From c97b779adba517f23afc25a47006732506cb8ef5 Mon Sep 17 00:00:00 2001
From: kellyLiu <kellyliu060687@gmail.com>
Date: Sun, 3 May 2026 21:09:42 +0800
Subject: [PATCH 1/2] =?UTF-8?q?=E5=AE=8C=E6=88=90=E4=BD=9C=E6=A5=AD?=
 =?UTF-8?q?=E7=B9=B3=E4=BA=A4=20-=20=E5=8A=89=E5=87=B1=E8=8E=89=20-=20AIPE?=
 =?UTF-8?q?03?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 homework/m1_numpy.py           |  29 +++++----
 homework/m2_pandas_cleaning.py |  34 +++++-----
 homework/m3_pandas_advanced.py |  37 ++++++-----
 homework/m4_timeseries.py      |  36 ++++++-----
 homework/m5_visualization.py   | 112 ++++++++++++++++++++++++++++-----
 homework/m6_plotly_capstone.py | 110 +++++++++++++++++++++++++++-----
 6 files changed, 271 insertions(+), 87 deletions(-)

diff --git a/homework/m1_numpy.py b/homework/m1_numpy.py
index 5ff41ab..07c7b96 100644
--- a/homework/m1_numpy.py
+++ b/homework/m1_numpy.py
@@ -18,20 +18,19 @@
 
 def green_mean():
     """建立 [10, 20, 30, 40, 50]，回傳所有元素的平均值 (float)"""
-    # TODO: 你的程式碼
-    pass
-
+    arr = np.array([10,20,30,40,50])
+    return arr.mean()
 
 def green_double():
     """建立 [10, 20, 30, 40, 50]，回傳所有元素乘以 2 的 ndarray"""
-    # TODO: 你的程式碼
-    pass
+    arr = np.array([10,20,30,40,50])
+    return arr * 2
 
 
 def green_filter():
     """建立 [10, 20, 30, 40, 50]，回傳大於 25 的元素 (ndarray)"""
-    # TODO: 你的程式碼
-    pass
+    arr = np.array([10,20,30,40,50])
+    return arr[arr > 25]
 
 
 # ============================================================
@@ -41,8 +40,8 @@ def green_filter():
 
 def yellow_expensive_count(prices):
     """回傳單價 > 1000 的商品數量 (int)"""
-    # TODO: 你的程式碼
-    pass
+    mask = prices > 1000
+    return mask.sum()
 
 
 def yellow_top3_stock_indices(stocks):
@@ -50,8 +49,8 @@ def yellow_top3_stock_indices(stocks):
     回傳庫存最多的前 3 個商品的索引位置 (ndarray, 由大到小排)
     提示：np.argsort
     """
-    # TODO: 你的程式碼
-    pass
+    idx = np.argsort(-stocks)
+    return idx[0:3]
 
 
 def yellow_restock_cost(prices, stocks):
@@ -59,8 +58,8 @@ def yellow_restock_cost(prices, stocks):
     單價 < 500 的商品，每種各進貨 50 個，回傳總花費 (float/int)
     提示：布林遮罩 + .sum()
     """
-    # TODO: 你的程式碼
-    pass
+    total = prices[prices < 500] *50
+    return total.sum()
 
 
 # ============================================================
@@ -76,5 +75,5 @@ def red_double11_prices(prices, stocks):
     回傳每個商品的雙 11 售價 (ndarray)
     提示：np.where 可以巢狀使用
     """
-    # TODO: 你的程式碼
-    pass
+    return np.where(stocks >= 100, prices * 0.7,
+         np.where(stocks >= 20, prices * 0.9, prices))
\ No newline at end of file
diff --git a/homework/m2_pandas_cleaning.py b/homework/m2_pandas_cleaning.py
index fa36bff..ee9d16d 100644
--- a/homework/m2_pandas_cleaning.py
+++ b/homework/m2_pandas_cleaning.py
@@ -19,8 +19,9 @@ def green_read_csv():
     讀取 orders_raw.csv，回傳原始 DataFrame（不做任何清理）
     提示：pd.read_csv()
     """
-    # TODO: 你的程式碼
-    pass
+    DATA = '../datasets/ecommerce/orders_raw.csv'
+    df = pd.read_csv(DATA)
+    return df
 
 
 def green_shape(df):
@@ -28,8 +29,7 @@ def green_shape(df):
     回傳 DataFrame 的 (列數, 欄數) tuple
     提示：df.shape
     """
-    # TODO: 你的程式碼
-    pass
+    return df.shape
 
 
 def green_dtypes(df):
@@ -37,8 +37,7 @@ def green_dtypes(df):
     回傳 DataFrame 的欄位型別 (Series)
     提示：df.dtypes
     """
-    # TODO: 你的程式碼
-    pass
+    return df.dtypes
 
