Data Analytics Lesson 3: Creating Your First Data Visualizations

# Install required packages for data analytics
import piplite
await piplite.install(['seaborn', 'matplotlib', 'pandas', 'numpy', 'scipy', 'plotly'])
print("Packages installed successfully!")
print("You can now import and use: seaborn, matplotlib, pandas, numpy, scipy, plotly")

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt  # This is our main plotting tool
import seaborn as sns           # This makes our plots look prettier

# Set up nice-looking plots
plt.style.use('default')  # Clean, simple style
sns.set_palette("husl")   # Pretty colors

# Our student dataset with all the information we've been using
student_data = {
    'Name': ['Alice', 'Bob', 'Charlie', 'Diana', 'Eva', 'Frank', 'Grace', 'Henry'],
    'Age': [16, 17, 16, 18, 17, 16, 17, 18],
    'Grade': ['10th', '11th', '10th', '12th', '11th', '10th', '11th', '12th'],
    'Math_Score': [85, 92, 78, 95, 88, 76, 91, 87],
    'Science_Score': [89, 87, 82, 98, 85, 79, 93, 89],
    'English_Score': [92, 85, 88, 91, 94, 83, 89, 86],
    'Hours_Studied': [5, 8, 4, 10, 6, 3, 9, 7],
    'Extracurriculars': [2, 1, 3, 2, 4, 1, 2, 3]
}

df = pd.DataFrame(student_data)
df['Average_Score'] = df[['Math_Score', 'Science_Score', 'English_Score']].mean(axis=1)

print("Ready to visualize our data!")

# Calculate average scores by grade
grade_averages = df.groupby('Grade')['Average_Score'].mean()

# Create our first bar chart
plt.figure(figsize=(8, 6))  # Set the size of our plot
plt.bar(grade_averages.index, grade_averages.values, 
        color=['lightblue', 'lightgreen', 'lightcoral'])

# Make it look nice with labels
plt.title('Average Scores by Grade Level', fontsize=16, fontweight='bold')
plt.xlabel('Grade Level', fontsize=12)
plt.ylabel('Average Score', fontsize=12)
plt.ylim(80, 95)  # Set the range of the y-axis for better visibility

# Add value labels on top of each bar
for i, v in enumerate(grade_averages.values):
    plt.text(i, v + 0.5, f'{v:.1f}', ha='center', fontweight='bold')

plt.tight_layout()  # Make sure everything fits nicely
plt.show()

# Let's also print the numbers
print("Grade Level Performance:")
for grade, avg in grade_averages.items():
    print(f"{grade} grade: {avg:.1f} points")

# Let's look at individual student performance
plt.figure(figsize=(10, 6))

# Create horizontal bar chart
plt.barh(df['Name'], df['Average_Score'], color='skyblue')

# Add labels and title
plt.title('Individual Student Performance', fontsize=16, fontweight='bold')
plt.xlabel('Average Score', fontsize=12)
plt.ylabel('Student Name', fontsize=12)

# Add score values at the end of each bar
for i, (name, score) in enumerate(zip(df['Name'], df['Average_Score'])):
    plt.text(score + 0.5, i, f'{score:.1f}', va='center', fontweight='bold')

plt.tight_layout()
plt.show()

# Find the top and bottom performers
top_student = df.loc[df['Average_Score'].idxmax()]
bottom_student = df.loc[df['Average_Score'].idxmin()]
print(f"Top performer: {top_student['Name']} with {top_student['Average_Score']:.1f}")
print(f"Needs support: {bottom_student['Name']} with {bottom_student['Average_Score']:.1f}")

# Let's see if more study hours lead to better performance
plt.figure(figsize=(10, 6))

# Sort by study hours to make the line make sense
df_sorted = df.sort_values('Hours_Studied')

plt.plot(df_sorted['Hours_Studied'], df_sorted['Average_Score'], 
         marker='o', linewidth=2, markersize=8, color='darkblue')

# Add labels for each point
for _, student in df_sorted.iterrows():
    plt.annotate(student['Name'], 
                (student['Hours_Studied'], student['Average_Score']),
                xytext=(5, 5), textcoords='offset points', fontsize=10)

plt.title('Study Hours vs. Average Performance', fontsize=16, fontweight='bold')
plt.xlabel('Hours Studied per Week', fontsize=12)
plt.ylabel('Average Score', fontsize=12)
plt.grid(True, alpha=0.3)  # Add a light grid to make it easier to read
plt.tight_layout()
plt.show()

# Calculate if there's a relationship
correlation = df['Hours_Studied'].corr(df['Average_Score'])
print(f"Correlation between study hours and performance: {correlation:.2f}")
if correlation > 0.7:
    print("Strong positive relationship - more study time = better grades!")
elif correlation > 0.3:
    print("Moderate positive relationship - study time helps somewhat")
else:
    print("Weak relationship - other factors might be more important")

# Create a scatter plot showing study hours vs performance
plt.figure(figsize=(10, 8))

# Different colors for different grades
grade_colors = {'10th': 'red', '11th': 'blue', '12th': 'green'}
colors = [grade_colors[grade] for grade in df['Grade']]

plt.scatter(df['Hours_Studied'], df['Average_Score'], 
           c=colors, s=100, alpha=0.7, edgecolors='black')

