Merge branch 'docs'

.dockerignore

@@ -0,0 +1,14 @@
+*.egg-info
+.cache
+data/clearpond
+data/figures
+data/FreeAssociation
+data/MemeTracker
+data/notebooks
+docs/_build
+docs/data
+Dockerfile
+.git
+.ipynb_checkpoints
+**/__pycache__
+treetagger

Dockerfile

@@ -0,0 +1,90 @@
+FROM ubuntu:16.04
+MAINTAINER Sébastien Lerique <sl@mehho.net>
+
+# Install all the system and build dependencies.
+ENV PYTHON_VERSION 3.5
+ENV PG_VERSION 9.5
+RUN set -x \
+    && apt-get update \
+    && apt-get install -y --no-install-recommends \
+        build-essential \
+        ca-certificates \
+        git \
+        libfreetype6-dev \
+        libpng12-0 \
+        libpng12-dev \
+        locales \
+        pkg-config \
+        postgresql-${PG_VERSION} \
+        postgresql-server-dev-${PG_VERSION} \
+        python${PYTHON_VERSION} \
+        python${PYTHON_VERSION}-dev \
+        python3 \
+        python3-pip \
+        sudo \
+        unzip \
+        wget \
+    && rm -rf /var/lib/apt/lists/*
+
+# Make the "en_US.UTF-8" locale so postgres and python Click will be utf-8
+# enabled by default.
+RUN set -x \
+    && localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8
+ENV LC_ALL en_US.utf8
+ENV LANG en_US.utf8
+
+# Set up postgres with user and analysis and test databases for brainscopypaste.
+RUN set -x \
+    && service postgresql start \
+    && sudo -u postgres psql -c 'create user brainscopypaste;' \
+    && sudo -u postgres psql -c 'create database brainscopypaste;' \
+    && sudo -u postgres psql -c 'alter database brainscopypaste owner to brainscopypaste;' \
+    && sudo -u postgres psql -c 'create database brainscopypaste_test;' \
+    && sudo -u postgres psql -c 'alter database brainscopypaste_test owner to brainscopypaste;' \
+    && sed -i 's/^\(\(local\|host\) \+all \+all \+.* \+\)\(peer\|md5\)$/\1trust/g' /etc/postgresql/${PG_VERSION}/main/pg_hba.conf
+
+# Copy the originating repository, and install requirements.
+COPY . /home/brainscopypaste
+RUN set -x \
+    && cd /home/brainscopypaste \
+    && pip3 install --upgrade pip setuptools \
+    && pip install $(cat requirements.txt | grep "^numpy") \
+    && pip install -r requirements.txt \
+    && pip install --editable .
+
+# Configure the brainscopypaste user.
+RUN set -x \
+    && useradd brainscopypaste \
+    && echo "brainscopypaste ALL=(ALL) NOPASSWD: ALL" > /etc/sudoers.d/brainscopypaste \
+    && chown -R brainscopypaste:brainscopypaste /home/brainscopypaste
+USER brainscopypaste
+
+# Install treetagger and datasets.
+RUN set -x \
+    && cd /home/brainscopypaste \
+    && ./install_treetagger.sh \
+    && ./install_datasets.sh
+
+# Clean up to reduce image size.
+RUN set -x \
+    && sudo rm -rf /root/.cache/pip \
+    && sudo apt-get purge -y --auto-remove \
+        build-essential \
+        ca-certificates \
+        libfreetype6-dev \
+        libpng12-dev \
+        pkg-config \
+        postgresql-server-dev-${PG_VERSION} \
+        python${PYTHON_VERSION}-dev \
+        python3-pip \
+        unzip \
+        wget
+
+# Check the software runs its tests.
+RUN set -x \
+    && cd /home/brainscopypaste \
+    && sudo service postgresql restart \
+    && py.test
+
+# Use the CLI tool, for easier use.
+CMD ["/home/brainscopypaste/dockerstart.sh"]

README.md

@@ -6,6 +6,6 @@ The latex source (along with compiled pdf) for the paper is at [wehlutyk/brainsc
 
 TODO/OUTDATED: See the [documentation](https://brainscopypaste.readthedocs.org/en/latest/) if you want to install, run, or understand any of this.
 
