cv/musicbrainzapi
1
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

adding latest working version

Browse Source
This commit is contained in:
dtomlinson
2020-03-06 18:05:12 +00:00
parent 6a3c09ca21
commit 2af1cc68f3
5 changed files with 209 additions and 202 deletions
Download Patch File Download Diff File Expand all files Collapse all files

258
lyrics_count.json
View File

@@ -4083,74 +4083,22 @@
[
[
"I",
38
18
],
[
"Im",
14
8
],
[
"when",
12
6
],
[
"pray",
11
],
[
"will",
10
],
[
"dance",
10
],
[
"walk",
10
],
[
"away",
10
],
[
"gonna",
10
],
[
"sing",
10
],
[
"wont",
10
],
[
"beg",
10
],
[
"or",
10
],
[
"oh",
9
],
[
"the",
7
],
[
"no",
5
],
[
"to",
4
],
[
"me",
"the",
4
],
[
@@ -4158,47 +4106,71 @@
4
],
[
"and",
"will",
4
],
[
"dance",
4
],
[
"walk",
4
],
[
"away",
4
],
[
"Oh",
4
],
[
"gonna",
4
],
[
"sing",
4
],
[
"wont",
4
],
[
"beg",
4
],
[
"or",
4
],
[
"me",
3
],
[
"now",
"to",
3
],
[
"gone",
3
],
[
"more",
3
],
[
"of",
3
],
[
"Ive",
"and",
2
],
[
"for",
"now",
2
],
[
"with",
2
],
[
"a",
2
],
[
"This",
2
],
[
"you",
"The",
2
],
[
@@ -4206,7 +4178,7 @@
2
],
[
"never",
"Cause",
2
],
[
@@ -4233,6 +4205,14 @@
"on",
2
],
[
"No",
2
],
[
"more",
2
],
[
"full",
2
@@ -4241,18 +4221,14 @@
"been",
2
],
[
"remember",
2
],
[
"Oh",
2
],
[
"In",
1
],
[
"our",
1
],
[
"cold",
1
@@ -4269,6 +4245,10 @@
"lingered",
1
],
[
"for",
1
],
[
"far",
1
@@ -4293,6 +4273,10 @@
"rosary",
1
],
[
"To",
1
],
[
"youd",
1
@@ -4301,6 +4285,14 @@
"stay",
1
],
[
"with",
1
],
[
"a",
1
],
[
"while",
1
@@ -4345,6 +4337,10 @@
"before",
1
],
[
"This",
1
],
[
"time",
1
@@ -4361,6 +4357,14 @@
"leaving",
1
],
[
"you",
1
],
[
"never",
1
],
[
"turn",
1
@@ -4369,10 +4373,6 @@
"around",
1
],
[
"Cause",
1
],
[
"standing",
1
@@ -4414,7 +4414,7 @@
1
],
[
"bridges",
"brigdes",
1
],
[
@@ -4449,10 +4449,22 @@
"earned",
1
],
[
"remember",
1
],
[
"why",
1
],
[
"Ive",
1
],
[
"Remember",
1
],
[
"where",
1
@@ -4464,70 +4476,6 @@
[
"from",
1
],
[
"ooo",
1
],
[
"leave",
1
],
[
"my",
1
],
[
"mask",
1
],
[
"The",
1
],
[
"part",
1
],
[
"played",
1
],
[
"knew",
1
],
[
"Tonight",
1
],
[
"youre",
1
],
[
"alone",
1
],
[
"No",
1
],
[
"is",
1
],
[
"not",
1
],
[
"home",
1
],
[
"oooo",
1
]
],
[

2
lyrics_sum_all_album.json
View File

@@ -1 +1 @@
[{"Le Pop [2009]": [1, 244, 203, 158, "No Lyrics", 129, 108, 1, 122, 163, 251, 176, 183]}, {"A Kiss Before You Go [2011]": [40, 319, 203, 205, 197, 188, 188, 177, 201, 323, 1, 101]}, {"Rockland [2015]": [187, 192, 313, 278, 290, 325, 264, 316, 200, 362, 237, 422, 194, 304]}]
[{"Le Pop [2009]": [1, 244, 203, 158, "No Lyrics", 129, 108, 1, 122, 163, 251, 176, 183]}, {"A Kiss Before You Go [2011]": [40, 191, 203, 205, 197, 188, 188, 177, 201, 323, 1, 101]}, {"Rockland [2015]": [187, 192, 313, 278, 290, 325, 264, 316, 200, 362, 237, 422, 194, 304]}]

