Douhh_sisy的博客

废话不多说直接上干货！# ES相关包from elasticsearch import Elasticsearchfrom elasticsearch.helpers import bulk class ElasticSearchClient(object): # 启动ES @staticmethod def get_es_servers(): ...

1、 下载EShttps://www.elastic.co/cn/downloads/past-releases#elasticsearch选择版本6.2.42、 启动双击bin目录下双击elasticsearch.bat即可，输入地址在浏览器中输入“http://127.0.0.1:9200/”，出现一下界面，表示启动成功。3、 安装ElasticSearch管理插件安装He...

import osimport timeimport pydotplusimport numpy as npfrom sklearn import treefrom sklearn.externals.six import StringIOfrom sklearn.model_selection import train_test_splitprint('Step 1.Loadi...

转自https://blog.csdn.net/qq_16000815/article/details/80954039'''scikit-learn中有两类决策树，它们均采用优化的CART决策树算法。'''from sklearn.tree import DecisionTreeRegressor'''回归决策树'''DecisionTreeRegressor(criterio...

机器学习算法需要作用于数据，而数据的本质则决定了应用的机器学习算法是否合适，而数据的质量也会决定算法表现的好坏程度。所以会研究数据，会分析数据很重要。本文作为学习研究数据系列博文的开篇，列举了4个最流行的机器学习数据集。IrisIris也称鸢尾花卉数据集，是一类多重变量分析的数据集。通过花萼长度，花萼宽度，花瓣长度，花瓣宽度4个属性预测鸢尾花卉属于（Setosa，Versicolour，V...

import torchimport torch.nn.functional as F # 激励函数都在这x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1) # x data (tensor), shape=(100, 1)y = x.pow(2) + 0.2*torch.rand(x.size()) ...

import torchimport torch.nn.functional as F # 激励函数都在这x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1) # x data (tensor), shape=(100, 1)y = x.pow(2) + 0.2*torch.rand(x.size()) ...

%matplotlib inlineimport matplotlib.pyplot as pltimport numpy as npfrom time import timefrom sklearn.datasets import load_filesprint("loading documents ...")t = time()docs = load_files('dat...

%matplotlib inlineimport matplotlib.pyplot as pltimport numpy as npfrom sklearn.datasets import make_blobsX, y = make_blobs(n_samples=200, n_features=2, cen...

%matplotlib inlineimport matplotlib.pyplot as pltimport numpy as npfrom time import timefrom sklearn.datasets import load_filesprint("loading train dataset ...")t = time()news_train = load_...

%matplotlib inlineimport matplotlib.pyplot as pltimport numpy as npdef plot_hyperplane(clf, X, y, h=0.02, draw_sv=True, title='hype...

%matplotlib inlineimport matplotlib.pyplot as pltimport numpy as npimport pandas as pddef read_dataset(fname): # 指定第一列作为行索引 data = pd.read_csv(fname, index_col=0) #列索引为csv文件第一行 ...

Bagging从原始样本集中抽取训练集。每轮从原始样本集中使用Bootstraping（有放回）的方法抽取n个训练样本（在训练集中，有些样本可能被多次抽取到，而有些样本可能一次都没有被抽中）。共进行k轮抽取，得到k个训练集。（我们这里假设k个训练集之间是相互独立的，事实上不是完全独立）每次使用一个训练集得到一个模型，k个训练集共得到k个模型。但是是同种模型。（注：k个训练集虽然有重合不完全...

地址戳我 # 基本CSV读写操作 # 我们需要读取给定的训练数据，再进行后续的数据(特征等)处理 def read_data(file_name): f = open(file_name) #ignore header f.readline() samples = [] target =...

比赛地址https://www.kaggle.com/c/sf-crime 这里用logistic regression来完成这个预测问题。 # 基本CSV读写操作 # 我们需要读取给定的训练数据，再进行后续的数据(特征等)处理def read_data(file_name): f = open(file_name) #ignore header ...

%matplotlib inlineimport matplotlib.pyplot as pltimport numpy as np# 载入数据from sklearn.datasets import load_breast_cancercancer = load_breast_cancer()X = cancer.datay = cancer.targetprint('...

%matplotlib inlineimport matplotlib.pyplot as pltimport numpy as npfrom sklearn.datasets import load_bostonboston = load_boston()X = boston.datay = boston.targetX.shape(506, 13)X[0]...

%matplotlib inlineimport matplotlib.pyplot as pltimport numpy as npn_dots = 200X = np.linspace(-2 * np.pi, 2 * np.pi, n_dots)Y = np.sin(X) + 0.2 * np.random.rand(n_dots) - 0.1X = X.reshape(-...

%matplotlib inlineimport matplotlib.pyplot as pltimport numpy as np# 生成训练样本n_dots = 40X = 5 * np.random.rand(n_dots, 1)y = np.cos(X).ravel()# 添加一些噪声y += 0.2 * np.random.rand(n_dots) - 0.1...

%matplotlib inlineimport matplotlib.pyplot as pltimport numpy as npimport pandas as pd# 加载数据data = pd.read_csv('datasets/pima-indians-diabetes/diabetes.csv')print('dataset shape {}'.for...