#+TITLE:  Analyse du journal
#+AUTHOR: Louis Lacoste
#+DATE:   2022-11-20
#+LANGUAGE: fr
# #+PROPERTY: header-args :eval never-export

#+HTML_HEAD: <link rel="stylesheet" type="text/css" href="http://www.pirilampo.org/styles/readtheorg/css/htmlize.css"/>
#+HTML_HEAD: <link rel="stylesheet" type="text/css" href="http://www.pirilampo.org/styles/readtheorg/css/readtheorg.css"/>
#+HTML_HEAD: <script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.3/jquery.min.js"></script>
#+HTML_HEAD: <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
#+HTML_HEAD: <script type="text/javascript" src="http://www.pirilampo.org/styles/lib/js/jquery.stickytableheaders.js"></script>
#+HTML_HEAD: <script type="text/javascript" src="http://www.pirilampo.org/styles/readtheorg/js/readtheorg.js"></script>

* Récupération des données du journal

Ici nous allons importer les étiquettes et les exporter dans un
fichier =data.csv=. 

#+begin_src shell :results output :exports both
grep -oP "(?<=:)([a-zA-Z]*)(?=:)" ~/org/journal.org > data.csv
head -n 5 data.csv
#+end_src

#+RESULTS:
: informatique
: wikipedia
: biologie
: virus
: allergie

* Traitement des données

#+NAME: import-python
#+begin_src python :results output :session :exports both :dir /home/polarolouis/Documents/MOOC/RR/mooc-rr/module2/exo4
import csv
from collections import Counter

temporaryList = []

with open('data.csv', 'r', encoding='utf8') as csvfile:
    reader = csv.reader(csvfile)
    for row in reader:
        temporaryList.append(row[0])

tagCount = Counter(temporaryList)

tagList = []
countList = []

for tag in tagCount:
    tagList.append(tag)
    countList.append(tagCount[tag])

#+end_src

Ici on convertit les données en dataframe =pandas= afin de pouvoir faire
l'affichage plus facilement.
 
#+RESULTS: import-python

#+NAME: conversion-dataframe
#+begin_src python :results output :session :exports both
import pandas as pd

preDataframe = dict(tagCount)


print(preDataframe)

tagCountDataframe = pd.DataFrame.from_dict({'tags':list(preDataframe), 'values':list(preDataframe.values())})
tagCountDataframe['values'] = pd.to_numeric(tagCountDataframe['values'])

print(tagCountDataframe)
#+end_src

#+RESULTS: conversion-dataframe
#+begin_example
{'informatique': 2, 'wikipedia': 1, 'biologie': 2, 'virus': 1, 'allergie': 1, 'noexport': 2, 'LOGBOOK': 2, 'END': 2, 'mooc': 1, 'science': 1, 'Epistemology': 1}
            tags  values
0   informatique       2
1      wikipedia       1
2       biologie       2
3          virus       1
4       allergie       1
5       noexport       2
6        LOGBOOK       2
7            END       2
8           mooc       1
9        science       1
10  Epistemology       1
#+end_example

* Affichage des données
** Diverses infos
   #+begin_src python :results output :session :exports both
print(f"Les tags les plus cités : {tagCount.most_common(3)}")
   #+end_src

   #+RESULTS:
   : Les tags les plus cités : [('informatique', 2), ('biologie', 2), ('noexport', 2)]
** Graphiques
   #+begin_src python :results file :session :var matplot_lib_filename=(org-babel-temp-file "figure" ".png") :exports both
import matplotlib.pyplot as plt
plt.figure(figsize=(10,5))
plt.tight_layout()

# Affichage 
ax = tagCountDataframe.plot(x="tags", y="values", kind='bar')

plt.savefig(matplot_lib_filename)
matplot_lib_filename

#+end_src

#+RESULTS:
[[file:/tmp/babel-Eb8JSG/figure6P1Fep.png]]