def write_table(data_frame,
table_name,
sep=',',
iotype='fs',
remove_tmpfile=True):
if iotype == 'fs':
data_frame.to_csv(nnenv.getResourcePath() + nnenv.getItem(table_name),
sep=sep,
index=False)
elif iotype == 'db':
##initlize data engine
engine = create_engine(nnenv.getConnectable())
##write data frame to csv tmp file
path_tmp_file = nnenv.getItem('tmp_dir') + '/' + nnenv.getItem(
table_name)
data_frame.to_csv(path_tmp_file, index=False, header=False)
##connect database
conn = engine.connect()
##initilize hive_sql
hive_sql_ = 'LOAD DATA LOCAL INPATH \'' + path_tmp_file + '\' OVERWRITE INTO TABLE ' + nnenv.getItem(
table_name)
##execute hive_sql
result = conn.execute(hive_sql_)
result.close()
else:
print('IOtype is only for db or fs')
raise (Exception)
def main():
# pre-define path & variables
corpus_raw = nn.Dataframefactory('labeledContent',sep = '|',iotype='db',con=nnenv.getItem('mysql_url'))
vector = "vectorizer.joblib"
matrix = "tfidf.npy"
outpath = nnenv.getResourcePath()
# load dict and stopwords
createDictStop()
# load corpus/
corpus = combineTitleAndContent(corpus_raw)
# save content_id mapping
content_id_mapping = corpus[["content_id"]]
content_id_mapping.index.name = 'index'
content_id_mapping.to_csv(outpath + nnenv.getItem('content_id_mapping'))
# transform corpus to right format
corpus["corpus"] = corpus["all"].apply(segment)
#create tfidf-matrix and vectorizer
tfidfMatrix, vectorizer = createTfidfMatrix(corpus)
#save esstenial files
with open(outpath + vector, 'wb') as f:
joblib.dump(vectorizer, f)
np.save(outpath + matrix, tfidfMatrix)
print("new tfidf_matrix and vectorizer have been saved into {""}".format(outpath))
def Dataframefactory(table_name, sep=',', iotype='fs'):
##directly return Pandas dataframe
if iotype == 'fs':
return (pd.read_csv(nnenv.getResourcePath() +
nnenv.getItem(table_name),
sep=sep))
if iotype == 'db':
return (pd.read_sql_table(table_name=nnenv.getItem(table_name),
con=nnenv.getConnectable()))
else:
print('IOtype is only for db or fs')
raise (Exception)
def Dataframefactory(table_name,
sep=',',
iotype='fs',
con=nnenv.getConnectable()):
##directly return Pandas dataframe
if iotype == 'fs':
return (pd.read_csv(nnenv.getResourcePath() +
nnenv.getItem(table_name),
sep=sep,
engine='python'))
if iotype == 'db':
return (pd.read_sql_table(table_name=nnenv.getItem(table_name),
con=con))
def Joblibfactory(vectorizer):
return (joblib.load(nnenv.getResourcePath() + vectorizer))
def Numpyarrayfactory(np_name):
return (np.load(nnenv.getResourcePath() + np_name))
