Python pour la data science

Lino Galiana

doi:10.5281/zenodo.8229676

Les parties précédentes étaient très tournées sur l’acquisition de compétences minimales dans chaque domaine de l’analyse de données. Cette partie propose des éléments plus avancés mais plus représentatifs du travail quotidien du data scientist. Cette partie présente la manière dont Python peut être utilisé dans une architecture moderne de type cloud. Elle illustre la manière dont Python peut servir de couteau-suisse faisant l’interface entre différents langages plus efficaces ou plusieurs types de données.

Cette partie est en cours de construction et présentera les éléments suivants :

0.1 Contenu de la partie

Informations additionnelles

environment files have been tested on.

Latest built version: 2024-04-27

Python version used:

'3.11.6 | packaged by conda-forge | (main, Oct  3 2023, 10:40:35) [GCC 12.3.0]'

Package	Version
affine	2.4.0
aiobotocore	2.12.2
aiohttp	3.9.3
aioitertools	0.11.0
aiosignal	1.3.1
alembic	1.13.1
aniso8601	9.0.1
annotated-types	0.6.0
appdirs	1.4.4
archspec	0.2.3
astroid	3.1.0
asttokens	2.4.1
attrs	23.2.0
Babel	2.14.0
bcrypt	4.1.2
beautifulsoup4	4.12.3
black	24.4.2
blinker	1.7.0
blis	0.7.11
bokeh	3.4.0
boltons	23.1.1
boto3	1.34.51
botocore	1.34.51
branca	0.7.1
Brotli	1.1.0
cachetools	5.3.3
cartiflette	0.0.2
Cartopy	0.23.0
catalogue	2.0.10
cattrs	23.2.3
certifi	2024.2.2
cffi	1.16.0
charset-normalizer	3.3.2
chromedriver-autoinstaller	0.6.4
click	8.1.7
click-plugins	1.1.1
cligj	0.7.2
cloudpathlib	0.16.0
cloudpickle	3.0.0
colorama	0.4.6
comm	0.2.2
commonmark	0.9.1
conda	24.3.0
conda-libmamba-solver	24.1.0
conda-package-handling	2.2.0
conda_package_streaming	0.9.0
confection	0.1.4
contextily	1.6.0
contourpy	1.2.1
cryptography	42.0.5
cycler	0.12.1
cymem	2.0.8
cytoolz	0.12.3
dask	2024.4.1
dask-expr	1.0.10
debugpy	1.8.1
decorator	5.1.1
dill	0.3.8
distributed	2024.4.1
distro	1.9.0
docker	7.0.0
duckdb	0.10.1
en-core-web-sm	3.7.1
entrypoints	0.4
et-xmlfile	1.1.0
exceptiongroup	1.2.0
executing	2.0.1
fastjsonschema	2.19.1
fiona	1.9.6
flake8	7.0.0
Flask	3.0.2
folium	0.16.0
fontawesomefree	6.5.1
fonttools	4.51.0
fr-core-news-sm	3.7.0
frozenlist	1.4.1
fsspec	2023.12.2
GDAL	3.8.4
gensim	4.3.2
geographiclib	2.0
geopandas	0.12.2
geoplot	0.5.1
geopy	2.4.1
gitdb	4.0.11
GitPython	3.1.43
google-auth	2.29.0
graphene	3.3
graphql-core	3.2.3
graphql-relay	3.2.0
graphviz	0.20.3
great-tables	0.5.0
greenlet	3.0.3
gunicorn	21.2.0
h11	0.14.0
htmltools	0.5.1
hvac	2.1.0
idna	3.6
imageio	2.34.1
importlib_metadata	7.1.0
importlib_resources	6.4.0
inflate64	1.0.0
ipykernel	6.29.3
ipython	8.22.2
ipywidgets	8.1.2
isort	5.13.2
itsdangerous	2.1.2
jedi	0.19.1
Jinja2	3.1.3
jmespath	1.0.1
joblib	1.3.2
jsonpatch	1.33
jsonpointer	2.4
jsonschema	4.21.1
jsonschema-specifications	2023.12.1
jupyter-cache	1.0.0
jupyter_client	8.6.1
jupyter_core	5.7.2
jupyterlab_widgets	3.0.10
kaleido	0.2.1
kiwisolver	1.4.5