 
 # ============================================================
@@ -51,8 +50,9 @@ def yellow_clean_columns(df):
     回傳清理後的 DataFrame（不要修改原始 df）
     提示：df.columns.str.strip().str.lower()
     """
-    # TODO: 你的程式碼
-    pass
+    df2 = df.copy()
+    df2.columns = df2.columns.str.strip().str.lower()
+    return df2
 
 
 def yellow_clean_amount(df):
@@ -62,8 +62,9 @@ def yellow_clean_amount(df):
     回傳清理後的 DataFrame（不要修改原始 df）
     提示：.str.replace() + .astype(float)
     """
-    # TODO: 你的程式碼
-    pass
+    df2 = df.copy()
+    df2['amount'] = df2['amount'].astype(str).str.replace('$','', regex=False).str.replace(',','', regex=False).astype(float)
+    return df2
 
 
 def yellow_drop_duplicates(df):
@@ -71,8 +72,8 @@ def yellow_drop_duplicates(df):
     移除完全重複的列，回傳去重後的 DataFrame
     提示：df.drop_duplicates()
     """
-    # TODO: 你的程式碼
-    pass
+    df = df.drop_duplicates()
+    return df
 
 
 # ============================================================
@@ -92,5 +93,10 @@ def red_clean_orders(path):
     回傳：清理後的 DataFrame
     提示：pd.to_datetime(errors='coerce')
     """
-    # TODO: 你的程式碼
-    pass
+    df = pd.read_csv(path)
+    df.columns = df.columns.str.strip().str.lower()
+    df['amount'] = df['amount'].astype(str).replace('$','',regex=False).replace(',','',regex=False).astype(float)
+    df['order_date'] = pd.to_datetime(df['order_date'], errors='coerce')
+    df = df.dropna(subset=['order_date','amount']) # 只要這兩個欄位中任一個有缺失值，該列就會被剔除。
+    df = df.drop_duplicates()
+    return df.shape[0]
\ No newline at end of file
diff --git a/homework/m3_pandas_advanced.py b/homework/m3_pandas_advanced.py
index 68410e8..e0f77f1 100644
--- a/homework/m3_pandas_advanced.py
+++ b/homework/m3_pandas_advanced.py
@@ -23,20 +23,22 @@ def green_load_and_merge():
     - 再 LEFT JOIN products.csv ON product_id
     提示：pd.merge(how='left')
     """
-    # TODO: 你的程式碼
-    pass
+    DATA="../datasets/ecommerce/"
+    orders = pd.read_csv(f'{DATA}/orders_clean.csv', parse_dates=['order_date'])
+    customers = pd.read_csv(f'{DATA}/customers.csv')
+    products  = pd.read_csv(f'{DATA}/products.csv')
+
+    return orders
 
 
 def green_row_count(df):
     """回傳 DataFrame 的列數 (int)"""
-    # TODO: 你的程式碼
-    pass
+    return df.shape[0]
 
 
 def green_column_list(df):
     """回傳 DataFrame 的所有欄位名稱 (list)"""
-    # TODO: 你的程式碼
-    pass
+    return list(df.columns)
 
 
 # ============================================================
@@ -49,9 +51,8 @@ def yellow_top_category(df):
     回傳該類別名稱 (str)
     提示：groupby('category')['amount'].sum()
     """
-    # TODO: 你的程式碼
-    pass
-
+    top = df.groupby('category')['amount'].sum().sort_values(ascending=False)
+    return f'{top.idxmax()}'
 
 def yellow_gold_vip_stats(df):
     """
@@ -59,9 +60,9 @@ def yellow_gold_vip_stats(df):
     回傳 tuple: (訂單數 int, 總金額 float)
     提示：df[df['vip_level'] == 'Gold']
     """
-    # TODO: 你的程式碼
-    pass
-
+    gold_mask = df[df['vip_level'] == 'Gold']
+    gold = gold_mask['amount'].agg(['count', 'sum'])
+    return f'訂單數: {int(gold['count'])}', f'總金額:{float(gold['sum'])}'
 
 def yellow_region_avg_amount(df):
     """
@@ -69,8 +70,8 @@ def yellow_region_avg_amount(df):
     回傳 Series（index=region, values=平均金額）
     提示：groupby('region')['amount'].mean()
     """
-    # TODO: 你的程式碼
-    pass
+    region_avg_amount = df.groupy('region')['amount'].mean().round(1)
+    return region_avg_amount
 
 
 # ============================================================
@@ -94,4 +95,10 @@ def red_rfm_top5(df):
     提示：groupby('customer_id').agg(...)
     """
     # TODO: 你的程式碼
-    pass
+    rfm = df.groupby('customer_id','customer_name').agg(
+        R=('order_date', 'max'),
+        F=('order_id', 'count'),
+        M=('amount', 'sum')
+    ).reset_index()
+    result = rfm.sort_values('M',ascending=False).head()
+    return result
diff --git a/homework/m4_timeseries.py b/homework/m4_timeseries.py
index 047af6a..e1d5a3f 100644
--- a/homework/m4_timeseries.py
+++ b/homework/m4_timeseries.py
@@ -26,8 +26,9 @@ def green_avg_by_month():
     回傳 Series（index=月份 1~12, values=平均金額）
     提示：df['order_date'].dt.month
     """
-    # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    df['month'] = df['order_date'].dt.month
+    return df.groupby(['month'])['amount'].mean().round(1)
 
 
 def green_top3_dates():
@@ -36,8 +37,8 @@ def green_top3_dates():
     回傳 Series（index=日期, values=訂單數, 由多到少排序）
     提示：value_counts().head(3)
     """
-    # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    return df['order_date'].value_counts().head(3)
 
 
 def green_date_range():
@@ -45,8 +46,8 @@ def green_date_range():
     回傳資料的日期範圍 tuple: (最早日期, 最晚日期)
     格式為 pandas Timestamp
     """
-    # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    return df['order_date'].min(),df['order_date'].max()
 
