matplotlib和numpy
# matplotlib
# 導(dǎo)入
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import numpy as np
# 使用100個(gè)點(diǎn) 繪制 [0 , 2π]正弦曲線圖
#.linspace 左閉右閉區(qū)間的等差數(shù)列
x = np.linspace(0, 2*np.pi, num=100)
print(x)
y = np.sin(x)
# 正弦和余弦在同一坐標(biāo)系下
cosy = np.cos(x)
plt.plot(x, y, color='g', linestyle='--',label='sin(x)')
plt.plot(x, cosy, color='r',label='cos(x)')
plt.xlabel('時(shí)間(s)')
plt.ylabel('電壓(V)')
plt.title('歡迎來(lái)到python世界')
# 圖例
plt.legend()
plt.show()

結(jié)果
- 導(dǎo)入matplotlib和numpy
from matplotlib import pyplot as plt
import numpy as np
2.使用100個(gè)點(diǎn) 繪制 [0 , 2π]正弦曲線圖
linspace 左閉右閉區(qū)間的等差數(shù)列
x = np.linspace(0, 2*np.pi, num=100)
print(x)
y = np.sin(x)
3.正弦和余弦在同一坐標(biāo)系下
cosy = np.cos(x)
plt.plot(x, y, color='g', linestyle='--',label='sin(x)')
plt.plot(x, cosy, color='r',label='cos(x)')
plt.xlabel('時(shí)間(s)')
plt.ylabel('電壓(V)')
plt.title('歡迎來(lái)到python世界')
# 圖例
plt.legend()
plt.show()
柱狀圖
import string
from random import randint
# print(string.ascii_uppercase[0:6])
# ['A', 'B', 'C'...]
x = ['口紅{}'.format(x) for x in string.ascii_uppercase[:5] ]
y = [randint(200, 500) for _ in range(5)]
print(x)
print(y)
plt.xlabel('口紅品牌')
plt.ylabel('價(jià)格(元)')
plt.bar(x, y)
plt.show()

結(jié)果
1.依次產(chǎn)生五個(gè)字母
x = ['口紅{}'.format(x) for x in string.ascii_uppercase[:5] ]
2.產(chǎn)生五個(gè)隨機(jī)數(shù),范圍在200-500
y = [randint(200, 500) for _ in range(5)]
3.設(shè)置、顯示
plt.xlabel('口紅品牌') #設(shè)置橫坐標(biāo)標(biāo)識(shí)
plt.ylabel('價(jià)格(元)') #設(shè)置縱坐標(biāo)標(biāo)識(shí)
plt.bar(x, y)
plt.show()
餅圖
from random import randint
import string
labels = ['員工{}'.format(x) for x in string.ascii_lowercase[:6] ]
counts = [randint(3500, 9000) for _ in range(6)]
# 距離圓心點(diǎn)距離
explode = [0.1,0,0, 0, 0,0]
colors = ['red', 'purple','blue', 'yellow','gray','green']
plt.pie(counts,explode = explode,shadow=True, labels=labels, autopct = '%1.1f%%',colors=colors)
plt.legend(loc=2)
plt.axis('equal')
plt.show()

結(jié)果
- 依次產(chǎn)生員工abcdef并且存入labels列表中
labels = ['員工{}'.format(x) for x in string.ascii_lowercase[:6] ]
- 隨機(jī)產(chǎn)生月薪,范圍在3500-9000,并且存入到counts列表中
counts = [randint(3500, 9000) for _ in range(6)]
3.設(shè)置、顯示
# 距離圓心點(diǎn)距離
explode = [0.1,0,0, 0, 0,0]
colors = ['red', 'purple','blue', 'yellow','gray','green']
plt.pie(counts,explode = explode,shadow=True, labels=labels, autopct = '%1.1f%%',colors=colors)
plt.legend(loc=2)
plt.axis('equal')
plt.show()
散點(diǎn)圖
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import numpy as np
# 均值為 0 標(biāo)準(zhǔn)差為1 的正太分布數(shù)據(jù)
x = np.random.normal(0, 1, 1000000)
y = np.random.normal(0, 1, 1000000)
# alpha透明度
plt.scatter(x, y, alpha=0.1)
plt.show()