kubernetes	29.0.0
langcodes	3.4.0
language_data	1.2.0
lazy_loader	0.4
libmambapy	1.5.7
llvmlite	0.42.0
locket	1.0.0
lxml	5.2.1
lz4	4.3.3
Mako	1.3.2
mamba	1.5.7
mapclassify	2.6.1
marisa-trie	1.1.0
Markdown	3.6
MarkupSafe	2.1.5
matplotlib	3.8.3
matplotlib-inline	0.1.6
mccabe	0.7.0
menuinst	2.0.2
mercantile	1.2.1
mizani	0.11.2
mlflow	2.11.3
mlflow-skinny	2.11.3
msgpack	1.0.7
multidict	6.0.5
multivolumefile	0.2.3
munkres	1.1.4
murmurhash	1.0.10
mypy	1.9.0
mypy-extensions	1.0.0
nbclient	0.10.0
nbformat	5.10.4
nest_asyncio	1.6.0
networkx	3.3
nltk	3.8.1
numba	0.59.1
numpy	1.26.4
oauthlib	3.2.2
opencv-python-headless	4.9.0.80
openpyxl	3.1.2
outcome	1.3.0.post0
OWSLib	0.28.1
packaging	23.2
pandas	2.2.1
paramiko	3.4.0
parso	0.8.4
partd	1.4.1
pathspec	0.12.1
patsy	0.5.6
Pebble	5.0.7
pexpect	4.9.0
pickleshare	0.7.5
pillow	10.3.0
pip	24.0
pkgutil_resolve_name	1.3.10
platformdirs	4.2.0
plotly	5.19.0
plotnine	0.13.5
pluggy	1.4.0
polars	0.20.18
preshed	3.0.9
prometheus_client	0.20.0
prometheus-flask-exporter	0.23.0
prompt-toolkit	3.0.42
protobuf	4.25.3
psutil	5.9.8
ptyprocess	0.7.0
pure-eval	0.2.2
py7zr	0.20.8
pyarrow	15.0.0
pyarrow-hotfix	0.6
pyasn1	0.5.1
pyasn1-modules	0.3.0
pybcj	1.0.2
pycodestyle	2.11.1
pycosat	0.6.6
pycparser	2.21
pycryptodomex	3.20.0
pydantic	2.7.1
pydantic_core	2.18.2
pyflakes	3.2.0
Pygments	2.17.2
PyJWT	2.8.0
pylint	3.1.0
PyNaCl	1.5.0
pynsee	0.1.7
pyOpenSSL	24.0.0
pyparsing	3.1.2
pyppmd	1.1.0
pyproj	3.6.1
pyshp	2.3.1
PySocks	1.7.1
python-dateutil	2.9.0
python-dotenv	1.0.1
python-magic	0.4.27
pytz	2024.1
pyu2f	0.1.5
pywaffle	1.1.0
PyYAML	6.0.1
pyzmq	25.1.2
pyzstd	0.15.10
QtPy	2.4.1
querystring-parser	1.2.4
rasterio	1.3.10
referencing	0.34.0
regex	2023.12.25
requests	2.31.0
requests-cache	1.2.0
requests-oauthlib	2.0.0
rpds-py	0.18.0
rsa	4.9
Rtree	1.2.0
ruamel.yaml	0.18.6
ruamel.yaml.clib	0.2.8
s3fs	2023.12.2
s3transfer	0.10.1
scikit-image	0.23.2
scikit-learn	1.4.1.post1
scipy	1.13.0
seaborn	0.13.2
selenium	4.20.0
setuptools	69.2.0
shapely	2.0.3
six	1.16.0
smart-open	6.4.0
smmap	5.0.0
sniffio	1.3.1
snuggs	1.4.7
sortedcontainers	2.4.0
soupsieve	2.5
spacy	3.7.4
spacy-legacy	3.0.12
spacy-loggers	1.0.5
SQLAlchemy	2.0.29
sqlparse	0.4.4
srsly	2.4.8
stack-data	0.6.2
statsmodels	0.14.1
tabulate	0.9.0
tblib	3.0.0
tenacity	8.2.3
texttable	1.7.0
thinc	8.2.3
threadpoolctl	3.4.0
tifffile	2024.4.24
tomli	2.0.1
tomlkit	0.12.4
toolz	0.12.1
topojson	1.8
tornado	6.4
tqdm	4.66.2
traitlets	5.14.2
trio	0.25.0
trio-websocket	0.11.1
truststore	0.8.0
typer	0.9.4
typing_extensions	4.11.0
tzdata	2024.1
Unidecode	1.3.8
url-normalize	1.4.3
urllib3	1.26.18
wasabi	1.1.2
wcwidth	0.2.13
weasel	0.3.4
webcolors	1.13
webdriver-manager	4.0.1
websocket-client	1.7.0
Werkzeug	3.0.2
wheel	0.43.0
widgetsnbextension	4.0.10
wordcloud	1.9.3
wrapt	1.16.0
wsproto	1.2.0
xgboost	2.0.3
xlrd	2.0.1
xyzservices	2024.4.0
yarl	1.9.4
yellowbrick	1.5
zict	3.0.0
zipp	3.17.0
zstandard	0.22.0

