def world_cloud2():
""" 生成职位词云
"""
counter = {}
with open(os.path.join("data", "post_pre_counter.csv"),
"r",
encoding="utf-8") as f:
f_csv = csv.reader(f)
for row in f_csv:
counter[row[0]] = counter.get(row[0], int(row[1]))
# pprint(counter)
x = [0] * 101
y = [0] * 101
i = 0
# tuple(counter)
for c in counter:
x[i] = c
y[i] = counter[c]
i = i + 1
if i > 100:
break
wordcloud = WordCloud(width=1300, height=620)
wordcloud.add("", x, y, word_size_range=[30, 100], shape='diamond')
wordcloud.render('wc.html')
make_a_snapshot('wc.html', os.path.join("images", "wc2.png"))
def drawTwoPie(self, fid, attrExprList, divideExprList, diseaseNameList, dbName,
year, isPercent, complete):
try:
innerLabel = diseaseNameList[0]
outerLabel = diseaseNameList[1]
dataList = []
n = len(diseaseNameList)
for i in range(0, n):
dataNow = self.dbInf.getDiffDistrictData(attrExprList[i], divideExprList[i], diseaseNameList[i],
dbName, "all", year, isPercent, complete)
dataNow = [x[0] for x in dataNow]
data = [x[1] for x in dataNow]
dataList.append(data)
large = 1.3
size = 0.8
pie = Pie("", title_pos='center', width=800 * size, height=480 * size)
pie.add("", outerLabel, dataList[1],
radius=[40 * large, 55 * large], is_label_show=True, legend_pos='left')
pie.add("", innerLabel, dataList[0], radius=[0 * large, 30 * large], legend_orient='vertical',
legend_pos='left', is_label_show=True, label_formatter='{d}%', label_pos='inside')
pie.render()
make_a_snapshot('render.html', fid + '.png')
print("图片生成完成：" + fid)
except Exception as e:
print(traceback.print_exc())
def render_chart_to_file(self,
chart,
object_name="chart",
path="render.png",
template_name="simple_chart.html",
verbose=True,
delay=DEFAULT_DELAY,
pixel_ratio=DEFAULT_PIXEL_RATIO,
**kwargs):
_, extension = os.path.splitext(path)
tmp_file_handle, tmp_file_path = mkstemp(suffix=".html")
super(SnapshotEnvironment,
self).render_chart_to_file(chart=chart,
object_name=object_name,
path=tmp_file_path,
template_name=template_name,
**kwargs)
make_a_snapshot(
tmp_file_path,
path,
delay=delay,
pixel_ratio=pixel_ratio,
verbose=verbose,
)
os.close(tmp_file_handle)
content = None
if extension == ".svg":
with codecs.open(path, "r", "utf-8") as f:
content = f.read()
else:
with open(path, "rb") as f:
content = f.read()
return content
def render_chart_to_file(
self,
chart,
object_name='chart',
path='render.png',
template_name='simple_chart.html',
verbose=True,
delay=DEFAULT_DELAY,
**kwargs):
_, extension = os.path.splitext(path)
tmp_file_handle, tmp_file_path = mkstemp(suffix='.html')
super(SnapshotEnvironment, self).render_chart_to_file(
chart=chart,
object_name=object_name,
path=tmp_file_path,
template_name=template_name,
**kwargs
)
make_a_snapshot(tmp_file_path, path, delay=delay, verbose=verbose)
os.close(tmp_file_handle)
content = None
if extension == '.svg':
with codecs.open(path, 'r', 'utf-8') as f:
content = f.read()
else:
with open(path, 'rb') as f:
content = f.read()
return content
def create_charts(data_path, path_html, path_png, length):
charts = GeoLines("TSP问题：全国34城市为例", '路径：%.3fkm' % (length / 1000),
**style.init_style)
charts.add('', data_path, **style_geo)
charts.render(path_html)
make_a_snapshot(path_html, path_png)
return print('绘图完毕')
def test_win32_shell_flag_is_false(fake_popen):
fake_popen.side_effect = CustomTestException("Enough. Stop testing")
try:
make_a_snapshot(os.path.join("tests", "fixtures", "render.html"),
'sample.png')
except CustomTestException:
eq_(fake_popen.call_args[1]['shell'], False)
def test_make_a_snapshot_real():
# cannot produce a consistent binary matching file
test_output = "real.png"
make_a_snapshot(
os.path.join("tests", "fixtures", "render.html"), test_output
)
assert os.path.exists(test_output) # exists just fine
def test_make_jpeg_snapshot(fake_check, fake_popen):
fake_popen.return_value.stdout = BytesIO(get_base64_image())
test_output = "custom.jpeg"
make_a_snapshot(
