Tools for mathematical optimization region

Overview

README.md

中文博客主页:https://blog.csdn.net/linjing_zyq

pip install optimtool

1. 无约束优化算法性能对比

前五个参数完全一致,其中第四个参数是绘图接口,默认绘制单个算法的迭代过程;第五个参数是输出函数迭代值接口,默认为不输出。

method:用于传递线搜索方式

  • from optimtool.unconstrain import gradient_descent
方法 函数参数 调用示例
解方程得到精确解法(solve) solve(funcs, args, x_0, draw=True, output_f=False, epsilon=1e-10, k=0) gradient_descent.solve(funcs, args, x_0)
基于Grippo非单调线搜索的梯度下降法 barzilar_borwein(funcs, args, x_0, draw=True, output_f=False, method="grippo", M=20, c1=0.6, beta=0.6, alpha=1, epsilon=1e-10, k=0) gradient_descent.barzilar_borwein(funcs, args, x_0, method="grippo")
基于ZhangHanger非单调线搜索的梯度下降法 barzilar_borwein(funcs, args, x_0, draw=True, output_f=False, method="ZhangHanger", M=20, c1=0.6, beta=0.6, alpha=1, epsilon=1e-10, k=0) gradient_descent.barzilar_borwein(funcs, args, x_0, method="ZhangHanger")
基于最速下降法的梯度下降法 steepest(funcs, args, x_0, draw=True, output_f=False, method="wolfe", epsilon=1e-10, k=0) gradient_descent.steepest(funcs, args, x_0)
  • from optimtool.unconstrain import newton
方法 函数参数 调用示例
经典牛顿法 classic(funcs, args, x_0, draw=True, output_f=False, epsilon=1e-10, k=0) newton.classic(funcs, args, x_0)
基于armijo线搜索方法的修正牛顿法 modified(funcs, args, x_0, draw=True, output_f=False, method="armijo", m=20, epsilon=1e-10, k=0) newton.modified(funcs, args, x_0, method="armijo")
基于goldstein线搜索方法的修正牛顿法 modified(funcs, args, x_0, draw=True, output_f=False, method="goldstein", m=20, epsilon=1e-10, k=0) newton.modified(funcs, args, x_0, method="goldstein")
基于wolfe线搜索方法的修正牛顿法 modified(funcs, args, x_0, draw=True, output_f=False, method="wolfe", m=20, epsilon=1e-10, k=0) newton.modified(funcs, args, x_0, method="wolfe")
基于armijo线搜索方法的非精确牛顿法 CG(funcs, args, x_0, draw=True, output_f=False, method="armijo", epsilon=1e-6, k=0) newton.CG(funcs, args, x_0, method="armijo")
基于goldstein线搜索方法的非精确牛顿法 CG(funcs, args, x_0, draw=True, output_f=False, method="goldstein", epsilon=1e-6, k=0) newton.CG(funcs, args, x_0, method="goldstein")
基于wolfe线搜索方法的非精确牛顿法 CG(funcs, args, x_0, draw=True, output_f=False, method="wolfe", epsilon=1e-6, k=0) newton.CG(funcs, args, x_0, method="wolfe")
  • from optimtool.unconstrain import newton_quasi
方法 函数参数 调用示例
基于BFGS方法更新海瑟矩阵的拟牛顿法 bfgs(funcs, args, x_0, draw=True, output_f=False, method="wolfe", m=20, epsilon=1e-10, k=0) newton_quasi.bfgs(funcs, args, x_0)
基于DFP方法更新海瑟矩阵的拟牛顿法 dfp(funcs, args, x_0, draw=True, output_f=False, method="wolfe", m=20, epsilon=1e-4, k=0) newton_quasi.dfp(funcs, args, x_0)
基于有限内存BFGS方法更新海瑟矩阵的拟牛顿法 L_BFGS(funcs, args, x_0, draw=True, output_f=False, method="wolfe", m=6, epsilon=1e-10, k=0) newton_quasi.L_BFGS(funcs, args, x_0)
  • from optimtool.unconstrain import trust_region
方法 函数参数 调用示例
基于截断共轭梯度法的信赖域算法 steihaug_CG(funcs, args, x_0, draw=True, output_f=False, m=100, r0=1, rmax=2, eta=0.2, p1=0.4, p2=0.6, gamma1=0.5, gamma2=1.5, epsilon=1e-6, k=0) trust_region.steihaug_CG(funcs, args, x_0)
import sympy as sp
import matplotlib.pyplot as plt
import optimtool as oo

f, x1, x2, x3, x4 = sp.symbols("f x1 x2 x3 x4")
f = (x1 - 1)**2 + (x2 - 1)**2 + (x3 - 1)**2 + (x1**2 + x2**2 + x3**2 + x4**2 - 0.25)**2
funcs = sp.Matrix([f])
args = sp.Matrix([x1, x2, x3, x4])
x_0 = (1, 2, 3, 4)

