#University Selection
#Competitive Strength for Further Study

• Top-notch teachers, professional teaching
• Concept understanding and hands-on practice every week
• Let children clearly grasp the key to solving problems
• The course consists of 30 lessons (60 minutes per lesson)
  
• Course tuition fee: 45,000 yuan

Course Planning

Phase 1: Data Analysis and Visualization

Course 1: NumPy Basics
● Content: Creation and manipulation of NumPy arrays, basic mathematical operations and statistical functions.
● Homework: Create a 5x5 random matrix and calculate the mean and standard deviation of each column.

Course 2: Pandas Basics(1)
● Content: Creation of DataFrame and Series, data selection and filtering.
● Homework: Use Pandas to read a CSV file and filter out data under certain conditions.

Course 3: Pandas Basics(2)
● Content: Summarization, grouping and aggregation of data, and handling of missing values.
● Homework: Group by a certain column, calculate the mean of each group, and fill in the missing values ​​in the data.

Course 4: Matplotlib and Seaborn
● Content: Drawing basic data visualization charts, customizing charts, and using Seaborn for advanced visualization.
● Homework: Use Matplotlib to draw line graphs and use Seaborn to draw scatter plots.

Phase 2: Machine Learning Basics

Course 5: Introduction to Machine Learning ● Content: Learn the theory and process of machine learning, the basic structure and process of Scikit-learn, and the implementation of a simple linear regression model.
● Homework: Use Scikit-learn to implement linear regression and predict a set of randomly generated data.

Course 6: Common Machine Learning Algorithms ● Content: Introduce common machine learning algorithms and perform simple implementations.
● Homework: Use Scikit-learn to build a random forest model and perform classification on a simple dataset.

Course 7: Model Evaluation and Selection ● Content: Model evaluation metrics (such as accuracy, recall, F1 score), cross-validation and model selection.
● Homework: Calculate the precision, recall, and F1 score on a binary classification problem and perform cross-validation.

Course 8: Introduction to Deep Learning ● Content: Basic concepts of deep learning, introduction to a simple feedforward neural network structure.
● Homework: Build a simple two-layer neural network using TensorFlow or PyTorch and train it on a small dataset.

Phase 3: Advanced Machine Learning, Deep Learning, and Kaggle Preparation

Course 9: Introduction to Kaggle Competition ● Content: Understand the Kaggle platform and its competition process, and choose a simple competition to start with (such as Titanic). ● Homework: Register a Kaggle account and enter the Titanic competition, and submit your first baseline result.

Course 10: EDA and Data Cleaning ● Content: Steps and techniques of exploratory data analysis (EDA), importance and practice of data cleaning.
● Homework: Perform EDA and cleaning on Titanic competition data and generate a cleaned data set.

Course 11: Model Building and Parameter Adjustment ● Content: Use different machine learning algorithms to build models and simply adjust parameters in the Kaggle competition.
● Homework: Use Scikit-learn to build at least two different models in the Titanic competition and compare their performance.

Course 12: Submitting and Improving Models ● Content: Learn how to submit Kaggle competition results and adjust the model based on feedback.
● Homework: Submit your model results in the Titanic competition and adjust your model based on the ranking.

Course 13: Feature Engineering and Feature Selection ● Content: Application of feature engineering techniques, feature selection and dimensionality reduction techniques (such as PCA).
● Homework: Try feature engineering in the Titanic competition and use PCA for dimensionality reduction.

Course 14: Model Evaluation and Tuning ● Content: Use cross-validation and grid search to evaluate and tune the model.
● Homework: Use GridSearchCV to perform hyperparameter tuning for the model in the Titanic competition.

Course 15: Advanced Deep Learning (1)
● Content: A deeper understanding of neural network structure and an introduction to convolutional neural networks (CNN).
● Homework: Implement a simple CNN model using TensorFlow or PyTorch and train it on an image dataset.

Course 16: Advanced Deep Learning (2)
● Content: Introduction to Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM).
● Homework: Build a simple LSTM model using TensorFlow or PyTorch and train it on sequence data.

Phase 4: Kaggle Challenges, In-depth Learning
Course 17 ~ Course 20: Advanced Kaggle Competition Preparation, Get Your First Bronze Medal ● Content: Choose a Kaggle competition, understand its data and problem background, and develop a strategy. Try to get the first bronze medal Course 20 ~ Course 30: Continue to improve and familiarize yourself with data science skills until you get Expert certification