# Add student names as labels
for _, student in df.iterrows():
    plt.annotate(student['Name'], 
                (student['Hours_Studied'], student['Average_Score']),
                xytext=(5, 5), textcoords='offset points', fontsize=9)

plt.title('Study Hours vs. Performance by Grade Level', fontsize=16, fontweight='bold')
plt.xlabel('Hours Studied per Week', fontsize=12)
plt.ylabel('Average Score', fontsize=12)

# Create a legend for the colors
for grade, color in grade_colors.items():
    plt.scatter([], [], c=color, label=grade, s=100, alpha=0.7, edgecolors='black')
plt.legend(title='Grade Level')

plt.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()

print("What does this tell us?")
print("- Red dots = 10th graders")  
print("- Blue dots = 11th graders")
print("- Green dots = 12th graders")
print("Look for patterns: Do different grades cluster together?")

# Let's look at the distribution of test scores
fig, axes = plt.subplots(2, 2, figsize=(12, 10))
fig.suptitle('Distribution of Test Scores', fontsize=16, fontweight='bold')

# Math scores
axes[0, 0].hist(df['Math_Score'], bins=6, color='lightblue', edgecolor='black', alpha=0.7)
axes[0, 0].set_title('Math Scores')
axes[0, 0].set_xlabel('Score')
axes[0, 0].set_ylabel('Number of Students')

# Science scores
axes[0, 1].hist(df['Science_Score'], bins=6, color='lightgreen', edgecolor='black', alpha=0.7)
axes[0, 1].set_title('Science Scores')
axes[0, 1].set_xlabel('Score')
axes[0, 1].set_ylabel('Number of Students')

# English scores
axes[1, 0].hist(df['English_Score'], bins=6, color='lightcoral', edgecolor='black', alpha=0.7)
axes[1, 0].set_title('English Scores')
axes[1, 0].set_xlabel('Score')
axes[1, 0].set_ylabel('Number of Students')

# Study hours
axes[1, 1].hist(df['Hours_Studied'], bins=5, color='lightyellow', edgecolor='black', alpha=0.7)
axes[1, 1].set_title('Study Hours per Week')
axes[1, 1].set_xlabel('Hours')
axes[1, 1].set_ylabel('Number of Students')

plt.tight_layout()
plt.show()

# Analyze what we see
print("What do these distributions tell us?")
for subject in ['Math_Score', 'Science_Score', 'English_Score']:
    mean_score = df[subject].mean()
    std_score = df[subject].std()
    print(f"{subject.replace('_', ' ')}: Average = {mean_score:.1f}, Spread = {std_score:.1f}")

# Compare subject performance across all students
plt.figure(figsize=(10, 6))

# Prepare data for box plot
subjects_data = [df['Math_Score'], df['Science_Score'], df['English_Score']]
subject_names = ['Math', 'Science', 'English']

box_plot = plt.boxplot(subjects_data, labels=subject_names, patch_artist=True)

# Make it colorful
colors = ['lightblue', 'lightgreen', 'lightcoral']
for patch, color in zip(box_plot['boxes'], colors):
    patch.set_facecolor(color)

plt.title('Score Distribution by Subject', fontsize=16, fontweight='bold')
plt.ylabel('Score', fontsize=12)
plt.xlabel('Subject', fontsize=12)
plt.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()

print("Understanding Box Plots:")
print("- The box shows where the middle 50% of scores fall")
print("- The line in the middle is the median (middle value)")
print("- The 'whiskers' show the range of most scores")
print("- Dots outside are outliers (unusual values)")

# Create a comprehensive view of our data
fig, axes = plt.subplots(2, 2, figsize=(15, 12))
fig.suptitle('Complete Student Performance Analysis', fontsize=18, fontweight='bold')

# 1. Performance by Grade (Bar Chart)
grade_avg = df.groupby('Grade')['Average_Score'].mean()
axes[0, 0].bar(grade_avg.index, grade_avg.values, color=['lightblue', 'lightgreen', 'lightcoral'])
axes[0, 0].set_title('Average Performance by Grade')
axes[0, 0].set_ylabel('Average Score')

# 2. Study Hours Effect (Scatter Plot)
axes[0, 1].scatter(df['Hours_Studied'], df['Average_Score'], 
                   c=df['Age'], cmap='viridis', s=100, alpha=0.7)
axes[0, 1].set_title('Study Hours vs. Performance (Color = Age)')
axes[0, 1].set_xlabel('Hours Studied')
axes[0, 1].set_ylabel('Average Score')

# 3. Subject Comparison (Box Plot)
subject_data = [df['Math_Score'], df['Science_Score'], df['English_Score']]
box_plot = axes[1, 0].boxplot(subject_data, labels=['Math', 'Science', 'English'])
axes[1, 0].set_title('Score Distribution by Subject')
axes[1, 0].set_ylabel('Score')

# 4. Individual Performance (Horizontal Bar)
axes[1, 1].barh(df['Name'], df['Average_Score'], color='skyblue')
axes[1, 1].set_title('Individual Student Performance')
axes[1, 1].set_xlabel('Average Score')

plt.tight_layout()
plt.show()

print("This comprehensive view helps us see:")
print("1. Which grades perform best overall")
print("2. How study time relates to performance")  
print("3. Which subjects are most/least challenging")
print("4. How individual students compare")