def test_grid_four_direction():
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
bar = Bar("柱状图示例", height=720, width=1200, title_pos="65%")
bar.add("商家A", CLOTHES, v1, is_stack=True)
bar.add("商家B", CLOTHES, v2, is_stack=True, legend_pos="80%")
line = Line("折线图示例")
line.add("最高气温", WEEK, [11, 11, 15, 13, 12, 13, 10],
mark_point=["max", "min"], mark_line=["average"])
line.add("最低气温", WEEK, [1, -2, 2, 5, 3, 2, 0],
mark_point=["max", "min"], mark_line=["average"],
legend_pos="20%")
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
scatter = Scatter("散点图示例", title_top="50%", title_pos="65%")
scatter.add("scatter", v1, v2, legend_top="50%", legend_pos="80%")
es = EffectScatter("动态散点图示例", title_top="50%")
es.add("es", [11, 11, 15, 13, 12, 13, 10], [1, -2, 2, 5, 3, 2, 0],
effect_scale=6, legend_top="50%", legend_pos="20%")
grid = Grid()
grid.add(bar, grid_bottom="60%", grid_left="60%")
grid.add(line, grid_bottom="60%", grid_right="60%")
grid.add(scatter, grid_top="60%", grid_left="60%")
grid.add(es, grid_top="60%", grid_right="60%")
grid.render()
def test_scatter_multi_dimension():
data = [
[28604, 77, 17096869],
[31163, 77.4, 27662440],
[1516, 68, 1154605773],
[13670, 74.7, 10582082],
[28599, 75, 4986705],
[29476, 77.1, 56943299],
[31476, 75.4, 78958237],
[28666, 78.1, 254830],
[1777, 57.7, 870601776],
[29550, 79.1, 122249285],
[2076, 67.9, 20194354],
[12087, 72, 42972254],
[24021, 75.4, 3397534],
[43296, 76.8, 4240375],
[10088, 70.8, 38195258],
[19349, 69.6, 147568552],
[10670, 67.3, 53994605],
[26424, 75.7, 57110117],
[37062, 75.4, 252847810]
]
x_lst = [v[0] for v in data]
y_lst = [v[1] for v in data]
extra_data = [v[2] for v in data]
sc = Scatter()
sc.add("scatter", x_lst, y_lst, extra_data=extra_data, is_visualmap=True,
visual_dimension=2, visual_orient='horizontal',
visual_type='size', visual_range=[254830, 1154605773],
visual_text_color='#000')
sc.render()
def main():
dutPl0 = []
dutpl1 = []
maxCntPl0 = []
maxCntPl1 = []
page = Page("Cluster Padding Figure")
txtFiles = [name for name in os.listdir('./') if name.endswith('.txt')]
for textLogName in txtFiles:
waferNum = re.split(r'_', textLogName)
with open(textLogName, 'rt') as clusterFile:
for line in clusterFile:
if re.match(r'IncomingBBKCount[A-Za-z0-9_.\+\-\*\/\s]*BBKP', line):
splitColon = re.split(r'\s*[:]\s*', line)
splitColon1 = splitColon[0]
splitColon2 = splitColon[1]
splitColon3 = splitColon[2]
listBlk = re.split(r'\s*[\s]\s*', splitColon3)
padBlk = paddingBlk(listBlk)
maxCnt = clusterBlk(padBlk)
splitSpace = re.split(r'\s*[\s]\s*', splitColon1)
intDut = int(splitSpace[1].replace('DUT', ''))
if splitSpace[2] == "BBKP0":
dutPl0.append(intDut)
maxCntPl0.append(maxCnt)
else:
dutpl1.append(intDut)
maxCntPl1.append(maxCnt)
scatter = Scatter(waferNum[2])
scatter.add("PL0", dutPl0, maxCntPl0, xaxis_name = "DUT", yaxis_name = "Max Padding BB", is_more_utils = True)
scatter.add("PL1", dutpl1, maxCntPl1, xaxis_name = "DUT", yaxis_name = "Max Padding BB", is_more_utils = True)
page.add(scatter)
page.render()
def test_scatter_visualmap_type_size():
scatter = Scatter("散点图示例")
scatter.add(
"B",
v1[::-1],
v2,
is_visualmap=True,
visual_type="size",
visual_range_size=[20, 80],
)
scatter.render()
def test_scatter_option(patched):
patched.return_value = "1"
v1 = [10, 20, 30, 40, 50, 60]
v2 = [10, 20, 30, 40, 50, 60]
scatter = Scatter("scatter test")
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2)
actual_options = json.dumps(
scatter.options, sort_keys=True, indent=4, cls=DefaultJsonEncoder
)
expected = get_fixture_content("scatter_options.json")
for a, b in zip(actual_options.split("\n"), expected.split("\n")):
eq_(a.strip(), b.strip())
def test_grid_left_right():
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
scatter = Scatter(width=1200)
scatter.add("散点图示例", v1, v2, legend_pos="70%")
es = EffectScatter()
es.add("动态散点图示例", [11, 11, 15, 13, 12, 13, 10], [1, -2, 2, 5, 3, 2, 0],
effect_scale=6, legend_pos="20%")
grid = Grid()
grid.add(scatter, grid_left="60%")
grid.add(es, grid_right="60%")
grid.render()
def test_overlap_es_scatter():
v1 = [10, 20, 30, 40, 50, 60]
v2 = [30, 30, 30, 30, 30, 30]
v3 = [50, 50, 50, 50, 50, 50]
v4 = [10, 10, 10, 10, 10, 10]
es = EffectScatter("Scatter-EffectScatter 示例")
es.add("es", v1, v2)
scatter = Scatter()
scatter.add("scatter", v1, v3)
es_1 = EffectScatter()
es_1.add("es_1", v1, v4, symbol='pin', effect_scale=5)
overlap = Overlap()
overlap.add(es)
overlap.add(scatter)
overlap.add(es_1)
overlap.render()
def test_scatter_xaxis_type_category():
scatter = Scatter("散点图示例")
scatter.add("A", ["a", "b", "c", "d", "e", "f"], v2)
scatter.add(
"B", ["a", "b", "c", "d", "e", "f"], v1[::-1], xaxis_type="category"
)
assert '"type": "category"' in scatter._repr_html_()
def test_scatter_default():
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2)
html_content = scatter._repr_html_()
assert '"type": "value"' in html_content
assert '"type": "category"' not in html_content
def RGB(r,g,b):
return "#{:02x}{:02x}{:02x}".format(r,g,b)
def HEX(hexcode):
return tuple(map(ord,hexcode[1:].decode('hex')))
# ----------------------------------------------------------------------------
# scatter
from pyecharts import Scatter
v1 = [10, 20, 30, 40, 50, 60]
v2 = [10, 20, 30, 40, 50, 60]
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2, is_visualmap=True,
visual_type='size', visual_range_size=[20, 80])
scatter.render()
# babble
data = [
[28604, 77, 17096869],
[31163, 77.4, 27662440],
[1516, 68, 1154605773],
[13670, 74.7, 10582082],
[28599, 75, 4986705],
[29476, 77.1, 56943299],
[31476, 75.4, 78958237],
[28666, 78.1, 254830],
def plot(self):
u"""
Do a echarts plot to view all the conditions
:return:
"""
def custom_formatter(params):
return params.value[3] + ": " + params.value[1]
line = Line("", width="100%", height=800)
attr = sorted([x["Name"] for x in self.data])
names = [x for x in self.name[5:] if x]
data = []
for idx, i in enumerate(sorted(names)):
if not i:
continue
tmp_value = []
extra_name = []
for x in self.data:
tmp = self.meta.get(x["Name"], "NA")
if isinstance(tmp, dict):
tmp.get("tissue", "NA")
extra_name.append("%s (%s)" % (x["Name"], tmp))
if x[i].endswith("%"):
tmp_value.append(float(x[i].replace("%", "")))
else:
tmp_value.append(int(x[i].replace(",", "")))
line.add(
i,
attr,
tmp_value,
is_datazoom_show=True,
datazoom_type="both",
datazoom_range=[0, 100],
is_datazoom_extra_show=True,
xaxis_rotate=30,
)
boxplot = Boxplot(i, width="60%", height=800)
boxplot.add(i, [i],
boxplot.prepare_data([tmp_value]),
is_legend_show=False,
tooltip_formatter=custom_formatter,
is_datazoom_extra_show=True,
datazoom_extra_range=[0, 100])
scatter = Scatter(width="60%", height=800)
scatter.add(i,
extra_name,
tmp_value,
extra_data=extra_name,
extra_name=extra_name,
is_legend_show=False,
tooltip_formatter=custom_formatter,
is_datazoom_extra_show=True,
datazoom_extra_range=[0, 100],
xaxis_type="category",
xaxis_rotate=45)
grid = Grid(
width="100%",
height=600,
)
grid.add(scatter, grid_right="25%", grid_bottom="25%")
grid.add(boxplot, grid_left="80%", grid_bottom="25%")
data.append(grid)
grid = Page()
grid.add(line)
for i in data:
grid.add(i)
grid.render(self.output)
def test_scatter():
# scatter_0
v1 = [10, 20, 30, 40, 50, 60]
v2 = [10, 20, 30, 40, 50, 60]
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2)
scatter.show_config()
scatter.render()
# scatter_0_1
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2, is_visualmap=True)
scatter.show_config()
scatter.render()
# scatter_0_2
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B",
v1[::-1],
v2,
is_visualmap=True,
visual_type='size',
visual_range_size=[20, 80])
scatter.show_config()
scatter.render()
# scatter_0_3
scatter = Scatter("散点图示例")
scatter.add("A", ["a", "b", "c", "d", "e", "f"], v2)
scatter.add("B", ["a", "b", "c", "d", "e", "f"],
v1[::-1],
xaxis_type="category")
scatter.show_config()
scatter.render()
# scatter_1
scatter = Scatter("散点图示例")
v1, v2 = scatter.draw("../images/pyecharts-0.png")
scatter.add("pyecharts", v1, v2, is_random=True)
scatter.show_config()
scatter.render()
# scatter_2
scatter = Scatter("散点图示例", width=800, height=480)
