def test_get_text(self):
r = StrictRedis()
r.set('test_get_2', "Open Mining")
DW = DataWarehouse()
self.assertEquals(
DW.get("test_get_2", content_type='application/text'),
"Open Mining")
def append(self):
self.data = DataFrame({})
DW = DataWarehouse()
self.data.append([DataFrame(
DW.get(rel['cube']).get('data'))
for rel in self.cube.get('relationship')],
ignore_index=True)
return self.data
def left(self):
fields = [rel['field'] for rel in self.cube.get('relationship')]
self.data = DataFrame({fields[0]: []})
DW = DataWarehouse()
for rel in self.cube.get('relationship'):
data = DW.get(rel['cube'])
self.data = self.data.merge(DataFrame(data.get('data')),
how='outer', on=fields[0])
return self.data
def append(self):
self.data = DataFrame({})
DW = DataWarehouse()
self.data.append([
DataFrame(DW.get(rel['cube']).get('data'))
for rel in self.cube.get('relationship')
],
ignore_index=True)
return self.data
def left(self):
fields = [rel['field'] for rel in self.cube.get('relationship')]
self.data = DataFrame({fields[0]: []})
DW = DataWarehouse()
for rel in self.cube.get('relationship'):
data = DW.get(rel['cube'])
self.data = self.data.merge(DataFrame(data.get('data')),
how='outer',
on=fields[0])
return self.data
def inner(self):
fields = [rel['field'] for rel in self.cube.get('relationship')]
DW = DataWarehouse()
for i, rel in enumerate(self.cube.get('relationship')):
data = DW.get(rel['cube']).get('data')
df = DataFrame(data)
if i == 0:
self.data = df
else:
self.data = self.data.merge(df, how='inner', on=fields[0])
return self.data
def inner(self):
fields = [rel['field'] for rel in self.cube.get('relationship')]
DW = DataWarehouse()
for i, rel in enumerate(self.cube.get('relationship')):
data = DW.get(rel['cube']).get('data')
df = DataFrame(data)
if i == 0:
self.data = df
else:
self.data = self.data.merge(df, how='inner', on=fields[0])
return self.data
def save(self):
log_it("SAVE DATA (JSON) ON DATA WAREHOUSE: {}".format(self.slug),
"bin-mining")
data = {'data': self.pdict, 'columns': self.keys}
DW = DataWarehouse()
DW.save(self.slug, data)
self.cube['status'] = True
self.cube['lastupdate'] = datetime.now()
self.cube['run'] = True
self.mongo['cube'].update({'slug': self.cube['slug']}, self.cube)
log_it("CLEAN MEMORY: {}".format(self.slug), "bin-mining")
gc.collect()
def save(self):
log_it("SAVE DATA (JSON) ON DATA WAREHOUSE: {}".format(self.slug),
"bin-mining")
data = {'data': self.pdict, 'columns': self.keys}
DW = DataWarehouse()
DW.save(self.slug, data)
self.cube['status'] = True
self.cube['lastupdate'] = datetime.now()
self.cube['run'] = True
self.mongo['cube'].update({'slug': self.cube['slug']}, self.cube)
log_it("CLEAN MEMORY: {}".format(self.slug), "bin-mining")
gc.collect()
def data(mongodb, slug, ext='xls'):
DW = DataWarehouse()
element = mongodb['element'].find_one({'slug': slug})
element['page_limit'] = 50
if request.GET.get('limit', True) is False:
element['page_limit'] = 9999999999
data = DW.get(element.get('cube'))
columns = data.get('columns') or []
fields = columns
if request.GET.get('fields', None):
fields = request.GET.get('fields').split(',')
filters = [i[0] for i in request.GET.iteritems()
if len(i[0].split('filter__')) > 1]
df = DataFrame(data.get('data') or {}, columns=fields)
if len(filters) >= 1:
for f in filters:
s = f.split('__')
field = s[1]
operator = s[2]
value = request.GET.get(f)
if operator == 'like':
df = df[df[field].str.contains(value)]
elif operator == 'regex':
df = DataFrameSearchColumn(df, field, value, operator)
else:
df = df.query(df_generate(df, value, f))
groupby = []
if request.GET.get('groupby', None):
groupby = request.GET.get('groupby', "").split(',')
if len(groupby) >= 1:
df = DataFrame(df.groupby(groupby).grouper.get_group_levels())
if request.GET.get('orderby',
element.get('orderby', None)) and request.GET.get(
'orderby', element.get('orderby', None)) in fields:
