Python Projects for Beginners a ten-Week Bootcamp Approach to Python Programming

Feature Engineering

• 
  Creating new information that isn’t depicted by the dataset is important. You can use your own expertise if you have knowledge of the subject, and you can isolate data which allows your algorithms to focus more on the important observations. Here you can feature engineer columns into a group, add dummy variables, remove unused features, etc. This is where you want to expand on the dataset with your own knowledge if you believe data is either missing or could be created from the information within the dataset.
  

Now that you know the process in which to clean a dataset, this will come in handy for the first exercise at the end of the day.
CHapter 10 INtroduCtIoN to data aNalYsIs

TUESDAY EXERCISES

1. 
   Loading a Dataset: Go to www.Kaggle.com, click “Datasets” in the top bar menu. Choose a dataset that you like, and download it into the “python_ bootcamp” folder. then, load the dataset into a pandas dataFrame using the read_csv method, and display the top five records.
   
2. 
   Dataset Analysis: this is an open-ended exercise. run some analysis on the dataset you chose from exercise #1. try to answer questions like these:
   
   1. 
      How many records are there?
      
   2. 
      What are the data types of each column?
      
   3. 
      Are there duplicate records or columns?
      
   4. 
      Is there missing data?
      
   5. 
      Is there a correlation between two or more columns?
      

today’s focus was on learning the all-important pandas library and how to work with dataFrames. We used some minor real-life examples, but for the most part, today was just about understanding what you could do in pandas. For Friday’s project, we’ll use pandas to help us analyze sporting statistics.
Wednesday: Data Visualization
Data visualization is one of the most powerful tools an analyst has for two main reasons. Firstly, it is unrivalled in its ability to guide the analyst’s hand in determining “what to look at next.” Often, a visual is revealing of patterns in the data that are not easily discernable by just looking at DataFrames. Secondly, they are an analyst’s greatest communication tool. Professional analysts need to present their results to groups of people responsible for acting based on what the data says. Visuals can tell your story much better than raw numbers.
CHapter 10 INtroduCtIoN to data aNalYsIs
Like how yesterday’s lesson began, we need to install a library into our virtual environment. To follow along with today’s lesson, cd into the “python_bootcamp” folder and activate the environment. We’ll begin today within the terminal.