|
1
|
|
|
# Copyright 2015 Quantopian, Inc. |
|
2
|
|
|
# |
|
3
|
|
|
# Licensed under the Apache License, Version 2.0 (the "License"); |
|
4
|
|
|
# you may not use this file except in compliance with the License. |
|
5
|
|
|
# You may obtain a copy of the License at |
|
6
|
|
|
# |
|
7
|
|
|
# http://www.apache.org/licenses/LICENSE-2.0 |
|
8
|
|
|
# |
|
9
|
|
|
# Unless required by applicable law or agreed to in writing, software |
|
10
|
|
|
# distributed under the License is distributed on an "AS IS" BASIS, |
|
11
|
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|
12
|
|
|
# See the License for the specific language governing permissions and |
|
13
|
|
|
# limitations under the License. |
|
14
|
|
|
import bcolz |
|
15
|
|
|
import json |
|
16
|
|
|
import os |
|
17
|
|
|
import pandas as pd |
|
18
|
|
|
|
|
19
|
|
|
MINUTES_PER_DAY = 390 |
|
20
|
|
|
|
|
21
|
|
|
METADATA_FILENAME = 'metadata.json' |
|
22
|
|
|
|
|
23
|
|
|
|
|
24
|
|
|
class BcolzMinuteBarReader(object): |
|
25
|
|
|
|
|
26
|
|
|
def __init__(self, rootdir, sid_path_func=None): |
|
27
|
|
|
self.rootdir = rootdir |
|
28
|
|
|
|
|
29
|
|
|
metadata = self._get_metadata() |
|
30
|
|
|
|
|
31
|
|
|
self.first_trading_day = pd.Timestamp( |
|
32
|
|
|
metadata['first_trading_day'], tz='UTC') |
|
33
|
|
|
|
|
34
|
|
|
self._sid_path_func = sid_path_func |
|
35
|
|
|
|
|
36
|
|
|
self._carrays = { |
|
37
|
|
|
'open': {}, |
|
38
|
|
|
'high': {}, |
|
39
|
|
|
'low': {}, |
|
40
|
|
|
'close': {}, |
|
41
|
|
|
'volume': {}, |
|
42
|
|
|
'sid': {}, |
|
43
|
|
|
'dt': {}, |
|
44
|
|
|
} |
|
45
|
|
|
|
|
46
|
|
|
def _get_metadata(self): |
|
47
|
|
|
with open(os.path.join(self.rootdir, METADATA_FILENAME)) as fp: |
|
48
|
|
|
return json.load(fp) |
|
49
|
|
|
|
|
50
|
|
|
def _get_ctable(self, asset): |
|
51
|
|
|
sid = int(asset) |
|
52
|
|
|
if self._sid_path_func is not None: |
|
53
|
|
|
path = self._sid_path_func(self.rootdir, sid) |
|
54
|
|
|
else: |
|
55
|
|
|
path = "{0}/{1}.bcolz".format(self.rootdir, sid) |
|
56
|
|
|
|
|
57
|
|
|
return bcolz.open(path, mode='r') |
|
58
|
|
|
|
|
59
|
|
|
def _find_position_of_minute(self, minute_dt): |
|
60
|
|
|
""" |
|
61
|
|
|
Internal method that returns the position of the given minute in the |
|
62
|
|
|
list of every trading minute since market open of the first trading |
|
63
|
|
|
day. |
|
64
|
|
|
|
|
65
|
|
|
IMPORTANT: This method assumes every day is 390 minutes long, even |
|
66
|
|
|
early closes. Our minute bcolz files are generated like this to |
|
67
|
|
|
support fast lookup. |
|
68
|
|
|
|
|
69
|
|
|
ex. this method would return 2 for 1/2/2002 9:32 AM Eastern, if |
|
70
|
|
|
1/2/2002 is the first trading day of the dataset. |
|
71
|
|
|
|
|
72
|
|
|
Parameters |
|
73
|
|
|
---------- |
|
74
|
|
|
minute_dt: pd.Timestamp |
|
75
|
|
|
The minute whose position should be calculated. |
|
76
|
|
|
|
|
77
|
|
|
Returns |
|
78
|
|
|
------- |
|
79
|
|
|
The position of the given minute in the list of all trading minutes |
|
80
|
|
|
since market open on the first trading day. |
|
81
|
|
|
""" |
|
82
|
|
|
NotImplementedError |
|
83
|
|
|
|
|
84
|
|
|
def _open_minute_file(self, field, asset): |
|
85
|
|
|
sid_str = str(int(asset)) |
|
86
|
|
|
|
|
87
|
|
|
try: |
|
88
|
|
|
carray = self._carrays[field][sid_str] |
|
89
|
|
|
except KeyError: |
|
90
|
|
|
carray = self._carrays[field][sid_str] = \ |
|
91
|
|
|
self._get_ctable(asset)[field] |
|
92
|
|
|
|
|
93
|
|
|
return carray |
|
94
|
|
|
|
quantopian /
zipline
