Merge branch 'release-0.1b1'

Makefile

@@ -24,7 +24,7 @@ DJANGO_TEST_SETTINGS_MODULE = $(PROJECT).settings.$(TEST_SETTINGS)
 DJANGO_TEST_POSTFIX := --settings=$(DJANGO_TEST_SETTINGS_MODULE) --pythonpath=$(PYTHONPATH)
 
 # Apps to test
-APPS := partisan
+APPS := partisan members
 
 # Export targets not associated with files
 .PHONY: test showenv coverage bootstrap pip virtualenv clean virtual_env_set truncate

README.md

@@ -16,6 +16,20 @@ This small web application is intended to highlight how to operationalize machin
 
 The image used in this README, [Partisan Fail][partisan.jpg] by [David Colarusso](https://www.flickr.com/photos/dcolarusso/) is licensed under [CC BY-NC 2.0](https://creativecommons.org/licenses/by-nc/2.0/)
 
+## Changelog
+
+The release versions that are deployed to the web servers are also tagged in GitHub. You can see the tags through the GitHub web application and download the tarball of the version you'd like.
+
+The versioning uses a three part version system, "a.b.c" - "a" represents a major release that may not be backwards compatible. "b" is incremented on minor releases that may contain extra features, but are backwards compatible. "c" releases are bug fixes or other micro changes that developers should feel free to immediately update to.
+
+### Version 0.1 Beta 1
+
+* **tag**: [v0.1b1](https://github.com/DistrictDataLabs/partisan-discourse/releases/tag/v0.1b1)
+* **deployment**: Monday, July 18, 2016
+* **commit**: [see tag](#)
+
+This is the first beta release of the Political Discourse application. Right now this simple web application allows users to sign in, then add links to go fetch web content to the global corpus. These links are then preprocessed using NLP foo. Users can tag the documents as Republican or Democrat, allowing us to build a political classifier. 
+
 <!-- References -->
 [travis_img]: https://travis-ci.org/DistrictDataLabs/partisan-discourse.svg
 [travis_href]: https://travis-ci.org/DistrictDataLabs/partisan-discourse

corpus/__init__.py

@@ -0,0 +1,25 @@
+# corpus
+# An application that allows the management of our classifier corpus.
+#
+# Author:   Benjamin Bengfort <[email protected]>
+# Created:  Sun Jul 17 19:29:55 2016 -0400
+#
+# Copyright (C) 2016 District Data Labs
+# For license information, see LICENSE.txt
+#
+# ID: __init__.py [] [email protected] $
+
+"""
+An application that allows the management of our classifier corpus.
+"""
+
+##########################################################################
+## Imports
+##########################################################################
+
+
+##########################################################################
+## Configuration
+##########################################################################
+
+default_app_config = 'corpus.apps.CorpusConfig'

corpus/admin.py

@@ -0,0 +1,29 @@
+# corpus.admin
+# Register models with the Django Admin for the corpus app.
+#
+# Author:   Benjamin Bengfort <[email protected]>
+# Created:  Sun Jul 17 19:30:33 2016 -0400
+#
+# Copyright (C) 2016 District Data Labs
+# For license information, see LICENSE.txt
+#
+# ID: admin.py [] [email protected] $
+
+"""
+Register models with the Django Admin for the corpus app.
+"""
+
+##########################################################################
+## Imports
+##########################################################################
+
+from django.contrib import admin
+from corpus.models import Document, Annotation, Label
+
+##########################################################################
+## Register Admin
+##########################################################################
+
+admin.site.register(Label)
+admin.site.register(Annotation)
+admin.site.register(Document)

corpus/apps.py

@@ -0,0 +1,33 @@
+# corpus.apps
+# Application definition for the corpus app.
+#
+# Author:   Benjamin Bengfort <[email protected]>
+# Created:  Sun Jul 17 19:31:28 2016 -0400
+#
+# Copyright (C) 2016 District Data Labs
+# For license information, see LICENSE.txt
+#
+# ID: apps.py [] [email protected] $
+
+"""
+Application definition for the corpus app.
+"""
+
+##########################################################################
+## Imports
+##########################################################################
+
+from django.apps import AppConfig
+
+
+##########################################################################
+## Corpus Config
+##########################################################################
+
+class CorpusConfig(AppConfig):
+
+    name = 'corpus'
+    verbose_name = "Corpora"
+
+    def ready(self):
+        import corpus.signals