 
 # ============================================================
@@ -59,8 +60,8 @@ def yellow_monthly_revenue():
     回傳 Series（index=月底日期 period, values=總營收）
     提示：set_index('order_date').resample('ME')['amount'].sum()
     """
-    # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    return df.set_index('order_date').resample('ME')['amount'].sum()
 
 
 def yellow_rolling_avg(monthly_revenue):
@@ -70,8 +71,8 @@ def yellow_rolling_avg(monthly_revenue):
     回傳 Series（同樣 index，values=移動平均，前 2 筆可為 NaN）
     提示：.rolling(window=3).mean()
     """
-    # TODO: 你的程式碼
-    pass
+    monthly_rev = yellow_monthly_revenue()
+    return monthly_rev.rolling(window=3).mean()
 
 
 def yellow_category_median(df):
@@ -80,8 +81,7 @@ def yellow_category_median(df):
     回傳 Series（index=category, values=中位數）
     提示：groupby + median + sort_values
     """
-    # TODO: 你的程式碼
-    pass
+    return df.groupby(['category'])['amount'].median().sort_values(ascending=False)
 
 
 # ============================================================
@@ -100,5 +100,13 @@ def red_monthly_report():
     index 為月份 (period 或 datetime)
     提示：resample + agg + pct_change
     """
-    # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    report = df.set_index('order_date').resample('ME').agg({
+        'order_id':'count',
+        'amount':'sum',
+        'customer_id':'nunique'
+    })
+    report.columns=['order_count','revenue','active_customers']
+    report['avg_order_value'] = report['revenue'] / report['order_count']
+    report['revenue_growth'] = report['revenue'].pct_change() * 100
+    return report
diff --git a/homework/m5_visualization.py b/homework/m5_visualization.py
index 7e7335d..e6c8e9a 100644
--- a/homework/m5_visualization.py
+++ b/homework/m5_visualization.py
@@ -28,8 +28,25 @@ def green_bar_category():
     回傳 matplotlib Figure 物件
     提示：sns.countplot 或 value_counts().plot.bar()
     """
-    # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    cat_counts = df['category'].value_counts().reset_index()
+    cat_counts.columns = ['category', 'order_count']
+
+    fig = plt.figure(figsize=(8, 4))
+    sns.barplot(
+        data=cat_counts,
+        x='category', y='order_count',
+        hue='category', palette='viridis', legend=False
+    )
+    
+    plt.title('Order Count by Category', fontweight='bold')
+    plt.xlabel('Category')
+    plt.ylabel('Order Count')
+    for i, v in enumerate(cat_counts['order_count']):
+        plt.text(i, v, f'{v:,}', ha='center', va='bottom', fontsize=10)
+    plt.tight_layout()
+
+    return fig
 
 
 def green_hist_amount():
@@ -38,8 +55,14 @@ def green_hist_amount():
     回傳 matplotlib Figure 物件
     提示：sns.histplot(bins=20) 或 plt.hist()
     """
-    # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    fig = plt.figure(figsize=(9,4))
+    sns.histplot(data=df, x='amount', bins=20, kde=True, color='steeblue')
+    plt.title('Order Amount Distribution', fontweight='bold')
+    plt.xlabel('Amount')
+    plt.ylabel('Frequency')
+    plt.tight_layout()
+    return fig
 
 
 def green_set_labels():
@@ -50,8 +73,15 @@ def green_set_labels():
     - Y 軸標籤 (ylabel)
     回傳 matplotlib Figure 物件
     """
-    # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    region_rev = df.groupby('region')['amount'].sum().sort_values(ascending=False).reset_index()
+    fig = plt.figure(figsize=(8,4))
+    sns.barplot(data=region_rev, x='region', y='amount', palette='viridis', hue='region', legend=False)
+    plt.title('Revenue by Region', fontweight='bold')
+    plt.xlabel('Region')
+    plt.ylabel('Revenue')
+    plt.tight_layout()
+    return fig
 
