【pandas数据可视化、pandas数据分析】新冠肺炎感染人数数据分析

文章目录

新冠肺炎感染人数数据分析
- 库函数引入
- 数据过滤
- 数据清洗
- 数据可视化
- - Covid-19 Cases in World
- Covid-19 Cases in China

还差地图后续更新

新冠肺炎感染人数数据分析库函数引入

#引入库函数
import numpy as np 
import pandas as pd 
import matplotlib.pyplot as plt
from datetime import datetime
import seaborn as sns

# Looking at the data 
data = pd.read_csv("./archive/covid_19_data.csv")
data.head()

# keep looking at the data but deeply
data.info()

数据过滤

# first way of filtering
x = data["Deaths"]>100000
data[x]

# second way
data[np.logical_and(data["Deaths"]>100000, data["/confirm/ied"]>1000000)]
# data[(data["Deaths"]>100000) & (data["/confirm/ied"]>1000000)]

数据清洗

data['Province/State'] = data['Province/State'].fillna("Unknown")
#使用fillna()函数填充缺失值

data.isnull().sum()

data = data.rename(columns = {"Province/State":"State"})
data = data.rename(columns = {"Country/Region":"Country"})

data[['/confirm/ied','Deaths','Recovered']] = data[['/confirm/ied','Deaths','Recovered']].astype(int)

data['Active'] = data['/confirm/ied']-data['Deaths']-data['Recovered']
data.columns

data['Date'] = data['ObservationDate'].copy()

数据可视化 Covid-19 Cases in World

#table

from pyecharts.components import Table
from pyecharts.options import ComponentTitleOpts


table = Table()

headers = ["Total /confirm/ied", "Total Deaths", "Total Recovered", "Total Active Cases"]
rows = [
    [sum(data['/confirm/ied']),sum(data['Deaths']),sum(data['Recovered']),sum(data['Active'])]
]
table.add(headers, rows)
table.set_global_opts(
    title_opts=ComponentTitleOpts(title="World-Covid-19 Cases"
                                 )
)
table.render_notebook()

from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker

labels = ["Active Cases","Recovered Cases","Death Cases"]

sumactive= sum(data['Active'])
sumrecovered = sum(data['Recovered'])
sumdeaths = sum(data['Deaths'])

c = (
    Pie()
    .add(
        "The percentage of Covid-19 Cases",
        [(labels[0],sumactive),(labels[1],sumrecovered),(labels[2],sumdeaths)],
        center=["35%", "50%"],
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title="The percentage of Covid-19 Cases in the world"),
        legend_opts=opts.LegendOpts(pos_left="50%"),
    )
    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
)
c.render_notebook()

data['Date'] = pd.to_datetime(data['Date'])
data = data.sort_values("Date")
datatime = data.groupby("Date")[["/confirm/ied","Active","Recovered","Deaths"]].sum().reset_index()

c = (
    Bar()
    .add_xaxis(list(datatime.Date))
    .add_yaxis("Active Cases",list(datatime.Active),  color = 'DarkRed')
    .set_global_opts(
        title_opts=opts.TitleOpts(title="Active Cases - Daily",subtitle="纵坐标感染病例，横坐标为感染时间"),
        datazoom_opts=[
            opts.DataZoomOpts(orient="vertical"), # 设置操作图表缩放功能，orient="vertical" 为Y轴 
            opts.DataZoomOpts(type_="inside")  # 设置内部可以滑动功能
        ],
    )
)
c.render_notebook()

c = (
    Bar()
    .add_xaxis(list(datatime.Date))
    .add_yaxis("Deaths Cases",list(datatime.Deaths),  color = 'DarkSlateGray')
    .set_global_opts(
        title_opts=opts.TitleOpts(title="Deaths Cases - Daily",subtitle="纵坐标感染病例，横坐标为感染时间"),
        datazoom_opts=[
            opts.DataZoomOpts(orient="vertical"), # 设置操作图表缩放功能，orient="vertical" 为Y轴 
            opts.DataZoomOpts(type_="inside")  # 设置内部可以滑动功能
        ],
    )
)
c.render_notebook()

data1 = data.groupby("Country")["/confirm/ied"].sum().sort_values(ascending = False).reset_index().head(30)