os.path.join("tests", "fixtures", "render.html"), test_output
)
assert filecmp.cmp(test_output, get_fixture("sample.jpeg"))
def test_win32_shell_flag(fake_popen):
fake_popen.side_effect = CustomTestException("Enough. Stop testing")
try:
with patch.object(sys, 'platform', 'win32'):
make_a_snapshot(os.path.join("tests", "fixtures", "render.html"),
'sample.png')
except CustomTestException:
eq_(fake_popen.call_args[1]['shell'], True)
def get_mem_data():
base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
performance_data = os.path.join(base_dir, 'data')
image_path = performance_data + "\\result.png"
html_path = "%s\\memory_report.html" % (performance_data)
hfile = ('%s\\memory_data.txt' % (performance_data))
fp = open(hfile, "r")
# fp = open(r'D:\moxiu\youyang\data\xin.txt', 'r')
meminfo_data = fp.readlines()
case_name_list = []
for i in range(len(meminfo_data)):
j = meminfo_data[i].replace('\n', '').split(',')
case_name_list.append(j[0:1][0])
heap_size_list = []
for i in range(len(meminfo_data)):
j = meminfo_data[i].replace('\n', '').split(',')
heap_size_list.append(float(j[1:2][0]))
heap_alloc_list = []
for i in range(len(meminfo_data)):
j = meminfo_data[i].replace('\n', '').split(',')
heap_alloc_list.append(float(j[2:3][0]))
heap_free_list = []
for i in range(len(meminfo_data)):
j = meminfo_data[i].replace('\n', '').split(',')
heap_free_list.append(float(j[3:4][0]))
bar = Line("有样__内存数据图形报表", "图表纵轴为数据大小，横轴为case名称，直线为平均值")
bar.add("heap_size",
case_name_list,
heap_size_list,
label_color=['#B22222'],
mark_line=["average"],
mark_point=["max", "min"],
xaxis_interval=0,
xaxis_rotate=90)
bar.add("heap_alloc",
case_name_list,
heap_alloc_list,
label_color=['#008080'],
mark_line=["average"],
mark_point=["max", "min"],
xaxis_interval=0,
xaxis_rotate=90)
bar.add("heap_free",
case_name_list,
heap_free_list,
label_color=['#483D8B'],
mark_line=["average"],
mark_point=["max", "min"],
xaxis_interval=0,
xaxis_rotate=90)
bar.use_theme("vintage")
base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
performance_data = os.path.join(base_dir, 'data')
bar.render('%s\\memory_report.html' % (performance_data))
make_a_snapshot(html_path, image_path)
im = Image.open(image_path)
out = im.resize((800, 400), Image.ANTIALIAS)
out.save(image_path)
def show(self, class_key: dict, title: str, image_name):
# print(self.show_coordinates)
scatter = Scatter(title=title, background_color='#ffe')
for i in range(0, self.show_coordinates.shape[0]):
point = self.show_coordinates.iloc[i]['point']
# print(point, class_key[point])
coordinates = self.show_coordinates.iloc[i]['vector']
# print(type(coordinates), type(class_key[point]))
scatter.add(class_key[point], [coordinates[0]], [coordinates[1]])
temp_path = 'html/render.html'
scatter.render(path=temp_path)
make_a_snapshot(temp_path, image_name)
def save_picture(name, data, p_path):
if len(data) == 0 or p_path is None:
return
data_value = [x["value"] for x in data]
line = Line(name, background_color='#EAEAEA')
attr = list(range(0, len(data_value)))
line.add("delta",
attr,
data_value,
mark_point=["max", "min"],
mark_line=["average"])
render_file = "{}/{}.html".format(p_path, name)
picture_file = "{}/{}.png".format(p_path, name)
line.render(path=render_file, )
make_a_snapshot(render_file, picture_file)
print("save picture {}.png in {}".format(name, p_path))
def post_salary_counter():
""" 薪酬统计
"""
with open(os.path.join("data", "post_salary.csv"),
"r",
encoding="utf-8") as f:
f_csv = csv.reader(f)
lst = [row[0] for row in f_csv]
counter = Counter(lst).most_common()
#pprint(counter)
x = [0] * len(counter)
y = [0] * len(counter)
i = 0
counter.sort()
for c in counter:
x[i] = float(c[0]) * 10000
y[i] = c[1]
i = i + 1
func = interpolate.interp1d(x, y, kind='cubic')
x = np.arange(x[0] + 50, x[-1] - 50, 10) # 差值平均化，使线条平滑
y = func(x)
i = 0
for xz in y:
if xz < 0:
y[i] = 0
i = i + 1
else:
y[i] = y[i]
i = i + 1
line = Line("")
