],
+      [
+        "r",
+        "e"
+      ],
+      [
+        "Ġ",
+        "2"
+      ],
+      [
+        "on",
+        "st"
+      ],
+      [
+        "Ġm",
+        "in"
+      ],
+      [
+        "Ġr",
+        "igh"
+      ],
+      [
+        "Ġclosest",
+        "Pair"
+      ],
+      [
+        "c",
+        "e"
+      ],
+      [
+        "o",
+        "m"
+      ],
+      [
+        "r",
+        "a"
+      ],
+      [
+        "r",
+        "n"
+      ],
+      [
+        "Ċ",
+        "ĠĠĠ"
+      ],
+      [
+        "Ġ",
+        "g"
+      ],
+      [
+        "Ġ",
+        "s"
+      ],
+      [
+        "Ġ",
+        "}"
+      ],
+      [
+        "Ġa",
+        "n"
+      ],
+      [
+        "ou",
+        "n"
+      ],
+      [
+        "ou",
+        "t"
+      ],
+      [
+        "lef",
+        "tPoints"
+      ],
+      [
+        "Ġrigh",
+        "tPoints"
+      ],
+      [
+        "l",
+        "i"
+      ],
+      [
+        "o",
+        "k"
+      ],
+      [
+        "o",
+        "ok"
+      ],
+      [
+        "Ġ",
+        "-"
+      ],
+      [
+        "Ġ",
+        "0"
+      ],
+      [
+        "Ġ",
+        "<"
+      ],
+      [
+        "Ġ",
+        "M"
+      ],
+      [
+        "Ġ",
+        "j"
+      ],
+      [
+        "Ġ",
+        "in"
+      ],
+      [
+        "Ġt",
+        "o"
+      ],
+      [
+        "Ġo",
+        "f"
+      ],
+      [
+        "]",
+        ";"
+      ],
+      [
+        "a",
+        "m"
+      ],
+      [
+        "a",
+        "th"
+      ],
+      [
+        "g",
+        "th"
+      ],
+      [
+        "i",
+        "d"
+      ],
+      [
+        "i",
+        "on"
+      ],
+      [
+        "n",
+        "gth"
+      ],
+      [
+        "o",
+        "de"
+      ],
+      [
+        "p",
+        "am"
+      ],
+      [
+        "u",
+        "m"
+      ],
+      [
+        "u",
+        "rn"
+      ],
+      [
+        "le",
+        "ngth"
+      ],
+      [
+        "ĠĊ",
+        "ĠĠĠ"
+      ],
+      [
+        "ĠĊ",
+        "ĠĠĠĠĠĠĠĠĠĠĠ"
+      ],
+      [
+        "Ġc",
+        "onst"
+      ],
+      [
+        "rr",
+        "ay"
+      ],
+      [
+        "Ġr",
+        "et"
+      ],
+      [
+        "an",
+        "ce"
+      ],
+      [
+        "Ġg",
+        "et"
+      ],
+      [
+        "oun",
+        "t"
+      ],
+      [
+        "Ġret",
+        "urn"
+      ],
+      [
+        "+",
+        "+"
+      ],
+      [
+        "A",
+        "rray"
+      ],
+      [
+        "]",
+        ")"
+      ],
+      [
+        "d",
+        "i"
+      ],
+      [
+        "f",
+        "or"
+      ],
+      [
+        "i",
+        "m"
+      ],
+      [
+        "i",
+        "t"
+      ],
+      [
+        "i",
+        "v"
+      ],
+      [
+        "l",
+        "a"
+      ],
+      [
+        "p",
+        "rint"
+      ],
+      [
+        "r",
+        "om"
+      ],
+      [
+        "s",
+        "pam"
+      ],
+      [
+        "v",
+        "e"
+      ],
+      [
+        "Ġ",
+        "1"
+      ],
+      [
+        "Ġ",
+        "C"
+      ],
+      [
+        "Ġ",
+        "S"
+      ],
+      [
+        "Ġ",
+        "int"
+      ],
+      [
+        "Ġ",
+        "let"
+      ],
+      [
+        "in",
+        "de"
+      ],
+      [
+        "Ġa",
+        "b"
+      ],
+      [
+        "ĠĊ",
+        "ĠĠ"
+      ],
+      [
+        "Ġi",
+        "s"
+      ],
+      [
+        "Ġf",
+        "or"
+      ],
+      [
+        "Ġb",
+        "ook"
+      ],
+      [
+        "Ġd",
+        "ist"
+      ],
+      [