v1, v2 = scatter.draw("../images/love.png")
scatter.add("Love", v1, v2)
scatter.render()
# scatter_3
scatter = Scatter("散点图示例", width=1000, height=480)
v1, v2 = scatter.draw("../images/cup.png")
scatter.add("Cup", v1, v2)
scatter.render()
# scatter_4
scatter = Scatter("散点图示例", width=1000, height=480)
v1, v2 = scatter.draw("../images/cup.png")
scatter.add("Cup", v1, v2, label_color=["#000"])
scatter.render()
def test_scatter_draw_sexy_black_bra():
scatter = Scatter("散点图示例", width=1000, height=480)
v1, v2 = scatter.draw("../images/cup.png")
scatter.add("Cup", v1, v2, label_color=["#000"])
scatter.render()
# -*- coding: utf-8 -*-
"""
Created on Mon Dec 3 10:04:14 2018
@author: xuziyi
create data of qc aiops 2018
"""
import numpy as np
from pyecharts import Scatter
x = np.arange(100)
y = np.arange(100) + np.random.normal(loc=0, scale=15, size=100)
scatter =Scatter("相关性检验")
scatter.add("相关性", x, y, yaxis_min=0,yaxis_max=101)
scatter.show_config()
scatter.render(r"C:\Users\Administrator\Desktop\相关性检验.html")
line = Line('分类数目')
line.add(
'数量',
df_type.index.tolist(),
df_type.values.tolist(),
area_opacity=0.4,
line_opacity=0.2,
)
page.add(line)
# print(as_order_datas.app_name.tolist())
datas = df.drop_duplicates(['app_name']).reset_index(drop=True)
'''scatter下载量图'''
scatter = Scatter('下载量图')
scatter.add('下载量',
datas.app_name.tolist(),
datas.install_count.tolist(),
is_visualmap=True,
xaxis_type="category",
visual_range=[10, 300000000],
is_datazoom_extra_show=True,
datazoom_extra_type="slider",
datazoom_extra_range=[0, 10000],
yaxis_min=10,
)
page.add(scatter)
page.render()
def test_scatter_draw_love():
scatter = Scatter("散点图示例", width=800, height=480)
v1, v2 = scatter.draw("../images/love.png")
scatter.add("Love", v1, v2)
scatter.render()
#散点图适合表现大量样本的多个属性的分布规律。散点图的每个点表示一个样本，每个坐标维度表示一个属性。
from pyecharts import Scatter
import pandas as pd
dfboy = pd.DataFrame()
dfboy['weight'] = [56,67,65,70,57,60,80,85,76,64]
dfboy['height'] = [162,170,168,172,168,172,180,176,178,170]
dfgirl = pd.DataFrame()
dfgirl['weight'] = [50,62,60,70,57,45,62,65,70,56]
dfgirl['height'] = [155,162,165,170,166,158,160,170,172,165]
scatter = Scatter(title = "体格数据",width = 600,height = 420)
scatter.add(name = "boy", x_axis = dfboy['weight'], y_axis = dfboy['height'])
scatter.add(name = "girl", x_axis = dfgirl['weight'], y_axis = dfgirl['height'],
yaxis_min = 130,yaxis_max = 200,xaxis_min = 30,xaxis_max = 100)
scatter.render("result.散点图示范.html")
scatter
#当样本属性维度多于2个时，散点图可以使用点的颜色或大小等方式来表达更多属性维度。下面示范使用点的大小表示第3个维度。
def custom_formatter(params):
return (params.value[3] + ':' +
str(params.value[0]) +','
+str(params.value[1]) + ','
+str(params.value[2]))
df = pd.DataFrame()
def overlap_charts():
page = Page()
chart_init = {
"width": WIDTH,
"height": HEIGHT,
}
attr = ['A', 'B', 'C', 'D', 'E', 'F']
v1 = [10, 20, 30, 40, 50, 60]
v2 = [38, 28, 58, 48, 78, 68]
bar = Bar("折线图-柱状图叠加", **chart_init)
bar.add("bar", attr, v1)
line = Line()
line.add("line", attr, v2)
chart = Overlap()
chart.add(bar)
chart.add(line)
page.add(chart)
v1 = [10, 20, 30, 40, 50, 60]
v2 = [30, 30, 30, 30, 30, 30]
v3 = [50, 50, 50, 50, 50, 50]
v4 = [10, 10, 10, 10, 10, 10]
es = EffectScatter("散点图-动态散点图叠加", **chart_init)
es.add("es", v1, v2)
scatter = Scatter()
scatter.add("scatter", v1, v3)
es_1 = EffectScatter()
es_1.add("es_1", v1, v4, symbol='pin', effect_scale=5)
chart = Overlap()
chart.add(es)
chart.add(scatter)
chart.add(es_1)
page.add(chart)
v1 = [[2320.26, 2320.26, 2287.3, 2362.94],
[2300, 2291.3, 2288.26, 2308.38],
[2295.35, 2346.5, 2295.35, 2345.92],
[2347.22, 2358.98, 2337.35, 2363.8],
[2360.75, 2382.48, 2347.89, 2383.76],
[2383.43, 2385.42, 2371.23, 2391.82],
[2377.41, 2419.02, 2369.57, 2421.15],
[2425.92, 2428.15, 2417.58, 2440.38],
[2411, 2433.13, 2403.3, 2437.42],
[2432.68, 2334.48, 2427.7, 2441.73],
[2430.69, 2418.53, 2394.22, 2433.89],
[2416.62, 2432.4, 2414.4, 2443.03],
[2441.91, 2421.56, 2418.43, 2444.8],
[2420.26, 2382.91, 2373.53, 2427.07],
[2383.49, 2397.18, 2370.61, 2397.94],
[2378.82, 2325.95, 2309.17, 2378.82],
[2322.94, 2314.16, 2308.76, 2330.88],
[2320.62, 2325.82, 2315.01, 2338.78],
[2313.74, 2293.34, 2289.89, 2340.71],
[2297.77, 2313.22, 2292.03, 2324.63],
[2322.32, 2365.59, 2308.92, 2366.16],
[2364.54, 2359.51, 2330.86, 2369.65],
[2332.08, 2273.4, 2259.25, 2333.54],
[2274.81, 2326.31, 2270.1, 2328.14],
[2333.61, 2347.18, 2321.6, 2351.44],
[2340.44, 2324.29, 2304.27, 2352.02],
[2326.42, 2318.61, 2314.59, 2333.67],
[2314.68, 2310.59, 2296.58, 2320.96],
[2309.16, 2286.6, 2264.83, 2333.29],
[2282.17, 2263.97, 2253.25, 2286.33],
[2255.77, 2270.28, 2253.31, 2276.22]]
attr = ["2017/7/{}".format(i + 1) for i in range(31)]
kline = Kline("K 线图-折线图叠加", **chart_init)
kline.add("日K", attr, v1)
line_1 = Line()
line_1.add("line-1", attr, [random.randint(2400, 2500) for _ in range(31)])
line_2 = Line()
line_2.add("line-2", attr, [random.randint(2400, 2500) for _ in range(31)])
chart = Overlap()
chart.add(kline)
chart.add(line_1)
chart.add(line_2)
page.add(chart)
attr = ["{}月".format(i) for i in range(1, 13)]
v1 = [2.0, 4.9, 7.0, 23.2, 25.6, 76.7, 135.6, 162.2, 32.6, 20.0, 6.4, 3.3]
v2 = [2.6, 5.9, 9.0, 26.4, 28.7, 70.7, 175.6, 182.2, 48.7, 18.8, 6.0, 2.3]
v3 = [2.0, 2.2, 3.3, 4.5, 6.3, 10.2, 20.3, 23.4, 23.0, 16.5, 12.0, 6.2]
bar = Bar("多 Y 轴叠加", **chart_init)
bar.add("蒸发量", attr, v1)
bar.add("降水量", attr, v2, yaxis_formatter=" ml", yaxis_max=250)
line = Line()
line.add("平均温度", attr, v3, yaxis_formatter=" °C")
chart = Overlap()
chart.add(bar)
chart.add(line, yaxis_index=1, is_add_yaxis=True)
page.add(chart)
return page
from pyecharts import Scatter
'''散点图'''
# 输入数据
v1 = [10, 20, 30, 40, 50, 60]
v2 = [10, 20, 30, 40, 50, 60]
# 设置标题
scatter = Scatter("示例")
# 设置标签
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2)
# 生成html，打开即可
scatter.render()
def test_scatter():
# scatter_0
v1 = [10, 20, 30, 40, 50, 60]
v2 = [10, 20, 30, 40, 50, 60]
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2)
scatter.show_config()
scatter.render()
# scatter_0_1
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2, is_visualmap=True)
scatter.show_config()
scatter.render()
# scatter_0_2
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2, is_visualmap=True, visual_type='size', visual_range_size=[20, 80])
scatter.show_config()
scatter.render()
# scatter_1
scatter = Scatter("散点图示例")
v1, v2 = scatter.draw("../images/pyecharts-0.png")
scatter.add("pyecharts", v1, v2, is_random=True)
scatter.show_config()
scatter.render()
# scatter_2
scatter = Scatter("散点图示例", width=800, height=480)
v1, v2 = scatter.draw("../images/love.png")
scatter.add("Love", v1, v2)
scatter.render()
# scatter_3
scatter = Scatter("散点图示例", width=1000, height=480)
v1, v2 = scatter.draw("../images/cup.png")
scatter.add("Cup", v1, v2)
scatter.render()
# scatter_4
scatter = Scatter("散点图示例", width=1000, height=480)
v1, v2 = scatter.draw("../images/cup.png")
scatter.add("Cup", v1, v2, label_color=["#000"])
scatter.render()
def test_grid():
# grid_0
attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
bar = Bar("柱状图示例", height=720, is_grid=True)
bar.add("商家A", attr, v1, is_stack=True, grid_bottom="60%")
bar.add("商家B", attr, v2, is_stack=True, grid_bottom="60%")
line = Line("折线图示例", title_top="50%")
attr = ['周一', '周二', '周三', '周四', '周五', '周六', '周日']
line.add("最高气温", attr, [11, 11, 15, 13, 12, 13, 10], mark_point=["max", "min"], mark_line=["average"])
line.add("最低气温", attr, [1, -2, 2, 5, 3, 2, 0], mark_point=["max", "min"],
mark_line=["average"], legend_top="50%")
bar.grid(line.get_series(), grid_top="60%")
bar.show_config()
bar.render()
# grid_1
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
scatter = Scatter(width=1200, is_grid=True)
scatter.add("散点图示例", v1, v2, grid_left="60%", legend_pos="70%")
es = EffectScatter()
es.add("动态散点图示例", [11, 11, 15, 13, 12, 13, 10], [1, -2, 2, 5, 3, 2, 0],
effect_scale=6, legend_pos="20%")
scatter.grid(es.get_series(), grid_right="60%")
scatter.show_config()
scatter.render()
# grid_2
attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
bar = Bar("柱状图示例", height=720, width=1200, title_pos="65%", is_grid=True)
bar.add("商家A", attr, v1, is_stack=True, grid_bottom="60%", grid_left="60%")