line.add("",
x,
y,
is_fill=True,
line_opacity=0.2,
area_opacity=0.4,
symbol=None)
line.render('xz.html')
make_a_snapshot('xz.html', os.path.join("images", "money.png"))
with open(os.path.join("data", "post_salary_counter1.csv"),
"w+",
encoding="utf-8",
newline='') as f:
f_csv = csv.writer(f)
f_csv.writerows(counter)
def post_salary_localcounter():
""" 地点统计
"""
with open(os.path.join("data", "post_salary_locate.csv"),
"r",
encoding="utf-8") as f:
f_csv = csv.reader(f)
lst = []
for row in f_csv:
row[2] = row[2].split("-")[0]
lst.append(row[2])
counter = Counter(lst).most_common()
x = [0] * len(counter)
y = [0] * len(counter)
i = 0
counter.sort()
for c in counter:
x[i] = c[0]
y[i] = c[1]
i = i + 1
geo = Geo("",
"",
title_color="#fff",
title_pos="center",
width=800,
height=500,
background_color='#404a59')
geo.add("",
x,
y,
is_visualmap=True,
visual_range=[0, max(y)],
symbol_size=15,
visual_text_color='#fff')
geo.render('dd.html') # 生成html
make_a_snapshot('dd.html', os.path.join("images",
"locate.png")) # 利用快照生成png图片
with open(os.path.join("data", "post_local.csv"),
"w+",
encoding="utf-8",
newline='') as f:
f_csv = csv.writer(f)
f_csv.writerows(counter)
def get_chart_image():
attr = [
"Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct",
"Nov", "Dec"
]
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]
bar = Bar("Bar chart", "precipitation and evaporation one year")
bar.add("precipitation",
attr,
v1,
mark_line=["average"],
mark_point=["max", "min"])
bar.add("evaporation",
attr,
v2,
mark_line=["average"],
mark_point=["max", "min"])
bar.render('test.html')
make_a_snapshot('test.html', 'test.png')
return 'test.png'
from pyecharts import Bar
from pyecharts_snapshot.main import make_a_snapshot
bar = Bar("我的第一个图表", "这里是副标题")
bar.add("服装", ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"], [5, 20, 36, 10, 75, 90])
bar.print_echarts_options()
bar.render()
make_a_snapshot('render.html', 'snapshot.png')
def test_unsupported_file_type():
# cannot produce a consistent binary matching file
test_output = 'real.shady'
make_a_snapshot(os.path.join("tests", "fixtures", "render.html"),
test_output)
def test_make_a_snapshot_real_pdf():
test_output = 'real.pdf'
make_a_snapshot(os.path.join("tests", "fixtures", "render.html"),
test_output)
assert(os.path.exists(test_output)) # exists just fine
def test_make_png_snapshot(fake_check, fake_popen):
fake_popen.return_value.stdout = BytesIO(get_base64_image())
test_output = "custom.png"
make_a_snapshot(get_fixture("render.html"), test_output)
assert filecmp.cmp(test_output, get_fixture("sample.png"))
def mytr(self,year,month):
make_a_snapshot(("db%d.html") % (year * 100 + month),("db%d.png") % (year * 100 + month))
def test_phantomjs_fails(fake_popen):
fake_popen.return_value.stdout = BytesIO('abc')
make_a_snapshot(os.path.join("tests", "fixtures", "render.html"),
'custom.jpeg')
def test_make_png_snapshot(fake_popen):
fake_popen.return_value.stdout = BytesIO(get_base64_image())
test_output = 'custom.png'
make_a_snapshot(os.path.join("tests", "fixtures", "render.html"),
test_output)
assert(filecmp.cmp(test_output, get_fixture('sample.png')))
def mytr(self):
make_a_snapshot("2015_to_2018.html", "2015_to_2018.png")
Python 3.6.3 (v3.6.3:2c5fed8, Oct 3 2017, 17:26:49) [MSC v.1900 32 bit (Intel)] on win32
Type "copyright", "credits" or "license()" for more information.
>>> # Part 2 Draw Pie Chart with Pyecharts
>>> from pyecharts import Pie
>>> from pyecharts_snapshot.main import make_a_snapshot #for creating output in forms of PNG and PDF
>>> attr=["V40","V60","V90","S90","S60","XC40","XC60","XC90","Polestar1"]
>>> v1=[500,200,360,1000,750,300,1200,1800,100]
>>> pie=Pie("MSales")
>>> pie.add("",attr,v1,is_label_show=True)
<pyecharts.charts.pie.Pie object at 0x03178F50>
>>> pie.render()
>>> make_a_snapshot('render.html', 'snapshot.png') # output png
phantomjs version: 2.1.1
Generating file ...
