Upload 4 files

AutoPreprocess.py

@@ -0,0 +1,147 @@
+import pandas as pd
+import numpy as np
+import pickle
+from sklearn.base import BaseEstimator, TransformerMixin
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.preprocessing import LabelEncoder
+from sklearn.preprocessing import RobustScaler
+
+class AutoPreprocess(BaseEstimator, TransformerMixin):
+    def __init__(self):         
+        self.scaler = {}
+        self.fillna_value = {}
+        self.onehotencode_value = {}
+        self.field_names = []
+        self.final_field_names = []
+        self.field_dtype = {}
+        
+    def fit(self, X, y = None, field_names=None):
+        self.__init__()
+        if field_names is None:
+            self.field_names = X.columns.tolist()
+        else:
+            self.field_names = field_names       
+
+        for fname in self.field_names:
+            self.field_dtype = X[fname].dtype
+        
+        for fname in self.field_names:
+            #自動補空值
+            # if (X[fname].dtype == object) or (X[fname].dtype == str): #字串型態欄位
+            if pd.api.types.is_string_dtype(X[fname]):
+                self.fillna_value[fname] = X[fname].mode()[0] #補眾數
+                # self.fillna_value[fname] = 'np.nan'
+                # self.fillna_value[fname] = np.nan # 維持空值
+            # elif X[fname].dtype == bool: #布林型態
+            elif pd.api.types.is_bool_dtype(X[fname]):
+                self.fillna_value[fname] = X[fname].mode()[0] #補眾數
+            else: # 數字型態
+                self.fillna_value[fname] = X[fname].median()  #補中位數
+            
+            #自動尺度轉換(scaling)
+            # if (X[fname].dtype == object) or (X[fname].dtype == str): #字串型態欄位
+            if pd.api.types.is_string_dtype(X[fname]):
+                pass #不用轉換
+            # elif X[fname].dtype == bool: #布林型態
+            elif pd.api.types.is_bool_dtype(X[fname]):
+                pass #不用轉換
+            else: # 數字型態
+                vc = X[fname].value_counts()
+                if X[fname].isin([0, 1]).all(): #當數值只有0跟1
+                    pass #不用轉換
+                elif pd.api.types.is_integer_dtype(X[fname]) and X[fname].nunique() <= 10: #是否簡單的整數型類別且數量小於10
+                    self.scaler[fname] = MinMaxScaler()    
+                    self.scaler[fname].fit(X[[fname]])
+                else: #其他的數字型態
+                    self.scaler[fname] = RobustScaler()    
+                    self.scaler[fname].fit(X[[fname]])
+
+            
+            #自動編碼
+            # if (X[fname].dtype == object) or (X[fname].dtype == str): #字串型態欄位
+            if pd.api.types.is_string_dtype(X[fname]):
+                field_value = X[fname].value_counts().index
+                self.onehotencode_value[fname] = field_value
+                for value in field_value:
+                    fn = fname+"_"+value
+                    # data[fn] = (data[fname] == value).astype('int8')
+                    self.final_field_names.append(fn)                    
+            # elif X[fname].dtype == bool: #布林型態
+            elif pd.api.types.is_bool_dtype(X[fname]):
+                # data[fname] = data[fname].astype(int)
+                self.final_field_names.append(fname)
+            else: # 數字型態 不用重新編碼
+                self.final_field_names.append(fname)
+                
+        return self
+
+    def transform(self, X):
+        #如果輸入的data是dict，要先轉成dataframe
+        if isinstance(X, dict):
+            for fname in self.field_names:
+                if fname in X:
+                    X[fname] = [X[fname]]
+                else:
+                    # X[fname] = [np.nan]
+                    X[fname] = self.fillna_value[fname]
+                
+            data = pd.DataFrame(X)