 
 # ============================================================
@@ -67,8 +97,19 @@ def yellow_line_region_trend():
     回傳 matplotlib Figure 物件
     提示：分別 groupby 再 plot，或用 sns.lineplot(hue='region')
     """
-    # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    ns_df = df[df['region'].isin(['North','South'])]
+    month_sn = (
+        ns_df.groupby(['month','region'])['amount'].sum().reset_index()
+    )
+    fig = plt.figure(figsize=(8,4))
+    sns.lineplot(data=month_sn, x='month', y='amount', hue='region', marker='o', linewidth=2)
+    plt.title('Monthly Revenue: North vs South', fontweight='bold')
+    plt.xlabel('Month')
+    plt.ylabel('Revenue')
+    plt.legend(title='Region')
+    plt.tight_layout()
+    return fig
 
 
 def yellow_box_vip():
@@ -77,8 +118,14 @@ def yellow_box_vip():
     回傳 matplotlib Figure 物件
     提示：sns.boxplot(x='vip_level', y='amount', data=df)
     """
-    # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    fig = plt.figure(figsize=(9,5))
+    sns.boxplot(data=df, x='vip_level', y='amount',hue='vip_level', palette='Set3', legend=False)
+    plt.title('Order Amount Distribution by VIP Level', fontweight='bold')
+    plt.xlabel('VIP Level')
+    plt.ylabel('Amount')
+    plt.tight_layout()
+    return fig
 
 
 def yellow_scatter_price_amount():
@@ -87,8 +134,14 @@ def yellow_scatter_price_amount():
     回傳 matplotlib Figure 物件
     提示：plt.scatter() 或 sns.scatterplot()
     """
-    # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    fig = plt.figure(figsize=(8, 5))
+    sns.scatterplot(data=df, x='unit_price', y='amount', alpha=0.6, color='gold')
+    plt.title('Relationship between Unit Price and Order Amount', fontweight='bold')
+    plt.xlabel('Unit Price')
+    plt.ylabel('Amount')
+    plt.tight_layout()
+    return fig
 
 
 # ============================================================
@@ -106,5 +159,36 @@ def red_category_dashboard(category="Electronics"):
     回傳 matplotlib Figure 物件
     提示：fig, axes = plt.subplots(2, 2, figsize=(14, 10))
     """
-    # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    target_df = df[df['category'] == category].copy()
+    monthly = (target_df.groupby('month')['amount'].sum().reset_index())
+    region = (target_df.groupby('region')['amount'].sum().sort_values(ascending=False).reset_index())
+    top5 = (target_df.groupby('product_name')['amount'].sum().sort_values(ascending=False).head().reset_index())
+
+    fig, axes = plt.subplots(2, 2, figsize=(14,10))
+    fig.suptitle('Electronics Category Dashboard', fontsize=16, fontweight='bold')
+
+    sns.lineplot(data=monthly, x='month', y='amount', marker='o', linewidth=2, ax=axes[0,0])
+    axes[0, 0].set_title('Monthly Revenue Trend')
+    axes[0, 0].set_xlabel('Month')
+    axes[0, 0].set_ylabel('Revenue')
+
+    sns.barplot(data=region, x='region',y='amount',hue='region',palette='viridis',legend=False,ax=axes[0,1])
+    axes[0, 1].set_title('Revenue by Region')
+    axes[0, 1].set_xlabel('Region')
+    axes[0, 1].set_ylabel('Revenue')
+    for i, v in enumerate(region['amount']):
+        axes[0, 1].text(i, v, f'{v:,.0f}', ha='center', va='bottom', fontsize=9)
+    
+    sns.barplot(data=top5, x='amount',y='product_name',hue='product_name',palette='magma',legend=False,ax=axes[1,0])
+    axes[1, 0].set_title('Top 5 Products')
+    axes[1, 0].set_xlabel('Revenue')
+    axes[1, 0].set_ylabel('Product')
+
+    sns.histplot(data=target_df,x='amount',bins=25,kde=True,color="#d6273e", ax=axes[1,1])
+    axes[1, 1].set_title('Amount Distribution')
+    axes[1, 1].set_xlabel('Amount')
+    axes[1, 1].set_ylabel('Frequency')
+
+    plt.tight_layout()
+    return fig
diff --git a/homework/m6_plotly_capstone.py b/homework/m6_plotly_capstone.py
index 0e2c32a..d5fdf9a 100644
--- a/homework/m6_plotly_capstone.py
+++ b/homework/m6_plotly_capstone.py
@@ -25,8 +25,17 @@ def green_plotly_bar():
     回傳 plotly Figure 物件
     提示：px.bar()
     """
-    # TODO: 你的程式碼
-    pass
+    df = pd.read_csv('../datasets/ecommerce/orders_enriched.csv',
+    parse_dates=['order_date'],)
+
+    category_sum = df.groupby('category', as_index=False)['amount'].sum().sort_values('amount', ascending=False)
+
+    fig = px.bar(category_sum, x='category', y='amount', text='amount', color='category', title='Revenue by product category')
+
+    fig.update_traces(texttemplate='%{text:,.0f}', textposition='outside')
+    
+    fig.update_layout(height=400, showlegend=False)
+    return fig
 
