bug fix: volume of data

This commit is contained in:
Steve Nyemba 2020-04-13 01:30:59 -05:00
parent 65a1fadfca
commit 310d599d06
2 changed files with 8 additions and 1 deletions

View File

@ -593,7 +593,7 @@ class Predict(GNet):
# #
# df = pd.DataFrame(np.round(f)).astype(np.int32) # df = pd.DataFrame(np.round(f)).astype(np.int32)
df = pd.DataFrame(np.round(f),dtype=np.int32) df = pd.DataFrame(np.round(f),dtype=int)
p = 0 not in df.sum(axis=1).values p = 0 not in df.sum(axis=1).values
x = df.sum(axis=1).values x = df.sum(axis=1).values

View File

@ -164,6 +164,13 @@ class Components :
# df = reader() # df = reader()
df = args['reader']() if 'reader' in args else args['data'] df = args['reader']() if 'reader' in args else args['data']
if 'slice' in args and 'max_rows' in args['slice']:
max_rows = args['slice']['max_rows']
if df.shape[0] > max_rows :
print (".. slicing ")
i = np.random.choice(df.shape[0],max_rows,replace=False)
df = df.iloc[i]
# bounds = Components.split(df,MAX_ROWS,PART_SIZE) # bounds = Components.split(df,MAX_ROWS,PART_SIZE)
# if partition != '' : # if partition != '' :