口袋里的小小哥的博客

这里layout是一个LTPage对象,里面存放着这个page解析出的各种对象,一般包括LTTextBox, LTFigure, LTImage, LTTextBoxHorizontal等等,想要获取文本就获得对象的text属性，for page in PDFPage.create_pages(doc): # doc.get_pages() 获取page列表。# 创建一个PDF解释器对象,对文档编码，解释成Python能够识别的格式：PDFPageInterpreter。# 需要写出编码格式。

python获取dos窗口/cmd/pycharm Terminal命令返回详情

RSA+python

图片切割

拼接方法有了，其他的自己看jy验证码

_sqlite3错误解决

centos ModuleNotFoundError: No module named ‘_lzma‘ 解决

import xlwtbook = xlwt.Workbook() #创建Excelsheet = book.add_sheet('sheet1') #创建sheet页data = [ ["A",99,100,98.5], ["B",90,30.5,95], ["C",67.5,49.6,88] ]title = ['姓名','语文成绩','数学成绩','英语成绩'] #把表头名称放入list里面#循环把表头写入row = 0for t in title.

二维码转链接import requests from pyzbar.pyzbarimport decodefrom PIL import Imagefrom io import BytesIO# 传入二维码图片链接，返回扫码后的真实urldef get_url(url): res=requests.get(url=url).content bio = BytesIO(res) img = Image.open(bio) barcodes = d...

Centos7安装Python3.7说明全部操作都在root用户下执行1.安装编译相关工具yum -y groupinstall "Development tools"yum -y install zlib-devel bzip2-devel openssl-devel ncurses-devel sqlite-devel readline-devel tk-devel gdbm-devel db4-devel libpcap-devel xz-develyum install lib

1. 电话号码code_list='򈊷򈊻򈊼򈊹򈊷򈊸򈊼򈊽򈊽򈊽&#x882b7'2. 要转换为16进制，需要把&#替换为0# 替换&#为0，用于后面直接转换为10进制数code_list=code_list.replace("&#

for i in collection.find({"raw":{"$exists":True},"raw3":{"$exists":False}},no_cursor_timeout=True).batch_size(100):

#以前的sheet数据很重要，又要新增sheet，很难受，看了一堆帖子没一个回答在点子上，找到了方法，分享给大家import openpyxlimport pandas as pdweatherfile = "0317.xlsx" #路径writer = pd.ExcelWriter(weatherfile,engine='openpyxl')pd_data=pd.DataFrame(数据) #writer = pd.ExcelWriter(weatherfile,...

2、进行基础配置，作为 git 的基础配置，作用是告诉 git 你是谁，你输入的信息将出现在你创建的提交中，使用下面两条命令：　　git config --global user.name"你的名字或昵称"　　git config --global user.email"你的邮箱"3.、在你自己人员文件夹中执行下面命令，完成初始化 git init ...

import tensorflow as tfimport numpy as npimport pandas as pdimport matplotlib.pyplot as plt(train_image, train_lable), (test_image, test_label) = tf.keras.datasets.fashion_mnist.load_data()trai...

import tensorflow as tfimport numpy as npimport pandas as pdimport matplotlib.pyplot as plt# fashion_mnist = tf.keras.datasets.fashion_mnist.load_data()(train_image, train_lable), (test_image, ...

# 分类问题的时候用交叉熵损失函数会更有效# binary_crossentropy 来计算二元交叉熵import tensorflow as tfimport numpy as npimport pandas as pdimport matplotlib.pyplot as pltdata = pd.read_csv('credit-a.csv', header=None)# ...

import tensorflow as tfimport pandas as pdimport matplotlib.pyplot as pltdata = pd.read_csv('TensorFlow学历与收入预测.csv')# print(data)plt.scatter(data.Education, data.Income)# plt.show()# 单变量线性回归...

import numpy as npimport pandas as pdpd.set_option('display.max_columns', None)from sklearn.linear_model import LogisticRegression as LRdata = pd.read_csv('评分卡模型数据.csv')# print(data.head())# ...