33
poetry.lock generated
View File

@@ -163,6 +163,14 @@ optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
version = "0.7.1"
[[package]]
category = "main"
description = "NumPy is the fundamental package for array computing with Python."
name = "numpy"
optional = false
python-versions = ">=3.5"
version = "1.18.1"
[[package]]
category = "dev"
description = "Core utilities for Python packages"
@@ -493,7 +501,7 @@ docs = ["sphinx", "jaraco.packaging (>=3.2)", "rst.linker (>=1.9)"]
testing = ["jaraco.itertools", "func-timeout"]
[metadata]
content-hash = "50cff0758d9f4bfa77596b28f6f5f0c7f1db897b7c0d615071379c288b1d110d"
content-hash = "16e37a137dfee91b8c49b120f770dc04b5361fb91d73ce60b0eae19f64ac2ce5"
python-versions = "^3.7"
[metadata.files]
@@ -560,6 +568,29 @@ musicbrainzngs = [
{file = "musicbrainzngs-0.7.1-py2.py3-none-any.whl", hash = "sha256:e841a8f975104c0a72290b09f59326050194081a5ae62ee512f41915090e1a10"},
{file = "musicbrainzngs-0.7.1.tar.gz", hash = "sha256:ab1c0100fd0b305852e65f2ed4113c6de12e68afd55186987b8ed97e0f98e627"},
]
numpy = [
{file = "numpy-1.18.1-cp35-cp35m-macosx_10_6_intel.whl", hash = "sha256:20b26aaa5b3da029942cdcce719b363dbe58696ad182aff0e5dcb1687ec946dc"},
{file = "numpy-1.18.1-cp35-cp35m-manylinux1_i686.whl", hash = "sha256:70a840a26f4e61defa7bdf811d7498a284ced303dfbc35acb7be12a39b2aa121"},
{file = "numpy-1.18.1-cp35-cp35m-manylinux1_x86_64.whl", hash = "sha256:17aa7a81fe7599a10f2b7d95856dc5cf84a4eefa45bc96123cbbc3ebc568994e"},
{file = "numpy-1.18.1-cp35-cp35m-win32.whl", hash = "sha256:f3d0a94ad151870978fb93538e95411c83899c9dc63e6fb65542f769568ecfa5"},
{file = "numpy-1.18.1-cp35-cp35m-win_amd64.whl", hash = "sha256:1786a08236f2c92ae0e70423c45e1e62788ed33028f94ca99c4df03f5be6b3c6"},
{file = "numpy-1.18.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:ae0975f42ab1f28364dcda3dde3cf6c1ddab3e1d4b2909da0cb0191fa9ca0480"},
{file = "numpy-1.18.1-cp36-cp36m-manylinux1_i686.whl", hash = "sha256:cf7eb6b1025d3e169989416b1adcd676624c2dbed9e3bcb7137f51bfc8cc2572"},