bar.add("商家B", attr, v2, is_stack=True, grid_bottom="60%", grid_left="60%", legend_pos="80%")
line = Line("折线图示例")
attr = ['周一', '周二', '周三', '周四', '周五', '周六', '周日']
line.add("最高气温", attr, [11, 11, 15, 13, 12, 13, 10], mark_point=["max", "min"], mark_line=["average"])
line.add("最低气温", attr, [1, -2, 2, 5, 3, 2, 0], mark_point=["max", "min"],
mark_line=["average"], legend_pos="20%")
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
scatter = Scatter("散点图示例", title_top="50%", title_pos="65%")
scatter.add("scatter", v1, v2, legend_top="50%", legend_pos="80%")
es = EffectScatter("动态散点图示例", title_top="50%")
es.add("es", [11, 11, 15, 13, 12, 13, 10], [1, -2, 2, 5, 3, 2, 0], effect_scale=6,
legend_top="50%", legend_pos="20%")
bar.grid(line.get_series(), grid_bottom="60%", grid_right="60%")
bar.grid(scatter.get_series(), grid_top="60%", grid_left="60%")
bar.grid(es.get_series(), grid_top="60%", grid_right="60%")
bar.show_config()
bar.render()
# grid_3
line = Line("折线图示例", width=1200, is_grid=True)
attr = ['周一', '周二', '周三', '周四', '周五', '周六', '周日']
line.add("最高气温", attr, [11, 11, 15, 13, 12, 13, 10], mark_point=["max", "min"],
mark_line=["average"], grid_right="65%")
line.add("最低气温", attr, [1, -2, 2, 5, 3, 2, 0], mark_point=["max", "min"],
mark_line=["average"], legend_pos="20%")
attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
v1 = [11, 12, 13, 10, 10, 10]
pie = Pie("饼图示例", title_pos="45%")
pie.add("", attr, v1, radius=[30, 55], legend_pos="65%", legend_orient='vertical')
line.grid(pie.get_series(), grid_left="60%")
line.show_config()
line.render()
# grid_4
line = Line("折线图示例", width=1200, is_grid=True)
attr = ['周一', '周二', '周三', '周四', '周五', '周六', '周日']
line.add("最高气温", attr, [11, 11, 15, 13, 12, 13, 10], mark_point=["max", "min"],
mark_line=["average"], grid_right="60%")
line.add("最低气温", attr, [1, -2, 2, 5, 3, 2, 0], mark_point=["max", "min"],
mark_line=["average"], legend_pos="20%", grid_right="60%")
attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
value = [20, 40, 60, 80, 100, 120]
v1 = [[2320.26, 2320.26, 2287.3, 2362.94],
[2300, 2291.3, 2288.26, 2308.38],
[2295.35, 2346.5, 2295.35, 2345.92],
[2347.22, 2358.98, 2337.35, 2363.8],
[2360.75, 2382.48, 2347.89, 2383.76],
[2383.43, 2385.42, 2371.23, 2391.82],
[2377.41, 2419.02, 2369.57, 2421.15],
[2425.92, 2428.15, 2417.58, 2440.38],
[2411, 2433.13, 2403.3, 2437.42],
[2432.68, 2334.48, 2427.7, 2441.73],
[2430.69, 2418.53, 2394.22, 2433.89],
[2416.62, 2432.4, 2414.4, 2443.03],
[2441.91, 2421.56, 2418.43, 2444.8],
[2420.26, 2382.91, 2373.53, 2427.07],
[2383.49, 2397.18, 2370.61, 2397.94],
[2378.82, 2325.95, 2309.17, 2378.82],
[2322.94, 2314.16, 2308.76, 2330.88],
[2320.62, 2325.82, 2315.01, 2338.78],
[2313.74, 2293.34, 2289.89, 2340.71],
[2297.77, 2313.22, 2292.03, 2324.63],
[2322.32, 2365.59, 2308.92, 2366.16],
[2364.54, 2359.51, 2330.86, 2369.65],
[2332.08, 2273.4, 2259.25, 2333.54],
[2274.81, 2326.31, 2270.1, 2328.14],
[2333.61, 2347.18, 2321.6, 2351.44],
[2340.44, 2324.29, 2304.27, 2352.02],
[2326.42, 2318.61, 2314.59, 2333.67],
[2314.68, 2310.59, 2296.58, 2320.96],
[2309.16, 2286.6, 2264.83, 2333.29],
[2282.17, 2263.97, 2253.25, 2286.33],
[2255.77, 2270.28, 2253.31, 2276.22]]
kline = Kline("K 线图示例", title_pos="60%")
kline.add("日K", ["2017/7/{}".format(i + 1) for i in range(31)], v1, legend_pos="80%")
line.grid(kline.get_series(), grid_left="55%")
line.show_config()
line.render()
# grid_5
import random
x_axis = ["12a", "1a", "2a", "3a", "4a", "5a", "6a", "7a", "8a", "9a", "10a", "11a",
"12p", "1p", "2p", "3p", "4p", "5p", "6p", "7p", "8p", "9p", "10p", "11p"]
y_aixs = ["Saturday", "Friday", "Thursday", "Wednesday", "Tuesday", "Monday", "Sunday"]
data = [[i, j, random.randint(0, 50)] for i in range(24) for j in range(7)]
heatmap = HeatMap("热力图示例", height=700, is_grid=True)
heatmap.add("热力图直角坐标系", x_axis, y_aixs, data, is_visualmap=True, visual_top="45%",
visual_text_color="#000", visual_orient='horizontal', grid_bottom="60%")
attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
bar = Bar("柱状图示例", title_top="52%")
bar.add("商家A", attr, v1, is_stack=True)
bar.add("商家B", attr, v2, is_stack=True, legend_top="50%")
heatmap.grid(bar.get_series(), grid_top="60%")
heatmap.show_config()
heatmap.render()
def test_scatter_draw__hot_red_bra():
scatter = Scatter("散点图示例", width=1000, height=480)
v1, v2 = scatter.draw("../images/cup.png")
scatter.add("Cup", v1, v2)
scatter.render()
# 散点图1
from pyecharts import Scatter
v1 = [10, 20, 30, 40, 50, 60]
v2 = [10, 20, 30, 40, 50, 60]
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2) #v1[::-1] 倒序
scatter.render("scatter01.html")
# 散点图2
v1 = [10, 20, 30, 40, 50, 60]
v2 = [10, 20, 30, 40, 50, 60]
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B",
v1[::-1],
v2,
is_visualmap=True,
visual_type="size",
visual_range_size=[20, 80]) #散点可见
scatter.render("scatter02.html")
attr,
[11, 11, 15, 13, 12, 13, 10],
mark_point=["max", "min"],
mark_line=["average"],
)
line.add(
"最低气温",
attr,
[1, -2, 2, 5, 3, 2, 0],
mark_point=["max", "min"],
mark_line=["average"],
legend_pos="20%",
)
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
scatter = Scatter("散点图示例", title_top="50%", title_pos="65%")
scatter.add("scatter", v1, v2, legend_top="50%", legend_pos="80%")
es = EffectScatter("动态散点图示例", title_top="50%")
es.add(
"es",
[11, 11, 15, 13, 12, 13, 10],
[1, -2, 2, 5, 3, 2, 0],
effect_scale=6,
legend_top="50%",
legend_pos="20%",
)
grid = Grid()
grid.add(bar, grid_bottom="60%", grid_left="60%")
grid.add(line, grid_bottom="60%", grid_right="60%")
grid.add(scatter, grid_top="60%", grid_left="60%")
""" 文件名: $NAME.py 日期: 25 作者: lvah 联系: [email protected] 代码描述: # 绘制电影时长和电影排名之间的关系 """ import pandas as pd import numpy as np from matplotlib import pyplot as plt filename = 'doc/special_top250.csv' data = pd.read_csv(filename) print(data.head()) # 获取电影时长 x_series = data.movie_duration # 获取电影排名 y_series = data.num from pyecharts import Scatter scatter = Scatter("散点图") scatter.add("", x_series, y_series) scatter.render()
def test_scatter_markline_coords():
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2, mark_line_coords=[[10, 10], [30, 30]])
assert '"coord": [' in scatter._repr_html_()
for i, element in enumerate(collections_detail.find({'boxoffice_num':{'$exists':True}})):
if element['rating']['average'] == 0 or element['rate_quantity'] == '0' or not element['boxoffice_num']:
continue
for index, gen in enumerate(element['genres'], start=1):
if gen not in other_list:
break
if index == len(element['genres']):
gen = '其它'
if not genre.get(gen):
genre[gen] = {'title': [], 'rate': [], 'boxoffice': [], 'rate_quantity': []}
genre[gen]['title'].append(element['title'])
genre[gen]['rate'].append(element['rating']['average'])
genre[gen]['boxoffice'].append(round(element['boxoffice_num']/10000,2))
genre[gen]['rate_quantity'].append(element['rate_quantity'])
scatter = Scatter("电影评分-票房")
other_setting = {
'legend_orient': 'vertical',
'legend_pos': 'right',
'legend_top': 'center',
'is_datazoom_show': True,
'datazoom_type': 'both',
'datazoom_range':[0,40],
}
total_num = 0
for i in genre:
total_num += len(genre[i]['rate'])
# print(i)
# print(len(genre[i]['boxoffice']), genre[i]['boxoffice'])
# print(len(genre[i]['rate']), genre[i]['rate'])
# print(len(genre[i]['title']), genre[i]['title'])
def create_charts():
page = Page()
attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
bar = Bar("柱状图示例", height=800, width=WIDTH)
bar.add("商家A", attr, v1, is_stack=True)
bar.add("商家B", attr, v2, is_stack=True)
line = Line("折线图示例", title_top="50%")
attr = ['周一', '周二', '周三', '周四', '周五', '周六', '周日']
line.add("最高气温",
attr, [11, 11, 15, 13, 12, 13, 10],
mark_point=["max", "min"],
mark_line=["average"])
line.add("最低气温",
attr, [1, -2, 2, 5, 3, 2, 0],
mark_point=["max", "min"],
mark_line=["average"],
legend_top="50%")
chart = Grid()
chart.add(bar, grid_bottom="60%")
chart.add(line, grid_top="60%")
page.add(chart)
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
scatter = Scatter("散点图示例", width=WIDTH, title_pos="55%")
scatter.add("scatter", v1, v2, legend_pos="70%")
es = EffectScatter("动态散点图示例")
es.add("effectScatter", [11, 11, 15, 13, 12, 13, 10],
[1, -2, 2, 5, 3, 2, 0],