# 无约束优化测试函数性能对比
f_list = []
title = ["gradient_descent_barzilar_borwein", "newton_CG", "newton_quasi_L_BFGS", "trust_region_steihaug_CG"]
colorlist = ["maroon", "teal", "slateblue", "orange"]
_, _, f = oo.unconstrain.gradient_descent.barzilar_borwein(funcs, args, x_0, False, True)
f_list.append(f)
_, _, f = oo.unconstrain.newton.CG(funcs, args, x_0, False, True)
f_list.append(f)
_, _, f = oo.unconstrain.newton_quasi.L_BFGS(funcs, args, x_0, False, True)
f_list.append(f)
_, _, f = oo.unconstrain.trust_region.steihaug_CG(funcs, args, x_0, False, True)
f_list.append(f)

# 绘图
handle = []
for j, z in zip(colorlist, f_list):
    ln, = plt.plot([i for i in range(len(z))], z, c=j, marker='o', linestyle='dashed')
    handle.append(ln)
plt.xlabel("$Iteration \ times \ (k)$")
plt.ylabel("$Objective \ function \ value: \ f(x_k)$")
plt.legend(handle, title)
plt.title("Performance Comparison")
plt.show()

2. 非线性最小二乘问题

  • from optimtool.unconstrain import nonlinear_least_square

method:用于传递线搜索方法

方法 函数参数 调用示例
基于高斯牛顿法的非线性最小二乘问题解法 gauss_newton(funcr, args, x_0, draw=True, output_f=False, method="wolfe", epsilon=1e-10, k=0) nonlinear_least_square.gauss_newton(funcr, args, x_0)
基于levenberg_marquardt的非线性最小二乘问题解法 levenberg_marquardt(funcr, args, x_0, draw=True, output_f=False, m=100, lamk=1, eta=0.2, p1=0.4, p2=0.9, gamma1=0.7, gamma2=1.3, epsilon=1e-10, k=0) nonlinear_least_square.levenberg_marquardt(funcr, args, x_0)
import sympy as sp
import matplotlib.pyplot as plt
import optimtool as oo

r1, r2, x1, x2 = sp.symbols("r1 r2 x1 x2")
r1 = x1**3 - 2*x2**2 - 1
r2 = 2*x1 + x2 - 2
funcr = sp.Matrix([r1, r2])
args = sp.Matrix([x1, x2])
x_0 = (2, 2)

f_list = []
title = ["gauss_newton", "levenberg_marquardt"]
colorlist = ["maroon", "teal"]
_, _, f = oo.unconstrain.nonlinear_least_square.gauss_newton(funcr, args, x_0, False, True) # 第五参数控制输出函数迭代值列表
f_list.append(f)
_, _, f = oo.unconstrain.nonlinear_least_square.levenberg_marquardt(funcr, args, x_0, False, True)
f_list.append(f)

# 绘图
handle = []
for j, z in zip(colorlist, f_list):
    ln, = plt.plot([i for i in range(len(z))], z, c=j, marker='o', linestyle='dashed')
    handle.append(ln)
plt.xlabel("$Iteration \ times \ (k)$")
plt.ylabel("$Objective \ function \ value: \ f(x_k)$")
plt.legend(handle, title)
plt.title("Performance Comparison")
plt.show()