+
+            # for fname in self.field_names:
+                # data[fname].astype(self.field_dtype[fname])
+
+        else: #將資料複製一份，不修改原本的資料
+            data = X.copy()
+        
+        for fname in self.field_names:
+            #自動補空值
+            if data[fname].isnull().any(): #有空值
+                # if fname in self.fillna_value:
+                    data[fname] = data[fname].fillna(self.fillna_value[fname])
+
+
+            #自動尺度轉換(scaling)
+            if fname in self.scaler:
+                data[fname] = self.scaler[fname].transform(data[[fname]])
+            
+            #自動編碼
+            # if (data[fname].dtype == object) or (data[fname].dtype == str): #字串型態欄位, onehotencode
+            if pd.api.types.is_string_dtype(data[fname]):
+                if fname in self.onehotencode_value:                   
+                    field_value = self.onehotencode_value[fname]
+                for value in field_value:
+                    fn = fname+"_"+value
+                    data[fn] = (data[fname] == value).astype('int8')
+            # elif data[fname].dtype == bool: #布林型態 轉成0跟1
+            elif pd.api.types.is_bool_dtype(data[fname]):
+                data[fname] = data[fname].astype(int)
+            else: # 數字型態 不用重新編碼
+                pass                
+        return data[self.final_field_names]
+
+    def save(self, file_name):
+        with open(file_name, "wb") as f:
+            pickle.dump(self, f)
+
+    @staticmethod
+    def load(file_name):
+        with open(file_name, "rb") as f:
+            return pickle.load(f)          
+        
+
+# import pandas as pd
+# mydata = pd.read_csv('C:/DATA/class/2025-07 AI數據應用人才養成班三期/data/Automobile_Train.csv')
+# ap = AutoPreprocess()
+# # ap.fit(mydata, field_names=['symboling', 'Normalized-losses', 'make', 'Fuel-type', 'aspiration',
+# #        'Num-of-doors', 'Body-style', 'Drive-wheels', 'Engine-location',
+# #        'Wheel-base', 'length', 'width', 'height', 'Curb-weight', 'Engine-type',
+# #        'Num-of-cylinders', 'Engine-size', 'Fuel-system', 'bore', 'stroke',
+# #        'Compression-ratio', 'horsepower', 'Peak-rpm', 'City-mpg',
+# #        'Highway-mpg'])
+# ap.fit(mydata)
+
+# # 轉換 panddas dataframe
+# t = ap.transform(mydata)
+# print(t.head())
+
+

DASS_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01fbbbc7c1caf29a57301ff82c22ff6460f1e5d4a1e4e04abccd8ce3f3edfc5
+size 3105621

app.py

@@ -0,0 +1,406 @@
+# -*- coding: utf-8 -*-
+"""DASS心理模型(Q12).ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/19ATyW5Lb692QV2Gk2I0rlsbeSQNwEDnQ
+
+建立環境
+"""
+
+!pip install gradio
+
+!pip install gspread google-auth
+
+import pandas as pd
+import matplotlib.pyplot as plt
+import numpy as np
+import gradio as gr
+import sklearn
+import pickle
+import joblib
+import time
+import os
+import json
+import gspread
+
+
+from sklearn.model_selection import train_test_split, RandomizedSearchCV
+from sklearn.compose import ColumnTransformer
+from sklearn.preprocessing import OneHotEncoder, StandardScaler
+from sklearn.pipeline import Pipeline
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import classification_report, confusion_matrix, f1_score, accuracy_score, precision_score, balanced_accuracy_score
+from sklearn.ensemble import RandomForestClassifier
+from lightgbm import LGBMClassifier
+from AutoPreprocess import AutoPreprocess
+from google.oauth2.service_account import Credentials
+from datetime import datetime, timezone, timedelta
+
+"""Gradio 使用者介面"""
+
+# 載入模型
+import pickle
+model_path = os.path.abspath("DASS_model.bin")
+
+with open(model_path, "rb") as f:
+    model = pickle.load(f)
+model
+
+"""定義歷史紀錄功能"""
+
