你知道吗？五大银行都在用Python软件
你知道吗？Python即将成为最热门的数据分析软件
赫赫有名的陈老师，隆重推出“Python就业实战班”，
两个月时间掌握，令您从众多竞争对手中脱颖而出，2016高薪就
您还在犹豫什么！订座热线：416-665-1888!
讲座时间：6/18（周六）2:30pm
Python处理数据的优势：
1. 异常快捷的开发速度，代码量巨少
2. 丰富的数据处理包，不管正则也好，html解析，xml解析，
3. 内部类型使用成本巨低，不需要额外怎么操作
4. 有处理大数据的框架，编码问题处理起来异常方便了
【主讲人】Mr. Chen
- 曾担任加拿大最大电信公司Director，
- 多次担任SAS公司技术讲座主讲嘉宾，获得大量好评
- 中国重点高校客座教授
- 多市最早从事数据分析工作的华人之一
- 多年北美政府，银行，通信，医药行业工作经验
- 对就业市场，数据分析工作的前景，简历准备，面试技巧，
- 维多利亚多年从教经验，
为什么我们选择Python?
Python是一种面向对象、直译式的电脑程式语言，
Python的设计哲学是“优雅”、“明确”、“简单”。 Python开发者的哲学是“用一种方法，
Python具备垃圾回收功能，能够自动管理内存使用。
加国“数据分析第一名师”陈老师重拳出击：
讲座时间：6/18（周六）2:30pm
第一次课：6月25日（周六）6pm;固定在每周六6pm-
[课程内容]
Session 1
Part 1: Introduction to Applied Data Science with Python Course
• Inclination
• Lessons
• Projects
• Recipes
• What You Learn From This Course
• FAQ
Part 2: Python Ecosystem for Machine Learning
• Python Ecosystem Installation
• Jupyter Installation
• SciPy – NumPy, Matplotlib, Pandas, Scikit-Learn, and statsmodels
Part 3: Python Programming Basics
• Variables and Data Types
• Basic Operators
• Number Type Conversion
• Mathematical, Random Number, Trigonometric Functions and Mathematics Constants
• Working With Lists, Tuples, Strings, Sets and Dictionary
• Working With Sequences
• Working With Collections
• Conditionals
• Loops
• Functions
• Class
• Exercises 1
Part 4: Data Ingestion and Munging
• Data Loading
a. Load CSV Files with the Python Standard Library
b. Load CSV Files with NumPy
c. Load CSV Files with Pandas
• Data Processing
a. Data Preprocessing with Pandas
a) Data Selection and Manipulation
b) Dealing with problematic data and Missing Value
c) Dealing with big datasets
d) Accessing other data formats
b. Data Preprocessing with NumPy
a) Creating NumPy Arrays
b) NumPy Fast Operation and Computations
• Working with Categorical and Textual Data
• Visualization
a) Introducing the basics of matplotlib
b) Selected graphical examples with pandas
c) Advanced data learning representation
• Exercises 2
Session 2
Part 5: Introducing EDA
• Understand Data With Descriptive Statistics
• Understand Data With Visualization
• The Detection and Treatment of Outliers
a. Univariate outlier detection
b. EllipticEnvelope
c. OneClassSVM
• Pre-Process Data
a. Data Transforms
b. Rescale Data
c. Standardize Data
d. Normalize Data
e. Binarize Data
• Dimensionality Reduction
a. The Covariance Matrix
b. Principal Component Analysis (PCA)
c. RandomizedPCA
d. Latent Factor Analysis (LFA)
e. Linear Discriminant Analysis (LDA)
f. Latent Semantical Analysis (LSA)
g. Independent Component Analysis (ICA)
h. Kernel PCA
• Exercise 3
Part 6: Feature Selection
• Univariate Selection
• Recursive Feature Elimination
• Stability and L1 Based Selection
• Feature Importance
• Exercise 4
Part 7: Resampling Methods
• Train and Test Sets.
• K-fold Cross Validation.
• Leave One Out Cross Validation.
• Repeated Random Test-Train Splits
Part 8: Algorithm Evaluation Metrics
• Classification Metrics
a. Classification Accuracy
b. Logarithmic Loss
c. Area under ROC Curve
d. Confusion Matrix
e. Classification Report
• Regression Metrics
a. Mean Absolute Error
b. Mean Squared Error
c. R-square
Part 9: Model Techniques Selection for Classification
• Linear Machine Learning Algorithms
a. Logistic Regression
b. Linear Discriminant Analysis
• Nonlinear Machine Learning Algorithms:
a. K-Nearest Neighbors.
b. Naive Bayes.
c. Classification and Regression Trees.
d. Support Vector Machines
• Exercise 5
Part 10: Model Techniques Exploration for Regression
• Linear Machine Learning Algorithms
a. Linear Regression.
b. Ridge Regression.
c. LASSO Linear Regression.
d. Elastic Net Regression
• Nonlinear Machine Learning Algorithms:
a. K-Nearest Neighbors.
b. Classification and Regression Trees.
c. Support Vector Machines
• Exercise 6
Part 11: Champion Model Technique Selection
• How to formulate an experiment to directly compare machine learning algorithms
• A reusable template for evaluating the performance of multiple algorithms
• How to report and visualize the results when comparing algorithm performance
• Exercise 7
Part 12: Pipelines Machine Learning Work Flows Automation
• How to use pipelines to minimize data leakage.
• How to construct a data preparation and modeling pipeline.
• How to construct a feature extraction and modeling pipeline
• Exercise 8
Part 13: Ensemble Methods
• Bagging. Building multiple models from different subsamples of the training dataset
a. Bagged Decision Trees
b. Random Forest
c. Extra Trees
• Boosting. Building multiple models (typically of the same type) each of which learns to fix the prediction errors of a prior model in the sequence of models
a. adaBoost
b. Stochastic Gradient Boosting
• Voting. Building multiple models (typically of differing types) and simple statistics (like calculating the mean) are used to combine predictions
• Exercise 9
Part 14: Algorithm Parameter Tuning
• The importance of algorithm parameter tuning to improve algorithm performance.
• How to use a grid search algorithm tuning strategy.
• How to use a random search algorithm tuning strategy
• Exercise 10
Part 15: Save and Load Machine Learning Models
• Finalize Your Model with pickle
• Finalize Your Model with joblib
Part 16: Projects
• Predictive Modeling Project Template
a. Use A Structured Step-By-Step Process
b. Machine Learning Project Template in Python
c. Machine Learning Project Template Steps
d. Tips For Using The Template Well
• Project 1: The Hello World of Classification Machine Learning (multinomial target model)
• Project 2: Regression Machine Learning Case Study Project (continuous target model)
• Project 3: Binary Classification Machine Learning Case Study Project (binary target model)
【主讲人】Mr. Chen
维多利亚培训中心(Victoria Training Center (Toronto)
订座电话：416-665-1888，Website：www.
地址：200 Consumers Road，Suite 118，M2J 4R4 (位于Consumers夹Sheppard东南角第三座楼，
)
订座电话：416-665-1888，Website：www.
地址：200 Consumers Road，Suite 118，M2J 4R4 (位于Consumers夹Sheppard东南角第三座楼，
)
