Première analyse

module2/exo4/analyse-journal.org

@@ -33,23 +33,78 @@ head -n 5 data.csv
 #+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:
-        print(row)
+        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
-#+begin_example
-
-['informatique']
-['wikipedia']
-['biologie']
-['virus']
-['allergie']
-['biologie']
-['LOGBOOK']
-['END']
-['LOGBOOK']
-['END']
-#+end_example
+
+#+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
+: {'informatique': 1, 'wikipedia': 1, 'biologie': 2, 'virus': 1, 'allergie': 1, 'LOGBOOK': 2, 'END': 2}
+:            tags  values
+: 0  informatique       1
+: 1     wikipedia       1
+: 2      biologie       2
+: 3         virus       1
+: 4      allergie       1
+: 5       LOGBOOK       2
+: 6           END       2
+
+* 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 : [('biologie', 2), ('LOGBOOK', 2), ('END', 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-DfWAKd/figureDe0QxU.png]]