+        "re",
+        "di"
+      ],
+      [
+        "ĠM",
+        "ath"
+      ],
+      [
+        "ode",
+        "l"
+      ],
+      [
+        "inde",
+        "x"
+      ],
+      [
+        "redi",
+        "ct"
+      ],
+      [
+        "'",
+        ")"
+      ],
+      [
+        "'",
+        ","
+      ],
+      [
+        "(",
+        "'"
+      ],
+      [
+        "S",
+        "ort"
+      ],
+      [
+        "T",
+        "h"
+      ],
+      [
+        "]",
+        ");"
+      ],
+      [
+        "]",
+        "];"
+      ],
+      [
+        "a",
+        "l"
+      ],
+      [
+        "a",
+        "rr"
+      ],
+      [
+        "e",
+        "at"
+      ],
+      [
+        "i",
+        "s"
+      ],
+      [
+        "o",
+        "t"
+      ],
+      [
+        "p",
+        "oints"
+      ],
+      [
+        "r",
+        "y"
+      ],
+      [
+        "u",
+        "l"
+      ],
+      [
+        "u",
+        "t"
+      ],
+      [
+        "Ġ",
+        "'"
+      ],
+      [
+        "Ġ",
+        "4"
+      ],
+      [
+        "Ġ",
+        "e"
+      ],
+      [
+        "Ġ",
+        "v"
+      ],
+      [
+        "Ġ",
+        "w"
+      ],
+      [
+        "Ġ",
+        "y"
+      ],
+      [
+        "Ġ",
+        "em"
+      ],
+      [
+        "or",
+        "i"
+      ],
+      [
+        "Ġp",
+        "air"
+      ],
+      [
+        "Ġp",
+        "rint"
+      ],
+      [
+        "ai",
+        "l"
+      ],
+      [
+        "Ġ[",
+        "-"
+      ],
+      [
+        "Ġarr",
+        "ay"
+      ],
+      [
+        "Ġmin",
+        "im"
+      ],
+      [
+        "++",
+        ")"
+      ],
+      [
+        "ĠC",
+        "ount"
+      ],
+      [
+        "Ġab",
+        "out"
+      ],
+      [
+        "')",
+        ","
+      ],
+      [
+        "Ġem",
+        "ail"
+      ],
+      [
+        "Ġminim",
+        "um"
+      ],
+      [
+        "R",
+        "O"
+      ],
+      [
+        "[",
+        "])"
+      ],
+      [
+        "a",
+        "p"
+      ],
+      [
+        "b",
+        "ra"
+      ],
+      [
+        "c",
+        "onst"
+      ],
+      [
+        "d",
+        "le"
+      ],
+      [
+        "e",
+        "d"
+      ],
+      [
+        "e",
+        "w"
+      ],
+      [
+        "g",
+        "e"
+      ],
+      [
+        "m",
+        "in"
+      ],
+      [
+        "m",
+        "en"
+      ],
+      [
+        "o",
+        "id"
+      ],
+      [
+        "p",
+        "oint"
+      ],
+      [
+        "p",
+        "ort"
+      ],
+      [
+        "p",
+        "redict"
+      ],
+      [
+        "q",
+        "u"
+      ],
+      [
+        "r",
+        "an"
+      ],
+      [
+        "s",
+        "ort"
+      ],
+      [
+        "u",
+        "n"
+      ],
+      [
+        "w",
+        "o"
+      ],
+      [
+        "x",
+        "t"
+      ],
+      [
+        "y",
+        "st"
+      ],
+      [
+        "Ċ",
+        "ĠĠĠĠ"
+      ],
+      [
+        "Ċ",
+        "ĠĠĠĠĠĠĠ"
+      ],
+      [
+        "Ċ",
+        "ĊĠ"
+      ],
+      [
+        "Ġ",
+        "or"
+      ],
+      [
+        "Ġ",
+        "li"
+      ],
+      [
+        "Ġ",
+        "Array"
+      ],
+      [
+        "in",
+        "d"
+      ],
+      [
+        "ĠĠĠĠ",
+        "ĠĠĠĠ"
+      ],
+      [
+        "Ġ=",
+        ">"
+      ],
+      [
+        "le",
+        "men"
+      ],
+      [
+        "ĠĊ",
+        "Ġ"
+      ],
+      [
+        "Ġp",
+        "oint"
+      ],
+      [
+        "Ġi",
+        "f"
+      ],
+      [
+        "Ġm",
