You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
47 lines
1005 B
Python
47 lines
1005 B
Python
import pandas as pd
|
|
import matplotlib.pyplot as plt
|
|
|
|
document_1 = "le chat mange la souris"
|
|
document_2 = "le chien regarde le canard"
|
|
document_3 = "le canard regarde le chat"
|
|
|
|
corpus = (document_1, document_2, document_3)
|
|
|
|
# construction du dictionnaire
|
|
vocabulary = []
|
|
for d in corpus:
|
|
for w in d.split(" "):
|
|
if w not in vocabulary:
|
|
vocabulary.append(w)
|
|
|
|
# calcul d'un histogramme simple sur le corpus
|
|
|
|
# initialisation de l'histogramme
|
|
freq = dict()
|
|
for v in vocabulary:
|
|
freq[v] = 0
|
|
|
|
# comptage des occurrences
|
|
for d in corpus:
|
|
for w in d.split(" "):
|
|
freq[w] += 1
|
|
|
|
print(freq)
|
|
df = pd.DataFrame({'freq':freq.values()}, index=freq.keys())
|
|
ax = df.plot.bar(rot=0)
|
|
plt.show()
|
|
|
|
# calcul d'un histogramme par document
|
|
import numpy as np
|
|
|
|
V = len(vocabulary)
|
|
D = len(corpus)
|
|
|
|
tf_idf = np.zeros([D, V])
|
|
|
|
for i, d in enumerate(corpus):
|
|
for w in d.split(" "):
|
|
j = vocabulary.index(w)
|
|
tf_idf[i,j] += 1
|
|
|
|
print(tf_idf) |