3. 等式约束优化测试

  • from optimtool.constrain import equal

无约束内核默认采用wolfe线搜索方法

方法 函数参数 调用示例
二次罚函数法 penalty_quadratic(funcs, args, cons, x_0, draw=True, output_f=False, method="gradient_descent", sigma=10, p=2, epsilon=1e-4, k=0) equal.penalty_quadratic(funcs, args, cons, x_0)
增广拉格朗日法 lagrange_augmented(funcs, args, cons, x_0, draw=True, output_f=False, method="gradient_descent", lamk=6, sigma=10, p=2, etak=1e-4, epsilon=1e-6, k=0) equal.lagrange_augmented(funcs, args, cons, x_0)
import numpy as np
import sympy as sp
import matplotlib.pyplot as plt
import optimtool as oo

f, x1, x2 = sp.symbols("f x1 x2")
f = x1 + np.sqrt(3) * x2
c1 = x1**2 + x2**2 - 1
funcs = sp.Matrix([f])
cons = sp.Matrix([c1])
args = sp.Matrix([x1, x2])
x_0 = (-1, -1)

f_list = []
title = ["penalty_quadratic", "lagrange_augmented"]
colorlist = ["maroon", "teal"]
_, _, f = oo.constrain.equal.penalty_quadratic(funcs, args, cons, x_0, False, True) # 第四个参数控制单个算法不显示迭代图,第五参数控制输出函数迭代值列表
f_list.append(f)
_, _, f = oo.constrain.equal.lagrange_augmented(funcs, args, cons, x_0, False, True)
f_list.append(f)

# 绘图
handle = []
for j, z in zip(colorlist, f_list):
    ln, = plt.plot([i for i in range(len(z))], z, c=j, marker='o', linestyle='dashed')
    handle.append(ln)
plt.xlabel("$Iteration \ times \ (k)$")
plt.ylabel("$Objective \ function \ value: \ f(x_k)$")
plt.legend(handle, title)
plt.title("Performance Comparison")
plt.show()

4. 不等式约束优化测试

  • from optimtool.constrain import unequal

无约束内核默认采用wolfe线搜索方法

方法 函数参数 调用示例
二次罚函数法 penalty_quadratic(funcs, args, cons, x_0, draw=True, output_f=False, method="gradient_descent", sigma=1, p=0.4, epsilon=1e-10, k=0) unequal.penalty_quadratic(funcs, args, cons, x_0)
内点(分式)罚函数法 penalty_interior_fraction(funcs, args, cons, x_0, draw=True, output_f=False, method="gradient_descent", sigma=12, p=0.6, epsilon=1e-6, k=0) unequal.penalty_interior_fraction(funcs, args, cons, x_0)
拉格朗日法(本质上为不存在等式约束) lagrange_augmented(funcs, args, cons, x_0, draw=True, output_f=False, method="gradient_descent", muk=10, sigma=8, alpha=0.2, beta=0.7, p=2, eta=1e-1, epsilon=1e-4, k=0) unequal.lagrange_augmented(funcs, args, cons, x_0)
import sympy as sp
import matplotlib.pyplot as plt
import optimtool as oo

f, x1, x2 = sp.symbols("f x1 x2")
f = x1**2 + (x2 - 2)**2
c1 = 1 - x1
c2 = 2 - x2
funcs = sp.Matrix([f])
cons = sp.Matrix([c1, c2])
args = sp.Matrix([x1, x2])
x_0 = (2, 3)

f_list = []
title = ["penalty_quadratic", "penalty_interior_fraction"]
colorlist = ["maroon", "teal"]
_, _, f = oo.constrain.unequal.penalty_quadratic(funcs, args, cons, x_0, False, True, method="newton", sigma=10, epsilon=1e-6) # 第四个参数控制单个算法不显示迭代图,第五参数控制输出函数迭代值列表
f_list.append(f)
_, _, f = oo.constrain.unequal.penalty_interior_fraction(funcs, args, cons, x_0, False, True, method="newton")
f_list.append(f)

# 绘图
handle = []
for j, z in zip(colorlist, f_list):
    ln, = plt.plot([i for i in range(len(z))], z, c=j, marker='o', linestyle='dashed')
    handle.append(ln)
plt.xlabel("$Iteration \ times \ (k)$")
plt.ylabel("$Objective \ function \ value: \ f(x_k)$")
plt.legend(handle, title)
plt.title("Performance Comparison")
plt.show()