effect_scale=6,
legend_pos="20%")
chart = Grid()
chart.add(scatter, grid_left="60%")
chart.add(es, grid_right="60%")
page.add(chart)
attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
bar = Bar("柱状图示例", height=740, width=WIDTH, title_pos="65%")
bar.add("商家A", attr, v1, is_stack=True)
bar.add("商家B", attr, v2, is_stack=True, legend_pos="80%")
line = Line("折线图示例")
attr = ['周一', '周二', '周三', '周四', '周五', '周六', '周日']
line.add("最高气温",
attr, [11, 11, 15, 13, 12, 13, 10],
mark_point=["max", "min"],
mark_line=["average"])
line.add("最低气温",
attr, [1, -2, 2, 5, 3, 2, 0],
mark_point=["max", "min"],
mark_line=["average"],
legend_pos="20%")
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
scatter = Scatter("散点图示例", title_top="50%", title_pos="65%")
scatter.add("scatter", v1, v2, legend_top="50%", legend_pos="80%")
es = EffectScatter("动态散点图示例", title_top="50%")
es.add("es", [11, 11, 15, 13, 12, 13, 10], [1, -2, 2, 5, 3, 2, 0],
effect_scale=6,
legend_top="50%",
legend_pos="20%")
chart = Grid()
chart.add(bar, grid_bottom="60%", grid_left="60%")
chart.add(line, grid_bottom="60%", grid_right="60%")
chart.add(scatter, grid_top="60%", grid_left="60%")
chart.add(es, grid_top="60%", grid_right="60%")
page.add(chart)
line = Line("折线图示例", width=WIDTH)
attr = ['周一', '周二', '周三', '周四', '周五', '周六', '周日']
line.add("最高气温",
attr, [11, 11, 15, 13, 12, 13, 10],
mark_point=["max", "min"],
mark_line=["average"])
line.add("最低气温",
attr, [1, -2, 2, 5, 3, 2, 0],
mark_point=["max", "min"],
mark_line=["average"],
legend_pos="20%")
attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
v1 = [11, 12, 13, 10, 10, 10]
pie = Pie("饼图示例", title_pos="55%")
pie.add("",
attr,
v1,
radius=[45, 65],
center=[70, 50],
legend_pos="85%",
legend_orient='vertical')
chart = Grid()
chart.add(line, grid_right="55%")
chart.add(pie, grid_left="60%")
page.add(chart)
line = Line("折线图示例", width=WIDTH)
attr = ['周一', '周二', '周三', '周四', '周五', '周六', '周日']
line.add("最高气温",
attr, [11, 11, 15, 13, 12, 13, 10],
mark_point=["max", "min"],
mark_line=["average"])
line.add("最低气温",
attr, [1, -2, 2, 5, 3, 2, 0],
mark_point=["max", "min"],
mark_line=["average"],
legend_pos="20%")
v1 = [[2320.26, 2320.26, 2287.3,
2362.94], [2300, 2291.3, 2288.26, 2308.38],
[2295.35, 2346.5, 2295.35, 2345.92],
[2347.22, 2358.98, 2337.35, 2363.8],
[2360.75, 2382.48, 2347.89, 2383.76],
[2383.43, 2385.42, 2371.23, 2391.82],
[2377.41, 2419.02, 2369.57, 2421.15],
[2425.92, 2428.15, 2417.58,
2440.38], [2411, 2433.13, 2403.3, 2437.42],
[2432.68, 2334.48, 2427.7, 2441.73],
[2430.69, 2418.53, 2394.22, 2433.89],
[2416.62, 2432.4, 2414.4, 2443.03],
[2441.91, 2421.56, 2418.43, 2444.8],
[2420.26, 2382.91, 2373.53, 2427.07],
[2383.49, 2397.18, 2370.61, 2397.94],
[2378.82, 2325.95, 2309.17, 2378.82],
[2322.94, 2314.16, 2308.76, 2330.88],
[2320.62, 2325.82, 2315.01, 2338.78],
[2313.74, 2293.34, 2289.89, 2340.71],
[2297.77, 2313.22, 2292.03, 2324.63],
[2322.32, 2365.59, 2308.92, 2366.16],
[2364.54, 2359.51, 2330.86, 2369.65],
[2332.08, 2273.4, 2259.25, 2333.54],
[2274.81, 2326.31, 2270.1, 2328.14],
[2333.61, 2347.18, 2321.6, 2351.44],
[2340.44, 2324.29, 2304.27, 2352.02],
[2326.42, 2318.61, 2314.59, 2333.67],
[2314.68, 2310.59, 2296.58, 2320.96],
[2309.16, 2286.6, 2264.83, 2333.29],
[2282.17, 2263.97, 2253.25, 2286.33],
[2255.77, 2270.28, 2253.31, 2276.22]]
kline = Kline("K 线图示例", title_pos="60%")
kline.add("日K", ["2017/7/{}".format(i + 1) for i in range(31)],
v1,
legend_pos="80%")
chart = Grid()
chart.add(line, grid_right="60%")
chart.add(kline, grid_left="55%")
page.add(chart)
data = [[i, j, random.randint(0, 50)] for i in range(24) for j in range(7)]
heatmap = HeatMap("热力图示例", width=WIDTH, height=700)
heatmap.add("热力图直角坐标系",
X_TIME,
Y_WEEK,
data,
is_visualmap=True,
visual_top="45%",
visual_text_color="#000",
visual_orient='horizontal')
attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
bar = Bar("柱状图示例", title_top="52%")
bar.add("商家A", attr, v1, is_stack=True)
bar.add("商家B", attr, v2, is_stack=True, legend_top="50%")
chart = Grid()
chart.add(heatmap, grid_bottom="60%")
chart.add(bar, grid_top="60%")
page.add(chart)
line = Line("折线图示例", width=WIDTH, height=700)
attr = ['周一', '周二', '周三', '周四', '周五', '周六', '周日']
line.add("最高气温",
attr, [11, 11, 15, 13, 12, 13, 10],
mark_point=["max", "min"],
mark_line=["average"])
line.add("最低气温",
attr, [1, -2, 2, 5, 3, 2, 0],
mark_point=["max", "min"],
legend_top="50%",
mark_line=["average"],
is_datazoom_show=True,
datazoom_xaxis_index=[0, 1])
v1 = [[2320.26, 2320.26, 2287.3,
2362.94], [2300, 2291.3, 2288.26, 2308.38],
[2295.35, 2346.5, 2295.35, 2345.92],
[2347.22, 2358.98, 2337.35, 2363.8],
[2360.75, 2382.48, 2347.89, 2383.76],
[2383.43, 2385.42, 2371.23, 2391.82],
[2377.41, 2419.02, 2369.57, 2421.15],
[2425.92, 2428.15, 2417.58,
2440.38], [2411, 2433.13, 2403.3, 2437.42],
[2432.68, 2334.48, 2427.7, 2441.73],
[2430.69, 2418.53, 2394.22, 2433.89],
[2416.62, 2432.4, 2414.4, 2443.03],
[2441.91, 2421.56, 2418.43, 2444.8],
[2420.26, 2382.91, 2373.53, 2427.07],
[2383.49, 2397.18, 2370.61, 2397.94],
[2378.82, 2325.95, 2309.17, 2378.82],
[2322.94, 2314.16, 2308.76, 2330.88],
[2320.62, 2325.82, 2315.01, 2338.78],
[2313.74, 2293.34, 2289.89, 2340.71],
[2297.77, 2313.22, 2292.03, 2324.63],
[2322.32, 2365.59, 2308.92, 2366.16],
[2364.54, 2359.51, 2330.86, 2369.65],
[2332.08, 2273.4, 2259.25, 2333.54],
[2274.81, 2326.31, 2270.1, 2328.14],
[2333.61, 2347.18, 2321.6, 2351.44],
[2340.44, 2324.29, 2304.27, 2352.02],
[2326.42, 2318.61, 2314.59, 2333.67],
[2314.68, 2310.59, 2296.58, 2320.96],
[2309.16, 2286.6, 2264.83, 2333.29],
[2282.17, 2263.97, 2253.25, 2286.33],
[2255.77, 2270.28, 2253.31, 2276.22]]
kline = Kline("K 线图示例", title_top="50%")
kline.add("日K", ["2017/7/{}".format(i + 1) for i in range(31)],
v1,
is_datazoom_show=True)
chart = Grid()
chart.add(line, grid_top="60%")
chart.add(kline, grid_bottom="60%")
page.add(chart)
attr = ['{}天'.format(i) for i in range(1, 31)]
line_top = Line("折线图示例", width=WIDTH, height=700)
line_top.add("最高气温",
attr, [random.randint(20, 100) for i in range(30)],
mark_point=["max", "min"],
mark_line=["average"],
legend_pos='38%')
line_bottom = Line()
line_bottom.add("最低气温",
attr, [random.randint(20, 100) for i in range(30)],
mark_point=["max", "min"],
mark_line=["average"],
is_yaxis_inverse=True,
xaxis_pos='top')
chart = Grid()
chart.add(line_top, grid_bottom='60%')
chart.add(line_bottom, grid_top='50%')
page.add(chart)
attr = ["{}月".format(i) for i in range(1, 13)]
v1 = [2.0, 4.9, 7.0, 23.2, 25.6, 76.7, 135.6, 162.2, 32.6, 20.0, 6.4, 3.3]
v2 = [2.6, 5.9, 9.0, 26.4, 28.7, 70.7, 175.6, 182.2, 48.7, 18.8, 6.0, 2.3]
v3 = [2.0, 2.2, 3.3, 4.5, 6.3, 10.2, 20.3, 23.4, 23.0, 16.5, 12.0, 6.2]
bar = Bar("Overlap+Grid 示例", title_pos="40%", width=1100, height=600)
bar.add("蒸发量", attr, v1)
bar.add("降水量",
attr,
v2,
yaxis_formatter=" ml",
yaxis_max=250,
legend_pos="85%",
legend_orient="vertical",
legend_top="45%")
line = Line()
line.add("平均温度", attr, v3, yaxis_formatter=" °C")
overlap = Overlap()
overlap.add(bar)
overlap.add(line, is_add_yaxis=True, yaxis_index=1)
chart = Grid()
chart.add(overlap, grid_right='20%')
page.add(chart)
return page
from pyecharts import Scatter
# v1 = [10, 20, 30, 40, 50, 60]
# v2 = [10, 20, 30, 40, 50, 60]
# scatter = Scatter("散点图示例")
# scatter.add("A", v1, v2)
# scatter.add("B", v1[::-1], v2)
# scatter.show_config()
# scatter.render(r"Scatter（散点图）.html")
scatter = Scatter("散点图示例", width=1000, height=480)
v1, v2 = scatter.draw("cup.png")
scatter.add("Cup", v1, v2, label_color='#000')
scatter.render(r"Scatter（散点图）.html")
def test_scatter_draw_pyecharts():
scatter = Scatter("散点图示例")
v1, v2 = scatter.draw("../images/pyecharts-0.png")
scatter.add("pyecharts", v1, v2, is_random=True)
scatter.render()
def test_scatter_visualmap():
# visual type 'color'
v1 = [10, 20, 30, 40, 50, 60]
v2 = [10, 20, 30, 40, 50, 60]
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2, is_visualmap=True)
scatter.render()
# visual type 'size'
scatter = Scatter("散点图示例")
# scatter.add("A", v1, v2)
scatter.add("B",
v1[::-1],
v2,
is_visualmap=True,
visual_type='size',
visual_range_size=[20, 80])
scatter.render()
