notebook status

large-corpus/Merge Vocab.ipynb

@@ -11,7 +11,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -33,24 +33,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
-    "files = ['pytorch_mlm_vocab-code.txt', 'sklearn_mlm_vocab-code.txt', 'keras_mlm_vocab-code.txt']\n",
+    "corpus_members = ['pytorch', 'sklearn', 'keras', 'ansible', 'youtube-dl', 'flask', 'httpie', 'requests', 'django', 'bert']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "files = [f+'_mlm_vocab-code.txt' for f in corpus_members]\n",
     "out_file = 'global_vocab.csv'"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "3823\n"
+      "9769\n"
      ]
     }
    ],

mid-corpus/Merge Vocab.ipynb

@@ -0,0 +1,131 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import csv\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def merge_vocab(files, out):\n",
+    "    global_vocab = []\n",
+    "    for f in files:\n",
+    "        with open(f, 'r') as csvfile:\n",
+    "            reader = csv.reader(csvfile, delimiter=' ', quotechar='|')\n",
+    "            for row in reader:\n",
+    "                if row[0] not in global_vocab:\n",
+    "                    global_vocab.append(row[0])\n",
+    "    print(len(set(global_vocab)))\n",
+    "    with open(out, 'w') as csvfile:\n",
+    "        writer = csv.writer(csvfile, delimiter=' ',\n",
+    "                                quotechar='|', quoting=csv.QUOTE_MINIMAL)\n",
+    "        for v in global_vocab:\n",
+    "            writer.writerow([v])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "files = ['pytorch_mlm_vocab-code.txt', 'sklearn_mlm_vocab-code.txt', 'keras_mlm_vocab-code.txt']\n",
+    "out_file = 'global_vocab.csv'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "3823\n"
+     ]
+    }
+   ],
+   "source": [
+    "merge_vocab(files, out_file)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "label_files = ['pytorch_cls_vocab-label.txt', 'sklearn_cls_vocab-label.txt', 'keras_cls_vocab-label.txt']\n",
+    "label_out = 'label_vocab.csv'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2490\n"
+     ]
+    }
+   ],
+   "source": [
+    "merge_vocab(label_files, label_out)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.5.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}