def plot_tendency(word, pos_dic, bin_size, output_dir, file_name):
plt.figure()
if word not in pos_dic:
raise Exception('Word ' + word + ' notfound')
df = pd.DataFrame(pos_dic[word], columns=['pos']) # .groupby(['pos'])['pos'].count()
df['bins'] = pd.cut(df['pos'], bins=range(0, 100 + bin_size, bin_size), labels=range(0, 100, bin_size))
df = df.groupby(['bins'])['bins'].count()
ax = df.plot(title="Position du mot '" + word + "' dans les descriptions des offres")
ax.set_xlabel("Position (en % de la longueur de la description)")
ax.set_ylabel("Nombre d'occurrences")
plt.savefig(os.path.join(output_dir, file_name), bbox_inches='tight')
评论列表
文章目录