Alive_lei的博客

coding=utf-8“”"author:leifunction: 实现的是构建词典，实现方法把句子转换为数字序列并将其翻转“”"class Word2Sequence(object):UNK_TAG = “UNK”PAD_TAG = “PAD”UNK = 0PAD = 1def __init__(self): self.dict = { self.UNK_TAG: self.UNK, self.PAD_TAG: self.PAD }

1、数据的属性¶import numpy as np​创建ndarrayscore = np.array([[80, 89, 86, 67, 79],[78, 97, 89, 67, 81],[90, 94, 78, 67, 74],[91, 91, 90, 67, 69],[76, 87, 75, 67, 86],[70, 79, 84, 67, 84],[94, 92, 93, 67, 64],[86, 85, 83, 67, 80]])​scorearray([[80,

coding=utf-8“”"author:leifunction: 对mnist数据集进行模型训练，预测“”"from sklearn.svm import SVCfrom sklearn.decomposition import PCAfrom sklearn.model_selection import train_test_splitimport pandas as pdimport joblibimport matplotlib.pyplot as pltimport ran

from sklearn.datasets import load_iris, make_classificationfrom sklearn.model_selection import train_test_splitimport tensorflow as tfimport numpy as npX, Y = make_classification(n_samples=500, n_features=5, n_classes=2)x_train, x_test, y_train, y_tes

coding=utf-8“”"author:leifunction: 使用svm识别mnist“”"import timeimport numpy as npimport pandas as pdimport matplotlib.pyplot as pltfrom sklearn import svmfrom sklearn.model_selection import train_test_splitfrom sklearn.decomposition import PCAdef

coding=utf-8“”"author:leifunction:“”"from sklearn.cluster import KMeansimport pandas as pdfrom sklearn.decomposition import PCAfrom sklearn.metrics import silhouette_scoreorder_product = pd.read_csv("./data/instacart/order_products__prior.csv")pr

from pylab import mpl设置显示中文字体mpl.rcParams[“font.sans-serif”] = [“SimHei”]设置正常显示符号mpl.rcParams[“axes.unicode_minus”] = False如果没有pylab，记得先pip install pylab 哦！

from pylab import mpl设置显示中文字体mpl.rcParams[“font.sans-serif”] = [“SimHei”]设置正常显示符号mpl.rcParams[“axes.unicode_minus”] = Falsex = range(60)y_beijing = [random.uniform(10, 15) for i in x]y_shanghai = [random.uniform(15, 25) for i in x]创建1行两列的画布fig, ax

import randomfrom pylab import mpl设置显示中文字体mpl.rcParams[“font.sans-serif”] = [“SimHei”]设置正常显示符号mpl.rcParams[“axes.unicode_minus”] = False0.生成数据x = range(60)y_beijing = [random.uniform(10, 15) for i in x]y_shanghai = [random.uniform(15, 25) for i in

coding=utf-8“”"author:leifunction: 虎牙直播爬取“”"import timefrom selenium import webdriverclass HuYa(object):def init(self):self.url = “https://www.huya.com/l”options = webdriver.ChromeOptions()options.binary_location = r"D:\文件2\Google\Chrome\Applica

解决chrome+selenium使用时出现：selenium.common.exceptions.WebDriverException: Message: unknown error: cannot find Chrome binary。有时候可能是我们的selenium和chrome对应版本有问题，或者未将chrome和selenium加入到环境变量。但有时当我们这些都解决后还是未能自动打开chrome，还会报这样错误，那我们就可以用如下的方式进行修改。其地址：是对应于你们的chrome_webdri

coding=utf-8“”"author:leifunction:“”"定义学生类class Student(object):def init(self, name, gender, tel):self.name = nameself.gender = genderself.tel = teldef __str__(self): return "{}, {}, {}".format(self.name, self.gender, self.tel)定义学生管理类clas

coding=utf-8“”"author:leifunction: L2正则化 解决过拟合，使得w的每个元素都很小，都接近于0越小的参数说明模型越简单，越简单的模型则越不容易产生过拟合现象线性回归：容易出现过拟合，为了把训练集数据表现的更好，可使用L2正则化：Ridge：岭回归，带有正则化的线性回归，解决过拟合。回归解决过拟合“”"岭回归from sklearn.linear_model import Ridgefrom sklearn.preprocessing import Sta

coding=utf-8“”"author:leifunction: 逻辑回归做二分类“”"import pandas as pdfrom sklearn.linear_model import LogisticRegressionimport numpy as npfrom sklearn.model_selection import train_test_splitfrom sklearn.preprocessing import StandardScalerfrom sklearn

coding=utf-8“”"author:leifunction:“”"from sklearn.datasets import load_bostonfrom sklearn.linear_model import LinearRegression, SGDRegressorfrom sklearn.model_selection import train_test_splitfrom sklearn.preprocessing import StandardScalerfrom sk

coding=utf-8“”"author:leifunction:“”"import pandas as pdfrom sklearn.cluster import KMeansbeer = pd.read_csv(“data.txt”, sep="")X = beer[[“calories”, “sodium”, “alcohol”, “cost”]]km = KMeans(n_clusters=3).fit(X)km2 = KMeans(n_clusters=2).fit(X)b

coding=utf-8“”"author:leifunction: k近邻算法，欧式距离，两点之间的距离公式需要进行标准化处理“”"from sklearn.neighbors import KNeighborsClassifierfrom sklearn.model_selection import train_test_splitfrom sklearn.preprocessing import StandardScalerfrom sklearn.datasets import f

