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 :

Informations additionnelles

environment files have been tested on.

Latest built version: 2024-11-20

Python version used:

'3.12.6 | packaged by conda-forge | (main, Sep 30 2024, 18:08:52) [GCC 13.3.0]'

Package	Version
affine	2.4.0
aiobotocore	2.15.1
aiohappyeyeballs	2.4.3
aiohttp	3.10.8
aioitertools	0.12.0
aiosignal	1.3.1
alembic	1.13.3
altair	5.4.1
aniso8601	9.0.1
annotated-types	0.7.0
appdirs	1.4.4
archspec	0.2.3
asttokens	2.4.1
attrs	24.2.0
babel	2.16.0
bcrypt	4.2.0
beautifulsoup4	4.12.3
black	24.8.0
blinker	1.8.2
blis	0.7.11
bokeh	3.5.2
boltons	24.0.0
boto3	1.35.23
botocore	1.35.23
branca	0.7.2
Brotli	1.1.0
cachetools	5.5.0
cartiflette	0.0.2
Cartopy	0.24.1
catalogue	2.0.10
cattrs	24.1.2
certifi	2024.8.30
cffi	1.17.1
charset-normalizer	3.3.2
click	8.1.7
click-plugins	1.1.1
cligj	0.7.2
cloudpathlib	0.20.0
cloudpickle	3.0.0
colorama	0.4.6
comm	0.2.2
commonmark	0.9.1
conda	24.9.1
conda-libmamba-solver	24.7.0
conda-package-handling	2.3.0
conda_package_streaming	0.10.0
confection	0.1.5
contextily	1.6.2
contourpy	1.3.0
cryptography	43.0.1
cycler	0.12.1
cymem	2.0.8
cytoolz	1.0.0
dask	2024.9.1
dask-expr	1.1.15
databricks-sdk	0.33.0
debugpy	1.8.6
decorator	5.1.1
Deprecated	1.2.14
diskcache	5.6.3
distributed	2024.9.1
distro	1.9.0
docker	7.1.0
duckdb	0.10.1
en-core-web-sm	3.7.1
entrypoints	0.4
et_xmlfile	2.0.0
exceptiongroup	1.2.2
executing	2.1.0
fastexcel	0.11.6
fastjsonschema	2.20.0
fiona	1.10.1
Flask	3.0.3
folium	0.17.0
fontawesomefree	6.6.0
fonttools	4.54.1
frozendict	2.4.4
frozenlist	1.4.1
fsspec	2023.12.2
gensim	4.3.2
geographiclib	2.0
geopandas	1.0.1
geoplot	0.5.1
geopy	2.4.1
gitdb	4.0.11
GitPython	3.1.43
google-auth	2.35.0
graphene	3.3
graphql-core	3.2.4
graphql-relay	3.2.0
graphviz	0.20.3
great-tables	0.12.0
greenlet	3.1.1
gunicorn	22.0.0
h2	4.1.0
hpack	4.0.0
htmltools	0.6.0
hyperframe	6.0.1
idna	3.10
imageio	2.36.0
importlib_metadata	8.5.0
importlib_resources	6.4.5
inflate64	1.0.0
ipykernel	6.29.5
ipython	8.28.0
itsdangerous	2.2.0
jedi	0.19.1
Jinja2	3.1.4
jmespath	1.0.1
joblib	1.4.2
jsonpatch	1.33
jsonpointer	3.0.0
jsonschema	4.23.0
jsonschema-specifications	2024.10.1
jupyter-cache	1.0.0
jupyter_client	8.6.3
jupyter_core	5.7.2
kaleido	0.2.1
kiwisolver	1.4.7
langcodes	3.5.0
language_data	1.3.0
lazy_loader	0.4
libmambapy	1.5.9
locket	1.0.0
lxml	5.3.0
lz4	4.3.3
Mako	1.3.5
mamba	1.5.9
mapclassify	2.8.1
marisa-trie	1.2.1
Markdown	3.6
markdown-it-py	3.0.0
MarkupSafe	2.1.5
matplotlib	3.9.2
matplotlib-inline	0.1.7
mdurl	0.1.2
menuinst	2.1.2
mercantile	1.2.1
mizani	0.11.4
mlflow	2.16.2
mlflow-skinny	2.16.2
msgpack	1.1.0
multidict	6.1.0
multivolumefile	0.2.3
munkres	1.1.4
murmurhash	1.0.10
mypy-extensions	1.0.0
