12  Jupyter Notebook

Jupyter Notebook is a powerful interactive computing environment widely used in business analytics, data science, and machine learning. It allows users to write and execute Python code in a web-based interface while combining code, text, and visualizations in a single document.

12.1 Key Features of Jupyter Notebook

  • Interactive Code Execution → Run code in small blocks (cells) and see results immediately.
  • Rich Text and Documentation → Supports Markdown for writing explanations alongside code.
  • Data Visualization → Integrates with Matplotlib, Seaborn, and Plotly for creating graphs and charts.
  • Support for Multiple Languages → Works with Python, R, Julia, and many other languages.
  • Notebook Sharing → Export notebooks as HTML, PDF, or .ipynb files for easy sharing.
  • Integration with Libraries → Works with libraries like Pandas, NumPy, SciPy, Scikit-learn, and TensorFlow.

12.2 Installing Jupyter Notebook

The easiest way to install Jupyter Notebook is through Anaconda, which includes Python and many data science packages.

1. Install Jupyter Notebook with Anaconda

  • Download Anaconda from Anaconda’s official website.
  • Follow installation instructions for Windows, macOS, or Linux.
  • Open Anaconda Navigator and launch Jupyter Notebook.

2. Install Jupyter Notebook Using pip

If you prefer installing Jupyter without Anaconda, use pip:

Code
!pip install jupyter
Running Jupyter Notebook

After installing, open Terminal (Mac/Linux) or Command Prompt (Windows) and type:

Code
!jupyter notebook

This opens Jupyter Notebook in your web browser, where you can create new Python notebooks.

12.2.1 Basic Jupyter Notebook Interface

  1. Notebook Cells
    • Code Cells → Execute Python code.
    • Markdown Cells → Add formatted text, equations, and documentation.
  2. Running Cells
    • Press Shift + Enter to execute a cell.
    • Use Kernel → Restart & Run All to re-run all cells.
  3. Saving Notebooks
    • Save as .ipynb (native format) or export to HTML/PDF.

12.2.2 Using Jupyter Notebook for Business Analytics

Jupyter Notebook makes it easy to analyze business data with Python.

1. Importing Libraries

Code

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

2. Loading a Dataset

Code
import os
os.chdir('/Users/vijay/Library/CloudStorage/OneDrive-Personal/Documents/1 Professional/3 My Books/BADM/Python Basics')
df = pd.read_csv("Diabetes.csv")
df.head()
   Unnamed: 0  Age  Gender  ...  C_Protein_Level Thyroid_Condition Diabetes_Status
0           1   48    Male  ...             7.46               Yes             Yes
1           2   18   Other  ...             5.64               Yes              No
2           3   21   Other  ...             7.20                No             Yes
3           4   25  Female  ...             6.53               Yes              No
4           5   78    Male  ...             0.58                No             Yes

[5 rows x 28 columns]

3. Data Analysis

Code
print(df.describe())  # Summary statistics
        Unnamed: 0          Age  ...  Vitamin_D_Level  C_Protein_Level
count  5292.000000  5292.000000  ...      5292.000000      5292.000000
mean   2646.500000    48.417989  ...        29.909883         5.258743
std    1527.813143    18.040544  ...        11.527951         2.754500
min       1.000000    18.000000  ...        10.000000         0.500000
25%    1323.750000    33.000000  ...        20.000000         2.880000
50%    2646.500000    48.000000  ...        29.800000         5.270000
75%    3969.250000    64.000000  ...        39.900000         7.660000
max    5292.000000    79.000000  ...        50.000000        10.000000

[8 rows x 13 columns]
Code
print(df.isnull().sum())  # Check missing values
Unnamed: 0                              0
Age                                     0
Gender                                  0
BMI                                     0
Family_History                          0
Physical_Activity                       0
Diet_Type                               0
Smoking_Status                          0
Alcohol_Intake                       1780
Stress_Level                            0
Hypertension                            0
Cholesterol_Level                       0
Fasting_Blood_Sugar                     0
Postprandial_Blood_Sugar                0
HBA1C                                   0
Heart_Rate                              0
Waist_Hip_Ratio                         0
Urban_Rural                             0
Health_Insurance                        0
Regular_Checkups                        0
Medication_For_Chronic_Conditions       0
Pregnancies                             0
Polycystic_Ovary_Syndrome               0
Glucose_Tolerance_Test_Result           0
Vitamin_D_Level                         0
C_Protein_Level                         0
Thyroid_Condition                       0
Diabetes_Status                         0
dtype: int64

4. Data Visualization

Code
import matplotlib.pyplot as plt

# Count the number of occurrences for each Diabetes Status
diabetes_counts = df["Diabetes_Status"].value_counts()

# Create a bar chart
plt.figure(figsize=(8,5))
diabetes_counts.plot(kind="bar", color=["green", "maroon"])

# Add labels and title
plt.title("Diabetes Status Distribution")
plt.xlabel("Diabetes Status")
plt.ylabel("Count")
plt.xticks(rotation=0)  # Keep labels horizontal
(array([0, 1]), [Text(0, 0, 'Yes'), Text(1, 0, 'No')])
Code
# Show plot
plt.show()