JD sliding verification code cracking of selenium and PIL

Single layer graph slide verification code of selenium and PIL How to crack the slide verification code preparation in advance Code operation How to crack the slide verification code There are various mechanisms of anti climbing on the market, among which the sliding verification code is divided into two-layer graph ...

Posted by Kev on Sun, 10 May 2020 01:54:26 -0700

Machine learning Chapter 4 training model

Reference: author's Jupyter NotebookChapter 2 – End-to-end Machine Learning project Generate picture and savefrom __future__ import division, print_function, unicode_literals import numpy as np import matplotlib as mpl import matplotlib.pyplot as plt import os np.random.seed(42) mpl.rc('axes', labelsize=14) mpl.rc('xtick', labelsize=12) mpl.r ...

Posted by Scriptor on Fri, 27 Mar 2020 03:26:21 -0700

Naive Bayesian understanding and code reproduction of statistical learning methods

Naive Bayes The joint probability P(A,B) = P(B|A)*P(A) = P(A|B)*P(B) combines the two equations on the right to get the following formula: P (a| b) indicates the probability of a in the case of B. P(A|B) = [P(B|A)*P(A)] / P(B) Let's have A visual understanding of this formula. As shown in the figure ...

Posted by PHP_apprentice on Sun, 15 Mar 2020 22:13:16 -0700

NO.89 - Applying Xgboost to Predict Insurance Compensation

Article Directory 1 Data analysis 1.1 First look at what the data looks like 1.2 Continuous and categorical variables 1.3 Number of attributes in categorical variables 1.4 Compensation value 1.5 Continuous Variable Characteristics 1.6 Correlation between features 2 Xgboost 2.1 Data Preprocessing 2.2 ...

Posted by rimelta on Wed, 11 Mar 2020 21:00:47 -0700

"Python drawing sharp tool": Matplotlib tutorial

Article directory 1. Preface 2. Introduction to Matplotlib 3. installation 4. Drawing basis 4.1 plot() function 4.1.1 Chinese display 4.1.2 text display 5. Drawing of common charts 5.1 histogram 5.1.1 simple example 5.1.2 function definition 5.1.3 histogram of normal distribution 5.2 pie chart ...

Posted by BLaZuRE on Thu, 05 Mar 2020 19:40:13 -0800

Python infrastructure

When building a house, the choice of wood is a problem. A carpenter's goal is essentially to carry a good cutting tool. When he has time, he sharpens his equipment. {-:} - Miyamoto Musashi (wulunshu) This article is excerpted from Chapter 2 of Python big data analysis (version 2) For new Python users, ...

Posted by jmurch on Wed, 26 Feb 2020 19:11:26 -0800

Splitting and Extracting Text Data in pandas

This paper mainly shares the splitting, extracting and merging of text data to prepare for the next visual analysis. The data comes from the employment information of boss and dragnet data analysis positions, totaling 9458. The crawling methods of the pull-hook are as follows: Python selenium+beautifuls ...

Posted by timelf123 on Mon, 24 Feb 2020 19:58:24 -0800

The application of Matplotlib in solving ordinary differential equation of Python 3 SCI

Python scientific calculation simply records several notes, uses SciPy to solve ordinary differential equations, and uses matplotlib to demonstrate in jupyter notebook. The following points need to be noted: odeint function provided by integration module On jupyter notebook of Anaconda 3 matplotlib 2D drawing to solve Newton's cooli ...

Posted by phpcodec on Thu, 13 Feb 2020 12:52:36 -0800

Docker build container build acceleration strategy

It takes a lot of time to download many kinds of software when building containers. hub.docker.com is slow in nature, especially when it encounters modules stored on gcr.io/aws and so on. pip installation of python module is also slow, and the download of conda is like a snail. There are several ways to speed up the download of container const ...

Posted by safrica on Thu, 30 Jan 2020 07:19:13 -0800

Advanced Neural Network for Python Deep Learning Experiment

Advanced Neural Network Experimental environment keras 2.1.5 tensor 1.4.0 Experimental tools Jupyter Notebook Experiment 1: MNIST generates antagonistic networks thinking Train two models, one to generate a given random noise as input output example G, and one to identify the generated m ...

Posted by jonat8 on Sat, 11 Jan 2020 16:58:06 -0800