Trained first GTP2

.gitignore

@@ -138,4 +138,16 @@ dmypy.json
 cython_debug/
 
 dataset.csv
-model.torch
+model.torch
+
+
+# Extension
+out/
+node_modules/
+
+# Editor
+.vscode
+
+# Training
+.output
+runs

build_dataset.py

@@ -0,0 +1,59 @@
+import os
+import re
+from pathlib import Path
+import pandas as pd
+import random
+
+from sklearn.utils import validation
+
+
+TRAIN_PATH = "data/dataset_train.txt"
+VALIDATION_PATH = "data/dataset_validation.txt"
+
+
+def parse_sections(f):
+    sections = []
+    for line in f:
+        line = line.rstrip()
+
+        if (line.startswith("//")
+            or line.startswith("ifndef")
+                or line.startswith(":experiment")):
+            continue
+
+        if re.match(r"^=+ \w+", line):
+            sections.append(line)
+        else:
+            try:
+                sections[-1] += "\n" + line
+            except IndexError:
+                pass
+
+    return sections
+
+
+sections = []
+
+# Find adoc files
+home = str(Path.home())
+coursedir = os.path.join(home, "Desarrollo")
+
+for dirpath, dnames, fnames in os.walk(coursedir):
+    for f in fnames:
+        if (f.endswith(".adoc") and
+            "guides" in dirpath and
+                "en-US" in dirpath):
+            filepath = os.path.join(dirpath, f)
+            print(filepath)
+            with open(filepath, "r") as f:
+                sections += parse_sections(f)
+
+random.Random(42).shuffle(sections)
+num_sections = len(sections)
+train_size = int(num_sections * 0.8)
+
+with open(TRAIN_PATH, "w") as f:
+    f.write("\n".join(sections[:train_size]))
+
+with open(VALIDATION_PATH, "w") as f:
+    f.write("\n".join(sections[train_size:]))

data/.gitignore

@@ -0,0 +1,3 @@
+*
+*/
+!.gitignore

extension/rht-text-generator/.eslintrc.json

@@ -0,0 +1,22 @@
+{
+    "root": true,
+    "parser": "@typescript-eslint/parser",
+    "parserOptions": {
+        "ecmaVersion": 6,
+        "sourceType": "module"
+    },
+    "plugins": [
+        "@typescript-eslint"
+    ],
+    "rules": {
+        "@typescript-eslint/naming-convention": "warn",
+        "@typescript-eslint/semi": "warn",
+        "curly": "warn",
+        "eqeqeq": "warn",
+        "no-throw-literal": "warn",
+        "semi": "off"
+    },
+    "ignorePatterns": [
+        "**/*.d.ts"
+    ]
+}

extension/rht-text-generator/.vscodeignore

@@ -0,0 +1,11 @@
+.vscode/**
+.vscode-test/**
+out/test/**
+src/**
+.gitignore
+.yarnrc
+vsc-extension-quickstart.md
+**/tsconfig.json
+**/.eslintrc.json
+**/*.map
+**/*.ts

extension/rht-text-generator/CHANGELOG.md

@@ -0,0 +1,9 @@
+# Change Log
+
+All notable changes to the "rht-text-generator" extension will be documented in this file.
+
+Check [Keep a Changelog](http://keepachangelog.com/) for recommendations on how to structure this file.
+
+## [Unreleased]
+
+- Initial release

extension/rht-text-generator/README.md

@@ -0,0 +1,70 @@
+# rht-text-generator README
+
+This is the README for your extension "rht-text-generator". After writing up a brief description, we recommend including the following sections.
+
+## Features
+
+Describe specific features of your extension including screenshots of your extension in action. Image paths are relative to this README file.
+
+For example if there is an image subfolder under your extension project workspace:
+
+\!\[feature X\]\(images/feature-x.png\)
+
+> Tip: Many popular extensions utilize animations. This is an excellent way to show off your extension! We recommend short, focused animations that are easy to follow.
+
+## Requirements
+
+If you have any requirements or dependencies, add a section describing those and how to install and configure them.
+
+## Extension Settings
+
+Include if your extension adds any VS Code settings through the `contributes.configuration` extension point.
+
+For example:
+
+This extension contributes the following settings:
+
+* `myExtension.enable`: enable/disable this extension
+* `myExtension.thing`: set to `blah` to do something
+
+## Known Issues
+
+Calling out known issues can help limit users opening duplicate issues against your extension.
+
+## Release Notes
+
+Users appreciate release notes as you update your extension.
+
+### 1.0.0
+
+Initial release of ...
+
+### 1.0.1
+
+Fixed issue #.
+
+### 1.1.0
+
+Added features X, Y, and Z.
+
+-----------------------------------------------------------------------------------------------------------
+## Following extension guidelines
+
+Ensure that you've read through the extensions guidelines and follow the best practices for creating your extension.
+
+* [Extension Guidelines](https://code.visualstudio.com/api/references/extension-guidelines)
+
+## Working with Markdown
+
+**Note:** You can author your README using Visual Studio Code.  Here are some useful editor keyboard shortcuts:
+
+* Split the editor (`Cmd+\` on macOS or `Ctrl+\` on Windows and Linux)
+* Toggle preview (`Shift+CMD+V` on macOS or `Shift+Ctrl+V` on Windows and Linux)
+* Press `Ctrl+Space` (Windows, Linux) or `Cmd+Space` (macOS) to see a list of Markdown snippets
+
+### For more information
+
+* [Visual Studio Code's Markdown Support](http://code.visualstudio.com/docs/languages/markdown)
+* [Markdown Syntax Reference](https://help.github.com/articles/markdown-basics/)
+
+**Enjoy!**