27 Commits

Author SHA1 Message Date
629ea88388 Merge branch 'master' into new_docs 2020-03-13 02:47:31 +00:00
05922fc9a7 updating builder docstring 2020-03-13 02:46:30 +00:00
c7cabe8d63 adding new doctype 2020-03-12 23:58:31 +00:00
5b24952e1e Merge branch 'develop' 2020-03-12 21:30:27 +00:00
511986a131 updating cli.py 2020-03-12 21:30:12 +00:00
21472e8100 adding mkdocs 2020-03-12 01:27:47 +00:00
4e0091f80f latest 2020-03-11 20:44:46 +00:00
cd8117343b Merge branch 'develop' 2020-03-09 12:26:00 +00:00
8dc88f6361 updating poetry installation instructions 2020-03-09 12:25:45 +00:00
306eb82237 Merge branch 'develop' 2020-03-09 12:22:43 +00:00
0a77fa34fd adding poetry to installation instructions 2020-03-09 12:22:35 +00:00
5aefcc2a2d Merge branch 'develop' 2020-03-09 12:12:28 +00:00
0034340d63 updating comments document 2020-03-09 12:12:11 +00:00
02cb79c4b2 Merge branch 'master' into develop 2020-03-09 11:57:22 +00:00
26b346d359 Merge branch 'documentation' 2020-03-09 11:56:19 +00:00
1dae95735f updating documentation 2020-03-09 11:56:03 +00:00
78544673b4 Merge branch 'develop' 2020-03-09 11:38:49 +00:00
e8ce4b59f8 Merge branch 'documentation' into develop 2020-03-09 11:38:36 +00:00
e09728a7c7 updating documentation 2020-03-09 11:38:22 +00:00
ae6c2bf985 Merge branch 'master' into documentation 2020-03-09 03:38:06 +00:00
fd144abff0 Merge branch 'develop' 2020-03-09 03:37:17 +00:00
d499ee175e removing badge 2020-03-09 03:37:11 +00:00
fadcb98d81 Merge branch 'develop' 2020-03-09 03:34:48 +00:00
aa98102d6a removing badge 2020-03-09 03:34:36 +00:00
a10426f043 Merge branch 'develop' 2020-03-09 03:31:09 +00:00
78ac63ca36 code quality improvements 2020-03-09 03:30:52 +00:00
2d8f8dc63f Merge branch 'master' into develop 2020-03-09 03:20:26 +00:00
34 changed files with 976 additions and 402 deletions

BIN
.DS_Store vendored

Binary file not shown.

View File

@@ -1,3 +1,8 @@
{
"python.pythonPath": "/Users/dtomlinson/.virtualenvs/musicbrainzapi/bin/python"
}
"python.pythonPath": "/Users/dtomlinson/.virtualenvs/musicbrainzapi/bin/python",
"restructuredtext.confPath": "${workspaceFolder}/docs/source",
"restructuredtext.linter.executablePath": "/Users/dtomlinson/.virtualenvs/utility-doc8/bin/doc8",
"files.trimTrailingWhitespace": true,
"restructuredtext.languageServer.trace.server": "messages",
"editor.fontSize": 13,
}

View File

@@ -10,7 +10,6 @@ Introduction
.. image:: https://img.shields.io/github/languages/code-size/dtomlinson91/musicbrainzapi-cv-airelogic?style=for-the-badge
.. image:: https://img.shields.io/github/languages/top/dtomlinson91/musicbrainzapi-cv-airelogic?style=for-the-badge
.. image:: https://img.shields.io/requires/github/dtomlinson91/musicbrainzapi-cv-airelogic?style=for-the-badge
.. image:: https://img.shields.io/codacy/grade/f9517450400d48b0a7222a383c2e8fe2?style=for-the-badge
Summary
========
@@ -71,6 +70,27 @@ In the root of the repo in a virtual environment run:
python ./setup.py install
poetry
------
Clone the repo:
.. code-block:: bash
git clone https://github.com/dtomlinson91/musicbrainzapi-cv-airelogic.git
In a virtual environment install poetry:
.. code-block:: bash
pip install poetry
In the root of the repo in a virtual environment run:
.. code-block:: bash
poetry install --no-dev
Docker
------