+def update_history(current_result_1, current_result_2, history_list):
+    """
+    current_result_1 & 2: 來自 predict_risk 的兩個回傳值 (HTML 字串)
+    history_list: 來自 gr.State 的現有紀錄列表
+    """
+
+    # 獲取當前時間，格式為：2023-10-27 14:30:05
+    now = datetime.now(tw_timezone).strftime("%Y-%m-%d %H:%M:%S")
+
+    # 組合這次的結果 (假設你想存這兩個 outputs 的組合)
+    new_entry = f"""
+    <div style="border-bottom: 2px solid #eee; padding-bottom: 20px; margin-bottom: 20px;">
+        <div style="font-size: 18px; color: #666; margin-bottom: 10px; font-weight: bold;">
+            🕒 測驗時間：{now}
+        </div>
+
+        <div style="
+        display: flex;
+        flex-direction: row;
+        justify-content: space-between;
+        align-items: flex-start;
+        gap: 20px;
+        border-bottom: 1px dashed #ccc;
+        padding-bottom: 15px;
+        margin-bottom: 15px;
+        width: 100%;">
+
+        <div style="flex: 1;">{current_result_1}</div>
+        <div style="flex: 1;">{current_result_2}</div>
+
+    </div>
+    </div>
+    """
+
+    # 將新紀錄放在最前面 (置頂)
+    history_list.insert(0, new_entry)
+
+    # 組合所有歷史紀錄，並整體縮小 80%
+    # 使用 zoom: 0.8 或 transform 達到字體與版面同時縮小的效果
+    combined_html = f"""
+    <div style="zoom: 0.8; -moz-transform: scale(0.8); -moz-transform-origin: 0 0;">
+        {"".join(history_list)}
+    </div>
+    """
+
+    return combined_html, history_list
+
+"""定義儲存測試資料的功能"""
+
+import os
+import json
+from datetime import datetime, timezone, timedelta
+import gspread
+from google.oauth2.service_account import Credentials
+
+# 設定台灣時區
+tw_timezone = timezone(timedelta(hours=8))
+
+def save_to_google_sheets(inputs, a_score, d_score, s_score, t_score, score):
+
+    # 1. 設定 Google Sheets 存取權限
+    scope = ['https://www.googleapis.com/auth/spreadsheets',
+             'https://www.googleapis.com/auth/drive']
+
+    # 設定Secret Variables(藏金鑰)
+    google_json = os.environ.get("DASS_JSON")
+    info = json.loads(google_json)
+    creds = Credentials.from_service_account_info(info, scopes=scope)
+    client = gspread.authorize(creds)
+
+    # 2. 開啟指定名稱的試算表 (確保已分享權限給 service account)
+    sheet = client.open("DASS使用者測試資料.csv").sheet1 # 存於檔案的第一張工作表
+
+
+    # 1. 拆分資料：前 3 個是基本資料，後面剩下的 (*rest) 是 12 題答案
+    user_info = inputs[:3]  # 取得前三個：姓名, 年齡, 性別
+    q_answers = inputs[3:]  # 取得剩下的 12 題
+    now = datetime.now(tw_timezone).strftime("%Y-%m-%d %H:%M:%S")
+
+    # 2. 準備要儲存的資料字典
+    row_to_add = [
+        now,             # 欄位 A: 測試時間
+        user_info[0],   # 欄位 B: 性別
+        user_info[1],   # 欄位 C: 年齡
+        user_info[2],   # 欄位 D: 家庭人數
+        a_score,         # 欄位 E: 焦慮分數
+        d_score,         # 欄位 F: 憂鬱分數
+        s_score,         # 欄位 G: 壓力分數
+        t_score,         # 欄位 H: 總體分數
+        score            # 欄位 I: 整體程度 (標籤)
+    ]
+
+    row_to_add.extend(q_answers) # 加入 Q1-Q12 (J欄以後)
+
+    # 4. 追加到試算表最後一行
+    sheet.append_row(row_to_add)
+
+"""定義重新測驗功能"""
+
+# 清空函數：回傳與輸入組件數量相同的 None (15個：gen, age, family + 12個問題)
+def clear_all():
+    # 15個輸入(gen, age, family, q1~q12) + 2個即時結果
+    return [None] * 15 + ["", ""]
+
+"""定義主要測試功能"""
+
+def predict_risk(gen, age, family, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11, q12):
+    inputs = [gen, age, family, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11, q12]
+
+    # 檢查是否有任何一個選項是 None (未按)
+    if any(v is None or v == "" for v in inputs):
+        # Return error message to a dedicated output component
+        return "", "", "<div style=\"color: red; font-weight: bold;\">⚠️測驗載入有誤：請確保每一題都已填答或查看填答格式是否正確。</div>"
+
+    # Clear any previous error message if inputs are valid
+    error_message = ""
+
+    # 1. 跑進度條 (需確保函式參數有 progress=gr.Progress())
+    progress = gr.Progress()
+    progress(0, desc="模型計算中...")
