Development Environment Setup and Data Exploration

Описание: The goal of this assignment is to establish a functional development environment for Machine Learning, demonstrate proficiency with essential Python libraries, and apply basic data exploration and visualization techniques to understand a real-world dataset.



I already had Python installed. After getting my GitHub Repository setup and connected to my local machine on VS Code I installed the necessary libraries (numpy, pandas, matplotlib/seaborn, scikit-learn).

Then I loaded the Iris dataset directly from the scikit-learn library into a Pandas DataFrame. I used the Pandas DataFrame in the past, during my Application Development 350 Database Engineering class. When I used it in the past it was via the learning tool, so I really enjoyed getting it setup on the IDE I feel more comfortable with. Good ol’ VS Code.

I created a Pandas DataFrame using the standard syntax. The data is in iris.data and the column nmaes are in iris.feature_names. The target species is in iris.target and the numberical target is mapped to the species names. The print statements confirm the data loading is completed .By default, if the method is called without any arguments, it returns the first 5 rows (I played with it as you can see in the terminal history).
df.info() shows the entries (as rows); confirms all the columns are non-null (not missing data) and shows the types of data in the file.

df.describe() provides key statistics such as count, mean, standard deviation, min, max, and quartiles (25%, 50%, 75%). These methods belong to the Pandas DataFrame object and are part of the reason why the Pandas library is such a household name (okay maybe not household name, more like one of the most popular in the industry – I don’t know that the average household is discussing the Pandas DataFrame (ahahHA).

I’m executing the script in the VS Code terminal in the virtual environment I setup by typing python followed by the python file name in this case python iris.py

The output appears in the terminal

Talk about the data set. The .describe() method is pretty bleepin cool – I must say. It makes sense why the iris dataset is so commonly used.

Now, to turn those numbers into insights via matplotlib and seaborn - popular Python libraries for data visualization

Matplotlib is a foundational and comprehensive library for creating static, interactive, and animated visualizations in Python

Seaborn is a high-level library built on top of Matplotlib, designed to simplify the creation of attractive and informative statistical graphics

Seaborn extends Matplotlib's capabilities and offers a more user friendly experience.

I/we utilize these Python libraries by importing them via the python iris.py file.
import matplotlib.pyplot as plt import seaborn as sns

I also added a visure style – whitegird for the plots - sns.set_theme(style="whitegrid")

Below that I have the codes for the histogram. I decided to make a histogram for the petal length.
plt.figure(figsize=(8, 5))

Next I have created a Box Plot to analyze the sepal width which shows the median, quartiles, and outliers.

Lastly, I have made a scatter plot to conduct data analysis based on petal lengths and petal widths, color coordinated by species type.

Executing the python file generates the data descriptions we talked about before. It also opens 1 separate window as a pop up on the screen. I need to close each plot window to make the next one appear – there are workarounds to this but I think this is fine as is.
The last thing I did was add lines of code which print the version numbers for my IDE, version of Python, and the library versions. Perhaps my script contains valuable insights and noting which version it was coded it will help ensure that it remains