单独测试拉格朗日方法

# 导入符号运算的包
import sympy as sp

# 导入约束优化
import optimtool as oo

# 构造函数
f1 = sp.symbols("f1")
x1, x2, x3, x4 = sp.symbols("x1 x2 x3 x4")
f1 = x1**2 + x2**2 + 2*x3**3 + x4**2 - 5*x1 - 5*x2 - 21*x3 + 7*x4
c1 = 8 - x1 + x2 - x3 + x4 - x1**2 - x2**2 - x3**2 - x4**2
c2 = 10 + x1 + x4 - x1**2 - 2*x2**2 - x3**2 - 2*x4**2
c3 = 5 - 2*x1 + x2 + x4 - 2*x1**2 - x2**2 - x3**2
cons_unequal1 = sp.Matrix([c1, c2, c3])
funcs1 = sp.Matrix([f1])
args1 = sp.Matrix([x1, x2, x3, x4])
x_1 = (0, 0, 0, 0)

x_0, _, f = oo.constrain.unequal.lagrange_augmented(funcs1, args1, cons_unequal1, x_1, output_f=True, method="trust_region", sigma=1, muk=1, p=1.2)
for i in range(len(x_0)):
     x_0[i] = round(x_0[i], 2)
print("\n最终收敛点:", x_0, "\n目标函数值:", f[-1])

result

最终收敛点: [ 2.5   2.5   1.87 -3.5 ] 
目标函数值: -50.94151192711454

5. 混合等式约束测试

  • from optimtool.constrain import mixequal

无约束内核默认采用wolfe线搜索方法

方法 函数参数 调用示例
二次罚函数法 penalty_quadratic(funcs, args, cons_equal, cons_unequal, x_0, draw=True, output_f=False, method="gradient_descent", sigma=1, p=0.6, epsilon=1e-10, k=0) mixequal.penalty_quadratic(funcs, args, cons_equal, cons_unequal, x_0)
L1罚函数法 penalty_L1(funcs, args, cons_equal, cons_unequal, x_0, draw=True, output_f=False, method="gradient_descent", sigma=1, p=0.6, epsilon=1e-10, k=0) mixequal.penalty_L1(funcs, args, cons_equal, cons_unequal, x_0)
增广拉格朗日函数法 lagrange_augmented(funcs, args, cons_equal, cons_unequal, x_0, draw=True, output_f=False, method="gradient_descent", lamk=6, muk=10, sigma=8, alpha=0.5, beta=0.7, p=2, eta=1e-3, epsilon=1e-4, k=0) mixequal.lagrange_augmented(funcs, args, cons_equal, cons_unequal, x_0)
import sympy as sp
import matplotlib.pyplot as plt
import optimtool as oo

f, x1, x2 = sp.symbols("f x1 x2")
f = (x1 - 2)**2 + (x2 - 1)**2
c1 = x1 - 2*x2
c2 = 0.25*x1**2 - x2**2 - 1
funcs = sp.Matrix([f])
cons_equal = sp.Matrix([c1])
cons_unequal = sp.Matrix([c2])
args = sp.Matrix([x1, x2])
x_0 = (0.5, 1)

f_list = []
title = ["penalty_quadratic", "penalty_L1", "lagrange_augmented"]
colorlist = ["maroon", "teal", "orange"]
_, _, f = oo.constrain.mixequal.penalty_quadratic(funcs, args, cons_equal, cons_unequal, x_0, False, True) # 第四个参数控制单个算法不显示迭代图,第五参数控制输出函数迭代值列表
f_list.append(f)
_, _, f = oo.constrain.mixequal.penalty_L1(funcs, args, cons_equal, cons_unequal, x_0, False, True)
f_list.append(f)
_, _, f = oo.constrain.mixequal.lagrange_augmented(funcs, args, cons_equal, cons_unequal, x_0, False, True)
f_list.append(f)

# 绘图
handle = []
for j, z in zip(colorlist, f_list):
    ln, = plt.plot([i for i in range(len(z))], z, c=j, marker='o', linestyle='dashed')
    handle.append(ln)
plt.xlabel("$Iteration \ times \ (k)$")
plt.ylabel("$Objective \ function \ value: \ f(x_k)$")
plt.legend(handle, title)
plt.title("Performance Comparison")
plt.show()

