擅长:python、mysql、java
<pre><code>def add_content(df, gc, k=5):
n = len(df)
gcs = set(gc.squeeze())
if n < k:
choices = list(gcs.difference(df.content))
mc = np.random.choice(choices, k - n, replace=False)
ids = np.repeat(df.Masteruserid.iloc[-1], k - n)
data = dict(Masteruserid=ids, content=mc)
return df.append(pd.DataFrame(data), ignore_index=True)
gb = df.groupby('Masteruserid', group_keys=False)
gb.apply(add_content, gc).reset_index(drop=True)
</code></pre>
<p><a href="https://i.stack.imgur.com/Cc4aA.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/Cc4aA.png" alt="enter image description here"/></a></p>