+        "odel"
+      ],
+      [
+        "Ġ[",
+        "["
+      ],
+      [
+        "Ġt",
+        "wo"
+      ],
+      [
+        "an",
+        "ge"
+      ],
+      [
+        "at",
+        "a"
+      ],
+      [
+        "at",
+        "e"
+      ],
+      [
+        "er",
+        "s"
+      ],
+      [
+        "Dist",
+        "ance"
+      ],
+      [
+        "en",
+        "d"
+      ],
+      [
+        "Ġo",
+        "b"
+      ],
+      [
+        "Ġmin",
+        "Dist"
+      ],
+      [
+        "id",
+        "dle"
+      ],
+      [
+        "Ġget",
+        "Distance"
+      ],
+      [
+        "ĠS",
+        "yst"
+      ],
+      [
+        "ĠĊĠĠ",
+        "ĊĠĠĠ"
+      ],
+      [
+        "Ġdist",
+        "ance"
+      ],
+      [
+        "Th",
+        "is"
+      ],
+      [
+        "Ġe",
+        "lemen"
+      ],
+      [
+        "Ġv",
+        "oid"
+      ],
+      [
+        "bra",
+        "ry"
+      ],
+      [
+        "qu",
+        "er"
+      ],
+      [
+        "ran",
+        "s"
+      ],
+      [
+        "ĊĠĠĠĠ",
+        "Ġ"
+      ],
+      [
+        "Ġli",
+        "brary"
+      ],
+      [
+        "ĠArray",
+        "Sort"
+      ],
+      [
+        "ĠSyst",
+        "em"
+      ],
+      [
+        "Ġelemen",
+        "t"
+      ],
+      [
+        "\"",
+        ");"
+      ],
+      [
+        "(",
+        ")"
+      ],
+      [
+        "(",
+        ");"
+      ],
+      [
+        ")",
+        ":"
+      ],
+      [
+        "B",
+        "Y"
+      ],
+      [
+        "B",
+        "ook"
+      ],
+      [
+        "C",
+        "T"
+      ],
+      [
+        "C",
+        "losest"
+      ],
+      [
+        "C",
+        "re"
+      ],
+      [
+        "D",
+        "E"
+      ],
+      [
+        "E",
+        "L"
+      ],
+      [
+        "E",
+        "CT"
+      ],
+      [
+        "F",
+        "RO"
+      ],
+      [
+        "I",
+        "D"
+      ],
+      [
+        "J",
+        "a"
+      ],
+      [
+        "N",
+        "B"
+      ],
+      [
+        "O",
+        "ut"
+      ],
+      [
+        "S",
+        "EL"
+      ],
+      [
+        "T",
+        "it"
+      ],
+      [
+        "V",
+        "e"
+      ],
+      [
+        "a",
+        "b"
+      ],
+      [
+        "a",
+        "se"
+      ],
+      [
+        "a",
+        "rn"
+      ],
+      [
+        "b",
+        "ers"
+      ],
+      [
+        "c",
+        "h"
+      ],
+      [
+        "c",
+        "v"
+      ],
+      [
+        "c",
+        "ount"
+      ],
+      [
+        "c",
+        "ul"
+      ],
+      [
+        "e",
+        "st"
+      ],
+      [
+        "e",
+        "en"
+      ],
+      [
+        "e",
+        "xt"
+      ],
+      [
+        "f",
+        "it"
+      ],
+      [
+        "f",
+        "rom"
+      ],
+      [
+        "f",
+        "eat"
+      ],
+      [
+        "g",
+        "ori"
+      ],
+      [
+        "i",
+        "de"
+      ],
+      [
+        "i",
+        "al"
+      ],
+      [
+        "k",
+        "le"
+      ],
+      [
+        "l",
+        "n"
+      ],
+      [
+        "l",
+        "gori"
+      ],
+      [
+        "m",
+        "odel"
+      ],
+      [
+        "m",
+        "port"
+      ],
+      [
+        "n",
+        "ot"
+      ],
+      [
+        "o",
+        "p"
+      ],
+      [
+        "o",
+        "w"
+      ],
+      [
+        "o",
+        "ve"
+      ],
+      [
+        "p",
+        "ut"
+      ],
+      [
+        "p",
+        "end"
+      ],
+      [
+        "p",
+        "ow"
+      ],