View File

@@ -53,7 +53,7 @@ Code restructure
The :class:`musicbrainzapi.api.lyrics.concrete_builder.LyricsConcreteBuilder` class could be improved. Many of the methods defined in here no longer need to be present. Some of the functionality (url checking for example) could be removed and implemented in other ways (a Mixin is one solution).
If other ways of filtering were to be added (as opposed to the current default of just Albums) this class would be useful in constructing our :class:`musicbrainzapi.api.lyrics.Lyrics` objects consistently.
If other ways of filtering were to be added (as opposed to the current default of just Albums) then this class would be useful to build our :class:`musicbrainzapi.api.lyrics.Lyrics` objects consistently.
Additional functionality to the lyrics command
-----------------------------------------------
@@ -68,7 +68,7 @@ The ability for the user to specify something other than album or year to group
Multiple artists
^^^^^^^^^^^^^^^^
Searching for multiple artists and comparing is certainly possible in the current iteration (click provides a nice way to accept multiple artists and then we create our ``Lyrics`` objects from these) this wasn't implemented. There are rate limiting factors which may slow down the program and increase runtime considerably.
Searching for multiple artists and comparing is certainly possible in the current iteration (click provides a nice way to accept multiple artists and then we create our ``Lyrics`` objects from these) this wasn't implemented. There are rate limiting factors which may slow down the program and in the current implementation it could increase runtime considerably.
Speed improvements
-------------------
@@ -79,7 +79,7 @@ One solution would be to implement threading - as we are waiting on HTTP request
This wasn't implemented primarily because of time - but threading could be implemented on each call we make to the API.
An alternative, and I beleive an interesting solution, would be to use AWS Lambda (serverless).
An alternative, and I believe an interesting solution, would be to use AWS Lambda (serverless).
There is a caveat to this solution and it is cost - threading is free but adds development time and increases complexity. AWS isn't free but allows you to scale the requests out.
@@ -98,4 +98,29 @@ If more control was needed one solution could be:
This requires the user to have an internet connection - which is a current requirement. Requests to the api could be made simultaneously - without adding the complexity that comes with threading. This would not solve any API rate limiting - we are required to provide an application user_agent to the api to identify the app.
An interesting solution, and one I did consider, was to have the program run entirely in lambda, requiring no depdencies and just a simple front end that sends requests, and uses ``boto3`` to retrieve. The simplicity of this, and the fact that AWS provide an SDK for many languages, means the cient code could run in any language.
An interface to AWS API Gateway would provide the entry point to the lambda.
Writing it in this manner (with an api backend) would mean a webapp of the program could be possible, with the frontend served with something like ``Vuejs`` or ``React``.
.. _Zappa: https://github.com/Miserlou/Zappa
Error catching
--------------
Handling missing data from both APIs is done with error catching (namely ``ValueError`` and ``TypeError``).
Although inelegant, and not guaranteed to capture the specific behaviour we want to catch (missing data etc.) it is a solution and appears to work quite well.
Musicbrainz provides a schema for their api. If this were to be placed in a production environment then readdressing this should be a priority - we should be checking the values returned, using the schema as a guide, and replacing missing values accordingly. We should not rely on ``try except`` blocks to do this as it can be unreliable and is prone to raise other errors.
Further statistical analysis
----------------------------
Standard descriptive statistics are provided. I did consider including a more deeper analysis but opted not to for several reasons:
- Without a specific problem or question to answer - explorative work can take a lot of time and may not yield satisfactory results. Questions I did consider are:
+ `For active artists, based on their previous lyrics count what is the predicition of their next album?` Although a sensible question I'm not sure how useful the predicition would be - I am sure for some artists they would follow a pattern over time, but I'm not convinced all artists would and I imagine the results would be mixed.
+ `Anomaly detection - for artists with large releases, what albums stood out as larger than usual and what feature (or track) caused this anomaly?` - This would be a good question to answer and we have many tools available. As we have numeric data - clustering could be a candidate (DBSCAN or even K-MEANS). I opted not to because of time and the fact it would bloat the requirements up. Feature flags are an option when handling extra packages, ``pip install musicbrainzapi[analysis]`` for example, but nonetheless this would be an interesting question to answer and I beleive one of the easier ones to implement if it was desired.