def bivar(data,feature,t_type,target=None,draw_type='line',bins=20,tree_depth=4,woe = None,d_reorder=False,cut='none',cut_way='auto',\
custom_bin=[],cut_num=None,cut_start=None,fill_na=-99999,text_print=True,save=None,path='./'):
# data is dataframe
# feature is feature name
# target is your target name, should be binary integer
# t_type has two selection, 'c' or 'd', 'c' means continue, 'd' means discreate
# draw_type has line and scatter
# bins means you can choose how many bins to cut by yourself
# tree_depth is only working for decision tree binning
# woe is only working for woe binning
# cut has three selection, 'none','qcut','cut','F-D' only for numerical col
# d_reorder will sort categorical values and reorder it
# example bivar(df,'feature2','is_over','c')
# make sure feature and target in your dataframe
data=data;feature=feature;target=target;t_type=t_type
X = data[feature]
if target != None:
Y = data[target]
if fill_na != -99999:
X = X.fillna(fill_na)
missing_exist = X.isnull().any()
#fillna value if it has.
if cut == 'none':
if (target != None) & (missing_exist == True):
# Data preprocessing
temp_df = data[[feature,target]].fillna('missing').copy()
feature_a = temp_df[[feature,target]].groupby(feature).size()
feature_b = temp_df[[feature,target]].groupby(feature).sum()
feature_final = pd.concat([feature_a,feature_b],axis=1)
feature_final.rename(columns = {0:'total'},inplace=True)
elif (target != None) & (missing_exist == False):
# Data preprocessing
temp_df = data[[feature,target]].fillna(fill_na).copy()
feature_a = temp_df[[feature,target]].groupby(feature).size()
feature_b = temp_df[[feature,target]].groupby(feature).sum()
feature_final = pd.concat([feature_a,feature_b],axis=1)
feature_final.rename(columns = {0:'total'},inplace=True)
elif (target == None) & (missing_exist == False):
# Data preprocessing
temp_df = data[[feature]].fillna(fill_na).copy()
feature_a = temp_df[[feature]].groupby(feature).size()
feature_b = temp_df[[feature]].groupby(feature).sum()
feature_final = pd.concat([feature_a,feature_b],axis=1)
feature_final.rename(columns = {0:'total'},inplace=True)
else:
# Data preprocessing
temp_df = data[[feature]].fillna('missing').copy()
feature_a = temp_df[[feature]].groupby(feature).size()
feature_b = temp_df[[feature]].groupby(feature).sum()
feature_final = pd.concat([feature_a,feature_b],axis=1)
feature_final.rename(columns = {0:'total'},inplace=True)
# check if has missing value in dataframe
# Data preprocessing with missing value
if missing_exist:
if (t_type == 'c'):
missing_df = feature_final.loc['missing':'missing']
feature_final = feature_final[feature_final.index != 'missing']
index_list = list(pd.cut(feature_final.index, bins = bins))
feature_final.index=index_list
feature_final.index.name=feature
feature_final = feature_final.groupby(feature_final.index).sum()
feature_final = feature_final.reindex(list(OrderedSet(index_list)))
if target != None:
feature_final[target+'_rate'] = feature_final[target]/feature_final['total']
elif target != None:
feature_final[target+'_rate'] = feature_final[target]/feature_final['total']
# Data preprocessing w/o missing value
else:
if (t_type == 'c'):
index_list = list(pd.cut(feature_final.index, bins = bins))
feature_final.index=index_list
feature_final.index.name=feature
feature_final = feature_final.groupby(feature_final.index).sum()
feature_final = feature_final.reindex(list(OrderedSet(index_list)))
feature_final.index = list(OrderedSet(index_list))
if target != None:
feature_final[target+'_rate'] = feature_final[target]/feature_final['total']
elif target != None:
feature_final[target+'_rate'] = feature_final[target]/feature_final['total']
feature_final.reset_index(inplace=True)
feature_final.rename(columns={'index':feature},inplace=True)
if cut == 'custom':
if (target != None) & (missing_exist == True):
# Data preprocessing
temp_df = data[[feature,target]].fillna('missing').copy()
feature_a = temp_df[[feature,target]].groupby(feature).size()
feature_b = temp_df[[feature,target]].groupby(feature).sum()
feature_final = pd.concat([feature_a,feature_b],axis=1)
feature_final.rename(columns = {0:'total'},inplace=True)
elif (target != None) & (missing_exist == False):
# Data preprocessing
temp_df = data[[feature,target]].fillna(fill_na).copy()
feature_a = temp_df[[feature,target]].groupby(feature).size()
feature_b = temp_df[[feature,target]].groupby(feature).sum()
feature_final = pd.concat([feature_a,feature_b],axis=1)
feature_final.rename(columns = {0:'total'},inplace=True)
elif (target == None) & (missing_exist == False):
# Data preprocessing
temp_df = data[[feature]].fillna(fill_na).copy()
feature_a = temp_df[[feature]].groupby(feature).size()
feature_b = temp_df[[feature]].groupby(feature).sum()
feature_final = pd.concat([feature_a,feature_b],axis=1)
feature_final.rename(columns = {0:'total'},inplace=True)
else:
# Data preprocessing
temp_df = data[[feature]].fillna('missing').copy()
feature_a = temp_df[[feature]].groupby(feature).size()
feature_b = temp_df[[feature]].groupby(feature).sum()
feature_final = pd.concat([feature_a,feature_b],axis=1)
feature_final.rename(columns = {0:'total'},inplace=True)
# check if has missing value in dataframe
# Data preprocessing with missing value
if missing_exist:
if ((t_type == 'c') & (len(temp_df[feature].unique())>=bins)):
missing_df = feature_final.loc['missing':'missing']
feature_final = feature_final[feature_final.index != 'missing']
index_list = list(pd.cut(feature_final.index, bins = custom_bin))
feature_final.index=index_list
feature_final.index.name=feature
feature_final = feature_final.groupby(feature_final.index).sum()
feature_final = feature_final.reindex(list(OrderedSet(index_list)))
if target != None:
feature_final[target+'_rate'] = feature_final[target]/feature_final['total']
elif target != None:
feature_final[target+'_rate'] = feature_final[target]/feature_final['total']
# Data preprocessing w/o missing value
else:
if ((t_type == 'c') & (len(temp_df[feature].unique())>=bins)):
index_list = list(pd.cut(feature_final.index, bins = custom_bin))
feature_final.index=index_list
feature_final.index.name=feature
feature_final = feature_final.groupby(feature_final.index).sum()
feature_final = feature_final.reindex(list(OrderedSet(index_list)))
feature_final.index = list(OrderedSet(index_list))
if target != None:
feature_final[target+'_rate'] = feature_final[target]/feature_final['total']
elif target != None:
feature_final[target+'_rate'] = feature_final[target]/feature_final['total']
feature_final.reset_index(inplace=True)
feature_final.rename(columns={'index':feature},inplace=True)
if ((t_type == 'c') & (cut == 'F-D') & (target != None)):
if missing_exist == True:
temp_df = data[[feature,target]].fillna('missing').copy()
elif missing_exist != True:
temp_df = data[[feature,target]].fillna(fill_na).copy()
# Data preprocessing
feature_a = temp_df[[feature,target]].groupby(feature).size()
feature_b = temp_df[[feature,target]].groupby(feature).sum()
feature_final = pd.concat([feature_a,feature_b],axis=1)
feature_final.rename(columns = {0:'total'},inplace=True)
# check if has missing value in dataframe
# Data preprocessing with missing value
if missing_exist:
if ((t_type == 'c')):
missing_df = feature_final.loc['missing':'missing']
feature_final = feature_final[feature_final.index != 'missing']
missing_temp_df = temp_df[temp_df[feature]=='missing']
missing_temp_df = pd.DataFrame(missing_temp_df.groupby(feature).size())
missing_temp_df.rename(columns={0:target},inplace=True)
missing_over_size = temp_df[temp_df[feature]=='missing'][temp_df[target]==1].shape[0]
missing_temp_df[target]['missing'] = missing_over_size
non_missing_temp_df = temp_df[temp_df[feature]!='missing']
non_missing_temp_df.index = non_missing_temp_df[feature]
Q1 = non_missing_temp_df[feature].astype(float).describe()['25%']
Q3 = non_missing_temp_df[feature].astype(float).describe()['75%']
min_value = non_missing_temp_df.index.min()
max_value = non_missing_temp_df.index.max()
bins_list = [min_value-0.0001]
temp_value = min_value
F_D = 2*(Q3-Q1)/math.pow(non_missing_temp_df.shape[0],1/3)
if F_D == 0:
print('since too many values in one bin, so we start use cut method!')
