matt-tries-dl
commited on
Commit
•
9084b03
1
Parent(s):
01e2d8f
turn query structure into sql text
Browse files- llama_test.ipynb +26 -7
llama_test.ipynb
CHANGED
@@ -160,7 +160,7 @@
|
|
160 |
},
|
161 |
{
|
162 |
"cell_type": "code",
|
163 |
-
"execution_count":
|
164 |
"metadata": {},
|
165 |
"outputs": [
|
166 |
{
|
@@ -172,27 +172,46 @@
|
|
172 |
"1-1000181-1\n",
|
173 |
"['State/territory', 'Text/background colour', 'Format', 'Current slogan', 'Current series', 'Notes']\n",
|
174 |
"\n",
|
175 |
-
"{'id': '1-1000181-1', 'header': ['State/territory', 'Text/background colour', 'Format', 'Current slogan', 'Current series', 'Notes'], 'types': ['text', 'text', 'text', 'text', 'text', 'text'], 'rows': [['Australian Capital Territory', 'blue/white', 'Yaa·nna', 'ACT · CELEBRATION OF A CENTURY 2013', 'YIL·00A', 'Slogan screenprinted on plate'], ['New South Wales', 'black/yellow', 'aa·nn·aa', 'NEW SOUTH WALES', 'BX·99·HI', 'No slogan on current series'], ['New South Wales', 'black/white', 'aaa·nna', 'NSW', 'CPX·12A', 'Optional white slimline series'], ['Northern Territory', 'ochre/white', 'Ca·nn·aa', 'NT · OUTBACK AUSTRALIA', 'CB·06·ZZ', 'New series began in June 2011'], ['Queensland', 'maroon/white', 'nnn·aaa', 'QUEENSLAND · SUNSHINE STATE', '999·TLG', 'Slogan embossed on plate'], ['South Australia', 'black/white', 'Snnn·aaa', 'SOUTH AUSTRALIA', 'S000·AZD', 'No slogan on current series'], ['Victoria', 'blue/white', 'aaa·nnn', 'VICTORIA - THE PLACE TO BE', 'ZZZ·562', 'Current series will be exhausted this year']], 'name': 'table_1000181_1'}\n"
|
|
|
|
|
176 |
]
|
177 |
}
|
178 |
],
|
179 |
"source": [
|
180 |
"import json\n",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
181 |
"with open('data/train.jsonl') as f:\n",
|
182 |
" j = f.readline()\n",
|
183 |
" js = json.loads(j)\n",
|
184 |
" print(js)\n",
|
185 |
-
"\n",
|
186 |
"print()\n",
|
187 |
"\n",
|
188 |
"with open('data/train.tables.jsonl') as f:\n",
|
189 |
" j = f.readline()\n",
|
190 |
-
"
|
191 |
" #print(js)\n",
|
192 |
-
" print(
|
193 |
-
" print(
|
194 |
" print()\n",
|
195 |
-
" print(
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
196 |
]
|
197 |
}
|
198 |
],
|
|
|
160 |
},
|
161 |
{
|
162 |
"cell_type": "code",
|
163 |
+
"execution_count": 12,
|
164 |
"metadata": {},
|
165 |
"outputs": [
|
166 |
{
|
|
|
172 |
"1-1000181-1\n",
|
173 |
"['State/territory', 'Text/background colour', 'Format', 'Current slogan', 'Current series', 'Notes']\n",
|
174 |
"\n",
|
175 |
+
"{'id': '1-1000181-1', 'header': ['State/territory', 'Text/background colour', 'Format', 'Current slogan', 'Current series', 'Notes'], 'types': ['text', 'text', 'text', 'text', 'text', 'text'], 'rows': [['Australian Capital Territory', 'blue/white', 'Yaa·nna', 'ACT · CELEBRATION OF A CENTURY 2013', 'YIL·00A', 'Slogan screenprinted on plate'], ['New South Wales', 'black/yellow', 'aa·nn·aa', 'NEW SOUTH WALES', 'BX·99·HI', 'No slogan on current series'], ['New South Wales', 'black/white', 'aaa·nna', 'NSW', 'CPX·12A', 'Optional white slimline series'], ['Northern Territory', 'ochre/white', 'Ca·nn·aa', 'NT · OUTBACK AUSTRALIA', 'CB·06·ZZ', 'New series began in June 2011'], ['Queensland', 'maroon/white', 'nnn·aaa', 'QUEENSLAND · SUNSHINE STATE', '999·TLG', 'Slogan embossed on plate'], ['South Australia', 'black/white', 'Snnn·aaa', 'SOUTH AUSTRALIA', 'S000·AZD', 'No slogan on current series'], ['Victoria', 'blue/white', 'aaa·nnn', 'VICTORIA - THE PLACE TO BE', 'ZZZ·562', 'Current series will be exhausted this year']], 'name': 'table_1000181_1'}\n",
|
176 |
+
"SELECT col5 FROM table WHERE col3 = SOUTH AUSTRALIA\n",
|
177 |
+
"SELECT Notes FROM table WHERE Current slogan = SOUTH AUSTRALIA\n"
|
178 |
]
|
179 |
}
|
180 |
],
|
181 |
"source": [
|
182 |
"import json\n",
|
183 |
+
"import sys\n",
|
184 |
+
"import re\n",
|
185 |
+
"sys.path.append('./WikiSQL')\n",
|
186 |
+
"from WikiSQL.lib.query import Query\n",
|
187 |
+
"\n",
|
188 |
+
"def replace_cols(qs,cmap):\n",
|
189 |
+
" for k,v in cmap.items():\n",
|
190 |
+
" qs = re.sub(f' {k} ',f' {v} ',qs)\n",
|
191 |
+
" return qs\n",
|
192 |
+
"\n",
|
193 |
"with open('data/train.jsonl') as f:\n",
|
194 |
" j = f.readline()\n",
|
195 |
" js = json.loads(j)\n",
|
196 |
" print(js)\n",
|
197 |
+
" \n",
|
198 |
"print()\n",
|
199 |
"\n",
|
200 |
"with open('data/train.tables.jsonl') as f:\n",
|
201 |
" j = f.readline()\n",
|
202 |
+
" js2 = json.loads(j)\n",
|
203 |
" #print(js)\n",
|
204 |
+
" print(js2['id'])\n",
|
205 |
+
" print(js2['header'])\n",
|
206 |
" print()\n",
|
207 |
+
" print(js2)\n",
|
208 |
+
"\n",
|
209 |
+
"sql = js['sql']\n",
|
210 |
+
"q = Query.from_dict(sql)\n",
|
211 |
+
"print(q)\n",
|
212 |
+
"cm = {f'col{i}':js2['header'][i] for i in range(len(js2['header']))}\n",
|
213 |
+
"qs = replace_cols(str(q),cm)\n",
|
214 |
+
"print(qs)"
|
215 |
]
|
216 |
}
|
217 |
],
|