1
docs/about.md Normal file
View File

@@ -0,0 +1 @@
# Some about page

17
docs/index.md Normal file
View File

@@ -0,0 +1,17 @@
# Welcome to MkDocs
For full documentation visit [mkdocs.org](https://www.mkdocs.org).
## Commands
* `mkdocs new [dir-name]` - Create a new project.
* `mkdocs serve` - Start the live-reloading docs server.
* `mkdocs build` - Build the documentation site.
* `mkdocs -h` - Print help message and exit.
## Project layout
mkdocs.yml # The configuration file.
docs/
index.md # The documentation homepage.
... # Other markdown pages, images and other files.

20
docs/python.md Normal file
View File

@@ -0,0 +1,20 @@
# Some python
## Some test python
!!! warning "Important warning"
This isn't yet complete.
```python
def _generate_word_cloud(self) -> None:
"""Generates a word cloud
"""
self.wc = WordCloud(
max_words=150,
width=1500,
height=1500,
mask=self.char_mask,
random_state=1,
).generate_from_frequencies(self.freq)
return self
```

83
docs/test.md Normal file
View File

@@ -0,0 +1,83 @@
# musicbrainzapi.wordcloud package
Wordcloud from lyrics.
### class musicbrainzapi.wordcloud.LyricsWordcloud(pillow_img: PIL.PngImagePlugin.PngImageFile, all_albums_lyrics_count: Lyrics.all_albums_lyrics_count)
Bases: `object`
Create a word cloud from Lyrics.
* **Variables**
* **all_albums_lyrics_count** (*list*) List of all albums + track lyrics counted by each word
* **char_mask** (*np.array*) numpy array containing data for the word cloud image
* **freq** (*collections.Counter*) Counter object containing counts for all words across all tracks
* **lyrics_list** (*list*) List of all words from all lyrics across all tracks.
* **pillow_img** (*PIL.PngImagePlugin.PngImageFile*) pillow image of the word cloud base
* **wc** (*wordcloud.WordCloud*) WordCloud object
#### \__init__(pillow_img: PIL.PngImagePlugin.PngImageFile, all_albums_lyrics_count: Lyrics.all_albums_lyrics_count)
Create a worcloud object.
* **Parameters**
* **pillow_img** (*PIL.PngImagePlugin.PngImageFile*) pillow image of the word cloud base
* **all_albums_lyrics_count** (*Lyrics.all_albums_lyrics_count*) List of all albums + track lyrics counted by each word
#### classmethod use_microphone(all_albums_lyrics_count: Lyrics.all_albums_lyrics_count)
Class method to instantiate with a microphone base image.
* **Parameters**
**all_albums_lyrics_count** (*Lyrics.all_albums_lyrics_count*) List of all albums + track lyrics counted by each word
#### static generate_grey_colours(\*args, \*\*kwargs)
Static method to generate a random grey colour.
#### _get_lyrics_list()
Gets all words from lyrics in a single list + cleans them.
#### _get_frequencies()
Get frequencies of words from a list.
#### _get_char_mask()
Gets a numpy array for the image file.
#### _generate_word_cloud()
Generates a word cloud
#### _generate_plot()
Plots the wordcloud and sets matplotlib options.
#### create_word_cloud()
Creates a word cloud

5
docs/testdoc.md Normal file
View File

@@ -0,0 +1,5 @@
# Test documentation using mkdocstrings
## Reference
::: musicbrainzapi.api.lyrics.builder

39
mkdocs.yml Normal file
View File

@@ -0,0 +1,39 @@
site_name: Musicbrainzapi
nav:
- Welcome:
- Home: index.md
- About: about.md
- API:
- API: test.md
- Code:
- python.md
- testdoc.md
# theme: material
theme:
name: "material"
palette:
primary: "yellow"
accent: "red"
feature:
tabs: true
markdown_extensions:
- admonition
- codehilite:
guess_lang: true
- toc:
permalink: true
plugins:
- search
- mkdocstrings
repo_name: "dtomlinson91/musicbrainzapi"
repo_url: "https://github.com/dtomlinson91/musicbrainzapi-cv-airelogic"
extra:
social:
- type: "github"
link: "https://github.com/dtomlinson91/musicbrainzapi"