coding=utf-8“”"author:leifunction: 决策树“”"from sklearn.tree import DecisionTreeClassifierfrom sklearn.feature_extraction import DictVectorizerfrom sklearn.model_selection import train_test_splitfrom sklearn.tree import export_graphvizfrom sklearn.d

coding=utf-8“”"author:lei 5function: 特征选择“”"from sklearn.feature_selection import VarianceThreshold # 特征选择from sklearn.decomposition import PCAnum_list = [[0, 2, 0, 3], [0, 1, 4, 3], [0, 1, 1, 3]]def var():“”"特征选择-删除低方差特征:return:“”"var = Va

coding=utf-8“”"author:leifunction: 特征抽取“”"from sklearn.feature_extraction import DictVectorizerfrom sklearn.feature_extraction.text import CountVectorizerfrom sklearn.feature_extraction.text import TfidfVectorizerimport jiebatext_list = [“life is

coding=utf-8“”"author:leifunction:“”"from sklearn.preprocessing import MinMaxScaler # 归一化from sklearn.preprocessing import StandardScaler # 标准化from sklearn.preprocessing import Imputer # 数据预处理import randomimport numpy as npnum_list = [[random.

coding=utf-8“”"author:leifunction:“”"import osimport torchfrom torch.optim import Adamfrom torch.nn import functional as Ffrom torch import nnfrom torch.utils.data import DataLoaderfrom torchvision.datasets import MNISTfrom torchvision.transfor

coding=utf-8“”"author:leifunction:“”"import torchfrom torch.utils.data import Dataset, DataLoaderimport mathdata_path = “./data/SMSSpamCollection”完成数据集类class MyDataset(Dataset):def init(self):self.lines = open(data_path, encoding=“utf8”).readli

coding=utf-8“”"author:leifunction:“”"from torch.optim import SGDimport torchfrom torch import nn定义一个device对象 如果要转换为gpu上运行device = torch.device(“cuda” if torch.cuda.is_available() else “cpu”)准备数据x = torch.rand([500, 1]).to(device)y_true = 3 * x

import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_data载入数据集mnist = input_data.read_data_sets(“mnist_data”, one_hot=True)每个批次的大小batch_size = 100计算一共多少个批次n_batch = mnist.train.num_examples // batch_size定义两个placeholder 一张图片

coding=utf-8“”"author:leifunction:“”"import tensorflow as tfimport numpy as npimport matplotlib.pyplot as pltfrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("./mnist_data/", one_hot=True)trainimgs, trai

import tensorflow as tf定义线性回归def linearregression():“”"实现线性回归:return:“”"# 准备数据集 x[100, 1] 0.8*x + 0.7 = [100, 1]with tf.variable_scope(“orginal_name”):x = tf.random_normal([100, 1], mean=0, stddev=1)y_true = tf.matmul(x, [[0.8]]) + [[0.7]]# 建立

coding=utf-8“”"author:leifunction:迁移学习“”"import tensorflow as tffrom tensorflow.python import kerasfrom tensorflow.python.keras.preprocessing.image import ImageDataGenerator, load_img, img_to_arrayfrom tensorflow.python.keras.applications.vgg16 imp

from tensorflow.python.keras.applications.vgg16 import VGG16, preprocess_input, decode_predictionsfrom tensorflow.python.keras.preprocessing.image import load_img, img_to_arraydef predict():model = VGG16()print(model.summary())# 预测一张图类别# 加载图片 要求是vgg

构建神经网络进行时装模型训练与预测class SinleNN(object):# 建立神经网络模型model = keras.Sequential([ # 将输入数据的形状进行修改为扁平化 keras.layers.Flatten(input_shape=[28, 28]), # 定义隐藏层，128个神经元的网络层 keras.layers.Dense(128, activation=tf.nn.relu), # 10个类别的分类问题，输出神经元的个数和输出类别

coding=utf-8“”"author:leifunction:“”"from tensorflow.python.keras.datasets import cifar100from tensorflow.python import kerasimport tensorflow as tffrom tensorflow.python.keras.applications import VGG16class CNNCifar(object):# 定义模型model = keras.

数据集下载:https://aistudio.baidu.com/aistudio/datasetDetail/16630主要训练模型:coding=utf-8“”"author:leifunction:使用googlenet进行图片分类“”"import tensorflow as tffrom tensorflow.contrib import slimimport nump...

-- coding: utf-8 --“”"@Time : 19-9-12 上午10:51@Author : lei@Site :@File : crx信誉分析.py@Software: PyCharm“”"import pandas as pdfrom sklearn.feature_extraction import DictVectorizerfrom sklearn.m...

-- coding: utf-8 --“”"@Time : 19-10-1 上午7:32@Author : lei@Site :@File : 神经网络预测股票.py@Software: PyCharm“”"股票预测import pandas as pdimport numpy as npfrom sklearn.model_selection import train_te...

-- coding: utf-8 --“”"@Time : 19-9-19 下午2:50@Author : lei@Site :@File : dermatology皮肤病.py@Software: PyCharm“”"import pandas as pdimport numpy as npfrom sklearn.ensemble import RandomForestCl...

这里写自定义目录标题欢迎使用Markdown编辑器新的改变功能快捷键合理的创建标题，有助于目录的生成如何改变文本的样式插入链接与图片如何插入一段漂亮的代码片生成一个适合你的列表创建一个表格设定内容居中、居左、居右SmartyPants创建一个自定义列表如何创建一个注脚注释也是必不可少的KaTeX数学公式新的甘特图功能，丰富你的文章UML 图表FLowchart流程图导出与导入导出导入新建一个迷你...