The dataset used in this project is from Kaggle: Education Inequality Data
License: MIT License
Original author: Shamim Hasan

• 🔼 It gives us a look into our 1st 5 row
• df.head()

• 🔼 shows all column, data types, missing values....
• df.info()

• 🔼 It gives min,max,mean....
• df.describe()

• 🔼 Checks if we have any missing values
• df.isnull().sum()

• 🔼 Checks if we have any duplicates
• df.duplicated().sum()

• 🔼 It gives us info on how many schools are there in states
• school_by_state

• 🔼 It gives us info on school type
• school_by_type

• 🔼 It gives us info on level of school
• school_by_level

• 🔼 Bar Graph on schools by type
• school_by_type

• 🔼 Histogram of funding per student (in usd)
• funding_per_student_usd

• 🔼 Histogram of average test score percent
• avg_test_score_percent

• 🔼 Correlation summary in table format
• corr

• 🔼 Correlation Heatmap of School Factors
• heatmap

• 🔍 Reading specific values

  • Funding vs Test Scores → 0.02 → Almost no correlation
  • Student–Teacher Ratio vs Dropout Rate → 0.01 → Essentially no relationship
  • Percent Low-Income vs Avg Test Score → -0.00 → No significant link
  • Internet Access vs Dropout Rate → 0.02 → Weak, negligible positive relationship
  • Most numbers lie between -0.07 and +0.04, showing no strong explanatory links

• 🔍 Key Insights

  • All correlations are weak (close to 0) → dataset doesn’t show strong linear relationships
  • Real-world expectations (but not seen strongly here):
    • More funding → better test scores
    • Higher low-income % → higher dropout rate
    • Better internet access → higher test scores

• 🔍 Strongest Positive Correlations

  • Student–Teacher Ratio vs Avg Test Score → 0.04
  • Internet Access vs Student–Teacher Ratio → 0.03
  • Internet Access vs Avg Test Score → 0.02
  • 👉 All negligible

• 🔍 Strongest Negative Correlations

  • Student–Teacher Ratio vs Percent Low Income → -0.07
  • Dropout Rate vs Id → -0.05
  • Id vs Percent Low Income → -0.05
  • 👉 Again, very weak

• 🔍 Summary

  • All correlations fall within -0.07 → +0.04
  • In practice → no strong linear relationships
  • Heatmap confirms near independence between variables

• 🔼 Average Test Scores by School Type
• avg_scores_by_type

• 🔼 Scatter Plots || Funding vs Test Score
• Funding vs Test Scores (with Trend Line)

• 🔼 Scatter Plots || Student-Teacher Ratio vs Test Score
• Student-Teacher Ratio vs Test Score (with Trend Line)

• 🔼 Scatter Plots || Percent Low-Income vs Dropout Rate
• Percent Low-Income vs Dropout Rate (with Trend Line)