import pandas as pd
import matplotlib.pyplot as plt


PASS_MARKS = 40

subjects = [
    "Physics",
    "Chemistry",
    "Maths",     # Corrected from "Mathematics"
    "Biology",
    "English I"  # Corrected from "English"
]

df = pd.read_csv("datasets/11science.csv")

df = df.drop(0).reset_index(drop=True)


for subject in subjects:
    # Use 'coerce' to convert non-numeric values (e.g., text for "Absent") to NaN
    df[subject] = pd.to_numeric(df[subject], errors='coerce')
    
pass_students = []

for subject in subjects:
    # Count students with marks >= PASS_MARKS. NaN values are treated as False (not passed).
    count = (df[subject] >= PASS_MARKS).sum()
    pass_students.append(count)

plt.figure(figsize=(10, 6))

plt.scatter(subjects, pass_students, color='skyblue', s=100)

plt.xlabel("Subjects")
plt.ylabel("Number of Pass Students")
plt.title(f"Subject-wise Pass Students (Pass Mark: {PASS_MARKS})")
plt.grid(axis='y', linestyle='--')

plt.tight_layout()
plt.show()
Week2 : Assignments¶

Data Visualization¶

XI Science Results¶