+      [
+        "r",
+        "o"
+      ],
+      [
+        "s",
+        "s"
+      ],
+      [
+        "s",
+        "li"
+      ],
+      [
+        "t",
+        "s"
+      ],
+      [
+        "t",
+        "in"
+      ],
+      [
+        "t",
+        "rans"
+      ],
+      [
+        "u",
+        "b"
+      ],
+      [
+        "u",
+        "re"
+      ],
+      [
+        "v",
+        "a"
+      ],
+      [
+        "w",
+        "een"
+      ],
+      [
+        "x",
+        "Dist"
+      ],
+      [
+        "z",
+        "er"
+      ],
+      [
+        "Ċ",
+        "ĠĠ"
+      ],
+      [
+        "Ċ",
+        "ĠĠĠĠĠĠĠĠĠĠĠ"
+      ],
+      [
+        "Ċ",
+        "ĠĊĠ"
+      ],
+      [
+        "Ġ",
+        "+"
+      ],
+      [
+        "Ġ",
+        "3"
+      ],
+      [
+        "Ġ",
+        "5"
+      ],
+      [
+        "Ġ",
+        "6"
+      ],
+      [
+        "Ġ",
+        "A"
+      ],
+      [
+        "Ġ",
+        "lo"
+      ],
+      [
+        "Ġ",
+        "se"
+      ],
+      [
+        "Ġ",
+        "leftPoints"
+      ],
+      [
+        "Ġ",
+        "un"
+      ],
+      [
+        "Ġ",
+        "BY"
+      ],
+      [
+        "Ġ",
+        "Ja"
+      ],
+      [
+        "Ġa",
+        "lgori"
+      ],
+      [
+        "ĠĊ",
+        "ĠĠĠĠĠĠĠĠ"
+      ],
+      [
+        "th",
+        "m"
+      ],
+      [
+        "Ġp",
+        "redict"
+      ],
+      [
+        "Ġc",
+        "on"
+      ],
+      [
+        "Ġc",
+        "al"
+      ],
+      [
+        "Ġi",
+        "mport"
+      ],
+      [
+        "on",
+        "e"
+      ],
+      [
+        "ou",
+        "r"
+      ],
+      [
+        "Ġm",
+        "iddle"
+      ],
+      [
+        "Ġr",
+        "ange"
+      ],
+      [
+        "Ġf",
+        "rom"
+      ],
+      [
+        "Ġf",
+        "eat"
+      ],
+      [
+        "Ġf",
+        "ind"
+      ],
+      [
+        "Ġt",
+        "em"
+      ],
+      [
+        "Ġt",
+        "est"
+      ],
+      [
+        "Ġth",
+        "at"
+      ],
+      [
+        "et",
+        "ween"
+      ],
+      [
+        "ct",
+        "ion"
+      ],
+      [
+        "ct",
+        "ori"
+      ],
+      [
+        "Ġb",
+        "etween"
+      ],
+      [
+        "Ġd",
+        "iv"
+      ],
+      [
+        "Ġd",
+        "ata"
+      ],
+      [
+        "Ġn",
+        "um"
+      ],
+      [
+        "Ġn",
+        "ew"
+      ],
+      [
+        "lef",
+        "t"
+      ],
+      [
+        "om",
+        "ial"
+      ],
+      [
+        "ra",
+        "in"
+      ],
+      [
+        "Ġg",
+        "iv"
+      ],
+      [
+        "Ġs",
+        "ort"
+      ],
+      [
+        "Ġs",
+        "kle"
+      ],
+      [
+        "Ġan",
+        "d"
+      ],
+      [
+        "oun",
+        "d"
+      ],
+      [
+        "ĠM",
+        "ul"
+      ],
+      [
+        "Ġget",
+        "Closest"
+      ],
+      [
+        "for",
+        "m"
+      ],
+      [
+        "la",
+        "b"
+      ],
+      [
+        "la",
+        "ss"
+      ],
+      [
+        "print",
+        "ln"
+      ],
+      [
+        "ve",
+        "ct"
+      ],
+      [
+        "Ġbook",
+        "ID"
+      ],
+      [
+        "Ġbook",
+        "Tit"
+      ],
+      [
+        "Ġw",
+        "h"
+      ],
+      [
+        "ĠCount",
+        "Ve"
+      ],
+      [
+        "ap",
+        "pend"
+      ],
+      [
+        "predict",
+        "ion"
+      ],
+      [
+        "sort",
+        "ed"
+      ],
+      [
+        "Ġlibrary",
+        "Book"
+      ],
+      [
