Related study recommendation: python tutorial
python's method for artificial intelligence:
Why choose Python?
Python and R are the two most important programming languages in the fields of data science and machine learning. Python is simple and easy to learn, with a wide range of applications (not limited to data analysis) and a gentle learning curve. It is suitable as the first introductory programming language. Data analysis can be carried out through pandas, SciPy/NumPy, sckikit-learn, matplotlib and statsmodels, and it is suitable for engineering tasks and projects that need to be integrated with network applications. As for R, because it is a programming language developed by statisticians, it is good at statistical analysis and chart drawing, and is often used in academic research. It is suggested that R should be mastered to some extent. In general, Python and R are not mutually exclusive, but complementary. Many data engineers and scientists often switch between Python and R, and use R for small-scale model verification, statistical analysis and chart drawing, and then switch to Python when writing algorithms and interacting with databases and network services. In order to reduce the learning cost.
besides data science, Python itself is a universal language, which can be widely used in network development, website building, game development, web crawler and other fields. When you need to integrate system products and services, Python can be used as a one-stop development language. More importantly, Python can also be used as a glue language to easily integrate with languages with better performance such as C/C++. In short, Python is a simple and easy-to-learn but powerful programming language that is worth investing in, so let's introduce it here first.
if you compare Python with r, here are two articles that you can refer to in the data science field: r versus Python peak, which is better for data analysis: r or python? .
how to start introductory machine learning?
in fact, data science is an interdisciplinary subject. In the process of learning how to use Python for machine learning, you usually have to master the following knowledge:
machine learning algorithm
Python programming language and data analysis function library
linear algebra/statistics and other related subjects
domain knowledge in professional fields
In order to master the above three major knowledge (let's focus on the core techniques of machine learning first, Temporarily ignore the mastery of domain knowledge in data science), Specifically, we can refer to the following steps:
1. Grasp the basic knowledge of Python programming language
Online learning resources:
o Codecademy
o DataCamp (you can also learn R)
o learn x in y minutes (x = Python).
o Learn Python theHard Way
2. Understand basic mathematics/ Basic knowledge of statistics and machine learning
o linear algebra of Khan Institute
o intro to de ive statistics
o intro to fundamental statistics
o Andrew Ng machine learning course
o Andrew ng machine learning notes
o CarnegieMellon. University machine learning
o machine learning foundations
3. Know how to use Python scientific computing function library and suite
It is recommended to install Anaconda, support multiple versions of Python across platforms, and install the suite for data analysis and scientific computing by default. It comes with spyder editor and JupyterNotebook (Ipython Notebook), which can provide a web interface for users to develop and maintain Julia, Python or R programs through browsers.
o numpy: scientific analysis, ScipyLecture Notes teaching document
o pandas: data analysis
o matplotlib: a glance at drawing
o scikit-learn: machine learning tool
4. Learning Python machine learning application with Scikit-learn
o MachineLearning: Python machine learning: using Pytho. N
5. Using Python to implement machine learning algorithm
o perceptron
o decision tree
o linear regression
o k-means clustering
6. Implementing advanced machine learning algorithm
o SVM
O KNN
O random forests
O to reduce dimensions
. Rning) implementation and application in Python
o NTU applied Deep Learning
o Stanford Deep Learning
o Deep learning self-study material recommendation
o Deep learning: Chinese learning resources arrangement
To learn more about related learning, please pay attention to the php training column!