Getting Started with Data Cleaning and Analysis Using Python in Google Colab

Getting Started with Data Cleaning and Analysis Using Python in Google Colab

Step 4: Perform Data Analysis

Step 1: Introduction

Brief explanation of Python and Google Colab

Analyze your dataset

Step 2: Setting Up Google Colab

Step 5: Final Assesment

Lets test your knolwedge

How to create your own notebook

Step 3: Import your dataset

Step 6: Future Work

Get resources to apply your knowledge in real datasets

Opening data set in Colab and modifying it with Pandas

Introduction

Brief explanation of Data Science and Google Colab

Google Colab is Google’s free Jupyter-notebook service that runs in the cloud. It gives you an instant Python environment with optional GPUs/TPUs, access to Google Drive, and real-time collaboration - so you can write, execute, and share code without installing anything locally.

Google Colab is like a data-science workbench in your browser:

• You can import datasets from Drive, the web, or BigQuery; explore and clean them with Python libraries such as pandas and NumPy
• Visualize results on the fly with matplotlib or Plotly
• Train machine-learning models with GPUs for heavier deep-learning jobs.

Google Colab Link

Starting a Google Colab Notebook

colab.research.google.com

Follow the Steps to get create with your own notebook

Activity

1. Create a new code cell in your Google Colab notebook by clicking the + Code button. 2. Type the following Python code into the newly created cell: name = input("What's your name? ") print(f"Hello, {name}! Welcome to your first Python activity.") 3. Run the cell by pressing Shift + Enter or clicking the play icon ▶️ in the cell. 4. When prompted, type your name and press Enter. 5. Try commenting with a text cell

Importing your dataset

Learn how to import and edit dataset

Depending on your familiarity with pandas, feel free to either practice data cleaning using your own dataset or follow the guided tutorial on the right for an introductory walkthrough of essential data cleaning techniques.

2 ways to import your own Dataset

1. Upload a file directly from your computer

In the left sidebar, click Files ▸ Upload (or run from google.colab import files; files.upload() in a code cell). Choose the file(s) on your computer. Colab stores them in the ephemeral working directory /content/. Access in code exactly like a local path:import pandas as pd df = pd.read_csv('/content/your_dataset.csv')

Pandas with a toutorial

2. Mount your Google Drive

In a code cell, run:from google.colab import drive drive.mount('/content/drive')A popup asks for OAuth permission → choose the Google account that owns the Drive.After the mount completes, your Drive appears under /content/drive/MyDrive/. Read or write files normally: !ls '/content/drive/MyDrive/data' df = pd.read_csv('/content/your_dataset.csv')

Perform Data Analysis

Learn how to find patterns in your data

GitHub link to the notebook

Learning Outcomes

Basic Data Analysis Tasks:

• Data Cleaning and Preprocessing:

• Identify and handle missing values

• Remove duplicates

• Detect and correct outliers

• Standardize and normalize data

Exploratory Data Analysis (EDA):

• Summarize key statistics (mean, median, standard deviation, min, max)

• Identify patterns and distributions

• Examine correlations between variables

• Execute data analysis and visualization using pandas and matplotlib

• Create simple visualizations (such as histograms, bar charts, and box plots) to effectively represent your data using matplotlib.

• Write and execute Python code in Google Colab to analyze data systematically.

Final Assesment

Final Assesment

Additional Resources

Congrats

Harvard Certification

This is the end of the course, now get out there and lets solve real world problems!

Guided Projects

Free Datasets

Online Forums