if __name__ == '__main__':
inputfile = r'E:\all1.csv'
reader = pd.read_csv(inputfile,encoding='gb2312',iterator=True)
chunkSize = 100000
chunks = []
while True:
try:
chunk = reader.get_chunk(chunkSize)
chunks.append(chunk)
except StopIteration:
print ("Iteration is stopped.")
break
data = pd.concat(chunks,ignore_index=True)
df1 = data.iloc[:,3:11]
df2 = data.iloc[:,14:23]
frames = [df1, df2]
x = pd.concat(frames,axis=1)
y = data.iloc[:,23]
features_train, features_test, labels_train, labels_test = train_test_split(x, y, test_size=0.2, random_state=0)
oversampler = SMOTE(random_state=0)
os_features,os_labels = oversampler.fit_sample(features_train, labels_train)
print (len(os_labels[os_labels==1]))
", line 25, in <module>
data = pd.concat(chunks,ignore_index=True)
File "C:\Anaconda3\lib\site-packages\pandas\tools\merge.py
", line 846, in concat
return op.get_result()
File "C:\Anaconda3\lib\site-packages\pandas\tools\merge.py
", line 1038, in get_result
copy=self.copy)
File "C:\Anaconda3\lib\site-packages\pandas\core\internals.py
", line 4545, in concatenate_block_managers
for placement, join_units in concat_plan]
File "C:\Anaconda3\lib\site-packages\pandas\core\internals.py
", line 4545, in <listcomp>
for placement, join_units in concat_plan]
File "C:\Anaconda3\lib\site-packages\pandas\core\internals.py
", line 4650, in concatenate_join_units
concat_values = _concat._concat_compat(to_concat, axis=concat_axis)
File "C:\Anaconda3\lib\site-packages\pandas\types\concat.py
", line 144, in _concat_compat
return np.concatenate(to_concat, axis=axis)
MemoryError
Process finished with exit code 1


雷达卡





京公网安备 11010802022788号