corpus/bitly.py

@@ -0,0 +1,58 @@
+# corpus.bitly
+# Access the bit.ly url shortening service.
+#
+# Author:   Benjamin Bengfort <[email protected]>
+# Created:  Mon Jul 18 09:59:27 2016 -0400
+#
+# Copyright (C) 2016 District Data Labs
+# For license information, see LICENSE.txt
+#
+# ID: bitly.py [] [email protected] $
+
+"""
+Access the bit.ly url shortening service.
+"""
+
+##########################################################################
+## Imports
+##########################################################################
+
+import requests
+
+from django.conf import settings
+from urllib.parse import urljoin
+from corpus.exceptions import BitlyAPIError
+
+##########################################################################
+## Shorten function
+##########################################################################
+
+def shorten(url, token=None):
+    """
+    Shortens a URL using the bit.ly API.
+    """
+
+    # Get the bit.ly access token from settings
+    token = settings.BITLY_ACCESS_TOKEN or token
+    if not token:
+        raise BitlyAPIError(
+            "Cannot call shorten URL without a bit.ly access token"
+        )
+
+    # Compute and make the request to the API
+    endpoint = urljoin(settings.BITLY_API_ADDRESS, "v3/shorten")
+    params = {
+        "access_token": token,
+        "longUrl": url,
+    }
+
+    # bit.ly tends not to send status code errors
+    response = requests.get(endpoint, params=params)
+
+    # Parse and return the result
+    data = response.json()
+    if data['status_code'] != 200:
+        raise BitlyAPIError(
+            "Could not shorten link: {}".format(data['status_txt'])
+        )
+    return data['data']['url']

corpus/exceptions.py

@@ -0,0 +1,38 @@
+# corpus.exceptions
+# Custom exceptions for corpus handling.
+#
+# Author:   Benjamin Bengfort <[email protected]>
+# Created:  Mon Jul 18 09:57:26 2016 -0400
+#
+# Copyright (C) 2016 District Data Labs
+# For license information, see LICENSE.txt
+#
+# ID: exceptions.py [] [email protected] $
+
+"""
+Custom exceptions for corpus handling.
+"""
+
+##########################################################################
+## Corpus Exceptions
+##########################################################################
+
+class CorpusException(Exception):
+    """
+    Something went wrong in the corpus app.
+    """
+    pass
+
+
+class BitlyAPIError(CorpusException):
+    """
+    Something went wrong trying to shorten a url.
+    """
+    pass
+
+
+class FetchError(CorpusException):
+    """
+    Something went wrong trying to fetch a url using requests.
+    """
+    pass

corpus/fixtures/labels.json

@@ -0,0 +1,35 @@
+[
+{
+  "model": "corpus.label",
+  "pk": 1,
+  "fields": {
+    "created": "2016-07-18T14:56:26.706Z",
+    "modified": "2016-07-18T14:56:26.708Z",
+    "name": "USA Political Parties",
+    "slug": "usa-political-parties",
+    "parent": null
+  }
+},
+{
+  "model": "corpus.label",
+  "pk": 2,
+  "fields": {
+    "created": "2016-07-18T14:57:33.059Z",
+    "modified": "2016-07-18T14:57:33.062Z",
+    "name": "Democratic",
+    "slug": "democratic",
+    "parent": 1
+  }
+},
+{
+  "model": "corpus.label",
+  "pk": 3,
+  "fields": {
+    "created": "2016-07-18T14:57:59.531Z",
+    "modified": "2016-07-18T14:57:59.534Z",
+    "name": "Republican",
+    "slug": "republican",
+    "parent": 1
+  }
+}
+]

corpus/managers.py

@@ -0,0 +1,39 @@
+# corpus.managers
+# Model managers for the corpus application.
+#
+# Author:   Benjamin Bengfort <[email protected]>
+# Created:  Mon Jul 18 23:09:19 2016 -0400
+#
+# Copyright (C) 2016 District Data Labs
+# For license information, see LICENSE.txt
+#
+# ID: managers.py [] [email protected] $
+
+"""
+Model managers for the corpus application.
+"""
+
+##########################################################################
+## Imports
+##########################################################################
+
+from django.db import models
+
+
+##########################################################################
+## Annotation Manager
+##########################################################################
+
+class AnnotationManager(models.Manager):
+
+    def republican(self):
+        """
+        Filters the annotations for only republican annotations.
+        """
+        return self.filter(label__slug='republican')
+
+    def democratic(self):
+        """
+        Filters the annotations for only democratic annotations.
+        """
+        return self.filter(label__slug='democratic')