View file history

md`Ce fichier a été modifié __${table_commit.length}__ fois depuis sa création le ${creation_string} (dernière modification le ${last_modification_string})`

creation = d3.min(
  table_commit.map(d => new Date(d.Date))
)

last_modification = d3.max(
  table_commit.map(d => new Date(d.Date))
)

creation_string = creation.toLocaleString("fr", {
  "day": "numeric",
  "month": "long",
  "year": "numeric"
})

last_modification_string = last_modification.toLocaleString("fr", {
  "day": "numeric",
  "month": "long",
  "year": "numeric"
})

html`<div>${git_history_table}</div>`

html`<div>${git_history_plot}</div>`

SHA	Date	Author	Description
005d89b	2023-12-20 17:23:04	Lino Galiana	Finalise l’affichage des statistiques Git (#478)
1f23de2	2023-12-01 17:25:36	Lino Galiana	Stockage des images sur S3 (#466)
889a71b	2023-11-10 11:40:51	Antoine Palazzolo	Modification TP 3 (#443)
a771183	2023-10-09 11:27:45	Antoine Palazzolo	Relecture TD2 par Antoine (#418)
154f09e	2023-09-26 14:59:11	Antoine Palazzolo	Des typos corrigées par Antoine (#411)
3bdf3b0	2023-08-25 11:23:02	Lino Galiana	Simplification de la structure 🤓 (#393)
5d4874a	2023-08-11 15:09:33	Lino Galiana	Pimp les introductions des trois premières parties (#387)
f21a24d	2023-07-02 10:58:15	Lino Galiana	Pipeline Quarto & Pages 🚀 (#365)
bacb5a0	2022-07-04 19:05:20	Lino Galiana	Enrichir la partie elastic (#241)

git_history_table = Inputs.table(
  table_commit,
  {
    format: {
      SHA: x => md`[${x}](${github_repo}/commit/${x})`,
      Description: x => md`${replacePullRequestPattern(x, github_repo)}`,
      /*Date: x => x.toLocaleString("fr", {
        "month": "numeric",
        "day": "numeric",
        "year": "numeric"
        })
      */
    }
  }
)

git_history_plot = Plot.plot({
  marks: [
    Plot.ruleY([0], {stroke: "royalblue"}),
    Plot.dot(
          table_commit,
          Plot.pointerX({x: (d) => new Date(d.date), y: 0, stroke: "red"})),
    Plot.dot(table_commit, {x: (d) => new Date(d.Date), y: 0, fill: "royalblue"})
  ]
})

function replacePullRequestPattern(inputString, githubRepo) {
    // Use a regular expression to match the pattern #digit
    var pattern = /#(\d+)/g;

    // Replace the pattern with ${github_repo}/pull/#digit
    var replacedString = inputString.replace(pattern, '[#$1](' + githubRepo + '/pull/$1)');

    return replacedString;
}

github_repo = "https://github.com/linogaliana/python-datascientist"

table_commit = {

// Get the HTML table by its class name
var table = document.querySelector('.commit-table');

// Check if the table exists
if (table) {
    // Initialize an array to store the table data
    var dataArray = [];

    // Extract headers from the first row
    var headers = [];
    for (var i = 0; i < table.rows[0].cells.length; i++) {
        headers.push(table.rows[0].cells[i].textContent.trim());
    }

    // Iterate through the rows, starting from the second row
    for (var i = 1; i < table.rows.length; i++) {
        var row = table.rows[i];
        var rowData = {};

        // Iterate through the cells in the row
        for (var j = 0; j < row.cells.length; j++) {
            // Use headers as keys and cell content as values
            rowData[headers[j]] = row.cells[j].textContent.trim();
        }

        // Push the rowData object to the dataArray
        dataArray.push(rowData);
    }
  }

  return dataArray

}

// Get the element with class 'git-details'
{
  var gitDetails = document.querySelector('.commit-table');

  // Check if the element exists
  if (gitDetails) {
      // Hide the element
      gitDetails.style.display = 'none';
  }
}

Plot = require('@observablehq/plot@0.6.12/dist/plot.umd.min.js')

Back to top

Citation

BibTeX citation:

@book{galiana2023,
  author = {Galiana, Lino},
  title = {Python Pour La Data Science},
  date = {2023},
  url = {https://pythonds.linogaliana.fr/},
  doi = {10.5281/zenodo.8229676},
  langid = {en}
}

For attribution, please cite this work as:

Galiana, Lino. 2023. Python Pour La Data Science. https://doi.org/10.5281/zenodo.8229676.