orderby = request.GET.get('orderby', element.get('orderby', ''))
if type(orderby) == str:
orderby = orderby.split(',')
orderby__order = request.GET.get('orderby__order',
element.get('orderby__order', ''))
if type(orderby__order) == str:
orderby__order = orderby__order.split(',')
ind = 0
for orde in orderby__order:
if orde == '0':
orderby__order[ind] = False
else:
orderby__order[ind] = True
ind += 1
df = df.sort(orderby, ascending=orderby__order)
# CLEAN MEMORY
del filters, fields, columns
gc.collect()
file_name = '{}/assets/exports/openmining-{}.{}'.format(
PROJECT_PATH, element.get('cube'), ext)
if ext == 'csv':
df.to_csv(file_name, sep=";")
contenttype = 'text/csv'
else:
df.to_excel(file_name)
contenttype = 'application/vnd.ms-excel'
response.set_header('charset', 'utf-8')
response.set_header('Content-disposition', 'attachment; '
'filename={}.{}'.format(element.get('cube'), ext))
response.content_type = contenttype
ifile = open(file_name, "r")
o = ifile.read()
ifile.close()
return o
def test_get_application_json(self):
r = StrictRedis()
data = {"id": 1, "name": "Open Mining"}
r.set('test_get_1', json.dumps(data))
DW = DataWarehouse()
self.assertEquals(DW.get("test_get_1"), data)
def test_save_text(self):
DW = DataWarehouse()
DW.save('test_2', "Open Mining", content_type='application/text')
r = StrictRedis()
self.assertEquals(r.get('test_2'), "Open Mining")
def test_save_application_json(self):
DW = DataWarehouse()
DW.save('test_1', {"id": 1, "name": "Open Mining"})
r = StrictRedis()
self.assertEquals(r.get('test_1'), '{"id": 1, "name": "Open Mining"}')
def test_connection(self):
DW = DataWarehouse()
self.assertTrue(isinstance(DW.conn(), StrictRedis))
def data(mongodb, slug, ext='xls'):
DW = DataWarehouse()
element = mongodb['element'].find_one({'slug': slug})
element['page_limit'] = 50
if request.GET.get('limit', True) is False:
element['page_limit'] = 9999999999
data = DW.get(element.get('cube'))
columns = data.get('columns') or []
fields = columns
if request.GET.get('fields', None):
fields = request.GET.get('fields').split(',')
filters = [
i[0] for i in request.GET.iteritems()
if len(i[0].split('filter__')) > 1
]
df = DataFrame(data.get('data') or {}, columns=fields)
if len(filters) >= 1:
for f in filters:
s = f.split('__')
field = s[1]
operator = s[2]
value = request.GET.get(f)
if operator == 'like':
df = df[df[field].str.contains(value)]
elif operator == 'regex':
df = DataFrameSearchColumn(df, field, value, operator)
else:
df = df.query(df_generate(df, value, f))
groupby = []
if request.GET.get('groupby', None):
groupby = request.GET.get('groupby', ).split(',')
if len(groupby) >= 1:
df = DataFrame(df.groupby(groupby).grouper.get_group_levels())
if request.GET.get('orderby',
element.get('orderby', None)) and request.GET.get(
'orderby', element.get('orderby', None)) in fields:
orderby = request.GET.get('orderby', element.get('orderby', ''))
if type(orderby) == str:
orderby = orderby.split(',')
orderby__order = request.GET.get('orderby__order',
element.get('orderby__order', ''))
if type(orderby__order) == str:
orderby__order = orderby__order.split(',')
ind = 0
for orde in orderby__order:
if orde == '0':
orderby__order[ind] = False
else:
orderby__order[ind] = True
ind += 1
df = df.sort(orderby, ascending=orderby__order)
# CLEAN MEMORY
del filters, fields, columns
gc.collect()
file_name = '{}/assets/exports/openmining-{}.{}'.format(
PROJECT_PATH, element.get('cube'), ext)
if ext == 'csv':
df.to_csv(file_name, sep=";")
contenttype = 'text/csv'
else:
df.to_excel(file_name)
contenttype = 'application/vnd.ms-excel'
response.set_header('charset', 'utf-8')
response.set_header(
'Content-disposition', 'attachment; '
'filename={}.{}'.format(element.get('cube'), ext))
response.content_type = contenttype
ifile = open(file_name, "r")
o = ifile.read()
ifile.close()
return o
def data(ws, mongodb, slug):
if not ws:
abort(400, 'Expected WebSocket request.')
