- The aim of this package is to produce indexes of dataset used for Walk Forward Optimization.
- Walk Forward Analysis optimizes on a training set; test on a period after the set and then rolls it all forward and repeats the process. There are multiple out-of-sample periods and the combined results can be analyzed.
- To facilitate Walk Forward Analysis, the package produces start and end of block bootstrap indexes within each training set data chunk.
- Block bootstrap indexes basically represents continuous chunks of time series indexes that are sampled with replacement within a training set data chunk. You may optimize your parameters within each of these block bootstrapped data chunks and averaged them to be tested on testing dataset.
- There is a 'window' argument that allows you to divide the data through a sliding or expanding window. See here for further explanations on sliding and expanding window.
- pip install bootstrapindex
- required packages: pandas, numpy, random, io, requests
import pandas as pd
import numpy as np
import random
import io
import requests
from bootstrapindex import bootstrapindex
url="https://github.com/jironghuang/trend_following/raw/main/quantopian_data/futures_incl_2016.csv"
s=requests.get(url).content
data=pd.read_csv(io.StringIO(s.decode('utf-8')))
data['Date'] = pd.to_datetime(data['Date'], format='%Y-%m-%d')
data.set_index('Date', inplace=True)
bootstrap = bootstrapindex(data, window='sliding', #expanding
num_samples_per_period=10,
min_sample_size=300,
prop_block_bootstrap=0.25,
days_block=252,
starting_index = 5
)
import pandas as pd
import numpy as np
import random
import io
import requests
from bootstrapindex import bootstrapindex
url="https://github.com/jironghuang/trend_following/raw/main/quantopian_data/futures_incl_2016.csv"
s=requests.get(url).content
data=pd.read_csv(io.StringIO(s.decode('utf-8')))
data['Date'] = pd.to_datetime(data['Date'], format='%Y-%m-%d')
data.set_index('Date', inplace=True)
bootstrap = bootstrapindex(data, window='sliding',
num_samples_per_period=10,
min_sample_size=300,
prop_block_bootstrap=0.25,
days_block=252,
starting_index = 5
)
bootstrap = bootstrap_index(data)
bootstrap.create_window_index()
Out[93]:
[[[5, 256], [257, 508]],
[[257, 508], [509, 760]],
[[509, 760], [761, 1012]],
...
import pandas as pd
import numpy as np
import random
import io
import requests
from bootstrapindex import bootstrapindex
url="https://github.com/jironghuang/trend_following/raw/main/quantopian_data/futures_incl_2016.csv"
s=requests.get(url).content
data=pd.read_csv(io.StringIO(s.decode('utf-8')))
data['Date'] = pd.to_datetime(data['Date'], format='%Y-%m-%d')
data.set_index('Date', inplace=True)
bootstrap = bootstrapindex(data, window='sliding',
num_samples_per_period=10,
min_sample_size=300,
prop_block_bootstrap=0.25,
days_block=252,
starting_index = 5
)
bootstrap.extract_block_bootstrap_periods(sample_size = 100, start_sample_index = 50, end_sample_index = 500)
Out[143]:
{'start_index': array([247, 118, 78, 171, 170, 368, 343, 215, 166, 287]),
'end_index': array([372, 243, 203, 296, 295, 493, 468, 340, 291, 412])}
import pandas as pd
import numpy as np
import random
import io
import requests
from bootstrapindex import bootstrapindex
url="https://github.com/jironghuang/trend_following/raw/main/quantopian_data/futures_incl_2016.csv"
s=requests.get(url).content
data=pd.read_csv(io.StringIO(s.decode('utf-8')))
data['Date'] = pd.to_datetime(data['Date'], format='%Y-%m-%d')
data.set_index('Date', inplace=True)
bootstrap = bootstrapindex(data, window='sliding',
num_samples_per_period=10,
min_sample_size=60,
prop_block_bootstrap=0.25,
days_block=252,
starting_index = 5
)
bootstrap.create_dictionary_window_n_bootstrap_index()
bootstrap.expanding_windows_w_bootstrap_info
{1: {'in_sample_index': [5, 256],
'out_sample_index': [257, 508],
'bootstrap_index': {'start_index': array([103, 39, 19, 65, 65, 164, 151, 87, 63, 123]),
'end_index': array([166, 102, 82, 128, 128, 227, 214, 150, 126, 186])}},
2: {'in_sample_index': [257, 508],
'out_sample_index': [509, 760],
'bootstrap_index': {'start_index': array([355, 291, 271, 317, 317, 416, 403, 339, 315, 375]),
'end_index': array([418, 354, 334, 380, 380, 479, 466, 402, 378, 438])}},
3: {'in_sample_index': [509, 760],
'out_sample_index': [761, 1012],
'bootstrap_index': {'start_index': array([607, 543, 523, 569, 569, 668, 655, 591, 567, 627]),
'end_index': array([670, 606, 586, 632, 632, 731, 718, 654, 630, 690])}},
4: {'in_sample_index': [761, 1012],
'out_sample_index': [1013, 1264],
'bootstrap_index': {'start_index': array([859, 795, 775, 821, 821, 920, 907, 843, 819, 879]),
...
import pandas as pd
import numpy as np
import random
import io
import requests
from bootstrapindex import bootstrapindex
url="https://github.com/jironghuang/trend_following/raw/main/quantopian_data/futures_incl_2016.csv"
s=requests.get(url).content
data=pd.read_csv(io.StringIO(s.decode('utf-8')))
data['Date'] = pd.to_datetime(data['Date'], format='%Y-%m-%d')
data.set_index('Date', inplace=True)
bootstrap = bootstrapindex(data, window='expanding',
num_samples_per_period=10,
min_sample_size=60,
prop_block_bootstrap=0.25,
days_block=252,
starting_index = 5
)
bootstrap.create_dictionary_window_n_bootstrap_index()
bootstrap.expanding_windows_w_bootstrap_info
{1: {'in_sample_index': [5, 256],
'out_sample_index': [257, 508],
'bootstrap_index': {'start_index': array([103, 39, 19, 65, 65, 164, 151, 87, 63, 123]),
'end_index': array([166, 102, 82, 128, 128, 227, 214, 150, 126, 186])}},
2: {'in_sample_index': [5, 508],
'out_sample_index': [509, 760],
'bootstrap_index': {'start_index': array([202, 73, 33, 126, 125, 323, 298, 170, 121, 242]),
'end_index': array([328, 199, 159, 252, 251, 449, 424, 296, 247, 368])}},
3: {'in_sample_index': [5, 760],
'out_sample_index': [761, 1012],
'bootstrap_index': {'start_index': array([399, 142, 62, 248, 246, 266, 87, 336, 237, 479]),
'end_index': array([588, 331, 251, 437, 435, 455, 276, 525, 426, 668])}},
4: {'in_sample_index': [5, 1012],
'out_sample_index': [1013, 1264],
'bootstrap_index': {'start_index': array([399, 142, 62, 248, 246, 642, 592, 336, 237, 479]),
...