print('='*60)
try:
result = draw.bivar(data=data, feature=feature,target=target,bins=bins,cut='none',t_type=t_type,cut_num=cut_num,cut_start=cut_start)
return result
except:
return draw.bivar(data=data, feature=feature,target=target,bins=bins,cut='none',t_type=t_type)
while temp_value < max_value:
temp_value += F_D
bins_list.append(temp_value)
index_list = list(pd.cut(feature_final.index, bins = bins_list))
feature_final.index=index_list
feature_final.index.name=feature
feature_final = feature_final.groupby(feature_final.index).sum()
feature_final = feature_final.reindex(list(OrderedSet(index_list)))
# Data preprocessing w/o missing value
else:
if ((t_type == 'c')):
non_missing_temp_df = temp_df.copy()
non_missing_temp_df.index = non_missing_temp_df[feature]
Q1 = non_missing_temp_df[feature].astype(float).describe()['25%']
Q3 = non_missing_temp_df[feature].astype(float).describe()['75%']
min_value = non_missing_temp_df.index.min()
max_value = non_missing_temp_df.index.max()
bins_list = [min_value-0.0001]
temp_value = min_value
F_D = 2*(Q3-Q1)/math.pow(non_missing_temp_df.shape[0],1/3)
if F_D == 0:
print('since too many values in one bin, so we start use cut method!')
print('='*60)
try:
result = draw.bivar(data=data, feature=feature,target=target,bins=bins,cut='none',t_type=t_type,cut_num=cut_num,cut_start=cut_start)
return result
except:
return draw.bivar(data=data, feature=feature,target=target,bins=bins,cut='none',t_type=t_type)
while temp_value < max_value:
temp_value += F_D
bins_list.append(temp_value)
index_list = list(pd.cut(feature_final.index, bins = bins_list))
feature_final.index=index_list
feature_final.index.name=feature
feature_final = feature_final.groupby(feature_final.index).sum()
feature_final = feature_final.reindex(list(OrderedSet(index_list)))
feature_final[target+'_rate'] = feature_final[target]/feature_final['total']
feature_final.reset_index(inplace=True)
feature_final.rename(columns={'index':feature},inplace=True)
feature_final[target+'_rate'] = feature_final[target]/feature_final['total']
if ((t_type == 'c') & (cut == 'qcut') & (target != None)):
try:
feature_final = draw.numerical_binning_qcut_for_draw(draw.numerical_binning_qcut(X,Y,n=bins,cut_way=cut_way,text_print=text_print),\
X,Y,missing_exist=missing_exist)
except:
print('since too many values in one bin, so we start use cut method!')
print('='*60)
return draw.bivar(data=data, feature=feature,target=target,bins=bins,cut='none',t_type=t_type)
elif ((t_type == 'c') & (cut == 'cut')& (target != None)):
try:
feature_final = draw.numerical_binning_qcut_for_draw(draw.numerical_binning_cut(X,Y,n=bins,cut_way=cut_way,text_print=True),\
X,Y,missing_exist=missing_exist)
except:
print('since too many values in one bin, so we start use cut method!')
print('='*60)
print('start using basic bins cut method.')
return draw.bivar(data=data, feature=feature,target=target,bins=bins,cut='none',t_type=t_type)
elif ((t_type == 'c') & (cut == 'dtree')& (target != None)):
try:
feature_final = draw.DecisionTreeBinning(data,feature,target,max_depth=tree_depth,missing_exist=False)
except:
print('since too many values in one bin, so we start use cut method!')
print('='*60)
print('start using basic bins cut method.')
return draw.bivar(data=data, feature=feature,target=target,bins=bins,cut='none',t_type=t_type)
elif((t_type == 'c') & (cut == 'woe')& (target != None)):
try:
feature_final = draw.woe_binning_cut_for_draw(X,Y,woe)
except:
print('since too many values in one bin, so we start use cut method!')
print('='*60)
print('start using basic bins cut method.')
return draw.bivar(data=data, feature=feature,target=target,bins=bins,cut='none',t_type=t_type)
if (cut_num != None) & (cut_start == 'start') & (t_type == 'c'):
try:
new_left = feature_final[feature_final['total']<cut_num][feature].iloc[0].left
new_right = feature_final[feature_final['total']>cut_num][feature].iloc[0].left
except:
print('data cannot be cut from head.')
print('='*60)
print('start using basic bins cut method.')
return draw.bivar(data=data, feature=feature,target=target,bins=bins,cut='none',t_type=t_type)
new_total = feature_final.iloc[:feature_final[feature_final['total']>=cut_num].index[0]].total.sum()
new_is_over = feature_final.iloc[:feature_final[feature_final['total']>=cut_num].index[0]][target].sum()
new_tmp_df = pd.DataFrame({feature:[pd.Interval(left=new_left, right=new_right)],'total':[new_total],\
target:[new_is_over],target+'_rate':[new_is_over/new_total]})
feature_final = pd.concat([new_tmp_df,feature_final.iloc[feature_final[feature_final['total']>cut_num].index[0]:]],\
axis=0).reset_index()
feature_final = feature_final.drop('index',axis=1)
elif (cut_num != None) & (cut_start == 'tail') & (t_type == 'c'):
try:
new_left = feature_final[feature_final['total']>=cut_num][feature].iloc[-1].right
new_right = feature_final[feature_final['total']<cut_num][feature].iloc[-1].right
except:
print('data cannot be cut from tail.')
print('='*60)
print('start using basic bins cut method.')
return draw.bivar(data=data, feature=feature,target=target,bins=bins,cut='none',t_type=t_type)
new_total = feature_final.iloc[feature_final[feature_final['total']>=cut_num].index[-1]+1:].total.sum()
new_is_over = feature_final.iloc[feature_final[feature_final['total']>=cut_num].index[-1]+1:][target].sum()
new_tmp_df = pd.DataFrame({feature:[pd.Interval(left=new_left, right=new_right)],'total':[new_total],\
target:[new_is_over],target+'_rate':[new_is_over/new_total]})
feature_final = pd.concat([feature_final.iloc[:feature_final[feature_final['total']>cut_num].index[-1]+1],new_tmp_df],\
axis=0).reset_index()
feature_final = feature_final.drop('index',axis=1)
elif (cut_num != None) & (cut_start == 'both') & (t_type == 'c'):
try:
new_left = feature_final[feature_final['total']<cut_num][feature].iloc[0].left
new_right = feature_final[feature_final['total']>cut_num][feature].iloc[0].left
except:
print('data cannot be cut from head.')
print('='*60)
print('start using basic bins cut method.')
return draw.bivar(data=data, feature=feature,target=target,bins=bins,cut='none',t_type=t_type)
new_total = feature_final.iloc[:feature_final[feature_final['total']>=cut_num].index[0]].total.sum()
new_is_over = feature_final.iloc[:feature_final[feature_final['total']>=cut_num].index[0]][target].sum()
new_tmp_df = pd.DataFrame({feature:[pd.Interval(left=new_left, right=new_right)],'total':[new_total],\
target:[new_is_over],target+'_rate':[new_is_over/new_total]})
feature_final = pd.concat([new_tmp_df,feature_final.iloc[feature_final[feature_final['total']>cut_num].index[0]:]],\
axis=0).reset_index()
feature_final = feature_final.drop('index',axis=1)
try:
new_left = feature_final[feature_final['total']>=cut_num][feature].iloc[-1].right
new_right = feature_final[feature_final['total']<cut_num][feature].iloc[-1].right
except:
print('data cannot be cut from head.')
print('='*60)
print('start using basic bins cut method.')
