def read_csv(path,
engine='python',
delimiter=',',
na_filter=False,
strip_col=False,
quoting=3,
encoding='utf-8'):
if quoting == True:
quoting = 0
elif quoting == False:
quoting = 3
dir_data = os.getcwd() + '/data'
path = os.path.join(dir_data, path)
res = pd.DataFrame()
if os.path.isfile(path):
res = table_reader.read_csv(path, engine, delimiter, na_filter,
strip_col, quoting, encoding)
elif os.path.isdir(path):
for f in os.listdir(path):
if f.endswith('.csv'):
f_path = os.path.join(path, f)
try:
tmp = table_reader.read_csv(f_path, engine, delimiter,
na_filter, strip_col, quoting,
encoding)
except:
raise BFE.from_errors([{
'0100':
'Can not read ' + f_path + '.'
}])
if res.shape != (0, 0) and not res.columns.equals(tmp.columns):
raise BFE.from_errors([{
'0100':
'Files under ' + path + ' do not have same schema.'
}])
res = pd.concat([res, tmp])
else:
raise BFE.from_errors([{'0100': 'Path ' + path + ' is incorrect.'}])
for i, col in enumerate(res.columns):
res = res.rename(
columns={'Unnamed: {i}'.format(i=i): 'Unnamed_{i}'.format(i=i)})
return {'table': res}
def read_csv(
path,
delimiter=',',
na_filter=False,
strip_col=False,
):
dir_data = os.getcwd() + '/data'
path = os.path.join(dir_data, path)
return {
'table': table_reader.read_csv(path, delimiter, na_filter, strip_col)
}
def read_csv(path,
engine='python',
delimiter=',',
na_filter=False,
strip_col=False,
quoting=3,
encoding='utf-8'):
if quoting == True:
quoting = 0
elif quoting == False:
quoting = 3
dir_data = os.getcwd() + '/data'
path = os.path.join(dir_data, path)
return {
'table':
table_reader.read_csv(path, engine, delimiter, na_filter, strip_col,
quoting, encoding)
}
def read_csv(path):
return {'table': table_reader.read_csv(path)}