创建大型随机数据集

In [1]: import pandas as pd
        import numpy as np

In [2]: df = pd.DataFrame(np.random.choice(['foo','bar','baz'], size=(100000,3)))
        df = df.apply(lambda col: col.astype('category'))

In [3]: df.head()
Out[3]: 
     0    1    2
0  bar  foo  baz
1  baz  bar  baz
2  foo  foo  bar
3  bar  baz  baz
4  foo  bar  baz

In [4]: df.dtypes
Out[4]:
0    category
1    category
2    category
dtype: object

In [5]: df.shape
Out[5]: (100000, 3)