File size: 8,403 Bytes
df3852e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
 "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
}