figure

README.md

@@ -10,7 +10,7 @@ A deep language model, GPT-2, is trained on scientific manuscripts from NASA's A
 ```python
 from transformers import pipeline
 
-exo = pipeline('text-generation',model='gpt2-exomachina/checkpoint-320000', tokenizer='gpt2', config={'max_length':1600})
+exo = pipeline('text-generation',model='pearsonkyle/gpt2-exomachina', tokenizer='gpt2', config={'max_length':1600})
 machina = lambda text: exo(text)[0]['generated_text']
 
 print(machina("Transiting exoplanets are"))
@@ -19,7 +19,7 @@ print(machina("Transiting exoplanets are"))
 ## Training Samples
 ~40,000 Abstracts from NASA's Astrophysical data system (ADS) and ArXiv. 
 
-![](Figures/exoplanet_keywords.png)
+![](exoplanet_keywords.png)
 
 A few generated samples are below: 
 
@@ -28,49 +28,7 @@ A few generated samples are below:
 `that large, deciduous forest fires are composed of mostly dry, unprocessed material that is distributed in a nearly patchy fashion. The distributions of these fires are correlated with temperature, and also with vegetation...`
 - *Directly imaged exoplanets probe* `key aspects of planet formation and evolution theory, as well as atmospheric and interior physics. These insights have led to numerous direct imaging instruments for exoplanets, many using polarimetry. However, current instruments take`
 
-## Instructions
-
-- ### Setup a SQL Databse to store training samples
-A postegres SQL database is set up on Amazon RDS in order to provide online access to the same data for multiple computers. Follow the instructions below to set up your own database using the Free Tier of services on AWS: 
-
-1. sign in or register: https://aws.amazon.com/
-2. Search for a services and go to RDS 
-
-Add your credentials to a new file called `settings.json` like such:
-```
-{
-    "database":{
-        "dialect":"postgresql",
-        "username":"readonly",
-        "password":"readonly",
-        "endpoint":"exomachina.c4luhvcn1k1s.us-east-2.rds.amazonaws.com",
-        "port":5432,
-        "dbname":"exomachina"
-    }
-}
-```
-
-## Scraping NASA ADS
-
-https://ads.readthedocs.io/en/latest/
-
-Scrape ADS and save entries into a sql database: 
-
-`python ads_query.py -s settings.json -q exoplanet`
-
-```
-usage: ads_query.py [-h] [-q QUERY] [-s SETTINGS] [-k KEY]
-
-optional arguments:
-  -h, --help            show this help message and exit
-  -q QUERY, --query QUERY
-                        Initial search criteria
-  -s SETTINGS, --settings SETTINGS
-                        Settings file
-  -k KEY, --key KEY     Settings key
-```
-
-Letting the scrape run for ~2 hours found articles from these publications in descending order:
+Letting the scrape run for ~2 hours found articles from these publications in descending amount:
 ```
  5364 - The Astrophysical Journal
  3365 - Astronomy and Astrophysics
@@ -87,24 +45,4 @@ Letting the scrape run for ~2 hours found articles from these publications in de
  129 - Planetary and Space Science
  114 - Space Science Reviews
  109 - Geophysical Research Letters
-```
-
-The number of manuscripts for each year: 
-![](Figures/exoplanet_histogram.png)
-
-## Pre-processing
-Extract abstracts from the database and create a new file where each line is an new sample. Try a new tokenizer
-
-## Things to improve
-
-## Export the models to an iOS application
-
-
-References
-- https://huggingface.co/roberta-base 
-- GPT-2 generative text
-- https://huggingface.co/docs
-- https://huggingface.co/transformers/training.html
-- https://huggingface.co/transformers/notebooks.html
-https://colab.research.google.com/drive/1vsCh85T_Od7RBwXfvh1iysV-vTxmWXQO#scrollTo=ljknzOlNoyrv
-http://jalammar.github.io/illustrated-gpt2/
+```