DW = DataWarehouse()
element = mongodb['element'].find_one({'slug': slug})
element['page_limit'] = 50
if request.GET.get('limit', True) is False:
element['page_limit'] = 9999999999
data = DW.get(element.get('cube'))
columns = data.get('columns') or []
fields = columns
if request.GET.get('fields', None):
fields = request.GET.get('fields').split(',')
cube_last_update = mongodb['cube'].find_one({'slug': element.get('cube')})
ws.send(json.dumps({'type': 'last_update',
'data': str(cube_last_update.get('lastupdate', ''))}))
ws.send(json.dumps({'type': 'columns', 'data': fields}))
filters = [i[0] for i in request.GET.iteritems()
if len(i[0].split('filter__')) > 1]
if element['type'] == 'grid':
page = int(request.GET.get('page', 1))
page_start = 0
page_end = element['page_limit']
if page >= 2:
page_end = element['page_limit'] * page
page_start = page_end - element['page_limit']
else:
page_start = None
page_end = None
df = DataFrame(data.get('data') or {}, columns=fields)
if len(filters) >= 1:
for f in filters:
s = f.split('__')
field = s[1]
operator = s[2]
value = request.GET.get(f)
if operator == 'like':
df = df[df[field].str.contains(value)]
elif operator == 'regex':
df = DataFrameSearchColumn(df, field, value, operator)
else:
df = df.query(df_generate(df, value, f))
groupby = []
if request.GET.get('groupby', None):
groupby = request.GET.get('groupby', ).split(',')
if len(groupby) >= 1:
df = DataFrame(df.groupby(groupby).grouper.get_group_levels())
if request.GET.get('orderby',
element.get('orderby', None)) and request.GET.get(
'orderby', element.get('orderby', None)) in fields:
orderby = request.GET.get('orderby', element.get('orderby', ''))
if type(orderby) == str:
orderby = orderby.split(',')
orderby__order = request.GET.get('orderby__order',
element.get('orderby__order', ''))
if type(orderby__order) == str:
orderby__order = orderby__order.split(',')
ind = 0
for orde in orderby__order:
if orde == '0':
orderby__order[ind] = False
else:
orderby__order[ind] = True
ind += 1
df = df.sort(orderby, ascending=orderby__order)
ws.send(json.dumps({'type': 'max_page', 'data': len(df)}))
# CLEAN MEMORY
del filters, fields, columns
gc.collect()
categories = []
for i in df.to_dict(outtype='records')[page_start:page_end]:
if element.get('categories', None):
categories.append(i[element.get('categories')])
ws.send(json.dumps({'type': 'data', 'data': i}))
# CLEAN MEMORY
del df
gc.collect()
ws.send(json.dumps({'type': 'categories', 'data': categories}))
ws.send(json.dumps({'type': 'close'}))
# CLEAN MEMORY
del categories
gc.collect()
def data(mongodb, slug, ext="xls"):
DW = DataWarehouse()
element = mongodb["element"].find_one({"slug": slug})
element["page_limit"] = 50
if request.GET.get("limit", True) is False:
element["page_limit"] = 9999999999
data = DW.get(element.get("cube"))
columns = data.get("columns") or []
fields = columns
if request.GET.get("fields", None):
fields = request.GET.get("fields").split(",")
filters = [i[0] for i in request.GET.iteritems() if len(i[0].split("filter__")) > 1]
df = DataFrame(data.get("data") or {}, columns=fields)
if len(filters) >= 1:
for f in filters:
s = f.split("__")
field = s[1]
operator = s[2]
value = request.GET.get(f)
if operator == "like":
df = df[df[field].str.contains(value)]
elif operator == "regex":
df = DataFrameSearchColumn(df, field, value, operator)
else:
df = df.query(df_generate(df, value, f))
groupby = []
if request.GET.get("groupby", None):
groupby = request.GET.get("groupby").split(",")
if len(groupby) >= 1:
df = DataFrame(df.groupby(groupby).grouper.get_group_levels())
if (
request.GET.get("orderby", element.get("orderby", None))
and request.GET.get("orderby", element.get("orderby", None)) in fields
):
orderby = request.GET.get("orderby", element.get("orderby", ""))
if type(orderby) == str:
orderby = orderby.split(",")
orderby__order = request.GET.get("orderby__order", element.get("orderby__order", ""))
if type(orderby__order) == str:
orderby__order = orderby__order.split(",")
ind = 0
for orde in orderby__order:
if orde == "0":
orderby__order[ind] = False
else:
orderby__order[ind] = True
ind += 1
df = df.sort(orderby, ascending=orderby__order)
# CLEAN MEMORY
del filters, fields, columns
gc.collect()
file_name = "{}/assets/exports/openmining-{}.{}".format(PROJECT_PATH, element.get("cube"), ext)
if ext == "csv":
df.to_csv(file_name, sep=";")
contenttype = "text/csv"
else:
df.to_excel(file_name)
contenttype = "application/vnd.ms-excel"
response.set_header("charset", "utf-8")
response.set_header("Content-disposition", "attachment; " "filename={}.{}".format(element.get("cube"), ext))
response.content_type = contenttype
ifile = open(file_name, "r")
o = ifile.read()
ifile.close()
return o
def element_cube(mongodb, slug=None):
DW = DataWarehouse()
data = DW.get(slug)
columns = data.get("columns") or []
return {'columns': columns}
