< Home
Week 1: Introduction to data science¶
This is an example file to introduce you to Juypter Labs and show you how you can organise and document your work. Feel free to edit this page as you please. The topmost cell is a small navigation to go back home and optionally you could link the following week here (ie week 2), when you start working on it to help visitors.
The dataset I liked the most from my tutor’s explanation Data:Florence Nightingale Changed Data Visualization Forever Screenshot 2025-11-21 at 3.25.02 PM.png
Summary:Florence Nightingale’s Coxcomb Diagram This image shows Florence Nightingale’s Coxcomb Diagram, also called the rose diagram or polar area chart, which she created to illustrate the causes of mortality among British soldiers during the Crimean War. The chart is divided into monthly wedges, with the size of each wedge representing the number of deaths for that month. Color-coded sections distinguish causes of death: large blue areas indicate deaths from preventable diseases, red areas show deaths from wounds, and black or gray areas represent deaths from other causes, clearly highlighting that disease was the leading cause of mortality.
By presenting the data in this visually striking format, Nightingale effectively demonstrated the urgent need for sanitary reforms in military hospitals. Her innovative approach not only communicated the severity of the problem in an accessible way but also marked a turning point in data visualization for public health advocacy, influencing how statistics could be used to drive social change.
Assignments: We are asked to choose one dataset
Compiled Dataset: result of class viii 2023 batch
IThe dataset includes scores for the following seven subjects: Dzongkha, English, Geography, History, ICT, Maths, and Science. A total of 29 students are listed in the dataset, with each student's performance recorded across these subjects, along with their overall pass or fail status. The file also includes summary statistics at the end, such as subject means, providing a comprehensive overview of the cohort's academic performance.
Reports
Based on the student performance data from the file viii_2023.csv, the overall results for Class VIII indicate a generally positive academic outcome, with the majority of students passing across all subjects. The average subject marks (S.M) reveal that English (74.03) and History (73.44) were the highest-scoring subjects, while ICT (61.61) and Science (61.94) had the lowest averages, suggesting areas where students may need additional support. Most students successfully met the passing criteria, though a few, such as Phurpa Wangmo, Nima Yangchen, and Sujal Sunar, did not pass, highlighting individual cases that may require further attention. The data provides a useful overview of class performance and can help in identifying both strengths and areas for improvement in the curriculum and teaching strategies.
import pandas as pd
import numpy as np
# Load the dataset
df = pd.read_csv('viii_2023.csv')
# Basic information about the dataset
print("=== DATASET OVERVIEW ===")
print(f"Dataset shape: {df.shape}")
print(f"Number of students: {len(df)-3}") # Subtract summary rows
print("\nColumns:", list(df.columns))
print("\nFirst few rows:")
print(df.head(8))
print("\n" + "="*50)
print("=== DATA EXPLANATION ===")
print("This dataset contains Class VIII student results with:")
print("- Student names in the first column")
print("- Subject scores: Dzongkha, English, Geography, History, ICT, Maths, Science")
print("- Pass/Fail status in the last column")
print("- Summary statistics at the bottom (subject means and totals)")
print("\n" + "="*50)
print("=== KEY STATISTICS ===")
# Filter out summary rows and get only student data
students_df = df.iloc[:-3].copy()
# Convert score columns to numeric
score_columns = ['Dzongkha', 'English', 'Geography', 'History', 'ICT ', 'Maths', 'Science']
for col in score_columns:
students_df[col] = pd.to_numeric(students_df[col], errors='coerce')
print(f"Total students: {len(students_df)}")
print(f"Pass rate: {(students_df.iloc[:,-1] == 'Pass').mean():.1%}")
print("\nAverage scores by subject:")
for col in score_columns:
avg_score = students_df[col].mean()
print(f"- {col}: {avg_score:.2f}")
print(f"\nHighest average: English (74.03)")
print(f"Lowest average: ICT (61.61)")
print("\n" + "="*50)
print("=== DATA QUALITY CHECK ===")
print("Missing values per column:")
print(students_df.isnull().sum())
=== DATASET OVERVIEW ===
Dataset shape: (40, 9)
Number of students: 37
Columns: ['Unnamed: 0', 'Dzongkha', 'English', 'Geography', 'History', 'ICT ', 'Maths', 'Science', 'Unnamed: 8']
First few rows:
Unnamed: 0 Dzongkha English Geography History ICT Maths \
0 Sangay Tenzin 66.63 59.8 57 60.45 47.06 58.3
1 Sujandeep Sunar 72.13 79.35 81.88 77.2 64.75 77.6
2 Singye Dorji 69.32 70.9 58.25 63.6 59.38 60.28
3 Tenzin Wangyal Tshering 70.25 83.95 86.7 81.5 71 79.85
4 Sushmita Kami 73.69 81.85 73.18 82.05 63.31 62.05
5 Singye Rada 68.38 74.08 77.93 70.1 60 68.93
6 Phurpa Wangmo 77.82 67.85 66.98 66.23 52.63 57.63
7 Sonam Eden 66.63 63.48 58.65 67.28 52.63 61.75