corpus/migrations/0001_initial.py

@@ -0,0 +1,95 @@
+# -*- coding: utf-8 -*-
+# Generated by Django 1.9.7 on 2016-07-18 17:31
+from __future__ import unicode_literals
+
+import autoslug.fields
+from django.conf import settings
+from django.db import migrations, models
+import django.db.models.deletion
+import django.utils.timezone
+import model_utils.fields
+import picklefield.fields
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='Annotation',
+            fields=[
+                ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('created', model_utils.fields.AutoCreatedField(default=django.utils.timezone.now, editable=False, verbose_name='created')),
+                ('modified', model_utils.fields.AutoLastModifiedField(default=django.utils.timezone.now, editable=False, verbose_name='modified')),
+            ],
+            options={
+                'db_table': 'annotations',
+                'get_latest_by': 'created',
+            },
+        ),
+        migrations.CreateModel(
+            name='Document',
+            fields=[
+                ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('created', model_utils.fields.AutoCreatedField(default=django.utils.timezone.now, editable=False, verbose_name='created')),
+                ('modified', model_utils.fields.AutoLastModifiedField(default=django.utils.timezone.now, editable=False, verbose_name='modified')),
+                ('title', models.CharField(blank=True, default=None, max_length=255, null=True)),
+                ('long_url', models.URLField(max_length=2000, unique=True)),
+                ('short_url', models.URLField(blank=True, default=None, max_length=30, null=True)),
+                ('raw_html', models.TextField(blank=True, default=None, null=True)),
+                ('content', picklefield.fields.PickledObjectField(blank=True, default=None, editable=False, null=True)),
+                ('signature', models.CharField(blank=True, default=None, editable=False, max_length=44, null=True)),
+                ('n_words', models.SmallIntegerField(blank=True, default=None, null=True)),
+                ('n_vocab', models.SmallIntegerField(blank=True, default=None, null=True)),
+                ('users', models.ManyToManyField(related_name='documents', through='corpus.Annotation', to=settings.AUTH_USER_MODEL)),
+            ],
+            options={
+                'db_table': 'documents',
+                'get_latest_by': 'created',
+            },
+        ),
+        migrations.CreateModel(
+            name='Label',
+            fields=[
+                ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('created', model_utils.fields.AutoCreatedField(default=django.utils.timezone.now, editable=False, verbose_name='created')),
+                ('modified', model_utils.fields.AutoLastModifiedField(default=django.utils.timezone.now, editable=False, verbose_name='modified')),
+                ('name', models.CharField(max_length=64, unique=True)),
+                ('slug', autoslug.fields.AutoSlugField(editable=False, populate_from='name', unique=True)),
+                ('documents', models.ManyToManyField(related_name='labels', through='corpus.Annotation', to='corpus.Document')),
+                ('parent', models.ForeignKey(blank=True, default=None, null=True, on_delete=django.db.models.deletion.CASCADE, to='corpus.Label')),
+            ],
+            options={
+                'db_table': 'labels',
+                'get_latest_by': 'created',
+            },
+        ),
+        migrations.AddField(
+            model_name='annotation',
+            name='document',
+            field=models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, related_name='annotations', to='corpus.Document'),
+        ),
+        migrations.AddField(
+            model_name='annotation',
+            name='label',
+            field=models.ForeignKey(blank=True, default=None, null=True, on_delete=django.db.models.deletion.CASCADE, related_name='annotations', to='corpus.Label'),
+        ),
+        migrations.AddField(
+            model_name='annotation',
+            name='user',
+            field=models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, related_name='annotations', to=settings.AUTH_USER_MODEL),
+        ),
+        migrations.AlterUniqueTogether(
+            name='document',
+            unique_together=set([('long_url', 'short_url')]),
+        ),
+        migrations.AlterUniqueTogether(
+            name='annotation',
+            unique_together=set([('document', 'user')]),
+        ),
+    ]