{file = "numpy-1.18.1-cp36-cp36m-manylinux1_x86_64.whl", hash = "sha256:b765ed3930b92812aa698a455847141869ef755a87e099fddd4ccf9d81fffb57"},
{file = "numpy-1.18.1-cp36-cp36m-win32.whl", hash = "sha256:2d75908ab3ced4223ccba595b48e538afa5ecc37405923d1fea6906d7c3a50bc"},
{file = "numpy-1.18.1-cp36-cp36m-win_amd64.whl", hash = "sha256:9acdf933c1fd263c513a2df3dceecea6f3ff4419d80bf238510976bf9bcb26cd"},
{file = "numpy-1.18.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:56bc8ded6fcd9adea90f65377438f9fea8c05fcf7c5ba766bef258d0da1554aa"},
{file = "numpy-1.18.1-cp37-cp37m-manylinux1_i686.whl", hash = "sha256:e422c3152921cece8b6a2fb6b0b4d73b6579bd20ae075e7d15143e711f3ca2ca"},
{file = "numpy-1.18.1-cp37-cp37m-manylinux1_x86_64.whl", hash = "sha256:b3af02ecc999c8003e538e60c89a2b37646b39b688d4e44d7373e11c2debabec"},
{file = "numpy-1.18.1-cp37-cp37m-win32.whl", hash = "sha256:d92350c22b150c1cae7ebb0ee8b5670cc84848f6359cf6b5d8f86617098a9b73"},
{file = "numpy-1.18.1-cp37-cp37m-win_amd64.whl", hash = "sha256:77c3bfe65d8560487052ad55c6998a04b654c2fbc36d546aef2b2e511e760971"},
{file = "numpy-1.18.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:c98c5ffd7d41611407a1103ae11c8b634ad6a43606eca3e2a5a269e5d6e8eb07"},
{file = "numpy-1.18.1-cp38-cp38-manylinux1_i686.whl", hash = "sha256:9537eecf179f566fd1c160a2e912ca0b8e02d773af0a7a1120ad4f7507cd0d26"},
{file = "numpy-1.18.1-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:e840f552a509e3380b0f0ec977e8124d0dc34dc0e68289ca28f4d7c1d0d79474"},
{file = "numpy-1.18.1-cp38-cp38-win32.whl", hash = "sha256:590355aeade1a2eaba17617c19edccb7db8d78760175256e3cf94590a1a964f3"},
{file = "numpy-1.18.1-cp38-cp38-win_amd64.whl", hash = "sha256:39d2c685af15d3ce682c99ce5925cc66efc824652e10990d2462dfe9b8918c6a"},
{file = "numpy-1.18.1.zip", hash = "sha256:b6ff59cee96b454516e47e7721098e6ceebef435e3e21ac2d6c3b8b02628eb77"},
]
packaging = [
{file = "packaging-20.1-py2.py3-none-any.whl", hash = "sha256:170748228214b70b672c581a3dd610ee51f733018650740e98c7df862a583f73"},
{file = "packaging-20.1.tar.gz", hash = "sha256:e665345f9eef0c621aa0bf2f8d78cf6d21904eef16a93f020240b704a57f1334"},