 
 def green_plotly_line():
@@ -36,8 +45,15 @@ def green_plotly_line():
     回傳 plotly Figure 物件
     提示：先 groupby 月份算總營收，再 px.line()
     """
-    # TODO: 你的程式碼
-    pass
+    df = pd.read_csv('../datasets/ecommerce/orders_enriched.csv',
+    parse_dates=['order_date'],)
+    df['month'] = df['order_date'].dt.strftime('%Y-%m')
+    monthly_revenue = df.groupby('month', as_index=False)['amount'].sum().sort_values('month')
+
+    fig = px.line(monthly_revenue, x='month', y='amount', text='amount', title='Revenue by monthly')
+    fig.update_xaxes(type='category')
+    fig.update_traces(texttemplate='%{text:,.0f}', textposition='top center')
+    return fig
 
 
 def green_plotly_pie():
@@ -47,8 +63,12 @@ def green_plotly_pie():
     回傳 plotly Figure 物件
     提示：px.pie()
     """
-    # TODO: 你的程式碼
-    pass
+    df = pd.read_csv('../datasets/ecommerce/orders_enriched.csv',
+    parse_dates=['order_date'],)
+    vip_orders = df.groupby('vip_level', as_index=False)['order_id'].count()
+    fig = px.pie(vip_orders,names='vip_level',values='order_id',hole=0.2,title='Percentage of orders by VIP tier')
+    fig.update_traces(textinfo='percent+label')
+    return fig
 
 
 # ============================================================
@@ -62,8 +82,26 @@ def yellow_clean_and_merge(raw_path, customers_path, products_path):
     2. 合併 customers.csv 和 products.csv
     回傳：合併後的 DataFrame
     """
-    # TODO: 你的程式碼
-    pass
+    df = pd.read_csv(raw_path)
+    df.columns = df.columns.str.strip().str.lower()
+
+    df['amount']=df['amount'].astype(str).str.replace('$','',regex=False).str.replace(',','',regex=False).astype(float)
+
+    df['order_date'] = pd.to_datetime(df['order_date'],errors='coerce')
+
+    df = df.dropna(subset=['order_date'])
+    df['qty'] = df['qty'].fillna(df['qty'].median())
+    df = df.drop_duplicates()
+    orders = df
+    customers = pd.read_csv(customers_path)
+    products = pd.read_csv(products_path)
+    df = (
+        orders
+        .merge(customers, on='customer_id', how='left')
+        .merge(products,  on='product_id',  how='left')
+    )
+
+    return df
 
 
 def yellow_kpi_summary(df):
@@ -76,9 +114,13 @@ def yellow_kpi_summary(df):
         "avg_order_value": float,     # 平均客單價
     }
     """
-    # TODO: 你的程式碼
-    pass
-
+    kpi = {
+        "total_revenue": float(df['amount'].sum()),
+        "order_count": int(len(df)),
+        "active_customers": int(df['customer_id'].nunique()),
+        "avg_order_value": float(df['amount'].sum() / len(df)),
+    }
+    return kpi
 
 def yellow_plotly_scatter(df):
     """
@@ -90,8 +132,15 @@ def yellow_plotly_scatter(df):
     回傳 plotly Figure 物件
     提示：px.scatter(hover_data=['product_name'])
     """
-    # TODO: 你的程式碼
-    pass
+    fig = px.scatter(
+        df,
+        x="unit_price",
+        y="amount",
+        color="category",
+        hover_data=["product_name"],
+        title="Price vs Amount",
+    )
+    return fig
 
 
 # ============================================================
@@ -114,5 +163,36 @@ def red_dashboard():
     回傳 plotly Figure 物件
     提示：from plotly.subplots import make_subplots
     """
-    # TODO: 你的程式碼
-    pass
+    df = yellow_clean_and_merge(
+        "datasets/ecommerce/orders_raw.csv",
+        "datasets/ecommerce/customers.csv",
+        "datasets/ecommerce/products.csv",
+    )
+    df["order_date"] = pd.to_datetime(df["order_date"])
+    df["month"] = df["order_date"].dt.to_period("M").astype(str)
+
+    fig = make_subplots(
+        rows=2, cols=2,
+        subplot_titles=('月營收趨勢', 'Top 10 商品營收', '各地區營收', '類別營收佔比'),
+        specs=[[{}, {}], [{}, {"type": "domain"}]]
+    )
+
+    # 左上：月營收趨勢 (line)
+    monthly = df.groupby('month',as_index=False)['amount'].sum()
+    fig.add_trace(go.Scatter(x=monthly['month'], y=monthly['amount'],
+                              mode='lines+markers', name='Monthly'),
+                   row=1, col=1)
+
+    # 右上：Top 10 商品營收 (bar)
+    top10 = df.groupby('product_name',as_index=False)['amount'].sum().sort_values('amount',ascending=False).head(10)
+    fig.add_trace(go.Bar(x=top10['product_name'], y=top10['amount'],name='Top'),    row=1, col=2)
+
+    # 左下：各地區營收 (bar)
+    region = df.groupby('region',as_index=False)['amount'].sum()
+    fig.add_trace(go.Bar(x=region['region'], y=region['amount'],name='Region'), row=2, col=1)
+
+    # 右下：類別營收佔比 (pie/donut)
+    category = df.groupby('category',as_index=False)['amount'].sum()
+    fig.add_trace(go.Pie(labels=category['category'], values=category['amount'],hole=0.3, name='Category'), row=2, col=2)
+
+    return fig
\ No newline at end of file

