Spaces:
Runtime error
Runtime error
Updated generated data
Browse files- app.py +1 -0
- generate_scores.ipynb +246 -0
- mrpc_test_corrected.csv +0 -0
- mrpc_test_scores.csv +0 -0
- mrpc_train_corrected.csv +0 -0
- mrpc_train_scores.csv +0 -0
app.py
CHANGED
@@ -139,6 +139,7 @@ def filter_df(df, display, ptype, filter_by, display_scores):
|
|
139 |
str)+"->"+df_sel["new_label"].astype(str)
|
140 |
df_sel["og/new label"]=label_col
|
141 |
df_sel.drop(["og_label", "new_label"], axis=1, inplace=True)
|
|
|
142 |
return df_sel
|
143 |
|
144 |
|
|
|
139 |
str)+"->"+df_sel["new_label"].astype(str)
|
140 |
df_sel["og/new label"]=label_col
|
141 |
df_sel.drop(["og_label", "new_label"], axis=1, inplace=True)
|
142 |
+
df_sel.drop_duplicates(inplace=True, ignore_index=True)
|
143 |
return df_sel
|
144 |
|
145 |
|
generate_scores.ipynb
ADDED
@@ -0,0 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 1,
|
6 |
+
"id": "32744c39-dae0-4f8c-beea-af8cf934f977",
|
7 |
+
"metadata": {},
|
8 |
+
"outputs": [],
|
9 |
+
"source": [
|
10 |
+
"from paraphrase_metrics import metrics as pm\n",
|
11 |
+
"import pandas as pd\n",
|
12 |
+
"import spacy\n",
|
13 |
+
"from tqdm import tqdm\n",
|
14 |
+
"nlp = spacy.load(\"en_core_web_sm\")"
|
15 |
+
]
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"cell_type": "code",
|
19 |
+
"execution_count": 2,
|
20 |
+
"id": "c219268a-d25b-4b27-b0eb-0bb578ec3450",
|
21 |
+
"metadata": {},
|
22 |
+
"outputs": [
|
23 |
+
{
|
24 |
+
"data": {
|
25 |
+
"text/html": [
|
26 |
+
"<div>\n",
|
27 |
+
"<style scoped>\n",
|
28 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
29 |
+
" vertical-align: middle;\n",
|
30 |
+
" }\n",
|
31 |
+
"\n",
|
32 |
+
" .dataframe tbody tr th {\n",
|
33 |
+
" vertical-align: top;\n",
|
34 |
+
" }\n",
|
35 |
+
"\n",
|
36 |
+
" .dataframe thead th {\n",
|
37 |
+
" text-align: right;\n",
|
38 |
+
" }\n",
|
39 |
+
"</style>\n",
|
40 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
41 |
+
" <thead>\n",
|
42 |
+
" <tr style=\"text-align: right;\">\n",
|
43 |
+
" <th></th>\n",
|
44 |
+
" <th>og_s1</th>\n",
|
45 |
+
" <th>og_s2</th>\n",
|
46 |
+
" <th>new_s1</th>\n",
|
47 |
+
" <th>new_s2</th>\n",
|
48 |
+
" <th>og_label</th>\n",
|
49 |
+
" <th>new_label</th>\n",
|
50 |
+
" <th>remarks</th>\n",
|
51 |
+
" </tr>\n",
|
52 |
+
" </thead>\n",
|
53 |
+
" <tbody>\n",
|
54 |
+
" <tr>\n",
|
55 |
+
" <th>0</th>\n",
|
56 |
+
" <td>Amrozi accused his brother, whom he called \"th...</td>\n",
|
57 |
+
" <td>Referring to him as only \"the witness\", Amrozi...</td>\n",
|
58 |
+
" <td>Amrozi accused his brother, whom he called \"th...</td>\n",
|
59 |
+
" <td>Referring to him as only \"the witness\", Amrozi...</td>\n",
|
60 |
+
" <td>1</td>\n",
|
61 |
+
" <td>1</td>\n",
|
62 |
+
" <td>no need to correct</td>\n",
|
63 |
+
" </tr>\n",
|
64 |
+
" <tr>\n",
|
65 |
+
" <th>1</th>\n",
|
66 |
+
" <td>Yucaipa owned Dominick's before selling the ch...</td>\n",
|
67 |
+
" <td>Yucaipa bought Dominick's in 1995 for $693 mil...</td>\n",
|
68 |
+
" <td>Yucaipa owned Dominick's before selling the ch...</td>\n",
|
69 |
+
" <td>Yucaipa bought Dominick's in 1995 for $693 mil...</td>\n",
|
70 |
+
" <td>0</td>\n",
|
71 |
+
" <td>0</td>\n",
|
72 |
+
" <td>no need to correct</td>\n",
|
73 |
+
" </tr>\n",
|
74 |
+
" <tr>\n",
|
75 |
+
" <th>2</th>\n",
|
76 |
+