+
+    # 2. 將 12 個輸入整理成模型認得的 DataFrame
+    # 欄位名稱必須與訓練時完全相同
+    cols = ["gender", "age", "familysize", "Q2A", "Q4A", "Q19A", "Q20A", "Q28A", "Q21A", "Q26A", "Q37A", "Q42A", "Q11A", "Q12A", "Q27A"]
+    input_df = pd.DataFrame([[gen, age, family, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11, q12]], columns=cols)
+
+    progress(0.5, desc="正在分析數據...")
+    time.sleep(0.5) # 模擬運算時間
+
+    # 3. 使用模型 model 進行預測
+    score = model.predict(input_df)[0]
+    progress(1.0, desc="計算完成！")
+
+
+    # 4. 定義風險標籤
+    if score == 0:
+        label = "低度風險"
+        color = "#91cd92"  # 綠色
+    elif score == 1:
+        label = "中度風險"
+        color = "#f59e0b"  # 橘色
+    elif score == 2:
+        label = "高度風險"
+        color = "#ef4444"  # 紅色
+    else:
+        label = "計算結果有誤，請重新測試。"
+
+    # 定義類別分數條
+    a_score = (q1 + q2 + q3 + q4 + q5)
+    d_score = (q6 + q7 + q8 + q9)
+    s_score = (q10 + q11 + q12)
+    t_score = a_score + d_score + s_score
+    max_val = 36
+
+    def make_bar(label, score, max_val, color):
+        percent = (score / max_val) * 100
+        return f"""
+        <div style="margin-bottom: 10px;">
+            <div style="display: flex; justify-content: space-between; margin-bottom: 5px;">
+                <span style="font-weight: bold;">{label}</span>
+            </div>
+            <div style="background-color: #e0e0e0; border-radius: 10px; height: 12px; width: 100%;">
+                <div style="background-color: {color}; width: {percent}%; height: 100%; border-radius: 10px;"></div>
+            </div>
+        </div>
+        """
+
+    # 5. 準備回傳內容
+    # 總分與風險標籤
+    result_score = f"""
+    <div style="text-align: center; font-family: sans-serif;">
+        <h2 style="color: #313230;">您的預測結果為</h2>
+        <h1 style="font-size: 60px; color: {color}; margin: 0;">
+            {label}
+        </h1>
+        <h1 style="font-size: 20px; color: #bbbbc2; margin: 0;">
+            {t_score}/36
+        </h1>
+    </div>
+    """
+
+    # 類別分數條
+    label_html = f"""
+    <div style="padding: 20px; background: white; border-radius: 10px; border: 1px solid #ddd;">
+        <h2 style="color: #313230;margin-top: 0; margin-bottom: 15px;">各面向之比重</h2>
+        {make_bar("焦慮 (Anxiety)", a_score, max_val, "#fccb42")}
+        {make_bar("憂鬱 (Depression)", d_score, max_val, "#6dc8fe")}
+        {make_bar("壓力 (Stress)", s_score, max_val, "#fb6d6d")}
+    </div>
+    """
+
+    # 儲存測試資料
+    save_to_google_sheets(inputs, a_score, d_score, s_score, t_score, score)
+
+
+    progress(1.0, desc="完成")
+
+    return result_score, label_html, error_message
