Python pour la data science

Lino Galiana

doi:10.5281/zenodo.8229676

Chapitre déplacé

Le programme du cours a été modifié. Ce chapitre se trouve maintenant dans la partie Manipulation de données

Informations additionnelles

environment files have been tested on.

Python version used:

Package	Version
affine	2.4.0
aiobotocore	2.22.0
aiohappyeyeballs	2.6.1
aiohttp	3.11.18
aioitertools	0.12.0
aiosignal	1.3.2
altair	5.4.1
annotated-types	0.7.0
anyio	4.9.0
appdirs	1.4.4
argon2-cffi	25.1.0
argon2-cffi-bindings	21.2.0
arrow	1.3.0
asttokens	3.0.0
async-lru	2.0.5
attrs	25.3.0
babel	2.17.0
beautifulsoup4	4.13.4
black	24.8.0
bleach	6.2.0
blis	1.3.0
boto3	1.37.3
botocore	1.37.3
branca	0.8.1
Brotli	1.1.0
bs4	0.0.2
cartiflette	0.0.3
Cartopy	0.24.1
catalogue	2.0.10
cattrs	24.1.3
certifi	2025.7.14
cffi	1.17.1
charset-normalizer	3.4.2
chromedriver-autoinstaller	0.6.4
click	8.2.1
click-plugins	1.1.1
cligj	0.7.2
cloudpathlib	0.21.1
comm	0.2.2
commonmark	0.9.1
confection	0.1.5
contextily	1.6.2
contourpy	1.3.2
cycler	0.12.1
cymem	2.0.11
dataclasses-json	0.6.7
debugpy	1.8.14
decorator	5.2.1
defusedxml	0.7.1
diskcache	5.6.3
duckdb	1.3.0
en_core_web_sm	3.8.0
et_xmlfile	2.0.0
executing	2.2.0
fastexcel	0.14.0
fastjsonschema	2.21.1
fiona	1.10.1
folium	0.19.6
fontawesomefree	6.6.0
fonttools	4.58.0
fqdn	1.5.1
fr_core_news_sm	3.8.0
frozenlist	1.6.0
fsspec	2025.5.0
geographiclib	2.0
geopandas	1.0.1
geoplot	0.5.1
geopy	2.4.1
graphviz	0.20.3
great-tables	0.12.0
greenlet	3.2.2
h11	0.16.0
htmltools	0.6.0
httpcore	1.0.9
httpx	0.28.1
httpx-sse	0.4.0
idna	3.10
imageio	2.37.0
importlib_metadata	8.7.0
importlib_resources	6.5.2
inflate64	1.0.1
ipykernel	6.29.5
ipython	9.3.0
ipython_pygments_lexers	1.1.1
ipywidgets	8.1.7
isoduration	20.11.0
jedi	0.19.2
Jinja2	3.1.6
jmespath	1.0.1
joblib	1.5.1
json5	0.12.0
jsonpatch	1.33
jsonpointer	3.0.0
jsonschema	4.23.0
jsonschema-specifications	2025.4.1
jupyter	1.1.1
jupyter-cache	1.0.0
jupyter_client	8.6.3
jupyter-console	6.6.3
jupyter_core	5.7.2
jupyter-events	0.12.0
jupyter-lsp	2.2.5
jupyter_server	2.16.0
jupyter_server_terminals	0.5.3
jupyterlab	4.4.3
jupyterlab_pygments	0.3.0
jupyterlab_server	2.27.3
jupyterlab_widgets	3.0.15
kaleido	0.2.1
kiwisolver	1.4.8
langchain	0.3.25
langchain-community	0.3.9
langchain-core	0.3.61
langchain-text-splitters	0.3.8
langcodes	3.5.0
langsmith	0.1.147
language_data	1.3.0
lazy_loader	0.4
loguru	0.7.3
lxml	5.4.0
mapclassify	2.8.1
marisa-trie	1.2.1
Markdown	3.8
markdown-it-py	3.0.0
