|
|
|
@ -236,8 +236,10 @@ class Components :
|
|
|
|
# We need to remove the continuous columns from the data-frame
|
|
|
|
# We need to remove the continuous columns from the data-frame
|
|
|
|
# @TODO: Abstract this !!
|
|
|
|
# @TODO: Abstract this !!
|
|
|
|
#
|
|
|
|
#
|
|
|
|
|
|
|
|
real_df = pd.DataFrame()
|
|
|
|
if x_cols :
|
|
|
|
if x_cols :
|
|
|
|
args['data'] = args['data'][list(set(args['data'].columns) - set(x_cols))]
|
|
|
|
args['data'] = args['data'][list(set(args['data'].columns) - set(x_cols))]
|
|
|
|
|
|
|
|
real_df = args[x_cols].copy()
|
|
|
|
|
|
|
|
|
|
|
|
args['candidates'] = 1 if 'candidates' not in args else int(args['candidates'])
|
|
|
|
args['candidates'] = 1 if 'candidates' not in args else int(args['candidates'])
|
|
|
|
if 'gpu' in args :
|
|
|
|
if 'gpu' in args :
|
|
|
|
@ -276,7 +278,7 @@ class Components :
|
|
|
|
_df = _df[list(set(_df.columns) - set(skip_columns))]
|
|
|
|
_df = _df[list(set(_df.columns) - set(skip_columns))]
|
|
|
|
if x_cols :
|
|
|
|
if x_cols :
|
|
|
|
for _col in x_cols :
|
|
|
|
for _col in x_cols :
|
|
|
|
if df[_col].unique().size > 0 :
|
|
|
|
if real_df[_col].unique().size > 0 :
|
|
|
|
_df[_col] = self.approximate(df[_col].fillna(-1))
|
|
|
|
_df[_col] = self.approximate(df[_col].fillna(-1))
|
|
|
|
else:
|
|
|
|
else:
|
|
|
|
_df[_col] = -1
|
|
|
|
_df[_col] = -1
|
|
|
|
@ -289,6 +291,7 @@ class Components :
|
|
|
|
# Let us merge the dataset here and and have a comprehensive dataset
|
|
|
|
# Let us merge the dataset here and and have a comprehensive dataset
|
|
|
|
|
|
|
|
|
|
|
|
_df = pd.DataFrame.join(df,_df)
|
|
|
|
_df = pd.DataFrame.join(df,_df)
|
|
|
|
|
|
|
|
|
|
|
|
if _schema :
|
|
|
|
if _schema :
|
|
|
|
for _item in _schema :
|
|
|
|
for _item in _schema :
|
|
|
|
if _item['type'] in ['DATE','TIMESTAMP','DATETIME'] :
|
|
|
|
if _item['type'] in ['DATE','TIMESTAMP','DATETIME'] :
|
|
|
|
|