821
poetry.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -20,20 +20,18 @@ click = "^7.0"
[tool.poetry.dev-dependencies]
pytest = "^5.2"
python-language-server = "^0.31.8"
Rope = "^0.16.0"
Pyflakes = "^2.1.1"
McCabe = "^0.6.1"
pycodestyle = "^2.5.0"
pydocstyle = "^5.0.2"
autopep8 = "^1.5"
YAPF = "^0.29.0"
pudb = "^2019.2"
pyls-black = "^0.4.4"
sphinx = "^2.4.4"
sphinx_rtd_theme = "^0.4.3"
sphinx-click = "^2.3.1"
coverage = "^5.0.3"
prospector = "^1.2.0"
pylint = "^2.4.4"
pydoc-markdown = {git = "https://github.com/NiklasRosenstein/pydoc-markdown.git", rev = "develop"}
mkdocs = "^1.1"
mkdocs-material = "^4.6.3"
pymdown-extensions = "^6.3"
mkdocstrings = "^0.8.0"
beeprint = "^2.4.10"
[tool.poetry.plugins."console_scripts"]
"musicbrainzapi" = "musicbrainzapi.cli.cli:cli"

View File

@@ -33,10 +33,8 @@ entry_points = \
setup_kwargs = {
'name': 'musicbrainzapi',
'version': '1.0.0',
'description': '',
'long_description': None,
'description': 'Python module to calculate statistics and generate a wordcloud for a given artist. Uses the Musicbrainz API and the lyrics.ovh API.',
'long_description': '',
'author': 'dtomlinson',
'author_email': 'dtomlinson@panaetius.co.uk',
'maintainer': None,

View File

@@ -1,6 +1,6 @@
"""
musicbrainzapi: A CLI lyrics searcher
=====================================
musicbrainzapi: A CLI lyrics searcher.
======================================
This module was written by dtomlinson <dtomlinson@panaetius.co.uk> for Aire Logic

View File

@@ -1,3 +1,7 @@
"""
Lyrics object with statistics.
===============================
"""
from __future__ import annotations
from typing import Union, Dict, List
from dataclasses import dataclass
@@ -10,8 +14,7 @@ import numpy as np
@dataclass
class Lyrics:
"""Lyrics object for an artist.
"""
"""Lyrics object for an artist."""
artist_id: str
artist: str

