aou/data-maker
aou
/
data-maker
1
1
Fork 0
Code Issues 4 Pull Requests Packages Projects 1 Releases Wiki Activity

bug fix: uploading data

This commit is contained in:
Steve Nyemba 2022-05-17 18:04:05 -05:00
parent 1dae4ffba8
commit 377e84daea
1 changed files with 45 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
data/maker/__init__.py
View File

@ -96,6 +96,7 @@ class Learner(Process):
#
# Below is a source of inefficiency, unfortunately python's type inference doesn't work well in certain cases
# - The code below tries to address the issue (Perhaps better suited for the reading components)
_log = {}
for name in columns :
_index = np.random.choice(np.arange(self._df[name].size),5,False)
no_value = [type(value) in [int,float,np.int64,np.int32,np.float32,np.float64] for value in self._df[name].values[_index]]
@ -103,7 +104,9 @@ class Learner(Process):
self._df[name] = self._df[name].fillna(no_value)
_log[name] = self._df[name].dtypes.name
_log = {'action':'structure','input':_log}
self.log(**_log)
#
# convert the data to binary here ...
_schema = self.get_schema()
@ -293,46 +296,52 @@ class Generator (Learner):
name = _item['name']
if _item['type'].upper() in ['DATE','DATETIME','TIMESTAMP'] :
FORMAT = '%Y-%m-%d'
FORMAT = '%m-%d-%Y'
try:
#
#-- Sometimes data isn't all it's meant to be
SIZE = -1
if 'format' in self.info and name in self.info['format'] :
FORMAT = self.info['format'][name]
SIZE = 10
elif _item['type'] in ['DATETIME','TIMESTAMP'] :
FORMAT = '%Y-%m-%d %H:%M:%S'
SIZE = 19
# try:
# #
# #-- Sometimes data isn't all it's meant to be
# SIZE = -1
# if 'format' in self.info and name in self.info['format'] :
# FORMAT = self.info['format'][name]
# SIZE = 10
# elif _item['type'] in ['DATETIME','TIMESTAMP'] :
# FORMAT = '%m-%d-%Y %H:%M:%S'
# SIZE = 19
if SIZE > 0 :
# if SIZE > 0 :
values = pd.to_datetime(_df[name], format=FORMAT).astype(str)
_df[name] = [_date[:SIZE] for _date in values]
# values = pd.to_datetime(_df[name], format=FORMAT).astype(str)
# _df[name] = [_date[:SIZE].strip() for _date in values]
r[name] = FORMAT
# _df[name] = pd.to_datetime(_df[name], format=FORMAT) #.astype('datetime64[ns]')
if _item['type'] in ['DATETIME','TIMESTAMP']:
pass #;_df[name] = _df[name].fillna('').astype('datetime64[ns]')
# # _df[name] = _df[name].astype(str)
# r[name] = FORMAT
# # _df[name] = pd.to_datetime(_df[name], format=FORMAT) #.astype('datetime64[ns]')
# if _item['type'] in ['DATETIME','TIMESTAMP']:
# pass #;_df[name] = _df[name].fillna('').astype('datetime64[ns]')
except Exception as e:
pass
finally:
pass
# except Exception as e:
# pass
# finally:
# pass
else:
#
# Because types are inferred on the basis of the sample being processed they can sometimes be wrong
# To help disambiguate we add the schema information
_type = None
if 'int' in _df[name].dtypes.name or 'int' in _item['type'].lower():
_type = np.int
elif 'float' in _df[name].dtypes.name or 'float' in _item['type'].lower():
_type = np.float
if _type :
_df[name] = _df[name].fillna(0).replace('',0).astype(_type)
_df[name] = _df[name].fillna(0).replace('',0).replace('NA',0).replace('nan',0).astype(_type)
# else:
# _df[name] = _df[name].astype(str)
# _df = _df.replace('NaT','').replace('NA','')
if r :
@ -373,10 +382,19 @@ class Generator (Learner):
_schema = self.get_schema()
_schema = [{'name':_item.name,'type':_item.field_type} for _item in _schema]
_df = self.format(_df,_schema)
_log = [{"name":_schema[i]['name'],"dataframe":_df[_df.columns[i]].dtypes.name,"schema":_schema[i]['type']} for i in np.arange(len(_schema)) ]
self.log(**{"action":"consolidate","input":_log})
# w = transport.factory.instance(doc='observation',provider='mongodb',context='write',db='IOV01_LOGS',auth_file='/home/steve/dev/transport/mongo.json')
# w.write(_df)
# print (_df[cols])
writer = transport.factory.instance(**_store)
writer.write(_df,schema=_schema)
# _df.to_csv('foo.csv')
self.log(**{'action':'write','input':{'rows':N,'candidates':len(_candidates)}})
class Shuffle(Generator):