+
+# 設定主題色
+
+theme = gr.themes.Default(
+    primary_hue="amber",
+    secondary_hue="amber",
+).set(
+    body_background_fill="#fffbeb"
+)
+
+# 線上主題調色器
+# gr.themes.builder()
+
+# 介面編排
+
+#按鈕及面板格式設定
+custom_css = """
+#my_green_btn {
+    background-color: #91cd92 !important;
+    color: white !important;
+    border: none;
+}
+#my_green_btn:hover {
+    background-color: #72a473 !important; /* 滑鼠懸停時變深 */
+}
+
+#my_white_btn {
+    background-color: #ffffff !important;
+    color: black !important;
+    border: 1px solid #e4e4e7;
+}
+
+#my_white_btn:hover {
+    background-color: #e4e4e7 !important;
+    color: black !important; /* 滑鼠懸停時變深 */
+}
+
+
+.my-custom-panel {
+    background-color: #fffef8 !important;
+    border: 2px solid #e4e4e7 !important;
+    padding: 20px;
+    border-radius: 15px;
+}
+
+#history_panel .label-wrap span {
+    font-weight: bold !important;
+}
+"""
+
+with gr.Blocks(theme=theme, css=custom_css) as demo:
+
+    # 建立 Session 狀態 (開啟瀏覽器時初始化為空列表)
+    history_state = gr.State([])
+
+    # 標題及說明
+    gr.Markdown("")
+    gr.HTML(f"""
+    <div style="text-align: center; font-family: sans-serif;">
+        <h2 style="font-size: 32px; color: #313230; margin: 0;">🌿心理健康風險程度測試📝</h2>
+    </div>
+    """)
+    gr.HTML(f"""
+    <div style="text-align: center; font-family: sans-serif;">
+        <h2 style="font-size: 18px; color: #313230; margin: 0;">歡迎來到心理健康風險程度測試環境！<br>
+        本測驗將透過12題問答，替您在5分鐘內簡單計算出潛在的心理健康風險程度。<br>
+        請輕鬆填答，無須思慮過度，測驗愉快！</h2>
+    </div>
+    """)
+
+    with gr.Column(variant="panel", elem_classes="my-custom-panel"):
+
+        # 輸入區塊1(人口靜態欄位)
+        gr.Markdown("## Step 1. 請輸入基本資訊")
+        with gr.Row():
+            with gr.Column():
+                name = gr.Textbox(label="暱稱")
+                gen = gr.Dropdown(choices=["男", "女", "其他"],
+                                    label="性別",
+                                    value=[])
+            with gr.Column():
+                age = gr.Number(label="年齡 (僅限填寫數字)", value ="")
+                family = gr.Number(label="家庭人數 (僅限填寫數字)", value ="")
+
+
+        # 輸入區塊2(測驗題)
+        gr.Markdown("")
+        gr.Markdown("## Step 2. 請依自身狀態選擇符合的答案")
+        q1 = gr.Radio([("從不", 0), ("偶爾", 1), ("經常", 2), ("總是", 3)],
+                    label="Q1.我感覺到口乾舌燥。")
+        q2 = gr.Radio([("從不", 0), ("偶爾", 1), ("經常", 2), ("總是", 3)],
+                    label="Q2.我感到呼吸困難（例如：在沒有體力勞動的情況下，呼吸過度急促或喘不過氣）。")
+        q3 = gr.Radio([("從不", 0), ("偶爾", 1), ("經常", 2), ("總是", 3)],
+                    label="Q3.在氣溫不高或沒有體力勞動的情況下，我明顯地流汗（例如：手汗）。")
