zzl150298的博客

原创 LDA算法

原创 决策树作业

原创 2021-10-21

import gym, os from itertools import count import paddle import paddle.nn as nn import paddle.optimizer as optim import paddle.nn.functional as F from paddle.distribution import Categorical print(paddle.version) device = paddle.get_device() env = gym.make(

原创 2021-09-26

import paddle from paddle.nn import Linear import paddle.nn.functional as F import os import numpy as np import matplotlib.pyplot as plt train_dataset = paddle.vision.datasets.MNIST(mode=‘train’) train_data0 = np.array(train_dataset[0][0]) train_label_0 =

原创 2021-09-17神经网络反向传播

转载 python实现感知器

from __future__ import print_function from functools import reduce class VectorOp(object): def dot(x, y): """ 计算两个向量x和y的内积 """ # 首先把x[x1,x2,x3...]和y[y1,y2,y3,...]按元素相乘 # 变成[x1*y1, x2*y2, x3*y3] # 然后利用re

原创 监督学习（房产）

import numpy as np import math import random x1= np.array([2104,1600,2400,1416,3000]) x2 = np.array([3,3,3,2,4]) t = np.array([400,330,369,232,540]) theta0=random.random() theta1=random.random() theta2=random.random() alpla = 0.1 e = 0.0000001 k0=random.ra

原创 zzl剩余作业

import numpy as np a1=np.random.choice(7,5) a1 array([6, 5, 2, 4, 6]) a2=np.random.choice([0,1,2,3,4,5,6],5) a2 array([0, 1, 6, 3, 5]) a3=np.random.choice(np.array([0,1,2,3,4,5,6]),5) a3 array([2, 0, 5, 0, 6]) a4=np.random.choice([0,1,2,3,4,5,6],

原创 np.prod()计算元素乘积

x=np.array([[1,2,3],[2,3,4]]) np.prod(x) 144 np.prod(x,axis=1) array([ 6, 24]) np.prod(x,axis=0) array([ 2, 6, 12])

原创 np.pad()函数进行padding操作

import numpy as np A= np.arange(95,99).reshape(2,2) A array([[95, 96], [97, 98]]) np.pad(A,((3,2),(2,3)),'constant',constant_values=(0,0)) array([[ 0, 0, 0, 0, 0, 0, 0], [ 0, 0, 0, 0, 0, 0, 0], [ 0, 0, 0, 0, 0, 0,

原创 np.newaxis在特定位置增加一个维度

import numpy as np c=np.array([1,2,5,4]) c[:,np.newaxis] array([[1], [2], [5], [4]]) c[np.newaxis,:] array([[1, 2, 5, 4]])

原创 np.meshgrid()快速生成网格

import numpy as np x=np.array([1,3,5]) y=np.array([4,6]) XX,YY=np.meshgrid(x,y) XX array([[1, 3, 5], [1, 3, 5]]) YY array([[4, 4, 4], [6, 6, 6]])

原创 np.hstack()和np.vstack()用于堆叠矩阵

import numpy as np x=np.array([[3,4,5],[1,3,4]]) y=np.array([[1,1,1],[2,2,2]]) np.hstack((x,y)) array([[3, 4, 5, 1, 1, 1], [1, 3, 4, 2, 2, 2]]) np.vstack((x,y)) array([[3, 4, 5], [1, 3, 4], [1, 1, 1], [2, 2, 2]])

原创 np.full生成形为shape的元素全为val的矩阵

import numpy as np c=np.array([[1,2],[3,4]]) c array([[1, 2], [3, 4]]) c.astype(np.float32) array([[1., 2.], [3., 4.]], dtype=float32)

原创 np.argmax

import numpy as np a=np.array([[1,1,1],[2,2,2],[0,3,6]]) a array([[1, 1, 1], [2, 2, 2], [0, 3, 6]]) b1=np.argmax(a) b1 8 b2=np.argmax(a,axis=0) b2 array([1, 2, 2], dtype=int64) b3=np.argmax(a,axis=1) b3 array([0, 0, 2], dtype=int6

原创 insert()函数

import numpy as np matrix=[ [1,2,3,4], [5,6,7,8], [9,10,11,12] ] q1=np.insert(matrix,1,[1,1,1,1],0) print(' >>>>q1>>>>\n' ,q1) >>>>q1>>>> [[ 1 2 3 4] [ 1 1 1 1] [ 5 6 7 8] [ 9 10

原创 delete()函数

import numpy as np matrix=[ [1,2,3,4], [5,6,7,8], [9,10,11,12] ] p1=np.delete(matrix,1,0) print(' >>>>p1>>>>\n' ,p1) >>>>p1>>>> [[ 1 2 3 4] [ 9 10 11 12]] p2=np.delete(matrix,1,1) prin

原创 append()函数

import numpy as np matrix=[ [1,2,3,4], [5,6,7,8], [9,10,11,12] ] m1=np.append(matrix,[[1,1,1,1]],axis=0) print(' >>>>m1>>>>\n' ,m1) >>>>m1>>>> [[ 1 2 3 4] [ 5 6 7 8] [ 9 10 11 12] [

原创 numpy作业

```python c = np.arange(1,13).reshape(6,2) ``` --------------------------------------------------------------------------- NameError Traceback (most recent call last) <ipython-input-1-267063bef37c>...