View File

@@ -1,53 +1,49 @@
from __future__ import annotations
from collections import Counter
import html
import json
import math
import string
from typing import Union, Dict
from collections import Counter
from typing import Dict, Union
import addict
import click
import musicbrainzngs
import numpy as np
import requests
from beeprint import pp
from musicbrainzapi.api.lyrics.concrete_builder import LyricsConcreteBuilder
from musicbrainzapi.api.lyrics import Lyrics
from musicbrainzapi.api import authenticate
from musicbrainzapi.api.lyrics import Lyrics
from musicbrainzapi.api.lyrics.concrete_builder import LyricsConcreteBuilder
class LyricsBuilder(LyricsConcreteBuilder):
"""docstring for LyricsBuilder
"""
This interface will build a Lyrics object.
Attributes
----------
album_statistics : addict.Dict
Dictionary containing album statistics
all_albums : list
List of all albums + track titles
all_albums_lyrics : list
List of all albums + track lyrics
all_albums_lyrics_count : list
List of all albums + track lyrics counted by each word
all_albums_lyrics_sum : list
List of all albums + track lyrics counted and summed up.
all_albums_lyrics_url : list
List of all albums + link to lyrics api for each track.
musicbrainz_artists : addict.Dict
Dictionary of response from Musicbrainzapi
release_group_ids : addict.Dict
Dictionary of Musicbrainz release-group ids
total_track_count : int
Total number of tracks across all albums
year_statistics : addict.Dict
Dictionary containing album statistics
!!! info "Attributes"
- musicbrainz_artists (addict.Dict): A dict response from the Musicbrainz api for all artists.
- release_group_ids (addict.Dict): : A dict response from the Musicbrainz api for all artists.
- all_albums (list): : A dict response from the Musicbrainz api for all artists.
- total_track_count (list): : A dict response from the Musicbrainz api for all artists.
- all_albums_lyrics_url (addict.Dict): : A dict response from the Musicbrainz api for all artists.
- all_albums_lyrics (addict.Dict): : A dict response from the Musicbrainz api for all artists.
- all_albums_lyrics_count (addict.Dict): : A dict response from the Musicbrainz api for all artists.
- all_albums_lyrics_sum (addict.Dict): : A dict response from the Musicbrainz api for all artists.
- album_statistics (addict.Dict): : A dict response from the Musicbrainz api for all artists.
- album_statistics (addict.Dict): : A dict response from the Musicbrainz api for all artists.
- year_statistics (addict.Dict): : A dict response from the Musicbrainz api for all artists.
- year_statistics (addict.Dict): : A dict response from the Musicbrainz api for all artists.
Example:
A test example.
"""
@property
def product(self) -> Lyrics:
product = self._product
return product
return self._product
@property
def artist(self) -> str:
@@ -95,17 +91,13 @@ class LyricsBuilder(LyricsConcreteBuilder):
def construct_lyrics_url(artist: str, song: str) -> str:
"""Builds the URL for the lyrics api.
Parameters
----------
artist : str
Artist
song : str
Track title
Args:
artist (str): Your chosen artist.
song (str): A song to find a lyrics url for.
Returns:
str: The url of the lyrics api for chosen song.
Returns
-------
str
URL for lyrics from the lyrics api.
"""
lyrics_api_base = 'https://api.lyrics.ovh/v1'
lyrics_api_url = html.escape(f'{lyrics_api_base}/{artist}/{song}')
@@ -123,7 +115,8 @@ class LyricsBuilder(LyricsConcreteBuilder):
Returns
-------
str
Lyrics of the trakc
Lyrics of the track.
"""
resp = requests.get(url)
@@ -165,7 +158,7 @@ class LyricsBuilder(LyricsConcreteBuilder):
Dict[str, int]
Dictionary of statistic and value.
"""
if len(nums) == 0:
if not nums:
return
avg = math.ceil(np.mean(nums))
median = math.ceil(np.median(nums))
@@ -177,21 +170,22 @@ class LyricsBuilder(LyricsConcreteBuilder):
p_75 = math.ceil(np.percentile(nums, 75))
p_90 = math.ceil(np.percentile(nums, 90))
count = len(nums)
_d = addict.Dict(
('avg', avg),
('median', median),
('std', std),
('max', _max),
('min', _min),
('p_10', p_10),
('p_25', p_25),
('p_75', p_75),
('p_90', p_90),
('count', count),
)
return _d
return addict.Dict(
('avg', avg),
('median', median),
('std', std),
('max', _max),
('min', _min),
('p_10', p_10),
('p_25', p_25),
('p_75', p_75),
('p_90', p_90),
('count', count),
)
def __init__(self) -> None:
"""Create a `LyricsBuilder`.
"""
self.reset()
def reset(self) -> None:
@@ -208,8 +202,7 @@ class LyricsBuilder(LyricsConcreteBuilder):
return self
def sort_artists(self) -> None:
"""Sort the artists from the Musicbrainzapi
"""
"""Sort the artists from the Musicbrainzapi."""
self._sort_names = dict(
(i.get('id'), f'{i.get("name")} | {i.get("disambiguation")}')
if i.get('disambiguation') is not None
@@ -241,8 +234,7 @@ class LyricsBuilder(LyricsConcreteBuilder):
return self
def find_all_albums(self) -> None:
"""Find all albums for the chosen artist
"""
"""Find all albums for the chosen artist."""
limit, offset, page = (100, 0, 1)
resp_0 = addict.Dict(
@@ -365,8 +357,7 @@ class LyricsBuilder(LyricsConcreteBuilder):
return self
def find_lyrics_urls(self) -> None:
"""Construct the URL for the lyrics api.
"""
"""Construct the URL for the lyrics api."""
self.all_albums_lyrics_url = list()
for x in self.all_albums:
for alb, tracks in x.items():
@@ -518,3 +509,6 @@ class LyricsBuilder(LyricsConcreteBuilder):
self.year_statistics = addict.Dict(
**self.year_statistics, **addict.Dict((year, _d))
)
if __name__ == "__main__":
pp(LyricsBuilder)