+        "Cre",
+        "ate"
+      ],
+      [
+        "FRO",
+        "M"
+      ],
+      [
+        "Out",
+        "put"
+      ],
+      [
+        "SEL",
+        "ECT"
+      ],
+      [
+        "ab",
+        "s"
+      ],
+      [
+        "sli",
+        "ce"
+      ],
+      [
+        "tin",
+        "omial"
+      ],
+      [
+        "trans",
+        "form"
+      ],
+      [
+        "ĊĠĠ",
+        "ĊĠ"
+      ],
+      [
+        "Ġun",
+        "sorted"
+      ],
+      [
+        "ĠJa",
+        "va"
+      ],
+      [
+        "Ġalgori",
+        "thm"
+      ],
+      [
+        "Ġcon",
+        "quer"
+      ],
+      [
+        "Ġcal",
+        "cul"
+      ],
+      [
+        "Ġtem",
+        "p"
+      ],
+      [
+        "ctori",
+        "zer"
+      ],
+      [
+        "Ġdiv",
+        "ide"
+      ],
+      [
+        "Ġnum",
+        "bers"
+      ],
+      [
+        "Ġgiv",
+        "en"
+      ],
+      [
+        "Ġskle",
+        "arn"
+      ],
+      [
+        "ĠMul",
+        "tinomial"
+      ],
+      [
+        "ĠgetClosest",
+        "Pair"
+      ],
+      [
+        "ĠbookTit",
+        "le"
+      ],
+      [
+        "ĠCountVe",
+        "ctorizer"
+      ],
+      [
+        "ĠMultinomial",
+        "NB"
+      ],
+      [
+        "\"",
+        "])"
+      ],
+      [
+        "'",
+        "]"
+      ],
+      [
+        "(",
+        "\""
+      ],
+      [
+        "(",
+        "*"
+      ],
+      [
+        "(",
+        "["
+      ],
+      [
+        ")",
+        ");"
+      ],
+      [
+        "1",
+        "0"
+      ],
+      [
+        "C",
+        "h"
+      ],
+      [
+        "D",
+        "r"
+      ],
+      [
+        "E",
+        "u"
+      ],
+      [
+        "F",
+        "ind"
+      ],
+      [
+        "G",
+        "RO"
+      ],
+      [
+        "I",
+        "M"
+      ],
+      [
+        "I",
+        "T"
+      ],
+      [
+        "L",
+        "IM"
+      ],
+      [
+        "M",
+        "ath"
+      ],
+      [
+        "N",
+        "T"
+      ],
+      [
+        "O",
+        "R"
+      ],
+      [
+        "O",
+        "U"
+      ],
+      [
+        "O",
+        "n"
+      ],
+      [
+        "P",
+        "rint"
+      ],
+      [
+        "Q",
+        "L"
+      ],
+      [
+        "S",
+        "C"
+      ],
+      [
+        "S",
+        "c"
+      ],
+      [
+        "S",
+        "t"
+      ],
+      [
+        "T",
+        "rain"
+      ],
+      [
+        "U",
+        "P"
+      ],
+      [
+        "W",
+        "e"
+      ],
+      [
+        "W",
+        "r"
+      ],
+      [
+        "[",
+        "'"
+      ],
+      [
+        "[",
+        "]"
+      ],
+      [
+        "]",
+        "]"
+      ],
+      [
+        "a",
+        "d"
+      ],
+      [
+        "a",
+        "in"
+      ],
+      [
+        "a",
+        "le"
+      ],
+      [
+        "a",
+        "rray"
+      ],
+      [
+        "a",
+        "ry"
+      ],
+      [
+        "a",
+        "ch"
+      ],
+      [
+        "b",
+        "in"
+      ],
+      [
+        "b",
+        "ay"
+      ],
+      [
+        "c",
+        "on"
+      ],
+      [
+        "c",
+        "losest"
+      ],
+      [
+        "c",
+        "li"
+      ],
+      [
+        "c",
+        "end"
+      ],
+      [
+        "c",
+        "count"
+      ],
+      [
+        "c",
+        "lass"
+      ],
+      [
+        "d",
+        "ist"
+      ],
+      [
+        "d",
+        "ata"
+      ],
+      [
+        "e",
+        "s"
+      ],
+      [
+        "e",
+        "th"