6. Lasso问题测试

  • from optimtool.example import Lasso
方法 函数参数 调用示例
梯度下降法 gradient_descent(A, b, mu, args, x_0, draw=True, output_f=False, delta=10, alp=1e-3, epsilon=1e-2, k=0) Lasso.gradient_descent(A, b, mu, args, x_0,)
次梯度算法 subgradient(A, b, mu, args, x_0, draw=True, output_f=False, alphak=2e-2, epsilon=1e-3, k=0) Lasso.subgradient(A, b, mu, args, x_0,)
import numpy as np
import sympy as sp
import matplotlib.pyplot as plt
import optimtool as oo

import scipy.sparse as ss
f, A, b, mu = sp.symbols("f A b mu")
x = sp.symbols('x1:9')
m = 4
n = 8
u = (ss.rand(n, 1, 0.1)).toarray()
A = np.random.randn(m, n)
b = A.dot(u)
mu = 1e-2
args = sp.Matrix(x)
x_0 = tuple([1 for i in range(8)])

f_list = []
title = ["gradient_descent", "subgradient"]
colorlist = ["maroon", "teal"]
_, _, f = oo.example.Lasso.gradient_descent(A, b, mu, args, x_0, False, True, epsilon=1e-4)# 第四个参数控制单个算法不显示迭代图,第五参数控制输出函数迭代值列表
f_list.append(f)
_, _, f = oo.example.Lasso.subgradient(A, b, mu, args, x_0, False, True)
f_list.append(f)

# 绘图
handle = []
for j, z in zip(colorlist, f_list):
    ln, = plt.plot([i for i in range(len(z))], z, c=j, marker='o', linestyle='dashed')
    handle.append(ln)
plt.xlabel("$Iteration \ times \ (k)$")
plt.ylabel("$Objective \ function \ value: \ f(x_k)$")
plt.legend(handle, title)
plt.title("Performance Comparison")
plt.show()

7. WanYuan问题测试

  • from optimtool.example import WanYuan
方法 函数参数 调用示例
构造7个残差函数并采用高斯牛顿法 gauss_newton(m, n, a, b, c, x3, y3, x_0, draw=False, eps=1e-10) WanYuan.gauss_newton(1, 2, 0.2, -1.4, 2.2, 2**(1/2), 0, (0, -1, -2.5, -0.5, 2.5, -0.05), draw=True)

问题描述

给定直线方程的斜率($m$)与截距($n$),给定一元二次方程的二次项系数($a$)、一次项系数($b$)、常数($c$),给定一个过定点的圆($x_3$,$y_3$​​),要求这个过定点的圆与直线($x_1$,$y_1$)和抛物线($x_2$,$y_2$)相切的切点以及该圆的圆心($x_0$,$y_0$)。

code

# 导包
import sympy as sp
import matplotlib.pyplot as plt
import optimtool as oo

# 构造数据
m = 1
n = 2
a = 0.2
b = -1.4
c = 2.2
x3 = 2*(1/2)
y3 = 0
x_0 = (0, -1, -2.5, -0.5, 2.5, -0.05)

# 训练
oo.example.WanYuan.gauss_newton(1, 2, 0.2, -1.4, 2.2, 2**(1/2), 0, (0, -1, -2.5, -0.5, 2.5, -0.05), draw=True)
You might also like...
A Python step-by-step primer for Machine Learning and Optimization

early-ML Presentation General Machine Learning tutorials A Python step-by-step primer for Machine Learning and Optimization This github repository gat

Implementation of linesearch Optimization Algorithms in Python

Nonlinear Optimization Algorithms During my time as Scientific Assistant at the Karlsruhe Institute of Technology (Germany) I implemented various Opti

Microsoft contributing libraries, tools, recipes, sample codes and workshop contents for machine learning & deep learning.

Microsoft contributing libraries, tools, recipes, sample codes and workshop contents for machine learning & deep learning.

A single Python file with some tools for visualizing machine learning in the terminal.
A single Python file with some tools for visualizing machine learning in the terminal.

Machine Learning Visualization Tools A single Python file with some tools for visualizing machine learning in the terminal. This demo is composed of t

🔬 A curated list of awesome machine learning strategies & tools in financial market.

🔬 A curated list of awesome machine learning strategies & tools in financial market.

A Tools that help Data Scientists and ML engineers train and deploy ML models.

Domino Research This repo contains projects under active development by the Domino R&D team. We build tools that help Data Scientists and ML engineers

A collection of Scikit-Learn compatible time series transformers and tools.
A collection of Scikit-Learn compatible time series transformers and tools.

tsfeast A collection of Scikit-Learn compatible time series transformers and tools. Installation Create a virtual environment and install: From PyPi p

Tools for Optuna, MLflow and the integration of both.
Tools for Optuna, MLflow and the integration of both.