View File

@@ -10,6 +10,7 @@ class LyricsClickDirector:
"""Director for Lyrics builder."""
def __init__(self) -> None:
"""Create a Director to orchestrate the builder."""
self._builder = None
@staticmethod
@@ -62,6 +63,7 @@ class LyricsClickDirector:
------
SystemExit
If no artist is found will cleanly quit.
"""
artist_meta = None
for i, j in self.builder._top_five_results.items():
@@ -111,8 +113,7 @@ class LyricsClickDirector:
return self
def _query_for_data(self) -> None:
"""Query Musicbrainz api for albums + track data.
"""
"""Query Musicbrainz api for albums + track data."""
self.builder.find_all_albums()
self.builder.find_all_tracks()
self.builder._product.all_albums_with_tracks = self.builder.all_albums

View File

@@ -6,55 +6,64 @@ import click
from musicbrainzapi.__version__ import __version__
from musicbrainzapi.__header__ import __header__
CONTEXT_SETTINGS = dict(auto_envvar_prefix='COMPLEX')
# pylint:disable=invalid-name
CONTEXT_SETTINGS = dict(auto_envvar_prefix="COMPLEX")
class Environment(object):
class Environment:
"""Environment class to house shared parameters between all subcommands."""
def __init__(self):
self.verbose = False
self.home = os.getcwd()
pass_environment = click.make_pass_decorator(Environment, ensure=True)
pass_environment = click.make_pass_decorator(
Environment, ensure=True
)
cmd_folder = os.path.abspath(
os.path.join(os.path.dirname(__file__), 'commands')
os.path.join(os.path.dirname(__file__), "commands")
)
class ComplexCLI(click.MultiCommand):
"""Access and run subcommands."""
def list_commands(self, ctx):
rv = []
for filename in os.listdir(cmd_folder):
if filename.endswith('.py') and filename.startswith('cmd_'):
rv.append(filename[4:-3])
"""List all subcommands."""
rv = [
filename[4:-3]
for filename in os.listdir(cmd_folder)
if filename.endswith(".py") and filename.startswith("cmd_")
]
rv.sort()
return rv
def get_command(self, ctx, cmd_name):
mod = import_module(f'musicbrainzapi.cli.commands.cmd_{cmd_name}')
"""Get chosen subcummands."""
mod = import_module(f"musicbrainzapi.cli.commands.cmd_{cmd_name}")
return getattr(mod, cmd_name)
@click.command(cls=ComplexCLI, context_settings=CONTEXT_SETTINGS)
@click.option(
'-p',
'--path',
type=click.Path(
exists=True, file_okay=False, resolve_path=True, writable=True
),
help='Local path to save any output files.',
default=os.getcwd()
"-p",
"--path",
type=click.Path(exists=True, file_okay=False, resolve_path=True, writable=True),
help="Local path to save any output files.",
default=os.getcwd(),
)
# @click.option('-v', '--verbose', is_flag=True, help='Enables verbose mode.')
@click.option("-v", "--verbose", is_flag=True, help="Enables verbose mode.")
@click.version_option(
version=__version__,
prog_name=__header__,
message=f'{__header__} version {__version__} 🎤',
message=f"{__header__} version {__version__} 🎤",
)
@pass_environment
def cli(ctx, path):
"""Base command for the musicbrainzapi program."""
# ctx.verbose = verbose
def cli(ctx, verbose, path):
"""Display base command for the musicbrainzapi program."""
ctx.verbose = verbose
if path is not None:
click.echo(f'Path set to {os.path.expanduser(path)}')
click.echo(f"Path set to {os.path.expanduser(path)}")
ctx.path = os.path.expanduser(path)

