Updated generated data

app.py

@@ -139,6 +139,7 @@ def filter_df(df, display, ptype, filter_by, display_scores):
         str)+"->"+df_sel["new_label"].astype(str)
     df_sel["og/new label"]=label_col
     df_sel.drop(["og_label", "new_label"], axis=1, inplace=True)
+    df_sel.drop_duplicates(inplace=True, ignore_index=True)
     return df_sel
 
 

generate_scores.ipynb

@@ -0,0 +1,246 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "32744c39-dae0-4f8c-beea-af8cf934f977",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from paraphrase_metrics import metrics as pm\n",
+    "import pandas as pd\n",
+    "import spacy\n",
+    "from tqdm import tqdm\n",
+    "nlp = spacy.load(\"en_core_web_sm\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c219268a-d25b-4b27-b0eb-0bb578ec3450",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>og_s1</th>\n",
+       "      <th>og_s2</th>\n",
+       "      <th>new_s1</th>\n",
+       "      <th>new_s2</th>\n",
+       "      <th>og_label</th>\n",
+       "      <th>new_label</th>\n",
+       "      <th>remarks</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Amrozi accused his brother, whom he called \"th...</td>\n",
+       "      <td>Referring to him as only \"the witness\", Amrozi...</td>\n",
+       "      <td>Amrozi accused his brother, whom he called \"th...</td>\n",
+       "      <td>Referring to him as only \"the witness\", Amrozi...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>no need to correct</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Yucaipa owned Dominick's before selling the ch...</td>\n",
+       "      <td>Yucaipa bought Dominick's in 1995 for $693 mil...</td>\n",
+       "      <td>Yucaipa owned Dominick's before selling the ch...</td>\n",
+       "      <td>Yucaipa bought Dominick's in 1995 for $693 mil...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>no need to correct</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>They had published an advertisement on the Int...</td>\n",
+       "      <td>On June 10, the ship's owners had published an...</td>\n",
+       "      <td>They had published an advertisement on the Int...</td>\n",
+       "      <td>On June 10, the ship's owners had published an...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>no need to correct</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Around 0335 GMT, Tab shares were up 19 cents, ...</td>\n",
+       "      <td>Tab shares jumped 20 cents, or 4.6%, to set a ...</td>\n",
+       "      <td>Around 0335 GMT, Tab shares were up 19 cents, ...</td>\n",
+       "      <td>Tab shares jumped 20 cents, or 4.6%, to set a ...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>no need to correct</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>The stock rose $2.11, or about 11 percent, to ...</td>\n",
+       "      <td>PG&amp;E Corp. shares jumped $1.63 or 8 percent to...</td>\n",
+       "      <td>The stock rose $2.11, or about 11 percent, to ...</td>\n",
+       "      <td>PG&amp;E Corp. shares jumped $1.63 or 8 percent to...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>can't correct</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                               og_s1  \\\n",
+       "0  Amrozi accused his brother, whom he called \"th...   \n",
+       "1  Yucaipa owned Dominick's before selling the ch...   \n",
+       "2  They had published an advertisement on the Int...   \n",
+       "3  Around 0335 GMT, Tab shares were up 19 cents, ...   \n",
+       "4  The stock rose $2.11, or about 11 percent, to ...   \n",
+       "\n",
+       "                                               og_s2  \\\n",
+       "0  Referring to him as only \"the witness\", Amrozi...   \n",
+       "1  Yucaipa bought Dominick's in 1995 for $693 mil...   \n",
+       "2  On June 10, the ship's owners had published an...   \n",
+       "3  Tab shares jumped 20 cents, or 4.6%, to set a ...   \n",
+       "4  PG&E Corp. shares jumped $1.63 or 8 percent to...   \n",
+       "\n",
+       "                                              new_s1  \\\n",
+       "0  Amrozi accused his brother, whom he called \"th...   \n",
+       "1  Yucaipa owned Dominick's before selling the ch...   \n",
+       "2  They had published an advertisement on the Int...   \n",
+       "3  Around 0335 GMT, Tab shares were up 19 cents, ...   \n",
+       "4  The stock rose $2.11, or about 11 percent, to ...   \n",
+       "\n",
+       "                                              new_s2  og_label  new_label  \\\n",
+       "0  Referring to him as only \"the witness\", Amrozi...         1          1   \n",
+       "1  Yucaipa bought Dominick's in 1995 for $693 mil...         0          0   \n",
+       "2  On June 10, the ship's owners had published an...         1          1   \n",
+       "3  Tab shares jumped 20 cents, or 4.6%, to set a ...         0          0   \n",
+       "4  PG&E Corp. shares jumped $1.63 or 8 percent to...         1          0   \n",
+       "\n",
+       "              remarks  \n",
+       "0  no need to correct  \n",
+       "1  no need to correct  \n",
+       "2  no need to correct  \n",
+       "3  no need to correct  \n",
+       "4       can't correct  "
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "split = \"train\"\n",
+    "df = pd.read_csv(\"./mrpc_\"+split+\"_corrected.csv\")\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "36cba8a1-8997-4563-9c33-4d4f6049ec5a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 4409/4409 [00:53<00:00, 82.98it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "og_wpd_list = []\n",
+    "og_ld_list = []\n",
+    "new_wpd_list = []\n",
+    "new_ld_list = []\n",
+    "\n",
+    "for index, row in tqdm(df.iterrows(), total=len(df)):\n",
+    "    # original pair\n",
+    "    og_s1, og_s2 = nlp(row['og_s1']), nlp(row['og_s2'])\n",
+    "    og_wpd = pm.wpd(og_s1, og_s2)\n",
+    "    og_ld = pm.ld(og_s1, og_s2)\n",
+    "    og_wpd_list.append(og_wpd)\n",
+    "    og_ld_list.append(og_ld)\n",
+    "    \n",
+    "    # new pair\n",
+    "    new_s1, new_s2 = nlp(row['new_s1']), nlp(row['new_s2'])\n",
+    "    new_wpd = pm.wpd(new_s1, new_s2)\n",
+    "    new_ld = pm.ld(new_s1, new_s2)\n",
+    "    new_wpd_list.append(new_wpd)\n",
+    "    new_ld_list.append(new_ld)\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "afcf311c-3c44-4d08-b8df-8decf051e315",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df[\"og_wpd\"] = og_wpd_list\n",
+    "df[\"og_ld\"] = og_ld_list\n",
+    "df[\"new_wpd\"] = new_wpd_list\n",
+    "df[\"new_ld\"] = new_ld_list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "9e8c3562-58ad-43d0-b887-218769a885b7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv(\"./mrpc_\"+split+\"_scores.csv\", index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "05aa6437-c11c-4f06-9e23-a300d26e128d",
+   "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
+}