擅长:python、mysql、java
<p>下面是另一个使用<code>pd.get_dummies</code>的解决方案。还增加了一些比较基准</p>
<pre><code>import pandas as pd, numpy as np
def jp(df):
df = df.join(pd.get_dummies(df.Property))
for col in ['prop1', 'prop2', 'prop9']:
df[col] = np.where(df[col], df.Value, df[col])
return df.drop(['Property', 'Value'], 1).groupby(['A', 'B', 'C'])\
.agg(lambda s: next((i for i in s if i), 0)).reset_index()
def maxu(df):
return df.pivot_table(index=['A','B','C'], columns='Property', values='Value', \
aggfunc='first', fill_value='-').reset_index().rename_axis(None,1)
def maxu2(df):
return df.set_index(['A','B','C','Property'])['Value']\
.unstack('Property', fill_value='-').reset_index().rename_axis(None,1)
%timeit jp(df.copy()) # 14 ms ± 176 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
%timeit maxu(df.copy()) # 14.1 ms ± 181 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)
%timeit maxu2(df.copy()) # 10.4 ms ± 1.98 ms per loop (mean ± std. dev. of 7 runs, 100 loops each)
</code></pre>