HPOflow - Sphinx DOC Tools for Optuna, MLflow and the integration of both. Detailed documentation with examples can be found here: Sphinx DOC Table of

ClearML - Auto-Magical Suite of tools to streamline your ML workflow. Experiment Manager, MLOps and Data-Management
ClearML - Auto-Magical Suite of tools to streamline your ML workflow. Experiment Manager, MLOps and Data-Management

ClearML - Auto-Magical Suite of tools to streamline your ML workflow Experiment Manager, MLOps and Data-Management ClearML Formerly known as Allegro T

Comments
  • Minimize the Amount of Guided Packages

    Minimize the Amount of Guided Packages

    Is it necessary to reconstruct the matrix operation system of numpy and the symbolic algebra operation system of sympy in order to reduce the amount of dependent packets in the process of guilding packets.

    opened by zzqwdwd 1
Releases(v1.5)
  • v1.5(Nov 10, 2022)

    This version reduces the memory pressure caused by typing compared to v1.4.

    import optimtool as oo
    x1, x2, x3, x4 = sp.symbols("x1 x2 x3 x4") # Declare symbolic variables
    f = (x1 - 1)**2 + (x2 - 1)**2 + (x3 - 1)**2 + (x1**2 + x2**2 + x3**2 + x4**2 - 0.25)**2
    oo.unconstrain.gradient_descent.barzilar_borwein(f, [x1, x2, x3, x4], (1, 2, 3, 4)) # funcs, args, x_0
    
    Source code(tar.gz)
    Source code(zip)
  • v1.4(Nov 8, 2022)

    import optimtool as oo
    x1, x2, x3, x4 = sp.symbols("x1 x2 x3 x4") # Declare symbolic variables
    f = (x1 - 1)**2 + (x2 - 1)**2 + (x3 - 1)**2 + (x1**2 + x2**2 + x3**2 + x4**2 - 0.25)**2
    oo.unconstrain.gradient_descent.barzilar_borwein(f, [x1, x2, x3, x4], (1, 2, 3, 4)) # funcs, args, x_0
    

    Use FuncArray, ArgArray, PointArray, IterPointType, OutputType in typing, and delete functions/ folder. I use many means to accelerate the method, I can't enumerate them here.

    Source code(tar.gz)
    Source code(zip)
  • v1.3(Apr 25, 2022)

    In v2.3.4, We call a method as follows:

    import optimtool as oo
    x1, x2, x3, x4 = sp.symbols("x1 x2 x3 x4")
    f = (x1 - 1)**2 + (x2 - 1)**2 + (x3 - 1)**2 + (x1**2 + x2**2 + x3**2 + x4**2 - 0.25)**2
    funcs = sp.Matrix([f])
    args = sp.Matrix([x1, x2, x3, x4])
    x_0 = (1, 2, 3, 4)
    oo.unconstrain.gradient_descent.barzilar_borwein(funcs, args, x_0)
    

    But in v2.3.5, We now call a method as follows: (It reduces the trouble of constructing data externally.)

    import optimtool as oo
    x1, x2, x3, x4 = sp.symbols("x1 x2 x3 x4") # Declare symbolic variables
    f = (x1 - 1)**2 + (x2 - 1)**2 + (x3 - 1)**2 + (x1**2 + x2**2 + x3**2 + x4**2 - 0.25)**2
    oo.unconstrain.gradient_descent.barzilar_borwein(f, [x1, x2, x3, x4], (1, 2, 3, 4)) # funcs, args, x_0
    # funcs(args) can be list, tuple, sp.Matrix
    

    Our function parameter input method is similar to matlab, and supports more methods than matlab.