+      ],
+      [
+        "f",
+        "lo"
+      ],
+      [
+        "f",
+        "er"
+      ],
+      [
+        "g",
+        "s"
+      ],
+      [
+        "g",
+        "ra"
+      ],
+      [
+        "i",
+        "c"
+      ],
+      [
+        "i",
+        "p"
+      ],
+      [
+        "i",
+        "r"
+      ],
+      [
+        "i",
+        "th"
+      ],
+      [
+        "i",
+        "ch"
+      ],
+      [
+        "l",
+        "t"
+      ],
+      [
+        "l",
+        "lo"
+      ],
+      [
+        "m",
+        "m"
+      ],
+      [
+        "m",
+        "iddle"
+      ],
+      [
+        "n",
+        "ai"
+      ],
+      [
+        "o",
+        "st"
+      ],
+      [
+        "o",
+        "le"
+      ],
+      [
+        "o",
+        "llo"
+      ],
+      [
+        "p",
+        "p"
+      ],
+      [
+        "q",
+        "r"
+      ],
+      [
+        "r",
+        "igh"
+      ],
+      [
+        "r",
+        "ing"
+      ],
+      [
+        "r",
+        "gs"
+      ],
+      [
+        "r",
+        "ip"
+      ],
+      [
+        "s",
+        "cend"
+      ],
+      [
+        "s",
+        "ole"
+      ],
+      [
+        "s",
+        "qr"
+      ],
+      [
+        "t",
+        "ext"
+      ],
+      [
+        "u",
+        "se"
+      ],
+      [
+        "u",
+        "la"
+      ],
+      [
+        "w",
+        "ing"
+      ],
+      [
+        "w",
+        "ap"
+      ],
+      [
+        "y",
+        "th"
+      ],
+      [
+        "y",
+        "Dist"
+      ],
+      [
+        "}",
+        ";"
+      ],
+      [
+        "Ġ",
+        "\""
+      ],
+      [
+        "Ġ",
+        "*"
+      ],
+      [
+        "Ġ",
+        "/"
+      ],
+      [
+        "Ġ",
+        "st"
+      ],
+      [
+        "Ġ",
+        "de"
+      ],
+      [
+        "Ġ",
+        "out"
+      ],
+      [
+        "Ġ",
+        "++"
+      ],
+      [
+        "Ġ",
+        "quer"
+      ],
+      [
+        "Ġ",
+        "\");"
+      ],
+      [
+        "Ġ",
+        "DE"
+      ],
+      [
+        "Ġ",
+        "xDist"
+      ],
+      [
+        "Ġ",
+        "one"
+      ],
+      [
+        "Ġ",
+        "our"
+      ],
+      [
+        "Ġ",
+        "left"
+      ],
+      [
+        "Ġ",
+        "lab"
+      ],
+      [
+        "Ġ",
+        "FROM"
+      ],
+      [
+        "Ġ",
+        "Output"
+      ],
+      [
+        "Ġ",
+        "Dr"
+      ],
+      [
+        "Ġ",
+        "Eu"
+      ],
+      [
+        "Ġ",
+        "Find"
+      ],
+      [
+        "Ġ",
+        "On"
+      ],
+      [
+        "Ġ",
+        "Print"
+      ],
+      [
+        "Ġ",
+        "use"
+      ],
+      [
+        "ĠĠĠĠ",
+        "ĠĠĠĠĠĠĠĠĠĠĠ"
+      ],
+      [
+        "ĠĠĠĠ",
+        "ĊĠĠĠĠĠĠĠĠĠĠĠ"
+      ],
+      [
+        "Ġa",
+        "ccount"
+      ],
+      [
+        "Ġa",
+        "pp"
+      ],
+      [
+        "Ġa",
+        "rgs"
+      ],
+      [
+        "ĠĊ",
+        "ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ"
+      ],
+      [
+        "Ġp",
+        "rom"
+      ],
+      [
+        "Ġp",
+        "op"
+      ],
+      [
+        "Ġp",
+        "ro"
+      ],
+      [
+        "Ġp",
+        "ub"
+      ],
+      [
+        "Ġp",
+        "yth"
+      ],
+      [
+        "Ġc",
+        "v"
+      ],
+      [
+        "Ġc",
+        "om"
+      ],
+      [
+        "Ġc",
+        "ode"
+      ],
+      [
+        "Ġc",
+        "ase"
+      ],
+      [
+        "Ġc",
+        "lass"
+      ],
+      [
+        "Ġi",
+        "t"
+      ],
+      [
