4.3 Data Visualization and Summary Statistics

Data analysis involves two key activities: computing summary statistics to numerically describe a dataset, and creating data visualizations to communicate patterns and trends effectively.

---

Summary Statistics

Summary statistics are numerical values that describe the key characteristics of a dataset. They help analysts quickly understand the distribution, center, and spread of data.

Measures of Central Tendency

Measures of Spread

• Range: Difference between the maximum and minimum values. $Range=Max-Min$
• Variance: Average of squared differences from the mean.
• Standard Deviation: Square root of variance; shows how spread out values are from the mean.

Parameter vs. Statistic

• A Parameter is a numerical value describing a characteristic of an entire population (e.g., average height of all students in Pakistan).
• A Statistic is a numerical value describing a characteristic of a sample taken from that population (e.g., average height of 100 students surveyed).

---

Data Visualization

Data visualization converts raw data into graphical formats, making it easier to identify patterns, trends, and outliers.

Bar Chart

• Purpose: Comparing discrete categories or groups.
• Structure: Rectangular bars where the length/height represents the value of each category.
• Best used when: Comparing sales across different products, population across cities, or scores across subjects.
• Example: Comparing the number of students enrolled in five different courses.

Pie Chart

• Purpose: Showing the proportion of parts relative to a whole.
• Structure: A circle divided into slices; each slice represents a category's percentage of the total.
• Sector Angle Formula: $\text{Angle}=\frac{\text{Category Value}}{\text{Total}}\times 360^{\circ }$
• Example: If a category is 25% of the total, its sector angle = $0.25\times 360^{\circ }=90^{\circ }$.
• Best used when: Showing market share, budget allocation, or survey response distribution.

Line Graph

• Purpose: Showing trends and changes over time (time-series data).
• Structure: Data points connected by lines along a horizontal time axis.
• Best used when: Tracking temperature over a month, stock prices over a year, or website traffic over weeks.
• Example: Plotting daily maximum temperatures for a city over 30 days.

Choosing the Right Chart

---

Using Python Libraries for Data Visualization

Python provides powerful libraries to create visualizations and compute summary statistics from pre-existing datasets.

Key Libraries

• matplotlib: The foundational plotting library for creating bar charts, line graphs, pie charts, and more.
• pandas: Used for loading and manipulating datasets; provides built-in .describe() for summary statistics.
• numpy: Provides mathematical functions for computing mean, median, standard deviation, etc.

Example: Summary Statistics with pandas

import pandas as pd

# Load a dataset
data = pd.read_csv('students.csv')

# Display summary statistics
print(data.describe())

# Individual statistics
print("Mean:", data['score'].mean())
print("Median:", data['score'].median())
print("Mode:", data['score'].mode()[0])

Example: Bar Chart with matplotlib

import matplotlib.pyplot as plt

categories = ['Math', 'Science', 'English', 'History', 'Art']
students = [45, 60, 55, 30, 40]

plt.bar(categories, students, color='steelblue')
plt.title('Student Enrollment by Subject')
plt.xlabel('Subject')
plt.ylabel('Number of Students')
plt.show()

Example: Pie Chart with matplotlib

import matplotlib.pyplot as plt

labels = ['Math', 'Science', 'English', 'History']
sizes = [30, 25, 25, 20]

plt.pie(sizes, labels=labels, autopct='%1.1f%%')
plt.title('Subject Distribution')
plt.show()

Example: Line Graph with matplotlib

import matplotlib.pyplot as plt

days = list(range(1, 8))
temperature = [22, 25, 23, 28, 30, 27, 24]

plt.plot(days, temperature, marker='o', color='tomato')
plt.title('Daily Temperature Over a Week')
plt.xlabel('Day')
plt.ylabel('Temperature (°C)')
plt.show()

---

Key Takeaways

• Summary statistics (mean, median, mode, range) describe a dataset numerically.
• Bar charts compare categories; pie charts show proportions; line graphs show trends over time.
• Python libraries like matplotlib, pandas, and numpy are essential tools for data analysis and visualization.
• A statistic describes a sample; a parameter describes a population.