Skip to content

Instantly share code, notes, and snippets.

View jeethu's full-sized avatar

Jeethu Rao jeethu

View GitHub Profile
@jeethu
jeethu / live_signals_sharpe_sortino.ipynb
Last active July 8, 2021 17:22
Live annualized Sharpe and Sortino metrics for Numerai Signals
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@jeethu
jeethu / evaluation.py
Created August 25, 2020 17:01
Numerai Model Evaluation
import functools
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
import matplotlib.table as table
import numpy as np
import pandas as pd
from scipy.stats import spearmanr
TOURNAMENT_NAME = "kazutsugi"
@jeethu
jeethu / example_model.py
Created April 23, 2020 19:20
numerai example_model with int8 features
#!/usr/bin/env python
"""
Example classifier on Numerai data using a xgboost regression.
To get started, install the required packages: pip install pandas numpy sklearn xgboost
"""
import csv
import pandas as pd
import numpy as np
@jeethu
jeethu / example_model.py
Created January 17, 2020 12:13
Numerai example_model.py using np.float16 for features and target
#!/usr/bin/env python
"""
Example classifier on Numerai data using a xgboost regression.
To get started, install the required packages: pip install pandas numpy sklearn xgboost
"""
import csv
import pandas as pd
import numpy as np
3.8_baseline4.json
==================
Performance version: 0.7.0
Report on Linux-4.15.0-43-generic-x86_64-with-glibc2.26
Number of logical CPUs: 4
Start date: 2019-01-23 23:27:43.675291
End date: 2019-01-24 00:00:30.138941
3.8_load_const_ref4.json
@jeethu
jeethu / gist:19430d802aa08e28d1cb5eb20a47a470
Created January 17, 2018 00:55
perf timeit comparison Raw
jeethu@Odin:~/Projects/cpython$ # Baseline
jeethu@Odin:~/Projects/cpython$ taskset -c 2,3,6,7 python3 -m perf timeit --python=~/Projects/cpython/venv/cpython3.7-487fa3ea092b/bin/python -s 'l=[]' $(python3 -c 'print("l.insert(0, None); " * 100 + "l.clear();")') --duplicate 100
.....................
WARNING: the benchmark result may be unstable
* the standard deviation (1.37 us) is 13% of the mean (10.5 us)
Try to rerun the benchmark with more runs, values and/or loops.
Run 'python3 -m perf system tune' command to reduce the system jitter.
Use perf stats, perf dump and perf hist to analyze results.
Use --quiet option to hide these warnings.
@jeethu
jeethu / gist:2d2de55afdb8ea4ad03b6a5d04d5227f
Created January 17, 2018 00:04
perf timeit comparison
jeethu@Odin:~/Projects/cpython$ # Baseline
jeethu@Odin:~/Projects/cpython$ ~/Projects/cpython/venv/cpython3.7-487fa3ea092b/bin/python -c "import sys;print(sys.version)"
3.7.0a4+ (heads/master:9f1b7b93f5, Jan 16 2018, 19:15:03)
[GCC 7.2.0]
jeethu@Odin:~/Projects/cpython$ taskset -c 2,3,6,7 python3 -m perf timeit --python=~/Projects/cpython/venv/cpython3.7-487fa3ea092b/bin/python -s 'l=[];ins=l.insert' $(python3 -c 'print("ins(0, None); " * 100 + "l.clear();")') --duplicate 100
.....................
Mean +- std dev: 6.55 us +- 0.03 us
jeethu@Odin:~/Projects/cpython$ # py37_list_insert_memmove
.file "listobject.c"
.intel_syntax noprefix
.text
.p2align 4,,15
.type list_reverse, @function
list_reverse:
.LFB125:
.cfi_startproc
mov rdx, QWORD PTR 16[rdi]
cmp rdx, 1
py37_baseline-no-pgo-no-lto.json
================================
Performance version: 0.6.0
Report on Linux-4.13.0-19-generic-x86_64-with-debian-stretch-sid
Number of logical CPUs: 8
Start date: 2018-01-16 21:08:29.457607
End date: 2018-01-16 21:46:10.018098
py37_list_insert_memmove-t32-no-pgo-no-lto.json
py37_baseline-no-pgo.json
=========================
Performance version: 0.6.0
Report on Linux-4.13.0-19-generic-x86_64-with-debian-stretch-sid
Number of logical CPUs: 8
Start date: 2018-01-15 23:36:29.563960
End date: 2018-01-16 00:13:14.443979
py37_list_insert_memmove-no-pgo.json