結(jié)果
1.設(shè)置均值、標(biāo)準(zhǔn)差
x = np.random.normal(0, 1, 1000000)
y = np.random.normal(0, 1, 1000000)
2.設(shè)置透明度和顯示
# alpha透明度
plt.scatter(x, y, alpha=0.1)
plt.show()
分析三國(guó)人物出現(xiàn)前十
import jieba
from wordcloud import WordCloud
# 1.讀取小說(shuō)內(nèi)容
with open('./novel/novel/threekingdom.txt', 'r', encoding='utf-8') as f:
words = f.read()
counts = {} # {‘曹操’:234,‘回寨’:56}
excludes = {"將軍", "卻說(shuō)", "丞相", "二人", "不可", "荊州", "不能", "如此", "商議",
"如何", "主公", "軍士", "軍馬", "左右", "次日", "引兵", "大喜", "天下",
"東吳", "于是", "今日", "不敢", "魏兵", "陛下", "都督", "人馬", "不知",
"孔明曰","玄德曰","劉備","云長(zhǎng)"}
# 2. 分詞
words_list = jieba.lcut(words)
# print(words_list)
for word in words_list:
if len(word) <= 1:
continue
else:
# 更新字典中的值
# counts[word] = 取出字典中原來(lái)鍵對(duì)應(yīng)的值 + 1
# counts[word] = counts[word] + 1 # counts[word]如果沒(méi)有就要報(bào)錯(cuò)
# 字典。get(k) 如果字典中沒(méi)有這個(gè)鍵 返回 NONE
counts[word] = counts.get(word, 0) + 1
print(len(counts))
# 3. 詞語(yǔ)過(guò)濾,刪除無(wú)關(guān)詞,重復(fù)詞
counts['孔明'] = counts['孔明'] + counts['孔明曰']
counts['玄德'] = counts['玄德'] + counts['玄德曰'] +counts['劉備']
counts['關(guān)公'] = counts['關(guān)公'] +counts['云長(zhǎng)']
for word in excludes:
del counts[word]
# 4.排序 [(), ()]
items = list(counts.items())
print(items)
# def sort_by_count(x):
# return x[1]
items.sort(key=lambda x:x[1], reverse=True)
li = [] # ['孔明', 孔明, 孔明,孔明...., '曹操'。。。。。]
lo = []
for i in range(10):
# 序列解包
role, count = items[i]
print(role, count)
li.append(role)
lo.append(count)
# _ 是告訴看代碼的人,循環(huán)里面不需要使用臨時(shí)變量
# for _ in range(count):
# li.append(role)
# 5得出結(jié)論
text = ' '.join(li)
WordCloud(
font_path='msyh.ttc',
background_color='white',
width=800,
height=600,
# 相鄰兩個(gè)重復(fù)詞之間的匹配
collocations=False
).generate(text).to_file('TOP10.png')
# 餅圖
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import numpy as np
from random import randint
import string
from random import randint
import string
# counts = [randint(3500, 9000) for _ in range(6)]
labels = ['孔明','玄德','曹操','關(guān)公','張飛','孫權(quán)','呂布','趙云','司馬懿','周瑜']
# 距離圓心點(diǎn)距離
explode = [0.1,0,0, 0, 0,0,0,0, 0, 0]
# colors = ['red', 'purple','blue', 'yellow','gray','green','bl']
plt.pie(lo,shadow=True,explode=explode, labels=li, autopct = '%1.1f%%')
plt.legend(loc=2)
plt.axis('equal')
plt.show()

