# pyecharts安装命令：
python -m pip install pyecharts
1.
2.

# sql中所使用的部分语法为hive sql中常规的语法，与mysql有所不同，请注意。
select rrrd1.hotel_code_new as hotel_code_new
      ,dda.natural_date as natural_date
      ,nvl(rrrd.room_nights, 0) as room_nights
 from ( select distinct substr(natural_dt,1,7) as natural_date 
    from dws.dws_test_date_calendar
    where dt_year='2019'
        )dda
        left join 
         (select 'CNSZVS_002' hotel_code_new
            UNION all select  'CWSWS_003' hotel_code_new
      )rrrd1
        left join
         (select  hotel_code_new
                    ,substr(stay_date,1,7) as stay_date
                    ,sum(number_of_room_nights) as room_nights
                from dwm.dwm_test_resvs_rom_daily_df
                where dt='2021-10-24'
                and hotel_code_new in(CNSZVS_002', 'CWSWS_003')
                    and resv_status in('CHECKEDSSSIN','CHECKEDSSSOUT')
                    and substr(stay_date,0,4) = '2019' 
                    group by hotel_code_new,substr(stay_date,1,7)
        )rrrd 
        on dda.natural_date = rrrd.stay_date 
        and rrrd1.hotel_code_new=rrrd.hotel_code_new
        order by rrrd.hotel_code_new;
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.

from impala.dbapi import connect
import warnings

#数据仓库数据获取准备
def hive_connect(sql):
    warnings.filterwarnings('ignore')
    config_hive_beta = {
        'host': '10.7.0.12',  #hive的host地址
        'port': 10000,    #hive的端口号
        'user': 'hive',    #hive的username
        'password': 'hive',    #hive的password
        'database': 'tmp',     #hive中需要查询的数据库名
        'auth_mechanism': 'PLAIN' #hive的hive-site.xml配置文件中获取
    }
    conn = connect(**config_hive_beta)
    cursor = conn.cursor()
    cursor.execute(sql)
    hive_all_data = cursor.fetchall()
    return hive_all_data


# all_data = hive_connect(hive_sql)
# 通过调用hive_connect方法获取到的数据库查询结果数据如all_data列表所示
all_data = [('CNSZVS_002', '2019-01', 0), ('CNSZVS_002', '2019-02', 0), ('CNSZVS_002', '2019-03', 0),
            ('CNSZVS_002', '2019-04', 0), ('CNSZVS_002', '2019-05', 0), ('CNSZVS_002', '2019-06', 2353),
            ('CNSZVS_002', '2019-07', 2939), ('CNSZVS_002', '2019-08', 5148), ('CNSZVS_002', '2019-09', 3850),
            ('CNSZVS_002', '2019-10', 4973), ('CNSZVS_002', '2019-11', 5467), ('CNSZVS_002', '2019-12', 4742),
            ('CWSWS_003', '2019-01', 5914), ('CWSWS_003', '2019-02', 4434), ('CWSWS_003', '2019-03', 6003),
            ('CWSWS_003', '2019-04', 6611), ('CWSWS_003', '2019-05', 6586), ('CWSWS_003', '2019-06', 5840),
            ('CWSWS_003', '2019-07', 6624), ('CWSWS_003', '2019-08', 7001), ('CWSWS_003', '2019-09', 5792),
            ('CWSWS_003', '2019-10', 6898), ('CWSWS_003', '2019-11', 6944), ('CWSWS_003', '2019-12', 5404)]

