editsql-cust's Issues
Do you have implemented SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain
hello sir, if you have implemented this paper, can you please provide the code, it'll be helpful..thanks in advance.
dev_use_predicted_queries_predictions.json.
Hi Param,
I am trying to run: bash test_sparc_editsql.sh but I don't see it creating a file called dev_use_predicted_queries_predictions.json, do you know why? Because in your article on towardsdatascience you say that it is supposed to save the prediction in that Json file. For this reason of course I also cannot run the output.py since the given json file doesn't exist. Do you know why this strange behaviour? When I run: bash test_sparc_editsql.sh it seemes that the model run well without any problem.
output.txt adding personalised data
Hi Param,
When I add new databases following your procedures, and then prints the output.txt I see that it prints only the first "subquestion" of the first question (interaction). Same happens of course in the
valid_use_predicted_queries_predictions.json it just prints me the first sub-question. Could you help me understand what is happening and how to solve it? I modified the files exactly as explained by you, tried with different sqilte databeses but always got just the first subquestion.
Thank you in advance,
Imanuel
Error File not found
Hi @Param-Raval. Your article on medium was great but there is a slight problem, I did all the steps as you said but got an error. i would really appreciate if you can have a look into it. Thanks in advance.
This is the output and error. :))
size of output_vocab 37
output_vocab ['_UNK', '_EOS', '=', 'select', 'value', ')', '(', 'where', ',', 'count', 'group_by', 'order_by', 'distinct', 'and', 'limit_value', 'limit', 'desc', '>', 'avg', 'having', 'max', 'in', '<', 'sum', 'intersect', 'not', 'min', 'except', 'or', 'asc', 'like', '!=', 'union', 'between', '-', '+', '/']
Reading spider database schema file
num_database 166 140 20
total number of schema_tokens / databases: 166
read_data_json data/sparc/train_no_value.json 3034
read_data_json data/sparc/dev_no_value.json 422
interaction_list length 160
train interaction: 3024
dev interaction: 422
Traceback (most recent call last):
File "run.py", line 12, in <module>
from data_util import atis_data
File "/content/drive/My Drive/editsql/data_util/atis_data.py", line 7, in <module>
from . import atis_batch
File "/content/drive/My Drive/editsql/data_util/atis_batch.py", line 5, in <module>
from . import sql_util
File "/content/drive/My Drive/editsql/data_util/sql_util.py", line 2, in <module>
import pymysql
ModuleNotFoundError: No module named 'pymysql'
Read prediction from logs_sparc_editsql/valid_use_predicted_queries_predictions.json
Traceback (most recent call last):
File "postprocess_eval.py", line 466, in <module>
predictions = read_prediction(pred_file)
File "postprocess_eval.py", line 384, in read_prediction
with open(pred_file) as f:
FileNotFoundError: [Errno 2] No such file or directory: 'logs_sparc_editsql/valid_use_predicted_queries_predictions.json'
Didn't get how to edit dev.json and dev_no_value.json
Hi @Param-Raval. I have query regarding the custom database. You said we have to edit the dev.json and add our question but do we have to add the query(answer) too?
I will really appreciate if you can help me out
Editing Tables.json
Hey Param,
Thank you for the pointers in training editsql for a custom database. My question is on editing tables.json. As the format is presented,
{
"column_names": [
[
0,
"id"
],
[
0,
"name"
],
[
0,
"country code"
],
[
0,
"district"
],
.
.
.
What do the indices 0,1,2 etc. represent here?
glove.840B.300d.txt
Hi Param,
I followed all your step, but in addition I also downloaded the glove.840B.300d.txt and change the path in the corresponding run_sparc_edistql.sh file and test_sparc_editsql.sh file and when I run the run_sparc_edistql.sh file it gives me the following Error:
Loading Glove Embedding from /content/gdrive/MyDrive/practica/glove.840B.300d.txt
Traceback (most recent call last):
File "run.py", line 338, in <module>
main()
File "run.py", line 301, in main
data.anonymizer if params.anonymize and params.anonymization_scoring else None)
File "/content/gdrive/My Drive/practica/editsql/model/schema_interaction_model.py", line 49, in __init__
anonymizer)
File "/content/gdrive/My Drive/practica/editsql/model/model.py", line 149, in __init__
input_vocabulary_embeddings, output_vocabulary_embeddings, output_vocabulary_schema_embeddings, input_embedding_size = load_word_embeddings(input_vocabulary, output_vocabulary, output_vocabulary_schema, params)
File "/content/gdrive/My Drive/practica/editsql/model/model.py", line 98, in load_word_embeddings
glove_embeddings = read_glove_embedding(params.embedding_filename, glove_embedding_size)
File "/content/gdrive/My Drive/practica/editsql/model/model.py", line 91, in read_glove_embedding
embedding = np.array([float(val) for val in l_split[-embedding_size:]])
File "/content/gdrive/My Drive/practica/editsql/model/model.py", line 91, in <listcomp>
embedding = np.array([float(val) for val in l_split[-embedding_size:]])
ValueError: could not convert string to float: 'squeeze2'
Read prediction from logs_sparc_editsql/valid_use_predicted_queries_predictions.json
Number of predictions 1203
Eval result in logs_sparc_editsql/valid_use_predicted_queries_predictions.json.eval
Could you help me? If I don't change the directory in GLOVE_PATH and leave it as it is I also have problems.
Thank you in advance.
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.