詞云結(jié)果

餅圖結(jié)果
- 讀取小說(shuō)內(nèi)容
with open('./novel/novel/threekingdom.txt', 'r', encoding='utf-8') as f:
words = f.read()
2.分詞
counts = {} # {‘曹操’:234,‘回寨’:56}
for word in words_list:
if len(word) <= 1:
continue
else:
# 更新字典中的值
# counts[word] = 取出字典中原來(lái)鍵對(duì)應(yīng)的值 + 1
# counts[word] = counts[word] + 1 # counts[word]如果沒(méi)有就要報(bào)錯(cuò)
# 字典。get(k) 如果字典中沒(méi)有這個(gè)鍵 返回 NONE
counts[word] = counts.get(word, 0) + 1
- 詞語(yǔ)過(guò)濾,刪除無(wú)關(guān)詞,重復(fù)詞
counts['孔明'] = counts['孔明'] + counts['孔明曰']
counts['玄德'] = counts['玄德'] + counts['玄德曰'] +counts['劉備']
counts['關(guān)公'] = counts['關(guān)公'] +counts['云長(zhǎng)']
for word in excludes:
del counts[word]
- 排序
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True) # lambda表達(dá)式,可以有多個(gè)參數(shù),但是只有一個(gè)表達(dá)式
# lambda x,y,z:x+y+z
li = [] # ['孔明', 孔明, 孔明,孔明...., '曹操'。。。。。]
lo = []
for i in range(10):
# 序列解包
role, count = items[i]
print(role, count)
li.append(role)
lo.append(count)
# _ 是告訴看代碼的人,循環(huán)里面不需要使用臨時(shí)變量
# for _ in range(count):
# li.append(role)
- 得出結(jié)論
5.1 詞云
text = ' '.join(li)
WordCloud(
font_path='msyh.ttc',
background_color='white',
width=800,
height=600,
# 相鄰兩個(gè)重復(fù)詞之間的匹配
collocations=False
).generate(text).to_file('TOP10.png')
5.2 餅圖
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import numpy as np
from random import randint
import string
from random import randint
import string
# counts = [randint(3500, 9000) for _ in range(6)]
labels = ['孔明','玄德','曹操','關(guān)公','張飛','孫權(quán)','呂布','趙云','司馬懿','周瑜']
# 距離圓心點(diǎn)距離
explode = [0.1,0,0, 0, 0,0,0,0, 0, 0]
# colors = ['red', 'purple','blue', 'yellow','gray','green','bl']
plt.pie(lo,shadow=True,explode=explode, labels=li, autopct = '%1.1f%%')
plt.legend(loc=2)
plt.axis('equal')
plt.show()
以同樣方法分析紅樓夢(mèng)人物出場(chǎng)次數(shù)前十
import jieba
from wordcloud import WordCloud
# 1.讀取小說(shuō)內(nèi)容
with open('./novel/novel/all.txt', 'r', encoding='utf-8') as f:
words = f.read()
counts = {}
excludes = {"什么", "一個(gè)", "我們", "你們", "如今", "說(shuō)道", "知道", "老太太", "姑娘",
"起來(lái)", "這里", "出來(lái)", "眾人", "那里", "奶奶", "自己", "太太", "一面",
"只見(jiàn)", "兩個(gè)", "沒(méi)有", "怎么", "不是", "不知", "這個(gè)", "聽(tīng)見(jiàn)", "這樣",
"進(jìn)來(lái)","咱們","就是","東西","告訴","回來(lái)","只是","大家","老爺","只得",
"丫頭","這些","他們","不敢","出去","所以","賈母笑","鳳姐兒","不過(guò)"}
# 2. 分詞
words_list = jieba.lcut(words)
for word in words_list:
if len(word) <= 1:
continue
else:
counts[word] = counts.get(word, 0) + 1
print(len(counts))
# 3. 詞語(yǔ)過(guò)濾,刪除無(wú)關(guān)詞,重復(fù)詞
counts['賈母'] = counts['賈母'] + counts['賈母笑'] + counts['老太太']
counts['鳳姐'] = counts['鳳姐兒'] + counts['鳳姐']
counts['王夫人'] = counts['王夫人'] + counts['太太']
counts['寶釵'] = counts['寶釵'] + counts['薛寶釵']
for word in excludes:
del counts[word]
# 4.排序 [(), ()]
items = list(counts.items())
def sort_by_count(x):
return x[1]
items.sort(key=lambda x:x[1], reverse=True)
li = []
lo = []
ll = []
for i in range(10):
# 序列解包
role, count = items[i]
# print(role, count)
li.append(role)
lo.append(count)
# print(li)
# print(lo)
# _ 是告訴看代碼的人,循環(huán)里面不需要使用臨時(shí)變量
for _ in range(count):
ll.append(role)
# 5得出結(jié)論
text = ' '.join(ll)
WordCloud(
font_path='msyh.ttc',
background_color='white',
width=800,
height=600,
# 相鄰兩個(gè)重復(fù)詞之間的匹配
collocations=False
).generate(text).to_file('HTOP10.png')
# # 餅圖
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
explode = [0.1,0,0, 0, 0,0,0,0, 0, 0]
plt.pie(lo,shadow=True,explode=explode, labels=li, autopct = '%1.1f%%')
plt.legend(loc=2)
plt.axis('equal')
plt.show()

詞云結(jié)果

餅圖結(jié)果