【数据分析可视化】病毒传播-随笔

# 基础
import numpy as np
import pandas as pd
from pandas import DataFrame, Series
from datetime import datetime
import json
import warnings
warnings.filterwarnings('ignore')# 忽略python运行过程中的警告

# 可视化
import matplotlib.pyplot as plt
import seaborn as sns
from wordcloud import WordCloud,STOPWORDS,ImageColorGenerator # 导入词云包
%matplotlib inline

url ='/Users/bennyrhys/Desktop/数据分析可视化/homework/2020冠状肺炎统计.xlsx'
df = pd.read_excel(url, index_col='日期')
df.head()

	累计确诊	疑似	新增疑似	死亡	治愈	现有确诊	境外输入	现有境外输入确诊
日期
2020-01-11	41.0	0.0	NaN	1.0	2.0	38.0	NaN	NaN
2020-01-12	41.0	0.0	NaN	1.0	7.0	33.0	NaN	NaN
2020-01-13	41.0	0.0	NaN	1.0	7.0	33.0	NaN	NaN
2020-01-14	41.0	0.0	NaN	1.0	7.0	33.0	NaN	NaN
2020-01-15	41.0	0.0	NaN	2.0	12.0	27.0	NaN	NaN

df['新增疑似'].isnull()

日期
2020-01-11     True
2020-01-12     True
2020-01-13     True
2020-01-14     True
2020-01-15     True
              ...  
2020-04-27    False
2020-04-28    False
2020-04-29    False
2020-04-30     True
2020-05-01     True
Name: 新增疑似, Length: 112, dtype: bool

df.fillna(0)

	累计确诊	疑似	新增疑似	死亡	治愈	现有确诊	境外输入	现有境外输入确诊
日期
2020-01-11	41.0	0.0	0.0	1.0	2.0	38.0	0.0	0.0
2020-01-12	41.0	0.0	0.0	1.0	7.0	33.0	0.0	0.0
2020-01-13	41.0	0.0	0.0	1.0	7.0	33.0	0.0	0.0
2020-01-14	41.0	0.0	0.0	1.0	7.0	33.0	0.0	0.0
2020-01-15	41.0	0.0	0.0	2.0	12.0	27.0	0.0	0.0
...	...	...	...	...	...	...	...	...
2020-04-27	82836.0	9.0	1.0	4633.0	77555.0	648.0	1639.0	552.0
2020-04-28	82858.0	10.0	2.0	4633.0	77578.0	647.0	1660.0	553.0
2020-04-29	82862.0	10.0	3.0	4633.0	77610.0	619.0	1664.0	525.0
2020-04-30	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2020-05-01	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

112 rows × 8 columns

# 直方图
plt.hist(df['新增疑似'])

(array([66.,  3.,  6.,  3.,  2.,  1.,  3.,  6.,  1.,  6.]),
 array([   0. ,  532.8, 1065.6, 1598.4, 2131.2, 2664. , 3196.8, 3729.6,
        4262.4, 4795.2, 5328. ]),
 <a list of 10 Patch objects>)

# 密度图 Series 的方法直接画.plot
df['新增疑似'].plot(kind='kde')

<matplotlib.axes._subplots.AxesSubplot at 0x1a27b80510>

# 直方图，密度图.distplot()
# 参数 数据，分块，是否直方图，是否密度图,rug分布情况
sns.distplot(df['新增疑似'], bins=20, hist=True, kde=True, rug=True)

<matplotlib.axes._subplots.AxesSubplot at 0x1a29f5a410>

# 密度图
# 参数 数据，颜色填充, 颜色
sns.kdeplot(df['新增疑似'], shade=True, color='r')

<matplotlib.axes._subplots.AxesSubplot at 0x1a2aee4150>

sns.rugplot(df['新增疑似'])

<matplotlib.axes._subplots.AxesSubplot at 0x1a2b140490>

plt.plot(df['新增疑似'])

[<matplotlib.lines.Line2D at 0x1a2aea7290>]

# 热力图(新增疑似)
sns.heatmap(df)

<matplotlib.axes._subplots.AxesSubplot at 0x1a2aed6cd0>

# df普通线性
df.plot()

<matplotlib.axes._subplots.AxesSubplot at 0x1a2a7e5550>

from pyecharts.faker import Faker  # 绘图导入数据需要
from pyecharts import options as opts  # 绘图选项
from pyecharts.charts import Map  # 绘图需要
import csv  # 读取中国各省gdp增长数据