From 47b1c10b3ce98330827a0a638075b1463674f694 Mon Sep 17 00:00:00 2001
From: kellyLiu <kellyliu060687@gmail.com>
Date: Sun, 3 May 2026 22:17:37 +0800
Subject: [PATCH 2/2] =?UTF-8?q?=E5=AE=8C=E6=88=90=E4=BD=9C=E6=A5=AD?=
 =?UTF-8?q?=E7=B9=B3=E4=BA=A4=20-=20=E5=8A=89=E5=87=B1=E8=8E=89=20-=20AIPE?=
 =?UTF-8?q?03?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 grading_report.md              | 111 +++++++++++++++++++++++++++++++++
 homework/m1_numpy.py           |   2 +-
 homework/m2_pandas_cleaning.py |   8 +--
 homework/m3_pandas_advanced.py |  27 ++++----
 homework/m5_visualization.py   |   6 +-
 homework/m6_plotly_capstone.py |  11 ++--
 6 files changed, 139 insertions(+), 26 deletions(-)
 create mode 100644 grading_report.md

diff --git a/grading_report.md b/grading_report.md
new file mode 100644
index 0000000..b41e9c1
--- /dev/null
+++ b/grading_report.md
@@ -0,0 +1,111 @@
+# 📊 作業批改結果
+
+**總分：600 / 600（100%）— 等級 A**
+
+---
+
+## M1 NumPy（100/100 — 100%）
+
+| 題目 | 分數 | 狀態 |
+|:-----|:----:|:----:|
+| `test_green_mean` | 10/10 | ✅ |
+| `test_green_double` | 10/10 | ✅ |
+| `test_green_filter` | 10/10 | ✅ |
+| `test_yellow_expensive_count` | 15/15 | ✅ |
+| `test_yellow_top3_stock_indices` | 15/15 | ✅ |
+| `test_yellow_restock_cost` | 15/15 | ✅ |
+| `test_red_double11_prices` | 20/20 | ✅ |
+| `test_red_no_forloop` | 5/5 | ✅ |
+
+> ⚠️ 解答模組未找到
+
+---
+
+## M2 Pandas 清理（100/100 — 100%）
+
+| 題目 | 分數 | 狀態 |
+|:-----|:----:|:----:|
+| `test_green_read_csv` | 10/10 | ✅ |
+| `test_green_shape` | 10/10 | ✅ |
+| `test_green_dtypes` | 10/10 | ✅ |
+| `test_yellow_clean_columns` | 15/15 | ✅ |
+| `test_yellow_clean_amount` | 15/15 | ✅ |
+| `test_yellow_drop_duplicates` | 15/15 | ✅ |
+| `test_red_clean_orders_returns_df` | 4/4 | ✅ |
+| `test_red_clean_orders_columns` | 4/4 | ✅ |
+| `test_red_clean_orders_amount_is_numeric` | 4/4 | ✅ |
+| `test_red_clean_orders_date_is_datetime` | 5/5 | ✅ |
+| `test_red_clean_orders_no_nulls` | 4/4 | ✅ |
+| `test_red_clean_orders_no_duplicates` | 4/4 | ✅ |
+
+> ⚠️ 解答模組未找到
+
+---
+
+## M3 Pandas 進階（100/100 — 100%）
+
+| 題目 | 分數 | 狀態 |
+|:-----|:----:|:----:|
+| `test_green_load_and_merge` | 10/10 | ✅ |
+| `test_green_row_count` | 10/10 | ✅ |
+| `test_green_column_list` | 10/10 | ✅ |
+| `test_yellow_top_category` | 15/15 | ✅ |
+| `test_yellow_gold_vip_stats` | 15/15 | ✅ |
+| `test_yellow_region_avg_amount` | 15/15 | ✅ |
+| `test_red_rfm_top5_shape` | 9/9 | ✅ |
+| `test_red_rfm_top5_columns` | 8/8 | ✅ |
+| `test_red_rfm_top5_sorted_by_m` | 8/8 | ✅ |
+
+> ⚠️ 解答模組未找到
+
+---
+
+## M4 時間序列（100/100 — 100%）
+
+| 題目 | 分數 | 狀態 |
+|:-----|:----:|:----:|
+| `test_green_avg_by_month` | 10/10 | ✅ |
+| `test_green_top3_dates` | 10/10 | ✅ |
+| `test_green_date_range` | 10/10 | ✅ |
+| `test_yellow_monthly_revenue` | 15/15 | ✅ |
+| `test_yellow_rolling_avg` | 15/15 | ✅ |
+| `test_yellow_category_median` | 15/15 | ✅ |
+| `test_red_monthly_report_columns` | 9/9 | ✅ |
+| `test_red_monthly_report_values` | 8/8 | ✅ |
+| `test_red_monthly_report_growth` | 8/8 | ✅ |
+
+> ⚠️ 解答模組未找到
+
+---
+
+## M5 視覺化（100/100 — 100%）
+
+| 題目 | 分數 | 狀態 |
+|:-----|:----:|:----:|
+| `test_green_bar_category` | 10/10 | ✅ |
+| `test_green_hist_amount` | 10/10 | ✅ |
+| `test_green_set_labels` | 10/10 | ✅ |
+| `test_yellow_line_region_trend` | 15/15 | ✅ |
+| `test_yellow_box_vip` | 15/15 | ✅ |
+| `test_yellow_scatter_price_amount` | 15/15 | ✅ |
+| `test_red_category_dashboard_is_figure` | 13/13 | ✅ |
+| `test_red_category_dashboard_has_4_subplots` | 12/12 | ✅ |
+
+> ⚠️ 解答模組未找到
+
+---
+
+## M6 Plotly Capstone（100/100 — 100%）
+
+| 題目 | 分數 | 狀態 |
+|:-----|:----:|:----:|
+| `test_green_plotly_bar` | 10/10 | ✅ |
+| `test_green_plotly_line` | 10/10 | ✅ |
+| `test_green_plotly_pie` | 10/10 | ✅ |
+| `test_yellow_clean_and_merge` | 15/15 | ✅ |
+| `test_yellow_kpi_summary` | 15/15 | ✅ |
+| `test_yellow_plotly_scatter` | 15/15 | ✅ |
+| `test_red_dashboard_is_figure` | 13/13 | ✅ |
+| `test_red_dashboard_has_traces` | 12/12 | ✅ |
+
+> ⚠️ 解答模組未找到
diff --git a/homework/m1_numpy.py b/homework/m1_numpy.py
index 07c7b96..e471522 100644
--- a/homework/m1_numpy.py
+++ b/homework/m1_numpy.py
@@ -19,7 +19,7 @@
 def green_mean():
     """建立 [10, 20, 30, 40, 50]，回傳所有元素的平均值 (float)"""
     arr = np.array([10,20,30,40,50])
-    return arr.mean()
+    return float(arr.mean())
 
