112-2 師大科技系程式語言 (Programming Language at National Taiwan Normal University (NTNU) in 2024)
授課教師:蔡芸琤老師(Pecu)
姓名:鍾孟傑(Michael)
系級:選讀生 (學號: 91299217Y)
- Read the data using Python Pandas and convert the DataFrame to a Set data type.
- Utilize the characteristics of the Set data type to perform union, intersection, and difference analyses.
- Explain the results of the analysis.
- Perform EDA on store sales data from Kaggle.
- Build machine learning model to predict store sales.
- Make hypothesis based on the previous result and then optimize the the model.
- Summarize the results of the analysis.
- Clean the scraped website content using regular expressions.
- Structure the relevant data into two formats: a DataFrame and a dictionary (you may modularize the code as desired).
- Export these two data formats into CSV and JSON files, respectively.
- Create an explanatory video of the code and upload it to YouTube.
- Continue exploring the dataset obtained from Assignment Three's web scraping.
- Extract features from the unstructured data.
- Use jieba for word segmentation and obtain keyword frequencies.
- Obtain a summary using an LLM (Large Language Model), then extract keywords from the summary.
- Visualize these features using an association graph.
- Sync files between local and GitHub: use GitHub Desktop
- Exercise: Demostrating LLM with RAG
- Exercise: Data visualization practice
- Exercise: Json data practice
- Exercise: Regex practice
- Exercise: Web scraping practice
- No class (Tomb Sweeping Day)
- Exercise: Data cleaning & Data Visualization
- Exercise: HuggingFace pipline practice
- Exercise: Try multiple LLM models on HuggingFace
- Exercise: Langchain practice
Linebot_PL_Assistant
Demo Video
Linebot ID & QRcode
Markdown 語法說明:https://markdown.tw/