# todo 重要参数 solver & multi_class# multi_class 输入告知模型，我们要处理分类问题的模型# 1. 输入 'ovr' 处理二分类，或者让模型使用‘一对多’的形式来处理多分类问题# 2.'multinomial' 处理多分类，这种输入在参数solverwe是linlinear时不可用# 3.'auto' ...

# max_iter 控制步长# max_iter越大，步长越小，迭代次数大，模型时间长，反之from sklearn.linear_model import LogisticRegression as LRfrom sklearn.datasets import load_breast_cancerimport numpy as npimport matplotlib.pyplot ...

# 方法1.自己分析# ＰＣＡ　和　ＳＶＤ　一般用不上# 方法2. 统计方法可以使用，但没必要# todo: 高效的嵌入法from sklearn.linear_model import LogisticRegression as LRfrom sklearn.datasets import load_breast_cancerimport numpy as npimport...

# linear_model.LogisticRegression 逻辑回归回归分类器（又叫logit回归，最大熵分类器）# linear_model.LogisticRegressionCV 带交叉验证的逻辑回归分类器# linear_model.logistic_regression_path 计算Logistic回归模型以获得正则化参数的列表# linear_model....

import pandas as pdimport numpy as npdata = pd.read_csv("digit recognizor.csv")# print(data.head())x = data.iloc[:, 1:]y = data.iloc[:, 0]# print(x.shape) ##(42000, 784)"""数据量相对夸张，如果使用支持向量机...

import pandas as pdfrom sklearn.impute import SimpleImputerdata = pd.read_csv('缺失预处理数据22222.csv', index_col=0) # 把第0列作为索引data.loc[:, "Age"] = SimpleImputer(strategy="median").fit_transform(data....

import pandas as pdfrom sklearn.impute import SimpleImputer # 专门补缺的类from sklearn.preprocessing import LabelEncoder # 标签专用，能够将分类转换为分类数值data = pd.read_csv('缺失预处理数据22222.csv', index_col=0) # 把第0列...

# 数据归一化from sklearn.preprocessing import MinMaxScalerimport pandas as pddata = [[-1, 2], [-0.5, 6], [0, 10], [1, 18]]# todo: 实现归一化scaler = MinMaxScaler() # 实例化# scaler = scaler.fit(data) # ...

# -*- coding: utf-8 -*-# rfc = RandomForestClassifier(n_estimators=68# ,random_state=90# ,criterion="gini"# ...

from sklearn.datasets import load_breast_cancerfrom sklearn.ensemble import RandomForestClassifierfrom sklearn.model_selection import GridSearchCVfrom sklearn.model_selection import cross_val_scor...

from pprint import pprintfrom sklearn.ensemble import RandomForestRegressor # 随机森林回归器from sklearn.impute import SimpleImputer # 用来填补缺失值的import numpy as npimport pandas as pdimport matplotlib....

# todo: 集成算法模块 集成学习 ensemble# 决策树非常容易 过拟合：在训练集上表现优秀，却在测试集上表现糟糕，一般用剪枝# 目前最受欢迎的集成算法GBDT# todo:三类集成算法：# ·装袋法（Bagging）：构建多个相互独立的评估器，然后对其预测进行平均或多数表决原则来决定集成评估器的结果。装袋法的代表模型就是随机森林# ·提升法（Boosting） ：基评...

import pandas as pdfrom sklearn.tree import DecisionTreeClassifierimport matplotlib.pyplot as pltfrom sklearn.model_selection import GridSearchCV, train_test_split, cross_val_score # 测试集训练集## da...

from sklearn.datasets import load_boston # 著名波士顿房价数据from sklearn.model_selection import cross_val_score # 交叉验证from sklearn.tree import DecisionTreeRegressor# todo：# 几乎所有参数，属性和接口都和分类树一模一样# 参数#...

from pprint import pprintfrom sklearn import treefrom sklearn.datasets import load_wine # 自带数据库，可以导入知名数据from sklearn.model_selection import train_test_split # 测试集训练集import graphvizimport pand...