Spaces:
Runtime error
Runtime error
File size: 10,603 Bytes
c5f0a6a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "1e3fc800",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import sys\n",
"import random\n",
"import statistics \n",
"import numpy as np\n",
"import matplotlib.pyplot as plt \n",
"import threading\n",
"import time\n",
"import queue\n",
"sys.path.append(os.path.abspath(\"../lib\"))\n",
"sys.path.append(os.path.abspath(\"../supv\"))\n",
"sys.path.append(os.path.abspath(\"../text\"))\n",
"from util import *\n",
"from sampler import *\n",
"from tnn import *\n",
"from txproc import *\n",
"\n",
"emailDoms = [\"yahoo.com\", \"gmail.com\", \"hotmail.com\", \"aol.com\"]"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "e9195f68",
"metadata": {},
"outputs": [],
"source": [
"def printNgramVec(ngv):\n",
" \"\"\"\n",
" print ngram vector\n",
" \"\"\"\n",
" print(\"ngram vector\")\n",
" for i in range(len(ngv)):\n",
" if ngv[i] > 0:\n",
" print(\"{} {}\".format(i, ngv[i]))"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "a78fc5c8",
"metadata": {},
"outputs": [],
"source": [
"def createNegMatch(tdata, ri):\n",
" \"\"\"\n",
" create negative match by randomly selecting another record\n",
" \"\"\"\n",
" nri = randomInt(0, len(tdata)-1)\n",
" while nri == ri:\n",
" nri = randomInt(0, len(tdata)-1)\n",
" return tdata[nri]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "3645fe7c",
"metadata": {},
"outputs": [],
"source": [
"def createNgramCreator():\n",
" \"\"\" create ngram creator \"\"\"\n",
" cng = CharNGram([\"lcc\", \"ucc\", \"dig\"], 3, True)\n",
" spc = [\"@\", \"#\", \"_\", \"-\", \".\"]\n",
" cng.addSpChar(spc)\n",
" cng.setWsRepl(\"$\")\n",
" cng.finalize()\n",
" return cng"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "f153bac5",
"metadata": {},
"outputs": [],
"source": [
"def getSim(rec, incOutput=True):\n",
" \"\"\" get rec pair similarity \"\"\"\n",
" #print(rec)\n",
" sim = list()\n",
" for i in range(6):\n",
" #print(\"field \" + str(i))\n",
" if i == 3:\n",
" s = levenshteinSimilarity(rec[i],rec[i+6])\n",
" else:\n",
" ngv1 = cng.toMgramCount(rec[i])\n",
" ngv2 = cng.toMgramCount(rec[i+6])\n",
" #printNgramVec(ngv1)\n",
" #printNgramVec(ngv2)\n",
" s = cosineSimilarity(ngv1, ngv2)\n",
" sim.append(s)\n",
" ss = toStrFromList(sim, 6)\n",
" srec = ss + \",\" + rec[-1] if incOutput else ss\n",
" return srec"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "9e9ef369",
"metadata": {},
"outputs": [],
"source": [
"class SimThread (threading.Thread):\n",
" \"\"\" multi threaded similarity calculation \"\"\"\n",
"\n",
" def __init__(self, tName, cng, qu, incOutput, outQu, outQuSize):\n",
" \"\"\" initialize \"\"\"\n",
" threading.Thread.__init__(self)\n",
" self.tName = tName\n",
" self.cng = cng\n",
" self.qu = qu\n",
" self.incOutput = incOutput\n",
" self.outQu = outQu\n",
" self.outQuSize = outQuSize\n",
"\n",
" def run(self):\n",
" \"\"\" exeution \"\"\"\n",
" while not exitFlag:\n",
" rec = dequeue(self.qu, workQuLock)\n",
" if rec is not None:\n",
" srec = getSim(rec, self.incOutput)\n",
" if outQu is None:\n",
" print(srec)\n",
" else:\n",
" enqueue(srec, self.outQu, outQuLock, self.outQuSize)\n",
"\n",
"def createThreads(nworker, cng, workQu, incOutput, outQu, outQuSize):\n",
" \"\"\"create worker threads \"\"\"\n",
" threadList = list(map(lambda i : \"Thread-\" + str(i+1), range(nworker)))\n",
" threads = list()\n",
" for tName in threadList:\n",
" thread = SimThread(tName, cng, workQu, incOutput, outQu, outQuSize)\n",
" thread.start()\n",
" threads.append(thread)\n",
" return threads\n",
"\n",
"\n",
"def enqueue(rec, qu, quLock, qSize): \n",
" \"\"\" enqueue record \"\"\"\n",
" queued = False\n",
" while not queued:\n",
" quLock.acquire()\n",
" if qu.qsize() < qSize - 1:\n",
" qu.put(rec)\n",
" queued = True\n",
" quLock.release()\n",
" time.sleep(1)\n",
"\n",
"def dequeue(qu, quLock): \n",
