Python：使用nltk統計詞頻并繪制統計圖

測試環境：

mac

python

3.6.5

安裝

pip install nltk      

代碼示例

# -*- coding: utf-8 -*-

from nltk import FreqDist
from matplotlib import rcParams

# matplotlib 設定中文字型
rcParams["font.family"] = "STHeiti"
rcParams["font.size"] = 8


words = ["你好", "你好", "我好", "我還有"]

freq = FreqDist(words)
print(freq.most_common(1))  # [('你好', 2)]
print(freq.freq("你好"))     # 頻率 0.5
print(freq["你好"])          # 次數 2

freq.tabulate()              # 頻率分布表

freq.plot()                  # 頻率分布圖