    Source code(tar.gz)
    Source code(zip)
Magenta: Music and Art Generation with Machine Intelligence

Magenta is a research project exploring the role of machine learning in the process of creating art and music. Primarily this involves developing new

Magenta 18.1k Dec 30, 2022
Pandas-method-chaining is a plugin for flake8 that provides method chaining linting for pandas code

pandas-method-chaining pandas-method-chaining is a plugin for flake8 that provides method chaining linting for pandas code. It is a fork from pandas-v

Francis 5 May 14, 2022
Confidence intervals for scikit-learn forest algorithms

forest-confidence-interval: Confidence intervals for Forest algorithms Forest algorithms are powerful ensemble methods for classification and regressi

272 Dec 01, 2022
Learn how to responsibly deliver value with ML.

Made With ML Applied ML · MLOps · Production Join 30K+ developers in learning how to responsibly deliver value with ML. 🔥 Among the top MLOps reposit

Goku Mohandas 32k Dec 30, 2022
Arquivos do curso online sobre a estatística voltada para ciência de dados e aprendizado de máquina.

Estatistica para Ciência de Dados e Machine Learning Arquivos do curso online sobre a estatística voltada para ciência de dados e aprendizado de máqui

Renan Barbosa 1 Jan 10, 2022
🌲 Implementation of the Robust Random Cut Forest algorithm for anomaly detection on streams

🌲 Implementation of the Robust Random Cut Forest algorithm for anomaly detection on streams

Real-time water systems lab 416 Jan 06, 2023
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

Horovod Horovod is a distributed deep learning training framework for TensorFlow, Keras, PyTorch, and Apache MXNet. The goal of Horovod is to make dis

Horovod 12.9k Jan 07, 2023
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

eXtreme Gradient Boosting Community | Documentation | Resources | Contributors | Release Notes XGBoost is an optimized distributed gradient boosting l

Distributed (Deep) Machine Learning Community 23.6k Jan 03, 2023
Tools for mathematical optimization region

Tools for mathematical optimization region

林景 15 Nov 30, 2022
A python library for Bayesian time series modeling

PyDLM Welcome to pydlm, a flexible time series modeling library for python. This library is based on the Bayesian dynamic linear model (Harrison and W

Sam 438 Dec 17, 2022
Steganography is the art of hiding the fact that communication is taking place, by hiding information in other information.

Steganography is the art of hiding the fact that communication is taking place, by hiding information in other information.

Priyansh Sharma 7 Nov 09, 2022
MCML is a toolkit for semi-supervised dimensionality reduction and quantitative analysis of Multi-Class, Multi-Label data

MCML is a toolkit for semi-supervised dimensionality reduction and quantitative analysis of Multi-Class, Multi-Label data. We demonstrate its use

Pachter Lab 26 Nov 29, 2022
Decision tree is the most powerful and popular tool for classification and prediction

Diabetes Prediction Using Decision Tree Introduction Decision tree is the most powerful and popular tool for classification and prediction. A Decision

Arjun U 1 Jan 23, 2022
Bayesian optimization based on Gaussian processes (BO-GP) for CFD simulations.

BO-GP Bayesian optimization based on Gaussian processes (BO-GP) for CFD simulations. The BO-GP codes are developed using GPy and GPyOpt. The optimizer

KTH Mechanics 8 Mar 31, 2022
In this Repo a simple Sklearn Model will be trained and pushed to MLFlow

SKlearn_to_MLFLow In this Repo a simple Sklearn Model will be trained and pushed to MLFlow Install This Repo is based on poetry python3 -m venv .venv

1 Dec 13, 2021
Python bindings for MPI

MPI for Python Overview Welcome to MPI for Python. This package provides Python bindings for the Message Passing Interface (MPI) standard. It is imple

MPI for Python 604 Dec 29, 2022
Management of exclusive GPU access for distributed machine learning workloads

TensorHive is an open source tool for managing computing resources used by multiple users across distributed hosts. It focuses on granting

Paweł Rościszewski 131 Dec 12, 2022
Retrieve annotated intron sequences and classify them as minor (U12-type) or major (U2-type)

(intron I nterrogator and C lassifier) intronIC is a program that can be used to classify intron sequences as minor (U12-type) or major (U2-type), usi

Graham Larue 4 Jul 26, 2022
Skoot is a lightweight python library of machine learning transformer classes that interact with scikit-learn and pandas.

Skoot is a lightweight python library of machine learning transformer classes that interact with scikit-learn and pandas. Its objective is to ex

Taylor G Smith 54 Aug 20, 2022
scikit-learn: machine learning in Python

scikit-learn is a Python module for machine learning built on top of SciPy and is distributed under the 3-Clause BSD license. The project was started

neurodata 3 Dec 16, 2022