return draw.bivar(data=data, feature=feature,target=target,bins=bins,cut='none',t_type=t_type)
new_total = feature_final.iloc[feature_final[feature_final['total']>=cut_num].index[-1]+1:].total.sum()
new_is_over = feature_final.iloc[feature_final[feature_final['total']>=cut_num].index[-1]+1:][target].sum()
new_tmp_df = pd.DataFrame({feature:[pd.Interval(left=new_left, right=new_right)],'total':[new_total],\
target:[new_is_over],target+'_rate':[new_is_over/new_total]})
feature_final = pd.concat([feature_final.iloc[:feature_final[feature_final['total']>cut_num].index[-1]+1],new_tmp_df],\
axis=0).reset_index()
feature_final = feature_final.drop('index',axis=1)
if (missing_exist) & (cut in ['none','F-D','custom']) & (t_type == 'c'):
missing_df[target+'_rate'] = missing_df[target]/missing_df['total']
missing_df = missing_df.reset_index()
feature_final = pd.concat([feature_final,missing_df],axis=0)
feature_final = feature_final.reset_index()
feature_final = feature_final.drop('index',axis=1)
if type(feature_final)!=pd.core.frame.DataFrame:
return 'There are less than 1 values in {}.'.format(feature)
if d_reorder:
feature_final.sort_values(['total',target],ascending=[False,False],inplace=True)
#Drawing bivar graph
attr = []
for c in feature_final[feature]:
attr.append(str(c))
if target != None:
v1 = list(feature_final[target].values)
v2 = [x - y for x, y in zip(feature_final['total'].tolist(), feature_final[target].tolist())]
v3 = list(np.round(feature_final[target+'_rate'].values*100,2))
yaxis_max = np.max(v3)
bar = Bar(width=1200, height=600,title=feature,background_color='#ffffff')
bar.add(target+"数量", attr, v1,is_stack=True,is_datazoom_show=True,datazoom_type='both',datazoom_range=[0,100],
label_color=['#00FF7F','#0081FF','#FF007C'],is_visualmap=True, visual_type='size',visual_range=[0,yaxis_max],
visual_range_size=[10,10],is_yaxislabel_align=False,visual_dimension=1,tooltip_text_color='#000000',
label_emphasis_textcolor='#000000',is_more_utils=True)
bar.add('non-'+target+"数量",attr,v2,is_stack=True,label_emphasis_textcolor='#000000')
overlap = Overlap()
overlap.add(bar)
if draw_type=='line':
line = Line()
line.add(target, attr, v3, yaxis_formatter="%", yaxis_min=0,yaxis_max=1.2*yaxis_max,label_emphasis_textcolor='#000000',line_width=3)
overlap.add(line, yaxis_index=1, is_add_yaxis=True)
if draw_type=='scatter':
scatter = Scatter()
scatter.add(target, attr, v3, yaxis_formatter="%", yaxis_min=0,yaxis_max=1.2*yaxis_max,label_emphasis_textcolor='#000000')
overlap.add(scatter, yaxis_index=1, is_add_yaxis=True)
else:
bar = Bar(width=1200, height=600,title=feature,background_color='#ffffff')
v1 = list(feature_final['total'].values)
bar.add("数量", attr, v1,is_stack=True,is_datazoom_show=True,datazoom_type='both',datazoom_range=[0,100],
label_color=['#0081FF','#FF007C'],is_visualmap=True, visual_type='size',
visual_range_size=[10,10],is_yaxislabel_align=False,visual_dimension=1,tooltip_text_color='#000000',
label_emphasis_textcolor='#000000',is_more_utils=True)
overlap = Overlap()
overlap.add(bar)
if save==None:
return overlap
elif save!= None:
return overlap.render(path=path+'{}.{}'.format(feature,save))
def test_scatter_draw_picture():
# draw pyecharts
scatter = Scatter("散点图示例")
v1, v2 = scatter.draw("../images/pyecharts-0.png")
scatter.add("pyecharts", v1, v2, is_random=True)
scatter.render()
# draw love
scatter = Scatter("散点图示例", width=800, height=480)
v1, v2 = scatter.draw("../images/love.png")
scatter.add("Love", v1, v2)
scatter.render()
# draw a hot red bra
scatter = Scatter("散点图示例", width=1000, height=480)
v1, v2 = scatter.draw("../images/cup.png")
scatter.add("Cup", v1, v2)
scatter.render()
# draw a sexy black bra
scatter = Scatter("散点图示例", width=1000, height=480)
v1, v2 = scatter.draw("../images/cup.png")
scatter.add("Cup", v1, v2, label_color=["#000"])
scatter.render()
help='only report R&D Center department',
action='store_true')
args = parser.parse_args()
rd_departments_list = [
'嵌入部', '系统部', '软件部', '项目管理部', '硬件部', '结构部', '测试部', '研发中心'
]
page = Page()
if args.only_rd:
subtitle = '创世科技研发中心2017年度(2016.12.25-2017.12.24)统计数据'
else:
subtitle = '创世科技2017年度(2016.12.25-2017.12.24)统计数据'
later_charts = Scatter(title='迟到', subtitle=subtitle, width=1920, height=1080)
overtime_charts = Scatter(title='加班',
subtitle=subtitle,
width=1920,
height=1080)
remedies_bar = Bar(title='补签', subtitle=subtitle, width=1920, height=1080)
sheet = xlrd.open_workbook(args.inputfile).sheets()[0]
name_list = []
remedies_count_list = []
for index in range(1, sheet.nrows):
items = sheet.row(index)
name = items[0].value
def test_scatter_markline_coords():
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2, mark_line_coords=[[10, 10], [30, 30]])
assert '"coord": [' in scatter._repr_html_()
def create_charts():
page = Page()
style = Style(width=WIDTH, height=HEIGHT)
v1 = [10, 20, 30, 40, 50, 60]
v2 = [10, 20, 30, 40, 50, 60]
chart = Scatter("散点图-双数值轴", **style.init_style)
chart.add("A", v1, v2)
chart.add("B", v1[::-1], v2)
page.add(chart)
chart = Scatter("散点图-x轴类目轴", **style.init_style)
chart.add("A", ["a", "b", "c", "d", "e", "f"], v2)
chart.add("B", ["a", "b", "c", "d", "e", "f"],
v1[::-1],
xaxis_type="category")
page.add(chart)
v1 = [10, 20, 30, 40, 50, 60]
v2 = [10, 20, 30, 40, 50, 60]
chart = Scatter("散点图-视觉通道(颜色)", **style.init_style)
chart.add("A", v1, v2)
chart.add("B", v1[::-1], v2, is_visualmap=True)
page.add(chart)
chart = Scatter("散点图-视觉通道(大小)", **style.init_style)
chart.add("A", v1, v2)
chart.add("B",
v1[::-1],
v2,
is_visualmap=True,
visual_type='size',
visual_range_size=[20, 80])
page.add(chart)
data = [[28604, 77, 17096869], [31163, 77.4, 27662440],
[1516, 68, 1154605773], [13670, 74.7, 10582082],
[28599, 75, 4986705], [29476, 77.1, 56943299],
[31476, 75.4, 78958237], [28666, 78.1, 254830],
[1777, 57.7, 870601776], [29550, 79.1, 122249285],
[2076, 67.9, 20194354], [12087, 72, 42972254],
[24021, 75.4, 3397534], [43296, 76.8, 4240375],
[10088, 70.8, 38195258], [19349, 69.6, 147568552],
[10670, 67.3, 53994605], [26424, 75.7, 57110117],
[37062, 75.4, 252847810]]
x_lst = [v[0] for v in data]
y_lst = [v[1] for v in data]
extra_data = [v[2] for v in data]
chart = Scatter("散点图-视觉通道(第三维度数据)", **style.init_style)
chart.add("scatter",
x_lst,
y_lst,
extra_data=extra_data,
is_visualmap=True,
visual_dimension=2,
visual_orient='horizontal',
visual_type='size',
visual_range=[254830, 1154605773],
visual_text_color='#000')
page.add(chart)
return page
def test_scatter_draw_love():
scatter = Scatter("散点图示例", width=800, height=480)
v1, v2 = scatter.draw("../images/love.png")
scatter.add("Love", v1, v2)
scatter.render()
pie = Pie("服装占比",title_pos='left',width=800)
pie.add("", attr, v1, is_label_show=True,radius=[30,75])
pie.render('pie.html')
#label_text_color字体颜色
attr = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "鞋", "袜子"]
v1 = [110, 112, 133, 100, 108, 120]
pie = Pie("饼图-服装占比", title_pos='center')
pie.add("服饰",attr,v1,radius=[40, 75],
label_text_color='red',is_label_show=True,legend_orient="vertical",legend_pos="left")
pie.render('pie.html')
# # # # # #散点图
from pyecharts import Scatter
iris = pd.read_csv('iris.csv')
scatter = Scatter('鸢尾花花瓣宽度和长度关系图')
scatter.add("setosa", iris.Petal_Width[iris.Species=='setosa'], iris.Petal_Length[iris.Species=='setosa'],
symbol_size = 8, mark_point_symbol='arrow')
scatter.add("versicolor", iris.Petal_Width[iris.Species=='versicolor'], iris.Petal_Length[iris.Species=='versicolor'],
symbol_size =10)
scatter.add("virginica", iris.Petal_Width[iris.Species=='virginica'], iris.Petal_Length[iris.Species=='virginica'],
symbol_size =12)
scatter.render('iris.html')
# # # # # #折线图
# 读取数据
GDP_data = pd.read_excel('国民经济核算季度数据.xlsx')
# 选择部分数据
# mark_point_symbol 指定标签的形状
# mark_point_textcolor 指定标签的字体颜色
# mark_point_symbolsize 指定标记标记的大小
def test_page_grid_timeline_overlap():
# Grid
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
bar = Bar("柱状图示例", height=720, width=1200, title_pos="65%")
bar.add("商家A", CLOTHES, v1, is_stack=True)
bar.add("商家B", CLOTHES, v2, is_stack=True, legend_pos="80%")
line = Line("折线图示例")
line.add(
"最高气温",
WEEK,
[11, 11, 15, 13, 12, 13, 10],
mark_point=["max", "min"],
mark_line=["average"],
)
line.add(
"最低气温",
WEEK,
[1, -2, 2, 5, 3, 2, 0],
mark_point=["max", "min"],
mark_line=["average"],
legend_pos="20%",
)
v1 = [5, 20, 36, 10, 75, 90]
v2 = [10, 25, 8, 60, 20, 80]
scatter = Scatter("散点图示例", title_top="50%", title_pos="65%")
scatter.add("scatter", v1, v2, legend_top="50%", legend_pos="80%")
es = EffectScatter("动态散点图示例", title_top="50%")
es.add(
"es",
[11, 11, 15, 13, 12, 13, 10],
[1, -2, 2, 5, 3, 2, 0],
effect_scale=6,
legend_top="50%",
legend_pos="20%",
)
grid = Grid()
grid.add(bar, grid_bottom="60%", grid_left="60%")
grid.add(line, grid_bottom="60%", grid_right="60%")
grid.add(scatter, grid_top="60%", grid_left="60%")
grid.add(es, grid_top="60%", grid_right="60%")
# Timeline
bar_1 = Bar("2012 年销量", "数据纯属虚构")