+        q4 = gr.Radio([("從不", 0), ("偶爾", 1), ("經常", 2), ("總是", 3)],
+                    label="Q4.我無緣無故地感到害怕。")
+        q5 = gr.Radio([("從不", 0), ("偶爾", 1), ("經常", 2), ("總是", 3)],
+                    label="Q5.我覺得自己接近恐慌發作的邊緣。")
+        q6 = gr.Radio([("從不", 0), ("偶爾", 1), ("經常", 2), ("總是", 3)],
+                    label="Q6.我覺得生命沒什麼意義/價值。")
+        q7 = gr.Radio([("從不", 0), ("偶爾", 1), ("經常", 2), ("總是", 3)],
+                    label="Q7.我感到垂頭喪氣、情緒低落。")
+        q8 = gr.Radio([("從不", 0), ("偶爾", 1), ("經常", 2), ("總是", 3)],
+                    label="Q8.我覺得未來毫無希望。")
+        q9 = gr.Radio([("從不", 0), ("偶爾", 1), ("經常", 2), ("總是", 3)],
+                    label="Q9.我發現自己很難打起精神主動去做事。")
+        q10 = gr.Radio([("從不", 0), ("偶爾", 1), ("經常", 2), ("總是", 3)],
+                    label="Q10.我發現自己很容易變得心煩意亂。")
+        q11 = gr.Radio([("從不", 0), ("偶爾", 1), ("經常", 2), ("總是", 3)],
+                    label="Q11.我覺得自己消耗了大量的神經能量（處於高度緊繃狀態）。")
+        q12 = gr.Radio([("從不", 0), ("偶爾", 1), ("經常", 2), ("總是", 3)],
+                    label="Q12.我發現自己非常易怒（容易焦躁）。")
+
+
+    # 確認送出按鈕
+    sub_button = gr.Button("確認送出", elem_id="my_green_btn")
+    # 重新測驗按鈕
+    with gr.Row():
+        btn_reset = gr.Button("重新測驗", elem_id="my_white_btn")
+
+    # 輸出測試結果
+    with gr.Row():
+            out_html = gr.HTML()
+            out_label = gr.HTML()
+
+
+    # --- 新增：歷史紀錄呈現區域 ---
+    with gr.Accordion("查看歷史紀錄", open=False, elem_id="history_panel"):
+        history_display = gr.HTML(value="目前尚無測驗紀錄")
+
+
+    # 按鈕設定
+    # 1. 確認送出
+    sub_button.click(fn=predict_risk,
+                inputs= [gen, age, family, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11, q12],
+                outputs= [out_html, out_label]
+                ).then(
+    fn=update_history,
+    inputs=[out_html, out_label, history_state],
+    outputs=[history_display, history_state])
+
+    # 2. 重新測驗 (清空所有輸入與輸出)
+    # 注意：outputs 必須包含所有輸入的組件
+    btn_reset.click(
+        fn=lambda: [None]*15 + ["", ""],
+        inputs=None,
+        outputs=[gen, age, family, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11, q12, out_html , out_label]
+    )
+
+    gr.Markdown("## 免責聲明")
+    gr.Markdown("""本測驗結果僅供參考，非屬正規醫療檢驗範疇。
+    若對於自身狀況有任何疑慮，敬請尋求正規專業醫療協助！♡第四組關心您♡""")
+
+demo.launch(share=True)
+
+# 如需免費永久托管，需在終端機模式執行「gradio deploy」部署到 Hugging Face Spaces。

requirements.txt

@@ -0,0 +1,17 @@
+gradio
+pandas
+numpy
+matplotlib.pyplot
+sklearn
+joblib
+lightgbm
+gspread
+google-auth
+pytz
+pickle
+lightgbm.LGBMClassifier
+AutoPreprocess.AutoPreprocess
+time
+datetime
+os
+json