" \"\"\" dequeue record \"\"\"\n",
" rec = None\n",
" quLock.acquire()\n",
" if not qu.empty():\n",
" rec = qu.get()\n",
" quLock.release()\n",
"\n",
" return rec"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "8248426b",
"metadata": {},
"outputs": [],
"source": [
"if __name__ == \"__main__\":\n",
" #multi threading related\n",
" workQuLock = threading.Lock()\n",
" outQuLock = threading.Lock()\n",
" exitFlag = False\n",
"\n",
" \"\"\" predict with neural network model \"\"\"\n",
" newFilePath = sys.argv[1]\n",
" existFilePath = sys.argv[2]\n",
" nworker = int(sys.argv[3])\n",
" prFile = sys.argv[4]\n",
" \n",
" regr = FeedForwardNetwork(prFile)\n",
" regr.buildModel()\n",
" cng = createNgramCreator()\n",
" \n",
" #create threads\n",
" qSize = 100\n",
" workQu = queue.Queue(qSize)\n",
" outQu = queue.Queue(qSize)\n",
" threads = createThreads(nworker, cng, workQu, False, outQu, qSize)\n",
" \n",
" for nrec in fileRecGen(newFilePath):\n",
" srecs = list()\n",
" ecount = 0\n",
" y_pred = []\n",
" #print(\"processing \", nrec)\n",
" for erec in fileRecGen(existFilePath):\n",
" rec = nrec.copy()\n",
" rec.extend(erec)\n",
" #print(rec)\n",
" \n",
" enqueue(rec, workQu, workQuLock, qSize)\n",
" srec = dequeue(outQu, outQuLock)\n",
" if srec is not None:\n",
" srecs.append(strToFloatArray(srec))\n",
" ecount += 1\n",
"\n",
" #wait til workq queue is drained\n",
" while not workQu.empty():\n",
" pass\n",
"\n",
" #drain out queue\n",
" while len(srecs) < ecount:\n",
" srec = dequeue(outQu, outQuLock)\n",
" if srec is not None:\n",
" srecs.append(strToFloatArray(srec))\n",
" #predict \n",
" simMax = 0\n",
" sims = FeedForwardNetwork.predict(regr, srecs)\n",
" sims = sims.reshape(sims.shape[0])\n",
" y_pred.append(max(sims))\n",
" #print(\"{} {:.3f}\".format(nrec, y_pred))\n",
" print(nrec, max(y_pred))\n",
"\n",
"# exitFlag = True"
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "62187449",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"self.config <mlutil.Configuration object at 0x00000205D0157F10>\n",
"..restoring model checkpoint\n",
"['Lawrence Lorens', '9 Hpy', 'Providence', 'RI', '2906', '[email protected]'] 0.9111754\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"Input \u001b[1;32mIn [34]\u001b[0m, in \u001b[0;36m<cell line: 1>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[43mpredict_main\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
"Input \u001b[1;32mIn [33]\u001b[0m, in \u001b[0;36mpredict_main\u001b[1;34m()\u001b[0m\n\u001b[0;32m 48\u001b[0m \u001b[38;5;66;03m#drain out queue\u001b[39;00m\n\u001b[0;32m 49\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(srecs) \u001b[38;5;241m<\u001b[39m ecount:\n\u001b[1;32m---> 50\u001b[0m srec \u001b[38;5;241m=\u001b[39m \u001b[43mdequeue\u001b[49m\u001b[43m(\u001b[49m\u001b[43moutQu\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43moutQuLock\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 51\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m srec \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m 52\u001b[0m srecs\u001b[38;5;241m.\u001b[39mappend(strToFloatArray(srec))\n",
"Input \u001b[1;32mIn [8]\u001b[0m, in \u001b[0;36mdequeue\u001b[1;34m(qu, quLock)\u001b[0m\n\u001b[0;32m 49\u001b[0m rec \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m 50\u001b[0m quLock\u001b[38;5;241m.\u001b[39macquire()\n\u001b[1;32m---> 51\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[43mqu\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mempty\u001b[49m():\n\u001b[0;32m 52\u001b[0m rec \u001b[38;5;241m=\u001b[39m qu\u001b[38;5;241m.\u001b[39mget()\n\u001b[0;32m 53\u001b[0m quLock\u001b[38;5;241m.\u001b[39mrelease()\n",
"\u001b[1;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"predict_main()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8fa85a13",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|