5
pyproject.toml
View File

@@ -10,6 +10,7 @@ requests = "^2.23.0"
musicbrainzngs = "^0.7.1"
addict = "^2.2.1"
progress = "^1.5"
numpy = "^1.18.1"
[tool.poetry.dev-dependencies]
pytest = "^5.2"
@@ -24,9 +25,9 @@ YAPF = "^0.29.0"
pudb = "^2019.2"
pyls-black = "^0.4.4"
[tool.poetry.plugins."console_scripts"]
"musicbrainzapi" = "musicbrainzapi.cli.cli:cli"
[build-system]
requires = ["poetry>=0.12"]
build-backend = "poetry.masonry.api"
[tool.poetry.plugins."console_scripts"]
"musicbrainzapi" = "musicbrainzapi.cli.cli:cli"

113
src/musicbrainzapi/api/command_builders/lyrics.py
View File

@@ -9,11 +9,13 @@ import os
from collections import Counter
import string
import math
import statistics
import musicbrainzngs
import click
import addict
import requests
import numpy
from musicbrainzapi.api import authenticate
@@ -396,63 +398,66 @@ class LyricsBuilder(LyricsConcreteBuilder):
d = addict.Dict(**d, **addict.Dict(album, album_avg))
except ValueError:
d = addict.Dict((album, album_avg))
print(d)
# print(d)
self.all_albums_lyrics_sum.append(d)
print(count)
# print(count)
with open(f'{os.getcwd()}/lyrics_sum_all_album.json', 'w+') as f:
json.dump(self.all_albums_lyrics_sum, f)
return self
def calculate_final_average_by_album(self) -> None:
self.album_averages = addict.Dict()
self.album_statistics = addict.Dict()
# album_lyrics = self.all_albums_lyrics_sum
with open(f'{os.getcwd()}/lyrics_sum_all_album.json', 'r') as f:
album_lyrics = json.load(f)
for i in album_lyrics:
for album, count in i.items():
album_total, album_running = (0, 0)
for c in count:
if isinstance(c, int):
album_running += c
album_total += 1
else:
pass
avg = math.ceil(album_running / album_total)
self.album_averages = addict.Dict(
**self.album_averages, **addict.Dict((album, avg))
)
print(self.album_averages)
for i in album_lyrics:
for album, count in i.items():
_count = [d for d in count if isinstance(d, int)]
avg = math.ceil(statistics.mean(_count))
stdev = math.ceil(statistics.stdev(_count))
# self.album_statistics = addict.Dict(
# **self.album_statistics, **addict.Dict((album, avg))
# )
self.album_statistics = addict.Dict(
**self.album_statistics,
**addict.Dict(
(album, addict.Dict(('avg', avg), ('std', stdev)))
),
)
print(self.album_statistics)
def calculate_final_average_by_year(self) -> None:
group_by_years = addict.Dict()
self.year_averages = addict.Dict()
# album_lyrics = self.all_albums_lyrics_sum
with open(f'{os.getcwd()}/lyrics_sum_all_album.json', 'r') as f:
album_lyrics = json.load(f)
for i in album_lyrics:
for album, count in i.items():
year = album.split('[')[-1].strip(']')
try:
group_by_years = addict.Dict(
**group_by_years, **addict.Dict((year, count))
)
# First loop returns value error for empty dict
except ValueError:
group_by_years = addict.Dict((year, count))
# Multiple years raise a TypeError - we append
except TypeError:
group_by_years.get(year).extend(count)
for year, y_count in group_by_years.items():
year_total, year_running = (0, 0)
for y in y_count:
if isinstance(y, int):
year_running += y
year_total += 1
else:
pass
avg = math.ceil(year_running / year_total)
print(year, avg)
self.year_averages = addict.Dict(
**self.year_averages, **addict.Dict((year, avg))
)
for i in album_lyrics:
for album, count in i.items():
year = album.split('[')[-1].strip(']')
try:
group_by_years = addict.Dict(
**group_by_years, **addict.Dict((year, count))
)
# First loop returns value error for empty dict
except ValueError:
group_by_years = addict.Dict((year, count))
# Multiple years raise a TypeError - we append
except TypeError:
group_by_years.get(year).extend(count)
for year, y_count in group_by_years.items():
year_total, year_running = (0, 0)
for y in y_count:
if isinstance(y, int):
year_running += y
year_total += 1
else:
pass
avg = math.ceil(year_running / year_total)
# print(year, avg)
self.year_averages = addict.Dict(
**self.year_averages, **addict.Dict((year, avg))
)
print(self.year_averages)
@staticmethod
@@ -477,6 +482,26 @@ class LyricsBuilder(LyricsConcreteBuilder):
_strip = word.translate(str.maketrans('', '', string.punctuation))
return _strip
@staticmethod
def get_descriptive_statistics(nums: list) -> Dict[str, int]:
avg = math.ceil(numpy.mean(nums))
median = math.ceil(numpy.median(nums))
std = math.ceil(numpy.std(nums))
max = math.ceil(numpy.max(nums))
min = math.ceil(numpy.min(nums))
p_25 = math.ceil(numpy.percentile(nums, 25))
p_75 = math.ceil(numpy.percentile(nums, 75))
_d = addict.Dict(
('avg', avg),
('median', median),
('std', std),
('max', max),
('min', min),
('p_25', p_25),
('p_75', p_75),
)
return _d
class LyricsClickDirector:
"""docstring for LyricsClickDirector"""
@@ -581,6 +606,8 @@ class LyricsClickDirector:
self.builder.all_albums_lyrics_sum
)
pprint(self.builder._product.all_albums_lyrics_sum)
self.builder.calculate_final_average_by_album()
self.builder.calculate_final_average_by_year()
def _dev(self) -> None:
self.builder.calculate_final_average_by_album()