narwhals	1.14.1
nbclient	0.10.0
nbformat	5.10.4
nest_asyncio	1.6.0
networkx	3.3
nltk	3.9.1
numpy	1.26.4
opencv-python-headless	4.10.0.84
openpyxl	3.1.5
opentelemetry-api	1.16.0
opentelemetry-sdk	1.16.0
opentelemetry-semantic-conventions	0.37b0
OWSLib	0.28.1
packaging	24.1
pandas	2.2.3
paramiko	3.5.0
parso	0.8.4
partd	1.4.2
pathspec	0.12.1
patsy	0.5.6
Pebble	5.0.7
pexpect	4.9.0
pickleshare	0.7.5
pillow	10.4.0
pip	24.2
platformdirs	4.3.6
plotly	5.24.1
plotnine	0.13.6
pluggy	1.5.0
polars	1.8.2
preshed	3.0.9
prometheus_client	0.21.0
prometheus_flask_exporter	0.23.1
prompt_toolkit	3.0.48
protobuf	4.25.3
psutil	6.0.0
ptyprocess	0.7.0
pure_eval	0.2.3
py7zr	0.20.8
pyarrow	17.0.0
pyarrow-hotfix	0.6
pyasn1	0.6.1
pyasn1_modules	0.4.1
pybcj	1.0.2
pycosat	0.6.6
pycparser	2.22
pycryptodomex	3.21.0
pydantic	2.9.2
pydantic_core	2.23.4
Pygments	2.18.0
PyNaCl	1.5.0
pynsee	0.1.8
pyogrio	0.10.0
pyOpenSSL	24.2.1
pyparsing	3.1.4
pyppmd	1.1.0
pyproj	3.7.0
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	1.1.1
PyYAML	6.0.2
pyzmq	26.2.0
pyzstd	0.16.2
querystring_parser	1.2.4
rasterio	1.4.2
referencing	0.35.1
regex	2024.9.11
requests	2.32.3
requests-cache	1.2.1
retrying	1.3.4
rich	13.9.4
rpds-py	0.21.0
rsa	4.9
ruamel.yaml	0.18.6
ruamel.yaml.clib	0.2.8
s3fs	2023.12.2
s3transfer	0.10.2
scikit-image	0.24.0
scikit-learn	1.5.2
scipy	1.13.0
seaborn	0.13.2
setuptools	74.1.2
shapely	2.0.6
shellingham	1.5.4
six	1.16.0
smart-open	7.0.5
smmap	5.0.0
sortedcontainers	2.4.0
soupsieve	2.5
spacy	3.7.5
spacy-legacy	3.0.12
spacy-loggers	1.0.5
SQLAlchemy	2.0.35
sqlparse	0.5.1
srsly	2.4.8
stack-data	0.6.2
statsmodels	0.14.4
tabulate	0.9.0
tblib	3.0.0
tenacity	9.0.0
texttable	1.7.0
thinc	8.2.5
threadpoolctl	3.5.0
tifffile	2024.9.20
toolz	1.0.0
topojson	1.9
tornado	6.4.1
tqdm	4.66.5
traitlets	5.14.3
truststore	0.9.2
typer	0.13.1
typing_extensions	4.12.2
tzdata	2024.2
Unidecode	1.3.8
url-normalize	1.4.3
urllib3	1.26.20
wasabi	1.1.3
wcwidth	0.2.13
weasel	0.4.1
webdriver-manager	4.0.2
websocket-client	1.8.0
Werkzeug	3.0.4
wheel	0.44.0
wordcloud	1.9.3
wrapt	1.16.0
xgboost	2.1.1
xlrd	2.0.1
xyzservices	2024.9.0
yarl	1.13.1
yellowbrick	1.5
zict	3.0.0
zipp	3.20.2
zstandard	0.23.0

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
0908656	2024-08-20 16:30:39	Lino Galiana	English sidebar (#542)
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')

Retour au sommet

Citation

BibTeX

@book{galiana2023,
  author = {Galiana, Lino},
  title = {Python pour la data science},
  date = {2023},
  url = {https://pythonds.linogaliana.fr/},
  doi = {10.5281/zenodo.8229676},
  langid = {fr}
}

Veuillez citer ce travail comme suit :

Galiana, Lino. 2023. Python pour la data science. https://doi.org/10.5281/zenodo.8229676.