+        "Ġi",
+        "ts"
+      ],
+      [
+        "lo",
+        "g"
+      ],
+      [
+        "Ġm",
+        "ove"
+      ],
+      [
+        "Ġm",
+        "one"
+      ],
+      [
+        "Ġm",
+        "ain"
+      ],
+      [
+        "Ġm",
+        "ost"
+      ],
+      [
+        "Ġ[",
+        "]"
+      ],
+      [
+        "Ġ[",
+        "],"
+      ],
+      [
+        "Ġ[",
+        "('"
+      ],
+      [
+        "de",
+        "r"
+      ],
+      [
+        "de",
+        "an"
+      ],
+      [
+        "Ġf",
+        "ew"
+      ],
+      [
+        "Ġf",
+        "un"
+      ],
+      [
+        "Ġf",
+        "ound"
+      ],
+      [
+        "Ġf",
+        "ir"
+      ],
+      [
+        "Ġf",
+        "ollo"
+      ],
+      [
+        "Ġt",
+        "rans"
+      ],
+      [
+        "Ġt",
+        "rain"
+      ],
+      [
+        "an",
+        "t"
+      ],
+      [
+        "at",
+        "ing"
+      ],
+      [
+        "at",
+        "ic"
+      ],
+      [
+        "er",
+        "e"
+      ],
+      [
+        "Ġclosest",
+        "Points"
+      ],
+      [
+        "ct",
+        "ing"
+      ],
+      [
+        "Ġb",
+        "y"
+      ],
+      [
+        "Ġb",
+        "ase"
+      ],
+      [
+        "Ġb",
+        "ound"
+      ],
+      [
+        "Ġd",
+        "is"
+      ],
+      [
+        "Ġn",
+        "ot"
+      ],
+      [
+        "Ġn",
+        "lt"
+      ],
+      [
+        "Ġrigh",
+        "t"
+      ],
+      [
+        "ra",
+        "ction"
+      ],
+      [
+        "ra",
+        "cting"
+      ],
+      [
+        "Ġs",
+        "o"
+      ],
+      [
+        "Ġs",
+        "pam"
+      ],
+      [
+        "Ġs",
+        "ub"
+      ],
+      [
+        "Ġs",
+        "ale"
+      ],
+      [
+        "li",
+        "c"
+      ],
+      [
+        "Ġ<",
+        "="
+      ],
+      [
+        "Ġreturn",
+        "s"
+      ],
+      [
+        "im",
+        "port"
+      ],
+      [
+        "it",
+        "e"
+      ],
+      [
+        "iv",
+        "er"
+      ],
+      [
+        "print",
+        "Array"
+      ],
+      [
+        "Ġ1",
+        "0"
+      ],
+      [
+        "Ġ1",
+        "1"
+      ],
+      [
+        "ĠC",
+        "OU"
+      ],
+      [
+        "ĠS",
+        "QL"
+      ],
+      [
+        "ĠS",
+        "wap"
+      ],
+      [
+        "Ġab",
+        "ove"
+      ],
+      [
+        "ĠĊĠĠ",
+        "ĊĠĠĠĠĠĠĠ"
+      ],
+      [
+        "ĠĊĠĠ",
+        "ĊĠĠĠĠĠĠĠĠĠĠĠ"
+      ],
+      [
+        "Ġbook",
+        "s"
+      ],
+      [
+        "Sort",
+        "ed"
+      ],
+      [
+        "Th",
+        "ere"
+      ],
+      [
+        "ot",
+        "ion"
+      ],
+      [
+        "Ġe",
+        "xt"
+      ],
+      [
+        "Ġv",
+        "ers"
+      ],
+      [
+        "Ġw",
+        "ith"
+      ],
+      [
+        "Ġw",
+        "ant"
+      ],
+      [
+        "Ġy",
+        "Dist"
+      ],
+      [
+        "Ġy",
+        "our"
+      ],
+      [
+        "Ġprint",
+        "s"
+      ],
+      [
+        "Ġprint",
+        "Array"
+      ],
+      [
+        "Ġor",
+        "der"
+      ],
+      [
+        "Ġ[[",
+        "-"
+      ],
+      [
+        "DE",
+        "R"
+      ],
+      [
+        "ext",
+        "raction"
+      ],
+      [
+        "feat",
+        "ure"
+      ],
+      [
+        "ro",
+        "ach"
+      ],
+      [
+        "ure",
+        "s"
+      ],
+      [
+        "ĠA",
+        "I"
+      ],
+      [
+        "ĠA",
+        "S"
+      ],
+      [
+        "Ġlo",
+        "op"
