python for data science
Python Basics
Learn the workflows, tools, and approaches that data scientists use to analyze and transform data it into insights
Fundamental Packages
Walk through the foundation of Python and commonly used Python packages including: pandas, matplotlib, and scikit-learn.
Machine Learning
Apply machine learning techniques at the beginner to intermediate level with Python and Jupyter Notebook.
OVERVIEW
Looking to kick-start your programming career in Python and not sure where to start? Or just looking to develop a more solid foundation in the Python programming language?
In this workshop, we'll work through the basics of leveraging data science using Python, from framing the problem and preparing the data to machine learning basics like building, scoring and improving your data model.
If you're a data science beginner, or want to get hands-on experience with the fundamental Python packages, this is the workshop for you.
EXPERIENCE LEVEL
AUDIENCE
MO MEDWANI
DATA SCIENCE CONSULTANT + INSTRUCTOR
BIO COMING SOON
AGENDA
7:30 AM - 4:00 PM
REGISTRATION + BREAKFAST
MORNING SESSION - Data Science + Machine Learning
Coffee Break Included in Each Session
-
How to install Python and Jupyter/Anaconda Notebook
-
Introduction to Python Programming
-
Learn Python using Pandas, Matplotlib, Scikit-learn,
-
Create DataFrames using a dictionary or list
-
Data Cleaning & Preparation for Analysis
-
Data Imputation
-
Aggregation, Wrangling, Rearranging, and Reshaping data
-
Join, Concatenate, Pivot, and Melt Functions
-
Data Manipulation
-
Time Series Data Analysis
-
Data visualization with Matplotlib
LUNCH + NETWORKING
AFTERNOON SESSION - Predictive Modeling
Coffee Break Included in Each Session
-
Feature engineering
-
Dealing with missing values
-
Normalization
-
Build a model with Scikit-learn
-
Split data into train/test set
-
Train a model with training data
-
Evaluate the performance of the model
-
Concepts of various evaluation metrics
-
Precision/recall
-
Accuracy
-
F1-score
-
ROC curve
-
Tune the Model for Better Performance
-
Model Persistence
-
Save and re-use trained model
-
Troubleshooting