 def green_double():
     """建立 [10, 20, 30, 40, 50]，回傳所有元素乘以 2 的 ndarray"""
diff --git a/homework/m2_pandas_cleaning.py b/homework/m2_pandas_cleaning.py
index ee9d16d..9d1c153 100644
--- a/homework/m2_pandas_cleaning.py
+++ b/homework/m2_pandas_cleaning.py
@@ -19,9 +19,7 @@ def green_read_csv():
     讀取 orders_raw.csv，回傳原始 DataFrame（不做任何清理）
     提示：pd.read_csv()
     """
-    DATA = '../datasets/ecommerce/orders_raw.csv'
-    df = pd.read_csv(DATA)
-    return df
+    return pd.read_csv('datasets/ecommerce/orders_raw.csv')
 
 
 def green_shape(df):
@@ -95,8 +93,8 @@ def red_clean_orders(path):
     """
     df = pd.read_csv(path)
     df.columns = df.columns.str.strip().str.lower()
-    df['amount'] = df['amount'].astype(str).replace('$','',regex=False).replace(',','',regex=False).astype(float)
+    df['amount'] = df['amount'].astype(str).str.replace('$','',regex=False).str.replace(',','',regex=False).astype(float)
     df['order_date'] = pd.to_datetime(df['order_date'], errors='coerce')
     df = df.dropna(subset=['order_date','amount']) # 只要這兩個欄位中任一個有缺失值，該列就會被剔除。
     df = df.drop_duplicates()
-    return df.shape[0]
\ No newline at end of file
+    return df
\ No newline at end of file
diff --git a/homework/m3_pandas_advanced.py b/homework/m3_pandas_advanced.py
index e0f77f1..46836c5 100644
--- a/homework/m3_pandas_advanced.py
+++ b/homework/m3_pandas_advanced.py
@@ -23,12 +23,15 @@ def green_load_and_merge():
     - 再 LEFT JOIN products.csv ON product_id
     提示：pd.merge(how='left')
     """
-    DATA="../datasets/ecommerce/"
-    orders = pd.read_csv(f'{DATA}/orders_clean.csv', parse_dates=['order_date'])
-    customers = pd.read_csv(f'{DATA}/customers.csv')
-    products  = pd.read_csv(f'{DATA}/products.csv')
-
-    return orders
+    orders = pd.read_csv('datasets/ecommerce/orders_clean.csv')
+    customers = pd.read_csv('datasets/ecommerce/customers.csv')
+    products  = pd.read_csv('datasets/ecommerce/products.csv')
+    df=(
+        orders
+        .merge(customers,on='customer_id',how='left')
+        .merge(products,on='product_id',how='left')
+    )
+    return df
 
 
 def green_row_count(df):
@@ -62,7 +65,7 @@ def yellow_gold_vip_stats(df):
     """
     gold_mask = df[df['vip_level'] == 'Gold']
     gold = gold_mask['amount'].agg(['count', 'sum'])
-    return f'訂單數: {int(gold['count'])}', f'總金額:{float(gold['sum'])}'
+    return (int(gold['count']), float(gold['sum']))
 
 def yellow_region_avg_amount(df):
     """
@@ -70,8 +73,7 @@ def yellow_region_avg_amount(df):
     回傳 Series（index=region, values=平均金額）
     提示：groupby('region')['amount'].mean()
     """
-    region_avg_amount = df.groupy('region')['amount'].mean().round(1)
-    return region_avg_amount
+    return df.groupby('region')['amount'].mean()
 