+      ],
+      [
+        "Ġlo",
+        "ad"
+      ],
+      [
+        "Ġse",
+        "t"
+      ],
+      [
+        "Ġse",
+        "ts"
+      ],
+      [
+        "ĠĊĠĠĠĠĠĠĠĠ",
+        "ĠĠĠĠĠĠĠĠĠĠĠ"
+      ],
+      [
+        "ĠĊĠĠĠĠĠĠĠĠ",
+        "ĠĠĠĠĊĠĠĠĠĠĠĠĠĠĠĠ"
+      ],
+      [
+        "Ġpredict",
+        "ing"
+      ],
+      [
+        "Ġfeat",
+        "ures"
+      ],
+      [
+        "Ġtest",
+        "ing"
+      ],
+      [
+        "Ġsort",
+        "s"
+      ],
+      [
+        "Ġwh",
+        "eth"
+      ],
+      [
+        "Ġwh",
+        "ich"
+      ],
+      [
+        "ĠJava",
+        "Sc"
+      ],
+      [
+        "Ġcalcul",
+        "ate"
+      ],
+      [
+        "Ġcalcul",
+        "ating"
+      ],
+      [
+        "\"])",
+        ")"
+      ],
+      [
+        "(*",
+        ")"
+      ],
+      [
+        "([",
+        "\""
+      ],
+      [
+        "Ch",
+        "ange"
+      ],
+      [
+        "GRO",
+        "UP"
+      ],
+      [
+        "LIM",
+        "IT"
+      ],
+      [
+        "OR",
+        "DER"
+      ],
+      [
+        "St",
+        "ring"
+      ],
+      [
+        "Wr",
+        "ite"
+      ],
+      [
+        "bin",
+        "e"
+      ],
+      [
+        "bay",
+        "es"
+      ],
+      [
+        "con",
+        "sole"
+      ],
+      [
+        "closest",
+        "Points"
+      ],
+      [
+        "cli",
+        "dean"
+      ],
+      [
+        "flo",
+        "or"
+      ],
+      [
+        "gra",
+        "mm"
+      ],
+      [
+        "nai",
+        "ve"
+      ],
+      [
+        "righ",
+        "t"
+      ],
+      [
+        "rip",
+        "t"
+      ],
+      [
+        "scend",
+        "ing"
+      ],
+      [
+        "sqr",
+        "t"
+      ],
+      [
+        "ula",
+        "r"
+      ],
+      [
+        "Ġst",
+        "atic"
+      ],
+      [
+        "Ġde",
+        "scending"
+      ],
+      [
+        "Ġquer",
+        "y"
+      ],
+      [
+        "ĠDE",
+        "SC"
+      ],
+      [
+        "ĠDr",
+        "iver"
+      ],
+      [
+        "ĠEu",
+        "clidean"
+      ],
+      [
+        "ĠOn",
+        "e"
+      ],
+      [
+        "ĠPrint",
+        "s"
+      ],
+      [
+        "Ġuse",
+        "s"
+      ],
+      [
+        "Ġapp",
+        "roach"
+      ],
+      [
+        "Ġprom",
+        "otion"
+      ],
+      [
+        "Ġpop",
+        "ular"
+      ],
+      [
+        "Ġpro",
+        "gramm"
+      ],
+      [
+        "Ġpub",
+        "lic"
+      ],
+      [
+        "Ġpyth",
+        "on"
+      ],
+      [
+        "Ġcom",
+        "bine"
+      ],
+      [
+        "Ġmone",
+        "y"
+      ],
+      [
+        "Ġfew",
+        "er"
+      ],
+      [
+        "Ġfun",
+        "ction"
+      ],
+      [
+        "Ġfir",
+        "st"
+      ],
+      [
+        "Ġfollo",
+        "wing"
+      ],
+      [
+        "Ġtrans",
+        "fer"
+      ],
+      [
+        "Ġtrain",
+        "ing"
+      ],
+      [
+        "Ġbound",
+        "ary"
+      ],
+      [
+        "Ġdis",
+        "count"
+      ],
+      [
+        "Ġnlt",
+        "k"
+      ],
+      [
+        "Ġsub",
+        "array"
+      ],
+      [
+        "ĠCOU",
+        "NT"
+      ],
+      [
+        "Ġext",
+        "racting"
+      ],
+      [
+        "Ġvers",
+        "ion"
+      ],
+      [
+        "Ġload",
+        "ing"
+      ],
+      [
+        "Ġwheth",
+        "er"
+      ],
+      [
+        "ĠJavaSc",
+        "ript"
+      ],
+      [
+        "Ġprogramm",
+        "ing"
+      ]
+    ]
+  }
+}