单词数据绘图

高中单词绘图

# -*- coding: utf-8 -*-
"""
Created on Mon Oct 19 21:34:31 2020

@author: DELL
"""
import matplotlib.pyplot as plt
with open('d:\\high school word.txt', 'r', encoding='utf-8') as f:
    data = f.read()
    data_list = data.split()
mins = mean = maxs = maxss = maxx =0
sum = 0
for i in data_list:
    if len(i)<=5:
        mins += 1
    if 5<len(i)<=10:
        mean += 1
    if 10<len(i)<=15:
        maxs +=1
    if 15<len(i)<=20:
        maxss +=1
    sum += 1
num_list = []
name_list = ['lenth<=5', '5<len<=10', '10<len<=15', 'len>15']
num_list.extend([mins, mean, maxs, maxss])
plt.bar(range(len(num_list)), num_list, color='rgb', tick_label=name_list)
plt.show()
print(sum)
    

计算机专业核心单词绘图（含数据清洗）

# -*- coding: utf-8 -*-
"""
Created on Mon Oct 19 21:34:31 2020

@author: DELL
"""
import matplotlib.pyplot as plt
import re
with open('d:\\computer major words.txt', 'r', encoding='utf-8') as f:
    data = f.read()
    data = data.replace('\t\u3000\u3000', '')
    data = data.replace('\\', '')
    data= re.sub('[\u4e00-\u9fff]+', "", data)
    data_list = data.split('\n')
print(data_list)
mins = mean = maxs = maxss = maxx =0
sum = 0
for i in data_list:
    if len(i)<=5:
        mins += 1
    if 5<len(i)<=10:
        mean += 1
    if 10<len(i)<=15:
        maxs +=1
    if 15<len(i)<=20:
        maxss +=1
    if len(i)<=15:
        sum += 1
num_list = []
name_list = ['lenth<=5', '5<len<=10', '10<len<=15', 'len>15']
num_list.extend([mins, mean, maxs, maxss])
plt.bar(range(len(num_list)), num_list, color='rgb', tick_label=name_list)
plt.show()
print(sum)