-## Licence
+## License
 
 GNU/GPLv3.

brainscopypaste/__init__.py

@@ -0,0 +1,4 @@
+"""Toolchain for analysing word substitutions in online quotes from the
+MemeTracker dataset.
+
+"""

brainscopypaste/cli.py

@@ -1,3 +1,8 @@
+"""CLI tool for stepping through the analysis.
+
+"""
+
+
 from os.path import exists, basename, split, join
 from os import remove
 import logging

brainscopypaste/conf.py

@@ -1,3 +1,9 @@
+"""Manage settings from :mod:`.settings`, allowing overriding
+of some values.
+
+"""
+
+
 import logging
 import importlib
 from contextlib import contextmanager

brainscopypaste/conftest.py

@@ -1,3 +1,8 @@
+"""Test fixtures.
+
+"""
+
+
 from datetime import datetime, timedelta
 
 import pytest

brainscopypaste/db.py

@@ -1,3 +1,8 @@
+"""Database models and related utilities.
+
+"""
+
+
 import re
 from io import StringIO
 import logging
@@ -325,8 +330,6 @@ def lemmas(self):
 
 
 def _copy(string, table, columns):
-    from brainscopypaste.utils import session_scope
-
     string.seek(0)
     with session_scope() as session:
         cursor = session.connection().connection.cursor()

brainscopypaste/db_test.py

@@ -1,3 +1,8 @@
+"""Tests for :mod:`.db`.
+
+"""
+
+
 from datetime import datetime, timedelta
 
 from sqlalchemy.exc import DataError

brainscopypaste/features.py

@@ -1,3 +1,8 @@
+"""Features for words in substitutions.
+
+"""
+
+
 import logging
 from csv import DictReader, reader as csvreader
 import warnings

brainscopypaste/features_test.py

@@ -1,3 +1,8 @@
+"""Tests for :mod:`.features`.
+
+"""
+
+
 from os.path import exists
 import pickle
 

brainscopypaste/filter.py

@@ -1,3 +1,8 @@
+"""Filter clusters and quotes to clean to MemeTracker dataset.
+
+"""
+
+
 from datetime import timedelta
 import logging
 

brainscopypaste/filter_test.py

@@ -1,3 +1,8 @@
+"""Tests for :mod:`.filter`.
+
+"""
+
+
 from datetime import datetime, timedelta
 
 import pytest

brainscopypaste/load.py

@@ -1,4 +1,6 @@
-"""Load data from the MemeTracker dataset."""
+"""Load data from the MemeTracker dataset.
+
+"""
 
 
 from datetime import datetime

brainscopypaste/load_test.py

@@ -1,3 +1,8 @@
+"""Tests for :mod:`.load`.
+
+"""
+
+
 import os
 from tempfile import mkstemp
 from datetime import timedelta

brainscopypaste/mine.py

@@ -1,3 +1,8 @@
+"""Mine substitutions with various mining models.
+
+"""
+
+
 from enum import Enum, unique
 from datetime import timedelta, datetime
 import logging

brainscopypaste/mine_test.py

@@ -1,3 +1,8 @@
+"""Tests for :mod:`.mine`.
+
+"""
+
+
 import os
 from tempfile import mkstemp
 from datetime import datetime

brainscopypaste/settings.py

@@ -1,3 +1,8 @@
+"""General settings for the analysis.
+
+"""
+
+
 from os.path import abspath, join
 
 

brainscopypaste/tagger.py

@@ -1,4 +1,6 @@
-"""Tag and tokenize sentences and quotes."""
+"""Tag and tokenize sentences and quotes.
+
+"""
 
 
 from treetaggerwrapper import TreeTagger, TreeTaggerError

brainscopypaste/tagger_test.py

@@ -1,3 +1,8 @@
+"""Tests for :mod:`.tagger`.
+
+"""
+
+
 from brainscopypaste.tagger import tag, tags, tokens, lemmas
 
 

brainscopypaste/utils.py

@@ -1,3 +1,8 @@
+"""Miscellaneous utilities.
+
+"""
+
+
 import logging
 import pickle
 from contextlib import contextmanager

brainscopypaste/utils_test.py

@@ -1,3 +1,8 @@
+"""Tests for :mod:`.utils`.
+
+"""
+
+
 import pickle
 from tempfile import mkstemp
 import os

data/.gitignore

@@ -1 +1,3 @@
-*.pickle
+FreeAssociation/
+MemeTracker/
+clearpond/