AI數據應用人才培訓班 - 專題作品集
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
Tableau 數據分析
個專 全台寵物登記數與新生兒數的數據分析 (2019-2023年)
-
簡報連結
Image Not Showing
Possible Reasons
- The image was uploaded to a note which you don't have access to
- The note which the image was originally uploaded to has been deleted
Learn More →
-
Tableau 數據圖表連結
Image Not Showing
Possible Reasons
- The image was uploaded to a note which you don't have access to
- The note which the image was originally uploaded to has been deleted
Learn More →
團專 最常發生車禍的時段、路段、肇因與肇事者輪廓分析
- Tableau 數據圖表連結
Image Not Showing
Possible Reasons
- The image was uploaded to a note which you don't have access to
- The note which the image was originally uploaded to has been deleted
Learn More →
Image Not Showing
Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
Learn More →
機器學習
團專 Steam 電子遊戲價格預測系統
Image Not Showing
Possible Reasons
- The image was uploaded to a note which you don't have access to
- The note which the image was originally uploaded to has been deleted
Learn More →
- 簡報連結 (UI介紹 p48-p51)
- 簡報錄影 (UI介紹:17:33 ~ 24:40)
- 個人貢獻:前端 UI 程式的撰寫
- 團專心得:
- 分組階段:考量到自身程式技術方面較弱, 所以會想找有機器學習基礎背景的團員, 可以借重他們的能力完成專案不至於開天窗, 也可以從中跟他們學習。其中有個組員剛好 Tableau 團專有同組過, 知道組員是樂於分享的個性, 所以是我會選擇加入的重點之一。另外, 組上的其他成員們, 似乎是對程式比較弱的人, 也沒有其他偏 PM 的角色, 剛好可以發揮我能力以及主動去承擔比較多責任與挑戰的地方。(但是後想想或許加入能力或是積極度比較好的組別, 可以激盪出更多的想法, 但在不認識彼此的情況下, 當時做的抉擇就是最好的選擇了。重點是自己從中學到了什麼。)
- 專案分工:開會後, 大家決定各自進行資料清洗與模型訓練, 再一起比較各自訓練後的評估結果, 從中選出一個大家都認為最可靠與分數最高的模型。由於我在資料前處理部分疑似有出現資料洩漏的問題, 導致模型評估結果出現 overfiting, 所以最終沒有被選取。
- 專題實作: 由於當初選擇是其他組員跑 AutoML 後的已訓練好的模型, 所以最終完成此系統的重點會是在完成介面與上雲的整合部分。雖然本人欠缺前端開發程式開發經驗, 還是勇敢主動接下此任務, 最終在借重 Cusor 以及 Claude 等 AI 工具協助下順利完成前端介面的撰寫與欄位優化。
- 後續精進:由於團專的時間有限, 所以當初用的AI套件是用在地端執行的程式, 介面很陽春。但在後來寫ML作業時, 改用Gradio套件做出了相同效果的介面, 而且更美觀, 可作為之後開發前端的選擇。 後續會嘗試在 kaggle 上找資料集, 試著自己在 GCP 上做資料前處理與模型訓練和推理當作練習。 也會嘗試找side project做, 看看自己有沒有辦法利用課堂所學和AI工具完成一些自動化的流程。