import pyecharts.options as opts
from pyecharts.charts import Line
c = (
    Line()
    .add_xaxis(list(data1.Country))
    .add_yaxis("/confirm/ied", list(data1./confirm/ied), is_smooth=True,color='Purple')
    .set_series_opts(
        areastyle_opts=opts.AreaStyleOpts(opacity=0.5),
        label_opts=opts.LabelOpts(is_show=False),
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title="Top 30 Countries with the most Confirmed Cases"),
        xaxis_opts=opts.AxisOpts(
            axistick_opts=opts.AxisTickOpts(is_align_with_label=True),
            is_scale=False,
            boundary_gap=False,
        ),
        legend_opts=opts.LegendOpts(pos_left="50%"),
    )
)

c.render_notebook()

data2 = data.groupby("Country")["Recovered"].sum().sort_values(ascending = False).reset_index().head(30)

c = (
    Line()
    .add_xaxis(list(data2.Country))
    .add_yaxis("Recovered", list(data2.Recovered), is_smooth=True,color='DarkGreen')
    .set_series_opts(
        areastyle_opts=opts.AreaStyleOpts(opacity=0.5),
        label_opts=opts.LabelOpts(is_show=False),
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title="Top 30 Countries with the most Recovered Cases"),
        xaxis_opts=opts.AxisOpts(
            axistick_opts=opts.AxisTickOpts(is_align_with_label=True),
            is_scale=False,
            boundary_gap=False,
        ),
        legend_opts=opts.LegendOpts(pos_left="50%"),
    )
)

c.render_notebook()

Covid-19 Cases in China

data['Country'] = data['Country'].replace('Mainland China', 'China')
data_ch = data[(data['Country'] == 'China') ].reset_index()

#table

from pyecharts.components import Table
from pyecharts.options import ComponentTitleOpts


table = Table()

headers = ["Total /confirm/ied", "Total Deaths", "Total Recovered", "Total Active Cases"]
rows = [
    [sum(data_ch['/confirm/ied']),sum(data_ch['Deaths']),sum(data_ch['Recovered']),sum(data_ch['Active'])]
]
table.add(headers, rows)
table.set_global_opts(
    title_opts=ComponentTitleOpts(title="China-Covid-19 Cases"
                                 )
)
table.render_notebook()

from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker

labels = ["Active Cases","Recovered Cases","Death Cases"]

sumactive= sum(data_ch['Active'])
sumrecovered = sum(data_ch['Recovered'])
sumdeaths = sum(data_ch['Deaths'])

c = (
    Pie()
    .add(
        "The percentage of Covid-19 Cases",
        [(labels[0],sumactive),(labels[1],sumrecovered),(labels[2],sumdeaths)],
        center=["35%", "50%"],
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title="The percentage of Covid-19 Cases in the China"),
        legend_opts=opts.LegendOpts(pos_left="50%"),
    )
    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
)
c.render_notebook()

data_ch1 = data_ch.groupby("Date")["/confirm/ied","Deaths","Recovered","Active"].sum().reset_index().sort_values("Date").reset_index()

from pyecharts import options as opts
from pyecharts.charts import Scatter
from pyecharts.faker import Faker

c = (
    Scatter()
    .add_xaxis(list(data_ch1.Date))
    .add_yaxis("/confirm/ied", list(data_ch1./confirm/ied))
    .add_yaxis("Active", list(data_ch1.Active))
    .add_yaxis("Deaths", list(data_ch1.Deaths))
    .add_yaxis("Recovered", list(data_ch1.Recovered))
    .set_global_opts(
        title_opts=opts.TitleOpts(title="Covid-19 Cases over the time in the China"),
        visualmap_opts=opts.VisualMapOpts(type_="size", max_=1000000, min_=20),
        legend_opts=opts.LegendOpts(pos_left="50%"),
    )
)
c.render_notebook()

state_ch= data_ch.groupby(["State"])["/confirm/ied","Active","Deaths"].sum().sort_values("/confirm/ied",ascending=False).reset_index()

from pyecharts.charts import Pie

c = (
    Pie()
    .add(
        "",
        [
            list(z)
            for z in zip(
                state_ch.State,
                state_ch.Confirmed + state_ch.Active + state_ch.Deaths,
            )
        ],
        center=["40%", "60%"],
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title="Confirmed Cases in China by States"),
        legend_opts=opts.LegendOpts(type_="scroll", pos_left="80%", orient="vertical"),
    )
    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
)
c.render_notebook()

本文用到的博客链接
法1将Dataframe转化为字典
法2将Dataframe转化为字典
python地图可视化
pandas中遍历Dataframe行
pandas Dataframe 数据转化为列表 list的方法

【pandas数据可视化、pandas数据分析】新冠肺炎感染人数数据分析

Python相关栏目本月热门文章