paulfitz / mlsql Goto Github PK
View Code? Open in Web Editor NEWinferring sql queries from plain-text questions about tables
inferring sql queries from plain-text questions about tables
Hi,
Thanks
Bill
Hi,
How to finetune the model with custom queries, tables in .csv and with SQL queries ?
Thank you in advance.
I have implemented it and used it and now I can get all the answers, but when I try the same on my custom csv file, it generates the query but doesn't "answer" for the query as it did to your csv files. May I know the reason?
and What is this params thing? I don't understand why not keeps the params in the query?
I got an error while running the program.
What could be the cause?
algorithm | datasets | Accuracy |
---|---|---|
gloom | chaos | 5 |
gloom | violin | 6 |
gloom | tooth | 5 |
brave | chaos | 4 |
brave | violin | 8 |
brave | tooth | 9 |
input:
curl -F "[email protected]" -F "q=Is the accuracy of the algorithm gloom in the dataset chaos smaller than the accuracy of the algorithm brave in the dataset tooth?" localhost:5050
error:
{"error":"invalid argument 0: Sizes of tensors must match except in dimension 2. Got 3 and 4 in dimension 1 at /Users/soumith/code/builder/wheel/pytorch-src/aten/src/TH/generic/THTensorMath.cpp:3616"}
Hi,
How to run in local environment without using docker?
also, I want to import a natural language sentence into a program and get the arithmetic value and the nth value.
Can you tell me how?
Thank you in advance.
Everything works fine with curl.
But when i am using requests.post() in python
it works for the first time but fails in the second time and so on.
I have to change the name of the parameter
import requests
url = 'http://localhost:5050'
path = 'bridges.csv'
csv = {'csv' : open(path ,'rb')}
payload = {'debug' : False, 'q' : 'how long is throgs neck'}
r = requests.post(url = url ,files=csv,data=payload)
r.json() > this works for the first time but fails afterwards
#Second time failed output
r.text > u'{"base":"bridges_b884af26-ef36-4876-9d01-469044242365","error":"object of type \'NoneType\' has no len()"}\n'
r.status_code > 500
#if i do csv1 = {'csv' : open(path ,'rb')} # CHANGED THE NAME OF csv to csv1(or anyother) it works fine again
r = requests.post(url = url ,files=csv1,data=payload)
Anybody knows the reason?
{
"error": "'utf-8' codec can't decode byte 0xc9 in position 602: invalid continuation byte"
}
The datasets like WikiSQL is that the table corresponding to question is given.
But in real industrial application, we have 100+ tables for 1 new question.
Thank you!
select col1, col2
from ...
is this type of query supported?
Hi,
as I am trying to run valuenet on my own examples, I am blocked at generating the "sqlite" format.
Here are the details.
Valuenet keeps the spider dat a in the directory valuenet/data/spider/original/database/
here , for each schema you have a directory, like "concert_singer", which contains two file:
"schema.sql" - the sql creation of the table and insertt values
and
"concert_singer.sqlite" which apparently contains the database and it is the file read by valuenet in order to execute
db_value_finder.find_similar_values_in_database
I would greatly appreciate if you could tell me how to generate the sqlite file form the "schema.sql" file , or anything will do.
Thank you
As 5050 port is already ON. How can I send and receive data using postman?
I used the following as given, however i do not get the expected results. Where do you think is the error, please help.
docker run --name sqlova -d -p 5050:5050 paulfitz/sqlova
\mlsql-master>curl -F "[email protected]" -F "q=how long is throgs neck" localhost:5050
curl: (52) Empty reply from server
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.