mirror of
https://github.com/wassname/catalyst.git
synced 2026-06-29 05:55:11 +08:00
Dale Jung
38e8d5214d
Limited use of `pandas` data structures in both `HistoryContainer` and `RollingPanel`. Where possible, methods were amended to return raw `ndarrays` with the indexing logic done separately. This allows us to cut down the number of times pandas objects are created both as returns and intermediate values. The separation of indexing from data access allowed us to minimize the times we’d make use of pandas indexes. This required that that certain methods like `NDFrame.ffill` be replaced with versions that work with `ndarrays`. Some of this was done via straight numpy methods and others by access pandas internal machinery. Outside of allowing us to use faster ndarrays, many of these function provided speedups over their pandas counterparts as we didn’t require the extra features like handling multiple dtypes. i.e. np.isnan is faster than pd.isnull, but only works with certain dtypes.
60 lines
1.6 KiB
Python
60 lines
1.6 KiB
Python
#
|
|
# Copyright 2015 Quantopian, Inc.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
import random
|
|
|
|
import pandas as pd
|
|
import numpy as np
|
|
from numpy.testing import assert_almost_equal
|
|
|
|
from zipline.utils.munge import bfill, ffill
|
|
|
|
|
|
def test_bfill():
|
|
# test ndim=1
|
|
N = 100
|
|
s = pd.Series(np.random.randn(N))
|
|
mask = random.sample(range(N), 10)
|
|
s.iloc[mask] = np.nan
|
|
|
|
correct = s.bfill().values
|
|
test = bfill(s.values)
|
|
assert_almost_equal(correct, test)
|
|
|
|
# test ndim=2
|
|
df = pd.DataFrame(np.random.randn(N, N))
|
|
df.iloc[mask] = np.nan
|
|
correct = df.bfill().values
|
|
test = bfill(df.values)
|
|
assert_almost_equal(correct, test)
|
|
|
|
|
|
def test_ffill():
|
|
# test ndim=1
|
|
N = 100
|
|
s = pd.Series(np.random.randn(N))
|
|
mask = random.sample(range(N), 10)
|
|
s.iloc[mask] = np.nan
|
|
|
|
correct = s.ffill().values
|
|
test = ffill(s.values)
|
|
assert_almost_equal(correct, test)
|
|
|
|
# test ndim=2
|
|
df = pd.DataFrame(np.random.randn(N, N))
|
|
df.iloc[mask] = np.nan
|
|
correct = df.ffill().values
|
|
test = ffill(df.values)
|
|
assert_almost_equal(correct, test)
|