File saved in C:\Users\LylionCj\AppData\Local\Programs\Python\Python36-32\snapshot.png
>>> make_a_snapshot('render.html', 'snapshot.pdf') # output PDF
phantomjs version: 2.1.1
Generating file ...
File saved in C:\Users\LylionCj\AppData\Local\Programs\Python\Python36-32\snapshot.pdf
>>>
from __future__ import unicode_literals
from pyecharts import Bar
from pyecharts_snapshot.main import make_a_snapshot
'''
如果想直接将图片保存为 png, pdf, gif 格式的文件，可以使用 pyecharts-snapshot
pip install pyecharts
保存为图片格式的插件
安装 phantomjs
npm install -g phantomjs-prebuilt
安装 pyecharts-snapshot
pip3 install pyecharts-snapshot
pip3 install pyecharts-snapshot==0.1.7
引入 pyecharts-snapshot
from pyecharts_snapshot.main import make_a_snapshot
调用方法
make_a_snapshot('render.html', 'snapshot.png')
'''
bar = Bar("我的第一个图表", "这里是副标题")
bar.add("服装", ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"], [5, 20, 36, 10, 75, 90])
# bar.print_echarts_options()
bar.render(path='snapshot.html')
bar.render(path='snapshot.png')
bar.render(path='snapshot.pdf')
data_f.append(data[i - 1])
for part in data_f:
data_tmp = []
for i in row:
data_tmp.append(part[i - 1])
data_f_f.append(data_tmp)
if chartid == 0:
pie = Pie("", width=600, height=500)
for part in range(0, len(categerise_f), +1):
pie.add(categerise_f[part],
legend_f,
data_f_f[part],
is_label_show=True)
pie.render()
make_a_snapshot('render.html', "pie.jpeg", 1)
os.remove("render.html")
shutil.copyfile("pie.jpeg", p_path)
os.remove("pie.jpeg")
if chartid == 1:
bar = Bar(title="", width=800, height=400)
for part in range(0, len(categerise_f), +1):
bar.add(categerise_f[part],
legend_f,
data_f_f[part],
is_label_show=True,
xaxis_name=xname,
yaxis_name=yname,
xaxis_name_pos="end",
yaxis_name_pos="end",
line = Line("折线图示例", width = 1200)
attr_line = ["周一", "周二", "周三", "周四", "周五", "周六", "周日"]
data1_line = [11, 11, 15, 13, 12, 13, 10]
data2_line = [1, -2, 2, 5, 3, 2, 0]
line.add("最高气温",
attr_line, data1_line,
mark_point = ["max", "min"],
mark_line = ["average"])
line.add("最低气温",
attr_line, data2_line,
mark_point = ["max", "min"],
mark_line = ["avergae"],
legend_pos = "20%")
# Pie
attr_pie = ["衬衫", "羊毛衫", "雪纺衫", "裤子", "高跟鞋", "袜子"]
data_pie = [11, 12, 13, 10, 10, 10]
pie = Pie("饼图示例", title_pos = "45%")
pie.add("",
attr_pie, data_pie,
radius = [30, 55],
legend_pos = "65%",
legend_orient = "horizonial")
# Grid
grid = Grid()
grid.add(line, grid_right = "65%")
grid.add(pie, grid_left = "60%")
grid.render("/home/wangzhefeng/project/DataVisualiztion/pyecharts/grid_test.html")
make_a_snapshot("grid_test.html", "grid_test.pdf")
result.to_csv(path + 'output/sum.csv', encoding="gbk")
# In[13]:
from pyecharts import Bar, WordCloud
from pyecharts_snapshot.main import make_a_snapshot
# In[14]:
n = result[result['count'] > 4000]['n'].tolist()
count = result[result['count'] > 4000]['count'].tolist()
bar1 = Bar('名词排序')
bar1.add("", n, count, is_convert=True)
bar1.render('bar1.html')
make_a_snapshot('bar1.html', path + '/output/bar1.png')
bar1
# In[15]:
n = result[result['count'] > 30]['n'].tolist()
count = result[result['count'] > 30]['count'].tolist()
cloud = WordCloud("词云")
cloud = WordCloud(width=900, height=600)
cloud.add('名词词云', n, count, word_size_range=[20, 150], shape='star')
cloud.render('cloud.html')
make_a_snapshot('cloud.html', path + '/output/cloud.png')
cloud
def mytr(self, year, top):
make_a_snapshot("wc%d.html" % (year * 100 + top),
("wc%d.png" % (year * 100 + top)))
def chart(self):
bar = Bar("ebooking")
bar.add("60客户", self.percent, self.sortList, is_stack=True)
bar.render()
make_a_snapshot('render.html', './pic/%s.png' % self.name)
