MODULE 15: Data Analysis with Python

In Module 15, we enter the world of Data Science. Python is the industry leader here because it allows you to take massive amounts of “raw” data and turn them into actionable insights and beautiful visualizations.

1. NumPy (Numerical Python)

NumPy is the foundational package for scientific computing. It introduces Arrays, which are much faster and more memory-efficient than standard Python lists for mathematical operations.

Example:

Python

import numpy as np

arr = np.array([1, 2, 3, 4, 5])
print(arr * 2)  # Multiplies every element: [2, 4, 6, 8, 10]

2. Pandas

Pandas is built on top of NumPy and provides the DataFrame—a 2D table structure that looks like an Excel spreadsheet. It is the go-to tool for data manipulation.

Example:

Python

import pandas as pd

data = {'Name': ['Alice', 'Bob'], 'Score': [85, 92]}
df = pd.DataFrame(data)
print(df.head())

3. Data Cleaning

Real-world data is “messy.” It has missing values, duplicates, and errors. Data cleaning involves:

• Handling Missing Data: Using df.dropna() (remove) or df.fillna() (replace).
• Removing Duplicates: Using df.drop_duplicates().
• Fixing Types: Converting strings to numbers where necessary.

4. Data Transformation

This involves reshaping your data to make it useful.

• Filtering: Selecting rows based on conditions.
• Grouping: Summarizing data using groupby().
• Merging: Combining multiple DataFrames like a SQL JOIN.

Example:

Python

# Grouping data by 'Category' and finding the average 'Price'
avg_prices = df.groupby('Category')['Price'].mean()

5. Working with Excel & CSV

Pandas makes it incredibly easy to move data between Python and your local files.

• Reading: df = pd.read_csv('file.csv') or pd.read_excel('file.xlsx').
• Saving: df.to_csv('new_file.csv', index=False).

6. Exploratory Data Analysis (EDA)

EDA is the process of “getting to know” your data before applying Machine Learning. You look for patterns, outliers, and correlations using methods like df.describe() (summary stats) and df.info().

7. Matplotlib & Seaborn

These are the primary libraries for Data Visualization.

• Matplotlib: The “grandfather” library; gives you total control over every pixel.
• Seaborn: Built on Matplotlib; makes statistical plots (like heatmaps and violin plots) look professional with very little code.

Example:

Python

import matplotlib.pyplot as plt
import seaborn as sns

sns.lineplot(data=df, x='Date', y='Sales')
plt.title("Sales Trends Over Time")
plt.show()