engine_hsa.py

from pandas.computation import engines
from numba import vectorize


class HSAEngine(engines.AbstractEngine):
    """Evaluate an expression using the Numba target.
    """
    has_neg_frac = False
    _func_cache = {}

    def __init__(self, expr):
        super(HSAEngine, self).__init__(expr)
        #print('__init__:', expr)
        self._args = [n for n in expr.names if isinstance(n, str)]

        function_name = '__numba_pandas_eval_ufunc'
        function_str = '''def %s(%s):
            return %s
        ''' % (function_name, ','.join(self._args), str(expr))

        if function_str in HSAEngine._func_cache:
            #print('cache hit')
            self._ufunc = HSAEngine._func_cache[function_str]
        else:
            #print('cache miss')
            scope = {}
            exec(function_str, scope)
            self._ufunc = vectorize(nopython=True)(scope[function_name])
            HSAEngine._func_cache[function_str] = self._ufunc

    def _evaluate(self):
        env = self.expr.env
        call_args = [env.resolve(name, False) for name in self._args]
        return self._ufunc(*call_args)

engines._engines['hsa'] = HSAEngine

test_engine_hsa.py

import engine_hsa  # register new engine

import pandas as pd

a = pd.DataFrame(dict(x=[1,2,3,4], y=[2,4,6,8]))

print('Input:', type(a), '\n', a)

b = a.eval('x + y', engine='hsa')
b = a.eval('x + y', engine='hsa')

print('Output:', type(b), '\n', b)

TimingTest.ipynb