bar_1.add("春季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_1.add("夏季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_1.add("秋季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_1.add("冬季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_2 = Bar("2013 年销量", "数据纯属虚构")
bar_2.add("春季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_2.add("夏季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_2.add("秋季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_2.add("冬季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_3 = Bar("2014 年销量", "数据纯属虚构")
bar_3.add("春季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_3.add("夏季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_3.add("秋季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_3.add("冬季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_4 = Bar("2015 年销量", "数据纯属虚构")
bar_4.add("春季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_4.add("夏季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_4.add("秋季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_4.add("冬季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_5 = Bar("2016 年销量", "数据纯属虚构", height=720, width=1200)
bar_5.add("春季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_5.add("夏季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_5.add("秋季", CLOTHES, [randint(10, 100) for _ in range(6)])
bar_5.add(
"冬季",
CLOTHES,
[randint(10, 100) for _ in range(6)],
is_legend_show=True,
)
timeline = Timeline(is_auto_play=True, timeline_bottom=0)
timeline.add(bar_1, "2012 年")
timeline.add(bar_2, "2013 年")
timeline.add(bar_3, "2014 年")
timeline.add(bar_4, "2015 年")
timeline.add(bar_5, "2016 年")
# Overlap
attr = ["{}月".format(i) for i in range(1, 13)]
v1 = [2.0, 4.9, 7.0, 23.2, 25.6, 76.7, 135.6, 162.2, 32.6, 20.0, 6.4, 3.3]
v2 = [2.6, 5.9, 9.0, 26.4, 28.7, 70.7, 175.6, 182.2, 48.7, 18.8, 6.0, 2.3]
v3 = [2.0, 2.2, 3.3, 4.5, 6.3, 10.2, 20.3, 23.4, 23.0, 16.5, 12.0, 6.2]
bar = Bar(height=720, width=1200)
bar.add("蒸发量", attr, v1)
bar.add("降水量", attr, v2, yaxis_formatter=" ml", yaxis_max=250)
line = Line()
line.add("平均温度", attr, v3, yaxis_formatter=" °C")
overlap = Overlap()
overlap.add(bar)
overlap.add(line, yaxis_index=1, is_add_yaxis=True)
page = Page()
page.add(grid)
page.add(timeline)
page.add(overlap)
page.render()
def scatter(bq,output):
page=Page()
page.height=900
c=0
fc=14 #fontsize
if len(bq.keys())>4:
fig=plt.figure(figsize=(24,10))
else:
fig=plt.figure(figsize=(24,5))
#fig.subplots_adjust(wspace=0.5,hspace=0.5)
#iden the fig shape
#2 col situation
if len(bq.keys())%2==0 and len(bq.keys())%3!=0 and len(bq.keys())%4!=0:
all_col=2
elif len(bq.keys())%3==0:
all_col=3
elif len(bq.keys())%4==0:
all_col=4
#iden shape end
if int(len(bq.keys())%all_col)==0:
row=int(len(bq.keys())/all_col)
else:
row=int(len(bq.keys())/all_col)+1
for key1 in bq:
cp=[] #completeness
ct=[] #contamination
a=sorted(bq[key1]['completeness'].items(),key=lambda x:x[1],reverse=True) #sort keys according to their values
#c=0
for e in a:
cp.append(bq[key1]['completeness'][e[0]])
ct.append(bq[key1]['contamination'][e[0]])
c+=1
x=range(1,len(cp)+1)
##### literature figure part #####
#fig.subplots_adjust(wspace=0.3,hspace=0.6)
if max(ct)>100:
ax1=fig.add_subplot(row,all_col,c)
ax1.set_xlabel(key1,color='black',fontsize=fc)
ax1.set_ylabel('Completeness',fontsize=fc+1)
ax1.scatter(x,cp,color='black',label='Completeness')
ax2=ax1.twinx()
ax2.scatter(x,ct,color='red',label='Contamination')
ax2.set_ylabel('Contamination',color='black',fontsize=fc+1)
ax2.tick_params(axis='y',colors='red')
ax2.spines['right'].set_color('red')
if max(ct)%10==0:
max_10_ct=max(ct)
else:
max_10_ct=(10-max(ct)%10)+max(ct)
ax2.axis([min(x),max(x),0,max_10_ct])
ax1.axis([min(x),max(x),0,max_10_ct])
#ax2.axis([min(x),max(x),0,max(cp)])
else:
ax1=fig.add_subplot(row,all_col,c)
ax1.set_xlabel(key1,color='black',fontsize=fc)
ax1.set_ylabel('Completeness',fontsize=fc+1)
ax1.scatter(x,cp,color='black',label='Completeness')
ax2=ax1.twinx()
ax2.scatter(x,ct,color='red',label='Contamination')
ax2.set_ylabel('Contamination',color='black',fontsize=fc+1)
ax2.tick_params(axis='y',colors='red')
ax2.spines['right'].set_color('red')
ax2.axis([min(x),max(x),0,100])
#plt.savefig(output+'/3.scatter.png')
##### literature figure end #####
#x=range(1,len(cp)+1)
#grid=Grid()
#overlap = Overlap()
#scatter = Scatter()
#scatter2 = Scatter(key1)
if c%2==0:
#2
if c%4!=0:
overlap2 = Overlap()
scatter3 = Scatter()
scatter3.add("Completeness",x,cp,yaxis_label_textcolor='red',yaxis_line_color='red',xaxis_type='category',xaxis_max=max(x),legend_pos="40%",legend_orient="vertical")
scatter4 = Scatter(key1,title_pos="25%")
scatter4.add('Contamination',x,ct,xaxis_type='category',xaxis_max=max(x),legend_pos="40%",legend_orient="vertical")
overlap2.add(scatter4)
overlap2.add(scatter3)
#4
else:
overlap4 = Overlap()
scatter7 = Scatter()
scatter7.add("Completeness",x,cp,yaxis_label_textcolor='red',yaxis_line_color='red',xaxis_type='category',xaxis_max=max(x),legend_pos="90%",legend_orient="vertical")
scatter8 = Scatter(key1,title_pos="75%")
scatter8.add('Contamination',x,ct,xaxis_type='category',xaxis_max=max(x),legend_pos="90%",legend_orient="vertical")
overlap4.add(scatter8)
overlap4.add(scatter7)
#overlap2.render(output+'/3.scatter_o2.html')
else:
#1
if (c+1)%4!=0:
overlap = Overlap()
scatter = Scatter()
scatter.add("Completeness",x,cp,yaxis_label_textcolor='red',yaxis_line_color='red',xaxis_type='category',xaxis_max=max(x),legend_pos="15%",legend_orient="vertical")
scatter2 = Scatter(key1)
scatter2.add('Contamination',x,ct,xaxis_type='category',xaxis_max=max(x),legend_pos="15%",legend_orient="vertical")
overlap.add(scatter2)
overlap.add(scatter)
#3
else:
overlap3 = Overlap()
scatter5= Scatter()
scatter5.add("Completeness",x,cp,yaxis_label_textcolor='red',yaxis_line_color='red',xaxis_type='category',xaxis_max=max(x),legend_pos="65%",legend_orient="vertical")
scatter6= Scatter(key1,title_pos="50%")
scatter6.add('Contamination',x,ct,xaxis_type='category',xaxis_max=max(x),legend_pos="65%",legend_orient="vertical")
overlap3.add(scatter6)
overlap3.add(scatter5)
#overlap.render(output+'/3.scatter_o1.html')
'''
if c==len(bq.keys()) and c%2!=0:
grid=Grid()
grid.add(overlap,grid_left="60%")
page.add(grid)
continue
'''
if c%2==0:
#2
if c%4!=0:
grid.add(overlap2,grid_left="30%",grid_width=250)
#4
else:
grid.add(overlap4,grid_left="80%",grid_width=200)
page.add(grid)
#grid.render(output+'/3.scatter.html')
#page.render(output+'/3.scatter.html')
else:
#3
if (c+1)%4==0:
grid.add(overlap3, grid_left="55%",grid_width=250)
#1
else:
grid=Grid()
grid.width=1500
grid.height=300
grid.add(overlap,grid_left="5%",grid_width=250)
#grid.render(output+'/3.scatter.html')
#page.render(output+'/3.scatter.html')
#exit()
if c==len(bq.keys()) and c%4!=0:
page.add(grid)
page.render(output+'/3_scatter.html')
#fig.subplots_adjust(wspace=0.3,hspace=0.3)
#ax1.legend(loc='center', bbox_to_anchor=(-1.3, 3.8),ncol=5,fontsize=20)
fig.subplots_adjust(wspace=0.5,hspace=0.4)
plt.savefig(output+'/3.scatter.png')
def test_scatter_draw_sexy_black_bra():
scatter = Scatter("散点图示例", width=1000, height=480)
v1, v2 = scatter.draw("../images/cup.png")
scatter.add("Cup", v1, v2, label_color=["#000"])
scatter.render()
def test_scatter_xaxis_type():
# xAxis type 'value'
v1 = [10, 20, 30, 40, 50, 60]
v2 = [10, 20, 30, 40, 50, 60]
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2)
assert '"type": "value"' in scatter._repr_html_()
assert '"type": "category"' not in scatter._repr_html_()
scatter.render()
# xAxis type 'category'
scatter = Scatter("散点图示例")
scatter.add("A", ["a", "b", "c", "d", "e", "f"], v2)
scatter.add("B", ["a", "b", "c", "d", "e", "f"],
v1[::-1],
xaxis_type="category")
assert '"type": "category"' in scatter._repr_html_()
scatter.render()
def test_scatter_visualmap_default():
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2, is_visualmap=True)
scatter.render()
def test_scatter_visualmap_default():
scatter = Scatter("散点图示例")
scatter.add("A", v1, v2)
scatter.add("B", v1[::-1], v2, is_visualmap=True)
scatter.render()
def test_scatter_draw_love():
scatter = Scatter("", width=800, height=480)
scatter.draw("../images/love.png")
def test_scatter_draw__hot_red_bra():
scatter = Scatter("散点图示例", width=1000, height=480)
v1, v2 = scatter.draw("../images/cup.png")
scatter.add("Cup", v1, v2)
scatter.render()
def test_scatter_draw__hot_red_bra():
scatter = Scatter("", width=1000, height=480)
scatter.draw("../images/cup.png")
'''
散点图
add
'''
from pyecharts import Scatter
x1 = [20, 13, 43, 53, 34, 89]
y1 = [10, 32, 43, 13, 54, 87]
x2 = [12, 24, 41, 33, 54, 19]
y2 = [13, 39, 31, 43, 24, 37]
scatter = Scatter('散点图')
scatter.add('A', x1, y1)
scatter.add('B',
x2,
y2,
is_visualmap=True,
visual_type='size',
visual_range_size=[10, 80])
scatter.render('a.html')
def test_scatter_draw_pyecharts():
scatter = Scatter("散点图示例")
v1, v2 = scatter.draw("../images/pyecharts-0.png")
scatter.add("pyecharts", v1, v2, is_random=True)
scatter.render()