Science Unnamed: 8
0 48.35 Pass
1 69.53 Pass
2 55.05 Pass
3 73.95 Pass
4 61.8 Pass
5 66.08 Pass
6 52.38 Fail
7 51.13 Pass
==================================================
=== DATA EXPLANATION ===
This dataset contains Class VIII student results with:
- Student names in the first column
- Subject scores: Dzongkha, English, Geography, History, ICT, Maths, Science
- Pass/Fail status in the last column
- Summary statistics at the bottom (subject means and totals)
==================================================
=== KEY STATISTICS ===
Total students: 37
Pass rate: 73.0%
Average scores by subject:
- Dzongkha: 71.33
- English: 73.82
- Geography: 71.69
- History: 71.93
- ICT : 60.98
- Maths: 67.63
- Science: 62.16
Highest average: English (74.03)
Lowest average: ICT (61.61)
==================================================
=== DATA QUALITY CHECK ===
Missing values per column:
Unnamed: 0 7
Dzongkha 7
English 7
Geography 7
History 7
ICT 7
Maths 7
Science 7
Unnamed: 8 7
dtype: int64
Visualizing datasets
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
# Load the dataset
df = pd.read_csv('viii_2023.csv')
# Clean the data - remove empty rows and summary rows
df_clean = df.iloc[:30] # Keep only student records (first 30 rows)
# Display basic dataset info
print("Dataset Shape:", df_clean.shape)
print("\nFirst few rows:")
print(df_clean.head())
print("\nDataset Info:")
print(df_clean.info())
# Get subject columns (excluding name and result columns)
subjects = ['Dzongkha', 'English', 'Geography', 'History', 'ICT ', 'Maths', 'Science']
# Convert marks to numeric (handling any potential errors)
for subject in subjects:
df_clean[subject] = pd.to_numeric(df_clean[subject], errors='coerce')
# Line graph for each subject across students
plt.figure(figsize=(15, 10))
for i, subject in enumerate(subjects, 1):
plt.subplot(3, 3, i)
plt.plot(range(len(df_clean)), df_clean[subject], marker='o', linewidth=2, markersize=4)
plt.title(f'{subject} Marks')
plt.xlabel('Student Index')
plt.ylabel('Marks')
plt.grid(True, alpha=0.3)
plt.ylim(0, 100)
plt.tight_layout()
plt.suptitle('Subject-wise Marks Distribution Across Students', y=1.02, fontsize=16)
plt.show()
# Calculate mean marks for each subject
mean_marks = df_clean[subjects].mean()
# Line graph for mean marks
plt.figure(figsize=(12, 6))
plt.plot(subjects, mean_marks, marker='o', linewidth=3, markersize=8,
color='red', markerfacecolor='blue', markeredgecolor='blue')
plt.title('Mean Marks by Subject - Class VIII (2023)', fontsize=14, fontweight='bold')
plt.xlabel('Subjects', fontsize=12)
plt.ylabel('Mean Marks', fontsize=12)
plt.ylim(0, 100)
plt.grid(True, alpha=0.3)
# Add value labels on points
for i, v in enumerate(mean_marks):
plt.text(i, v + 2, f'{v:.1f}', ha='center', va='bottom', fontweight='bold')
plt.tight_layout()
plt.show()
# Display mean marks
print("\nMean Marks by Subject:")
for subject, mean_mark in mean_marks.items():
print(f"{subject}: {mean_mark:.2f}")
Dataset Shape: (30, 9)
First few rows:
Unnamed: 0 Dzongkha English Geography History ICT Maths \
0 Sangay Tenzin 66.63 59.8 57 60.45 47.06 58.3
1 Sujandeep Sunar 72.13 79.35 81.88 77.2 64.75 77.6
2 Singye Dorji 69.32 70.9 58.25 63.6 59.38 60.28
3 Tenzin Wangyal Tshering 70.25 83.95 86.7 81.5 71 79.85
4 Sushmita Kami 73.69 81.85 73.18 82.05 63.31 62.05
Science Unnamed: 8
0 48.35 Pass
1 69.53 Pass
2 55.05 Pass
3 73.95 Pass
4 61.8 Pass
Dataset Info:
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 30 entries, 0 to 29
Data columns (total 9 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Unnamed: 0 30 non-null object
1 Dzongkha 30 non-null object
2 English 30 non-null object
3 Geography 30 non-null object
4 History 30 non-null object
5 ICT 30 non-null object
6 Maths 30 non-null object
7 Science 30 non-null object
8 Unnamed: 8 30 non-null object
dtypes: object(9)
memory usage: 2.2+ KB
None
/tmp/ipykernel_216/2645454200.py:23: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame. Try using .loc[row_indexer,col_indexer] = value instead See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy df_clean[subject] = pd.to_numeric(df_clean[subject], errors='coerce')
Mean Marks by Subject: Dzongkha: 71.33 English: 73.82 Geography: 71.69 History: 71.93 ICT : 60.98 Maths: 67.63 Science: 62.16
Explanation:¶
The code loads a Class VIII results dataset using pandas and begins by displaying basic information such as the dataset shape, column names, and the first few rows. It explains that the dataset includes student names, subject scores, and pass/fail status, along with summary statistics at the end. To analyze only the actual student records, the last three summary rows are removed. The score columns are converted to numeric values to avoid errors during calculations. The script then computes key statistics, including the total number of students, the overall pass rate, and the average score for each subject. It also identifies the subjects with the highest and lowest averages. Finally, the code performs a data-quality check by counting missing values in each column, helping to ensure the dataset is clean and ready for further analysis.