 
 # ============================================================
@@ -95,10 +97,11 @@ def red_rfm_top5(df):
     提示：groupby('customer_id').agg(...)
     """
     # TODO: 你的程式碼
-    rfm = df.groupby('customer_id','customer_name').agg(
+    rfm = df.groupby('customer_id').agg(
         R=('order_date', 'max'),
         F=('order_id', 'count'),
-        M=('amount', 'sum')
+        M=('amount', 'sum'),
+        customer_name=("customer_name", "first")
     ).reset_index()
     result = rfm.sort_values('M',ascending=False).head()
-    return result
+    return result[["customer_id", "customer_name", "R", "F", "M"]]
diff --git a/homework/m5_visualization.py b/homework/m5_visualization.py
index e6c8e9a..5b7bce8 100644
--- a/homework/m5_visualization.py
+++ b/homework/m5_visualization.py
@@ -57,7 +57,7 @@ def green_hist_amount():
     """
     df = _load_data()
     fig = plt.figure(figsize=(9,4))
-    sns.histplot(data=df, x='amount', bins=20, kde=True, color='steeblue')
+    sns.histplot(data=df, x='amount', bins=30, kde=True, color='steelblue')
     plt.title('Order Amount Distribution', fontweight='bold')
     plt.xlabel('Amount')
     plt.ylabel('Frequency')
@@ -98,6 +98,7 @@ def yellow_line_region_trend():
     提示：分別 groupby 再 plot，或用 sns.lineplot(hue='region')
     """
     df = _load_data()
+    df["month"] = df["order_date"].dt.to_period("M").astype(str)
     ns_df = df[df['region'].isin(['North','South'])]
     month_sn = (
         ns_df.groupby(['month','region'])['amount'].sum().reset_index()
@@ -136,7 +137,7 @@ def yellow_scatter_price_amount():
     """
     df = _load_data()
     fig = plt.figure(figsize=(8, 5))
-    sns.scatterplot(data=df, x='unit_price', y='amount', alpha=0.6, color='gold')
+    sns.scatterplot(data=df, x='unit_price', y='amount', alpha=0.5)
     plt.title('Relationship between Unit Price and Order Amount', fontweight='bold')
     plt.xlabel('Unit Price')
     plt.ylabel('Amount')
@@ -160,6 +161,7 @@ def red_category_dashboard(category="Electronics"):
     提示：fig, axes = plt.subplots(2, 2, figsize=(14, 10))
     """
     df = _load_data()
+    df["month"] = df["order_date"].dt.to_period("M").astype(str)
     target_df = df[df['category'] == category].copy()
     monthly = (target_df.groupby('month')['amount'].sum().reset_index())
     region = (target_df.groupby('region')['amount'].sum().sort_values(ascending=False).reset_index())
diff --git a/homework/m6_plotly_capstone.py b/homework/m6_plotly_capstone.py
index d5fdf9a..f49ab42 100644
--- a/homework/m6_plotly_capstone.py
+++ b/homework/m6_plotly_capstone.py
@@ -25,8 +25,7 @@ def green_plotly_bar():
     回傳 plotly Figure 物件
     提示：px.bar()
     """
-    df = pd.read_csv('../datasets/ecommerce/orders_enriched.csv',
-    parse_dates=['order_date'],)
+    df = pd.read_csv('datasets/ecommerce/orders_enriched.csv')
 
     category_sum = df.groupby('category', as_index=False)['amount'].sum().sort_values('amount', ascending=False)
 
@@ -45,8 +44,8 @@ def green_plotly_line():
     回傳 plotly Figure 物件
     提示：先 groupby 月份算總營收，再 px.line()
     """
-    df = pd.read_csv('../datasets/ecommerce/orders_enriched.csv',
-    parse_dates=['order_date'],)
+    df = pd.read_csv('datasets/ecommerce/orders_enriched.csv',
+    parse_dates=['order_date'])
     df['month'] = df['order_date'].dt.strftime('%Y-%m')
     monthly_revenue = df.groupby('month', as_index=False)['amount'].sum().sort_values('month')
 
@@ -63,8 +62,8 @@ def green_plotly_pie():
     回傳 plotly Figure 物件
     提示：px.pie()
     """
-    df = pd.read_csv('../datasets/ecommerce/orders_enriched.csv',
-    parse_dates=['order_date'],)
+    df = pd.read_csv('datasets/ecommerce/orders_enriched.csv',
+    parse_dates=['order_date'])
     vip_orders = df.groupby('vip_level', as_index=False)['order_id'].count()
     fig = px.pie(vip_orders,names='vip_level',values='order_id',hole=0.2,title='Percentage of orders by VIP tier')
     fig.update_traces(textinfo='percent+label')