View File

@@ -1,3 +1,7 @@
"""
Wordcloud from lyrics.
"""
from __future__ import annotations
import collections
from importlib import resources
@@ -16,55 +20,57 @@ if typing.TYPE_CHECKING:
import PIL.PngImagePlugin.PngImageFile
# pylint:disable=line-too-long
class LyricsWordcloud:
"""Create a word cloud from Lyrics.
Attributes
----------
all_albums_lyrics_count : list
List of all albums + track lyrics counted by each word
char_mask : np.array
numpy array containing data for the word cloud image
freq : collections.Counter
Counter object containing counts for all words across all tracks
lyrics_list : list
List of all words from all lyrics across all tracks.
pillow_img : PIL.PngImagePlugin.PngImageFile
pillow image of the word cloud base
wc : wordcloud.WordCloud
WordCloud object
"""
Create a Wordcloud from Lyrics.
The docstring continues here.
It should contain:
- something
- something else
Args:
pillow_img (PIL.PngImagePlugin.PngImageFile): pillow image of the word
cloud base
all_albums_lyrics_count (dict): A dictionary containing the lyrics from
a whole album.
!!! Attributes
- `pillow_img` (pillow): A pillow image.
Anything else can go here.
Example:
Here is how you can use it
"""
def __init__(
self,
pillow_img: 'PIL.PngImagePlugin.PngImageFile',
all_albums_lyrics_count: 'Lyrics.all_albums_lyrics_count',
pillow_img: "PIL.PngImagePlugin.PngImageFile",
all_albums_lyrics_count: "Lyrics.all_albums_lyrics_count",
):
"""
Parameters
----------
pillow_img : PIL.PngImagePlugin.PngImageFile
pillow image of the word cloud base
all_albums_lyrics_count : Lyrics.all_albums_lyrics_count
List of all albums + track lyrics counted by each word
"""
self.pillow_img = pillow_img
self.all_albums_lyrics_count = all_albums_lyrics_count
self.test = []
@classmethod
def use_microphone(
cls, all_albums_lyrics_count: 'Lyrics.all_albums_lyrics_count',
cls, all_albums_lyrics_count: "Lyrics.all_albums_lyrics_count",
) -> LyricsWordcloud:
"""Class method to instantiate with a microphone base image.
"""Create a LyricsWordcloud using a microphone as a base image.
Args:
all_albums_lyrics_count (dict): A dictionary containing the lyrics from a whole album.
Returns:
LyricsWordcloud: Instance of itself with a micrphone image loaded in.
Parameters
----------
all_albums_lyrics_count : Lyrics.all_albums_lyrics_count
List of all albums + track lyrics counted by each word
"""
mic_resource = resources.path(
'musicbrainzapi.wordcloud.resources', 'mic.png'
)
mic_resource = resources.path("musicbrainzapi.wordcloud.resources", "mic.png")
with mic_resource as m:
mic_img = Image.open(m)
@@ -72,15 +78,20 @@ class LyricsWordcloud:
@staticmethod
def generate_grey_colours(
# word: str,
# font_size: str,
# random_state: typing.Union[None, bool] = None,
*args,
**kwargs,
) -> str:
"""Static method to generate a random grey colour"""
colour = f'hsl(0, 0%, {random.randint(60, 100)}%)'
return colour
# word: str,
# font_size: str,
# random_state: typing.Union[None, bool] = None,
*args,
**kwargs,
) -> str:
"""Static method to return a random grey color.
Returns:
str: A random grey colour in `hsl` form.
Can be any grey colour.
"""
return f"hsl(0, 0%, {random.randint(60, 100)}%)"
def _get_lyrics_list(self) -> None:
"""Gets all words from lyrics in a single list + cleans them.
@@ -93,12 +104,8 @@ class LyricsWordcloud:
for word in track:
for _ in range(1, word[1]):
cleaned = word[0]
cleaned = re.sub(
r'[\(\[].*?[\)\]]', ' ', cleaned
)
cleaned = re.sub(
r'[^a-zA-Z0-9\s]', '', cleaned
)
cleaned = re.sub(r"[\(\[].*?[\)\]]", " ", cleaned)
cleaned = re.sub(r"[^a-zA-Z0-9\s]", "", cleaned)
cleaned = cleaned.lower()
if cleaned in STOPWORDS:
continue
@@ -121,11 +128,7 @@ class LyricsWordcloud:
"""Generates a word cloud
"""
self.wc = WordCloud(
max_words=150,
width=1500,
height=1500,
mask=self.char_mask,
random_state=1,
max_words=150, width=1500, height=1500, mask=self.char_mask, random_state=1,
).generate_from_frequencies(self.freq)
return self
@@ -133,18 +136,16 @@ class LyricsWordcloud:
"""Plots the wordcloud and sets matplotlib options.
"""
plt.imshow(
self.wc.recolor(
color_func=self.generate_grey_colours, random_state=3
),
interpolation='bilinear',
self.wc.recolor(color_func=self.generate_grey_colours, random_state=3),
interpolation="bilinear",
)
plt.axis('off')
plt.axis("off")
return self
# def show_word_cloud(self):
# """Shows the word cloud.
# """
# plt.show()
# """Shows the word cloud.
# """
# plt.show()
def create_word_cloud(self) -> None:
"""Creates a word cloud

Binary file not shown.