MarkupSafe	3.0.2
marshmallow	3.26.1
matplotlib	3.10.3
matplotlib-inline	0.1.7
mdurl	0.1.2
mercantile	1.2.1
mistune	3.1.3
mizani	0.11.4
multidict	6.4.4
multivolumefile	0.2.3
murmurhash	1.0.13
mypy_extensions	1.1.0
narwhals	1.40.0
nbclient	0.10.0
nbconvert	7.16.6
nbformat	5.10.4
nest-asyncio	1.6.0
networkx	3.4.2
nltk	3.9.1
notebook	7.4.3
notebook_shim	0.2.4
numpy	2.2.6
openpyxl	3.1.5
orjson	3.10.18
outcome	1.3.0.post0
overrides	7.7.0
OWSLib	0.33.0
packaging	24.2
pandas	2.2.3
pandocfilters	1.5.1
parso	0.8.4
pathspec	0.12.1
patsy	1.0.1
Pebble	5.1.1
pexpect	4.9.0
pillow	11.2.1
pip	25.1.1
platformdirs	4.3.8
plotly	6.1.2
plotnine	0.13.6
polars	1.8.2
preshed	3.0.9
prometheus_client	0.22.1
prompt_toolkit	3.0.51
propcache	0.3.1
psutil	7.0.0
ptyprocess	0.7.0
pure_eval	0.2.3
py7zr	0.22.0
pyarrow	17.0.0
pybcj	1.0.6
pycparser	2.22
pycryptodomex	3.23.0
pydantic	2.11.5
pydantic_core	2.33.2
pydantic-settings	2.9.1
Pygments	2.19.1
pynsee	0.1.8
pyogrio	0.11.0
pyparsing	3.2.3
pyppmd	1.1.1
pyproj	3.7.1
pyshp	2.3.1
PySocks	1.7.1
python-dateutil	2.9.0.post0
python-dotenv	1.0.1
python-json-logger	3.3.0
python-magic	0.4.27
pytz	2025.2
pywaffle	1.1.1
PyYAML	6.0.2
pyzmq	26.4.0
pyzstd	0.17.0
rasterio	1.4.3
referencing	0.36.2
regex	2024.11.6
requests	2.32.3
requests-cache	1.2.1
requests-toolbelt	1.0.0
retrying	1.3.4
rfc3339-validator	0.1.4
rfc3986-validator	0.1.1
rich	14.0.0
rpds-py	0.25.1
rtree	1.4.0
s3fs	2025.5.0
s3transfer	0.11.3
scikit-image	0.24.0
scikit-learn	1.6.1
scipy	1.13.0
seaborn	0.13.2
selenium	4.34.2
Send2Trash	1.8.3
setuptools	80.8.0
shapely	2.1.1
shellingham	1.5.4
six	1.17.0
smart-open	7.1.0
sniffio	1.3.1
sortedcontainers	2.4.0
soupsieve	2.7
spacy	3.8.4
spacy-legacy	3.0.12
spacy-loggers	1.0.5
SQLAlchemy	2.0.41
srsly	2.5.1
stack-data	0.6.3
statsmodels	0.14.4
tabulate	0.9.0
tenacity	9.1.2
terminado	0.18.1
texttable	1.7.0
thinc	8.3.6
threadpoolctl	3.6.0
tifffile	2025.5.24
tinycss2	1.4.0
topojson	1.9
tornado	6.5.1
tqdm	4.67.1
traitlets	5.14.3
trio	0.30.0
trio-websocket	0.12.2
typer	0.15.3
types-python-dateutil	2.9.0.20250516
typing_extensions	4.14.1
typing-inspect	0.9.0
typing-inspection	0.4.1
tzdata	2025.2
Unidecode	1.4.0
uri-template	1.3.0
url-normalize	2.2.1
urllib3	2.5.0
wasabi	1.1.3
wcwidth	0.2.13
weasel	0.4.1
webcolors	24.11.1
webdriver-manager	4.0.2
webencodings	0.5.1
websocket-client	1.8.0
widgetsnbextension	4.0.14
wordcloud	1.9.3
wrapt	1.17.2
wsproto	1.2.0
xlrd	2.0.1
xyzservices	2025.4.0
yarl	1.20.0
yellowbrick	1.5
zipp	3.21.0

