report_author = u'冥王星人'
save_file = 'E:/Report/Region_Report_first_version.pdf'
def dataframe2list(dframe):
dictdata = dframe.to_dict('split')
result = dictdata['data']
[result[i].insert(0,dictdata['index'][i]) for i in range(len(result))]
title = [u'变量']
title.extend(dictdata['columns'])
result.insert(0,title)
nrow = len(result)
ncol = len(result[0])
return {'data':result,'ncol':ncol,'nrow':nrow}
# 1. 报告的初始化
region_data = RegionData()
report = Report(title=report_title,author=report_author)
for i in range(len(vars)):
var = vars[i]
restvar = list(vars)
del restvar[i]
# 生成章节
report.createSection(var)
period = region_data.databases['citystatiscs'].period(var)
for year in period:
# 生成分支章节
report.createSubSection(year)
mdata = region_data.query(region=['t'],year=[year],variable=[var])
mdata = mdata['data']
if isinstance(var,str):
var = [var]
for v in var:
if not (self._data[v]>0).all():
return False
return True
# 储存图像
def _save(self,savepath='E:/Report/'):
x = str(int(datetime.now().timestamp()*1000))
filename = savepath + 'graph/' + x + '.pdf'
plt.savefig(filename)
if __name__ == '__main__':
rdata = RegionData()
mdata = rdata.query(region=['t'],year=[2010],variable=[u'地区生产总值',u'年末总人口'],scale=u'全市')
mdata = mdata['data']
csdexplorer = CrossSectionRegionDataExplorer(mdata)
#dframe = csdexplorer.perVar(pop=mdata[u'年末总人口'],var=[u'地区生产总值',u'年末总人口'])
#print(dframe)
'''
dframe = csdexplorer.lgVar()
dframe2 = csdexplorer.describe().applymap(lambda x:'{0:.2f}'.format(x))
print(dframe2)
csdexplorer.hist(var=u'地区生产总值',save=True)
csdexplorer.scatter(y=u'地区生产总值',x=u'年末总人口',kind='kde')
csdexplorer.pair(vars=[u'地区生产总值',u'年末总人口'])'''
csdexplorer.ols(y=u'地区生产总值',x=u'年末总人口')
#print(csdexplorer.corr())
# coding=UTF-8
import matplotlib.pyplot as plt
import seaborn as sns
from application.DataWarehouse.data.class_regiondata import RegionData
from application.DataWarehouse.toolkit.class_crosssectiondataexplorer import CrossSectionRegionDataExplorer
sns.set(style="white", palette="muted", color_codes=True)
# 载入数据
rdata = RegionData()
mdata = rdata.query(region=["t"], year=[2010], variable=[u"地区生产总值", u"年末总人口"], scale=u"全市")
mdata = mdata["data"]
csdexplorer = CrossSectionRegionDataExplorer(mdata)
"""
plt.style.use('ggplot')
mdata = mdata[u'地区生产总值']
mdata.plot(kind='hist')
plt.show()
"""
print(sns.axes_style())
sns.set_style(
"white", {"font.sans-serif": ["Microsoft YaHei", "Arial", "Liberation Sans", "Bitstream Vera Sans", "sans-serif"]}
)
mdata = mdata[u"地区生产总值"]
sns.distplot(mdata, kde=False)
plt.show()