Python for Research – 8 Week Roadmap
This roadmap will guide you from beginner-level Python to being research-ready for
data/image preprocessing, training, testing, and classification.
Week 1 – Python Basics
• Install Anaconda (https://www.anaconda.com/download)
• Learn Jupyter Notebook basics
(https://www.datacamp.com/tutorial/jupyter-notebook-tutorial)
• Variables, data types, if/else, loops, functions, File I/O
• Resources: W3Schools Python Tutorial (https://www.w3schools.com/python/), Python
for Beginners (https://www.youtube.com/watch?v=rfscVS0vtbw)
Week 2 – Python Intermediate Skills
• List comprehensions, error handling, importing modules
• Using os & glob for file handling
• Small practice programs
• Resources: Real Python List Comprehensions
(https://realpython.com/list-comprehension-python/), Python Modules and Packages
(https://realpython.com/python-modules-packages/)
Week 3 – NumPy & Pandas
• NumPy: arrays, indexing, slicing, broadcasting, random generation
• Pandas: DataFrame, filtering, grouping, missing values
• Reading/writing CSV & Excel files
• Resources: NumPy Quickstart (https://numpy.org/doc/stable/user/quickstart.html),
Pandas Tutorial Kaggle (https://www.kaggle.com/learn/pandas)
Week 4 – Data Visualization
• Matplotlib: line, scatter, bar, hist
• Seaborn: heatmaps, pair plots
• Customizing charts
• Resources: Matplotlib Tutorial (https://matplotlib.org/stable/tutorials/index.html),
Seaborn Documentation (https://seaborn.pydata.org/tutorial.html)
Week 5 – Image Processing
• OpenCV: read, display, resize, crop, color conversion
• Pillow: basic edits (rotate, flip, filter)
• Image preprocessing & augmentation
• Resources: OpenCV-Python Tutorials
(https://docs.opencv.org/4.x/d6/d00/tutorial_py_root.html), Pillow Docs
(https://pillow.readthedocs.io/en/stable/)
Week 6 – Machine Learning Basics
• Scikit-learn: train/test split, scaling data
• Classification models: Logistic Regression, Decision Tree, Random Forest
• Model evaluation: accuracy, precision, recall, F1-score
• Resources: Scikit-learn User Guide (https://scikit-learn.org/stable/user_guide.html),
Google ML Crash Course
(https://developers.google.com/machine-learning/crash-course)
Week 7 – Deep Learning for Images
• PyTorch or TensorFlow basics
• CNN layers: Conv2D, Pooling, Flatten, Dense
• Training on MNIST or CIFAR-10
• Transfer Learning (VGG16, ResNet)
• Resources: PyTorch Tutorials (https://pytorch.org/tutorials/), TensorFlow Keras Guide
(https://www.tensorflow.org/guide/keras), Deep Learning with PyTorch
(https://www.youtube.com/watch?v=GIsg-ZUy0MY)
Week 8 – Research-Level Practice
• Load custom datasets, apply augmentation
• Experiment with transfer learning
• Document experiments in Jupyter
• Read one research paper from Papers With Code
(https://paperswithcode.com/task/image-classification) and replicate results
• Resources: Albumentations Docs (https://albumentations.ai/docs/), Kaggle Datasets
(https://www.kaggle.com/datasets)
