bug fix ...

data/maker/__init__.py

@@ -24,24 +24,25 @@ class ContinuousToDiscrete :
         # BOUNDS = np.repeat(np.divide(X.max(),n),n).cumsum().tolist()
         # print ( X.values.astype(np.float32))
         # print ("___________________________")
-        values = X.values.astype(np.float32)
+        values = np.array(X).astype(np.float32)
         BOUNDS = ContinuousToDiscrete.bounds(values,n)
         # _map = [{"index":BOUNDS.index(i),"ubound":i} for i in BOUNDS]
         _matrix = []
         m = []
         for value in X :
             x_ = np.zeros(n)
-            _matrix.append(x_)
+            
             for row in BOUNDS :
             
                 if value>= row.left and value <= row.right :
                     index = BOUNDS.index(row)
                     x_[index]  = 1
                     break
+            _matrix += x_.tolist()
         #
         # for items in BOUNDS :
         #   index = BOUNDS.index(items)
-        return np.array(_matrix)
+        return np.array(_matrix).reshape(len(X),n)
     
     @staticmethod
     def bounds(x,n):
@@ -92,7 +93,7 @@ def train (**args) :
     :context    label of what we are synthesizing
     """
     column      = args['column'] if (isinstance(args['column'],list)) else [args['column']]
-    CONTINUOUS  = args['continuous'] if 'continuous' in args else []
+    # CONTINUOUS  = args['continuous'] if 'continuous' in args else []
     # column_id   = args['id']
     df          = args['data'] if not isinstance(args['data'],str) else pd.read_csv(args['data'])
     df.columns = [name.lower() for name in df.columns]
@@ -109,15 +110,16 @@ def train (**args) :
         # args['real']        = pd.get_dummies(df[col].fillna('')).astype(np.float32).values 
         # if 'float' not in df[col].dtypes.name :
             # args['real']        = pd.get_dummies(df[col].fillna('')).astype(np.float32).values 
-        if col in CONTINUOUS:
-            BIN_SIZE = 4 if 'bin_size' not in args else int(args['bin_size'])
-            args['real']    = ContinuousToDiscrete.binary(df[col],BIN_SIZE).astype(np.float32)
-            # print ( pd.DataFrame(args['real']).head() ) 
-        else:
+        # if col in CONTINUOUS:
+        #     BIN_SIZE = 4 if 'bin_size' not in args else int(args['bin_size'])
+        #     args['real']    = ContinuousToDiscrete.binary(df[col],BIN_SIZE).astype(np.float32)
+        #     # args['real'] = args['real'].reshape(df.shape[0],BIN_SIZE)
+            
+        # else:
             # df.to_csv('tmp-'+args['logs'].replace('/','_')+'-'+col+'.csv',index=False)
             # print (df[col].dtypes)
             # print (df[col].dropna/(axis=1).unique())
-            args['real']  = pd.get_dummies(df[col].dropna()).astype(np.float32).values
+        args['real']  = pd.get_dummies(df[col].dropna()).astype(np.float32).values
 
             
         
@@ -170,6 +172,7 @@ def generate(**args):
     #@TODO:
     #   If the identifier is not present, we should fine a way to determine or make one
     #
+    BIN_SIZE    = 4 if 'bin_size' not in args else int(args['bin_size'])
     _df     = df.copy()
     for col in column :
         args['context'] = col
@@ -181,10 +184,15 @@ def generate(**args):
         #     BIN_SIZE = 4 if 'bin_size' not in args else int(args['bin_size'])
         #     values = ContinuousToDiscrete.continuous(df[col].values,BIN_SIZE)
         #     # values = np.unique(values).tolist()
+        # else:
+        # if col in CONTINUOUS :
+        #     values = ContinuousToDiscrete.binary(df[col],BIN_SIZE).astype(np.float32).T
+            
         # else:
         values          = df[col].dropna().unique().tolist()
         
         
+        
         args['values']      = values    
         args['row_count']   = df.shape[0]
         #
@@ -192,10 +200,9 @@ def generate(**args):
         handler     = gan.Predict (**args)
         handler.load_meta(col)
         r           =  handler.apply()                
-        BIN_SIZE    = 4 if 'bin_size' not in args else int(args['bin_size'])
         
-        # _df[col]    = ContinuousToDiscrete.continuous(r[col],BIN_SIZE) if col in CONTINUOUS else r[col]
-        _df[col]    = r[col]
+        _df[col]    = ContinuousToDiscrete.continuous(r[col],BIN_SIZE) if col in CONTINUOUS else r[col]
+        # _df[col]    = r[col]
         #
         # @TODO: log basic stats about the synthetic attribute
         #