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
8f8e6563	2025-06-16 15:42:32	lgaliana	Les chapitres dans le bon ordre, ça serait mieux…
d8bacc63	2025-06-16 17:34:16	Lino Galiana	Ménage de printemps: retire les vieux chapitres inutiles (#615)
88890345	2024-12-27 14:38:09	lgaliana	Sur la récupération de données
c1853b92	2024-11-20 15:09:19	Lino Galiana	Reprise eval + reprise S3 (#576)
005d89b8	2023-12-20 17:23:04	Lino Galiana	Finalise l’affichage des statistiques Git (#478)
3fba6124	2023-12-17 18:16:42	Lino Galiana	Remove some badges from python (#476)
4cd44f35	2023-12-11 17:37:50	Antoine Palazzolo	Relecture NLP (#474)
1f23de28	2023-12-01 17:25:36	Lino Galiana	Stockage des images sur S3 (#466)
a06a2689	2023-11-23 18:23:28	Antoine Palazzolo	2ème relectures chapitres ML (#457)
09654c71	2023-11-14 15:16:44	Antoine Palazzolo	Suggestions Git & Visualisation (#449)
889a71ba	2023-11-10 11:40:51	Antoine Palazzolo	Modification TP 3 (#443)
a7711832	2023-10-09 11:27:45	Antoine Palazzolo	Relecture TD2 par Antoine (#418)
8556b79f	2023-09-27 17:29:23	Julien PRAMIL	Typo chapitre S3 (#415)
154f09e4	2023-09-26 14:59:11	Antoine Palazzolo	Des typos corrigées par Antoine (#411)
9977c5dc	2023-08-28 10:43:36	Lino Galiana	Fix bug path pandas (#397)
3bdf3b06	2023-08-25 11:23:02	Lino Galiana	Simplification de la structure 🤓 (#393)
5d4874a8	2023-08-11 15:09:33	Lino Galiana	Pimp les introductions des trois premières parties (#387)
3f60d55d	2023-02-02 18:59:16	Lino Galiana	WIP: Change path S3 (#349)
9000723c	2023-01-22 12:01:25	Lino Galiana	Corrige code s3fs upload (#345)
1fe65ac9	2022-12-25 21:39:51	Lino Galiana	Dark boxes (#336)
2227f8eb	2022-12-25 18:56:57	Lino Galiana	Fix problem s3 chapter (#335)
8e5edba6	2022-09-02 11:59:57	Lino Galiana	Ajoute un chapitre dask (#264)
688cc15e	2022-09-01 18:38:59	Lino Galiana	Update index.qmd
2117d2c7	2022-09-01 08:54:38	Lino Galiana	Ajoute des éléments sur arrow (#262)
f10815b5	2022-08-25 16:00:03	Lino Galiana	Notebooks should now look more beautiful (#260)
d201e3cd	2022-08-03 15:50:34	Lino Galiana	Pimp la homepage ✨ (#249)
bacb5a01	2022-07-04 19:05:20	Lino Galiana	Enrichir la partie elastic (#241)
12965bac	2022-05-25 15:53:27	Lino Galiana	:launch: Bascule vers quarto (#226)
aa945cb7	2022-03-31 09:28:14	Lino Galiana	corrige une ou deux typos (#225)
34b08ec8	2022-03-24 16:37:37	Lino Galiana	Ajoute code sur write_parquet dans S3
c51a87b9	2022-03-24 16:29:39	Lino Galiana	retire typo nom bucket (#223)
3b1d9ff1	2022-03-09 10:38:15	Lino Galiana	Ajoute détails arrow dans la partie S3 (#220)
9c71d6e7	2022-03-08 10:34:26	Lino Galiana	Plus d’éléments sur S3 (#218)
2a8809fb	2021-10-27 12:05:34	Lino Galiana	Simplification des hooks pour gagner en flexibilité et clarté (#166)
2e4d5862	2021-09-02 12:03:39	Lino Galiana	Simplify badges generation (#130)
80877d20	2021-06-28 11:34:24	Lino Galiana	Ajout d’un exercice de NLP à partir openfood database (#98)
6729a724	2021-06-22 18:07:05	Lino Galiana	Mise à jour badge onyxia (#115)
4cdb759c	2021-05-12 10:37:23	Lino Galiana	:sparkles: :star2: Nouveau thème hugo :snake: :fire: (#105)
7f9f97bc	2021-04-30 21:44:04	Lino Galiana	🐳 + 🐍 New workflow (docker 🐳) and new dataset for modelization (2020 🇺🇸 elections) (#99)
0a0d0348	2021-03-26 20:16:22	Lino Galiana	Ajout d’une section sur S3 (#97)

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.