# 从pyecharts模块导入柱状图-Bar
from pyecharts import Bar
# 设置横轴行名，这里使用12个月份的英文简称
columns = ["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"]
# 分别新建2个空list用于存储每个月份对应的RNs的值
CNSZVS_002 = []
CWSWS_003 = []

for i in all_data:
    if i[0] == 'CNSZVS_002':
        CNSZVS_002.append(i[2])
    elif i[0] == 'CWSWS_003':
        CWSWS_003.append(i[2])
    else:
        pass
# 设置柱状图的主标题与副标题
bar = Bar("柱状图", "Test需求—2019年的RNs")
# 添加柱状图的数据及配置项-求平均值、最大值、最小值
bar.add("CNSZVS_002", columns, CNSZVS_002, mark_line=["average"], mark_point=["max", "min"])
bar.add("CWSWS_003", columns, CWSWS_003, mark_line=["average"], mark_point=["max", "min"])
# 在本py文件同级目录下生成名为render.html的本地文件（默认为.html文件）
bar.render()
# 也可设置成指定的路径用于保存html文件
#bar.render(r"D:bar_render.html")
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.
27.
28.
29.
30.
31.
32.
33.
34.
35.
36.
37.
38.
39.
40.
41.
42.
43.
44.
45.
46.
47.
48.
49.
50.
51.
52.
53.
54.
55.
56.

# 从pyecharts模块中导入饼图Pie
from pyecharts import Pie
# 设置主标题与副标题，标题设置居中，设置宽度为1000
pie = Pie("饼状图", "Test需求—2019年的RNs", title_pos='left', width=1000)
# 使用add导入数据，设置坐标位置为【20，50】，上方的colums选项取消显示
pie.add("CNSZVS_002", columns, CNSZVS_002, center=[20, 50], is_legend_show=True)
# 使用add导入数据，设置坐标位置为【75，50】，上方的colums选项正常显示
pie.add("CWSWS_003", columns, CWSWS_003, center=[75, 50], is_legend_show=False, is_label_show=True)
# 保存图表
pie.render()
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.

# 从pyecharts模块导入箱型图Boxplot
from pyecharts import Boxplot
boxplot = Boxplot("箱型图", "Test需求—2019年的RNs")
x_axis = ['CNSZVS_002', 'CWSWS_003']
y_axis = [CNSZVS_002, CWSWS_003]
# prepare_data方法可以将数据转为嵌套的 [min, Q1, median (or Q2), Q3, max]
yaxis = boxplot.prepare_data(y_axis)
boxplot.add("2019年RNs统计", x_axis, yaxis)
boxplot.render()
1.
2.
3.
4.
5.
6.
7.
8.
9.

from pyecharts import Line
line = Line("折线图", "Test需求—2019年的RNs")
# is_label_show属性是设置上方数据是否显示
line.add("CNSZVS_002", columns, CNSZVS_002, is_label_show=True)
line.add("CWSWS_003", columns, CWSWS_003, is_label_show=True)
line.render()
1.
2.
3.
4.
5.
6.

from pyecharts import Radar
radar = Radar("雷达图", "Test需求—2019年的RNs")
# 由于雷达图传入的数据得为多维数据，需要将list再进行list转换一次
CNSZVS_002 = [CNSZVS_002]
CWSWS_003 = [CWSWS_003]
# 设置column的最大值，为了雷达图更为直观，这里的月份最大值设置依据真实数据的值来设置，因此各个月份有所不同
schema_diff = [
    ("Jan", 7000), ("Feb", 5000), ("Mar", 6500),
    ("Apr", 7000), ("May", 7000), ("Jun", 6200),
    ("Jul", 6800), ("Aug", 7200), ("Sep", 6000),
    ("Oct", 7300), ("Nov", 7500), ("Dec", 6000)
]
# 传入坐标
radar.config(schema_diff)
radar.add("CNSZVS_002", CNSZVS_002)
# 一般默认为同一种颜色，这里为了便于区分，需要设置item的颜色
radar.add("CWSWS_003", CWSWS_003, item_color="#1C86EE")
radar.render()
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.

from pyecharts import Scatter
scatter = Scatter("散点图", "Test需求—2019年的RNs")
# xais_name是设置横坐标名称，这里由于显示问题，还需要将y轴名称与y轴的距离进行设置
scatter.add("CWSWS_003&CNSZVS_002 RNs的散点分布", CNSZVS_002, CWSWS_003, xaxis_name="CNSZVS_002", yaxis_name="CWSWS_003", yaxis_name_gap=40)
scatter.render()
1.
2.
3.
4.
5.