" <td>They had published an advertisement on the Int...</td>\n",
|
77 |
+
" <td>On June 10, the ship's owners had published an...</td>\n",
|
78 |
+
" <td>They had published an advertisement on the Int...</td>\n",
|
79 |
+
" <td>On June 10, the ship's owners had published an...</td>\n",
|
80 |
+
" <td>1</td>\n",
|
81 |
+
" <td>1</td>\n",
|
82 |
+
" <td>no need to correct</td>\n",
|
83 |
+
" </tr>\n",
|
84 |
+
" <tr>\n",
|
85 |
+
" <th>3</th>\n",
|
86 |
+
" <td>Around 0335 GMT, Tab shares were up 19 cents, ...</td>\n",
|
87 |
+
" <td>Tab shares jumped 20 cents, or 4.6%, to set a ...</td>\n",
|
88 |
+
" <td>Around 0335 GMT, Tab shares were up 19 cents, ...</td>\n",
|
89 |
+
" <td>Tab shares jumped 20 cents, or 4.6%, to set a ...</td>\n",
|
90 |
+
" <td>0</td>\n",
|
91 |
+
" <td>0</td>\n",
|
92 |
+
" <td>no need to correct</td>\n",
|
93 |
+
" </tr>\n",
|
94 |
+
" <tr>\n",
|
95 |
+
" <th>4</th>\n",
|
96 |
+
" <td>The stock rose $2.11, or about 11 percent, to ...</td>\n",
|
97 |
+
" <td>PG&E Corp. shares jumped $1.63 or 8 percent to...</td>\n",
|
98 |
+
" <td>The stock rose $2.11, or about 11 percent, to ...</td>\n",
|
99 |
+
" <td>PG&E Corp. shares jumped $1.63 or 8 percent to...</td>\n",
|
100 |
+
" <td>1</td>\n",
|
101 |
+
" <td>0</td>\n",
|
102 |
+
" <td>can't correct</td>\n",
|
103 |
+
" </tr>\n",
|
104 |
+
" </tbody>\n",
|
105 |
+
"</table>\n",
|
106 |
+
"</div>"
|
107 |
+
],
|
108 |
+
"text/plain": [
|
109 |
+
" og_s1 \\\n",
|
110 |
+
"0 Amrozi accused his brother, whom he called \"th... \n",
|
111 |
+
"1 Yucaipa owned Dominick's before selling the ch... \n",
|
112 |
+
"2 They had published an advertisement on the Int... \n",
|
113 |
+
"3 Around 0335 GMT, Tab shares were up 19 cents, ... \n",
|
114 |
+
"4 The stock rose $2.11, or about 11 percent, to ... \n",
|
115 |
+
"\n",
|
116 |
+
" og_s2 \\\n",
|
117 |
+
"0 Referring to him as only \"the witness\", Amrozi... \n",
|
118 |
+
"1 Yucaipa bought Dominick's in 1995 for $693 mil... \n",
|
119 |
+
"2 On June 10, the ship's owners had published an... \n",
|
120 |
+
"3 Tab shares jumped 20 cents, or 4.6%, to set a ... \n",
|
121 |
+
"4 PG&E Corp. shares jumped $1.63 or 8 percent to... \n",
|
122 |
+
"\n",
|
123 |
+
" new_s1 \\\n",
|
124 |
+
"0 Amrozi accused his brother, whom he called \"th... \n",
|
125 |
+
"1 Yucaipa owned Dominick's before selling the ch... \n",
|
126 |
+
"2 They had published an advertisement on the Int... \n",
|
127 |
+
"3 Around 0335 GMT, Tab shares were up 19 cents, ... \n",
|
128 |
+
"4 The stock rose $2.11, or about 11 percent, to ... \n",
|
129 |
+
"\n",
|
130 |
+
" new_s2 og_label new_label \\\n",
|
131 |
+
"0 Referring to him as only \"the witness\", Amrozi... 1 1 \n",
|
132 |
+
"1 Yucaipa bought Dominick's in 1995 for $693 mil... 0 0 \n",
|
133 |
+
"2 On June 10, the ship's owners had published an... 1 1 \n",
|
134 |
+
"3 Tab shares jumped 20 cents, or 4.6%, to set a ... 0 0 \n",
|
135 |
+
"4 PG&E Corp. shares jumped $1.63 or 8 percent to... 1 0 \n",
|
136 |
+
"\n",
|
137 |
+
" remarks \n",
|
138 |
+
"0 no need to correct \n",
|
139 |
+
"1 no need to correct \n",
|
140 |
+
"2 no need to correct \n",
|
141 |
+
"3 no need to correct \n",
|
142 |
+
"4 can't correct "
|
143 |
+
]
|
144 |
+
},
|
145 |
+
"execution_count": 2,
|
146 |
+
"metadata": {},
|
147 |
+
"output_type": "execute_result"
|
148 |
+
}
|
149 |
+
],
