I'm new to python and unfortunately I'm not sure how to share a reproductible example. I'm looking for anomalies in a dataset for an anti-fraud exercice. I'm trying to use the Z-score to find outliers. However, I get an error code. I think the issue is the shape of the data (not sure) but I have no idea how to fix that. Any pointer would help! thanks!
from scipy.stats import zscore
daily_fraud['zscore'] = zscore(daily_fraud.values)
anomalies = daily_fraud[daily_fraud['zscore'].abs() >2]
~\Anaconda3\lib\site-packages\scipy\stats\stats.py in zscore(a, axis, ddof)
2313 np.expand_dims(sstd, axis=axis))
2314 else:
-> 2315 return (a - mns) / sstd
2316
2317
ValueError: operands could not be broadcast together with shapes (183,) (182,)
发布者：admin，转转请注明出处：http://www.yc00.com/questions/1736216034a3870382.html
评论列表（0条）