|
150 |
+
"source": [
|
151 |
+
"split = \"train\"\n",
|
152 |
+
"df = pd.read_csv(\"./mrpc_\"+split+\"_corrected.csv\")\n",
|
153 |
+
"df.head()"
|
154 |
+
]
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"cell_type": "code",
|
158 |
+
"execution_count": 3,
|
159 |
+
"id": "36cba8a1-8997-4563-9c33-4d4f6049ec5a",
|
160 |
+
"metadata": {},
|
161 |
+
"outputs": [
|
162 |
+
{
|
163 |
+
"name": "stderr",
|
164 |
+
"output_type": "stream",
|
165 |
+
"text": [
|
166 |
+
"100%|██████████| 4409/4409 [00:53<00:00, 82.98it/s]\n"
|
167 |
+
]
|
168 |
+
}
|
169 |
+
],
|
170 |
+
"source": [
|
171 |
+
"og_wpd_list = []\n",
|
172 |
+
"og_ld_list = []\n",
|
173 |
+
"new_wpd_list = []\n",
|
174 |
+
"new_ld_list = []\n",
|
175 |
+
"\n",
|
176 |
+
"for index, row in tqdm(df.iterrows(), total=len(df)):\n",
|
177 |
+
" # original pair\n",
|
178 |
+
" og_s1, og_s2 = nlp(row['og_s1']), nlp(row['og_s2'])\n",
|
179 |
+
" og_wpd = pm.wpd(og_s1, og_s2)\n",
|
180 |
+
" og_ld = pm.ld(og_s1, og_s2)\n",
|
181 |
+
" og_wpd_list.append(og_wpd)\n",
|
182 |
+
" og_ld_list.append(og_ld)\n",
|
183 |
+
" \n",
|
184 |
+
" # new pair\n",
|
185 |
+
" new_s1, new_s2 = nlp(row['new_s1']), nlp(row['new_s2'])\n",
|
186 |
+
" new_wpd = pm.wpd(new_s1, new_s2)\n",
|
187 |
+
" new_ld = pm.ld(new_s1, new_s2)\n",
|
188 |
+
" new_wpd_list.append(new_wpd)\n",
|
189 |
+
" new_ld_list.append(new_ld)\n",
|
190 |
+
" "
|
191 |
+
]
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"cell_type": "code",
|
195 |
+
"execution_count": 4,
|
196 |
+
"id": "afcf311c-3c44-4d08-b8df-8decf051e315",
|
197 |
+
"metadata": {},
|
198 |
+
"outputs": [],
|
199 |
+
"source": [
|
200 |
+
"df[\"og_wpd\"] = og_wpd_list\n",
|
201 |
+
"df[\"og_ld\"] = og_ld_list\n",
|
202 |
+
"df[\"new_wpd\"] = new_wpd_list\n",
|
203 |
+
"df[\"new_ld\"] = new_ld_list"
|
204 |
+
]
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"cell_type": "code",
|
208 |
+
"execution_count": 5,
|
209 |
+
"id": "9e8c3562-58ad-43d0-b887-218769a885b7",
|
210 |
+
"metadata": {},
|
211 |
+
"outputs": [],
|
212 |
+
"source": [
|
213 |
+
"df.to_csv(\"./mrpc_\"+split+\"_scores.csv\", index=False)"
|
214 |
+
]
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"cell_type": "code",
|
218 |
+
"execution_count": null,
|
219 |
+
"id": "05aa6437-c11c-4f06-9e23-a300d26e128d",
|
220 |
+
"metadata": {},
|
221 |
+
"outputs": [],
|
222 |
+
"source": []
|
223 |
+
}
|
224 |
+
],
|
225 |
+
"metadata": {
|
226 |
+
"kernelspec": {
|
227 |
+
"display_name": "Python 3 (ipykernel)",
|
228 |
+
"language": "python",
|
229 |
+
"name": "python3"
|
230 |
+
},
|
231 |
+
"language_info": {
|
232 |
+
"codemirror_mode": {
|
233 |
+
"name": "ipython",
|
234 |
+
"version": 3
|
235 |
+
},
|
236 |
+
"file_extension": ".py",
|
237 |
+
"mimetype": "text/x-python",
|
238 |
+
"name": "python",
|
239 |
+
"nbconvert_exporter": "python",
|
240 |
+
"pygments_lexer": "ipython3",
|
241 |
+
"version": "3.9.12"
|
242 |
+
}
|
243 |
+
},
|
244 |
+
"nbformat": 4,
|
245 |
+
"nbformat_minor": 5
|
246 |
+
}
|
mrpc_test_corrected.csv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
mrpc_test_scores.csv
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
mrpc_train_corrected.csv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
mrpc_train_scores.csv
CHANGED
The diff for this file is too large to render.
See raw diff
|
|