From a92cdac1f470f6ec6349930fc0c08dc985a1e5f6 Mon Sep 17 00:00:00 2001
From: Django <django.cheng@gmail.com>
Date: Sun, 10 May 2026 13:21:47 +0800
Subject: [PATCH] =?UTF-8?q?=E5=AE=8C=E6=88=90=E4=BD=9C=E6=A5=AD-=E9=84=AD?=
 =?UTF-8?q?=E5=85=B8-AIPE03?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 homework/m1_numpy.py           |  34 ++++++--
 homework/m2_pandas_cleaning.py |  50 +++++++++--
 homework/m3_pandas_advanced.py |  42 +++++++--
 homework/m4_timeseries.py      |  54 ++++++++++--
 homework/m5_visualization.py   | 140 ++++++++++++++++++++++++++++--
 homework/m6_plotly_capstone.py | 151 +++++++++++++++++++++++++++++++--
 6 files changed, 428 insertions(+), 43 deletions(-)

diff --git a/homework/m1_numpy.py b/homework/m1_numpy.py
index 5ff41ab..ff7ee20 100644
--- a/homework/m1_numpy.py
+++ b/homework/m1_numpy.py
@@ -19,19 +19,22 @@
 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
+    np_mean = np.array([10, 20, 30, 40, 50])
+    return float(np.mean(np_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
+    np_double = np.array([10, 20, 30, 40, 50]) * 2
+    return np_double
 
 
 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
+    np_filter = np.array([10, 20, 30, 40, 50])
+    return np_filter[np_filter > 25]
 
 
 # ============================================================
@@ -42,7 +45,10 @@ 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_expensive = prices > 1000
+    num_expensive = mask_expensive.sum()
+    return num_expensive
+
 
 
 def yellow_top3_stock_indices(stocks):
@@ -51,7 +57,9 @@ def yellow_top3_stock_indices(stocks):
     提示：np.argsort
     """
     # TODO: 你的程式碼
-    pass
+    sorted_stock = np.argsort(stocks)
+    top3_stock = sorted_stock[-3:][::-1]
+    return top3_stock
 
 
 def yellow_restock_cost(prices, stocks):
@@ -60,7 +68,10 @@ def yellow_restock_cost(prices, stocks):
     提示：布林遮罩 + .sum()
     """
     # TODO: 你的程式碼
-    pass
+    mask_cheap = prices < 500
+    cheap_prices = prices[mask_cheap]
+    total_cost = round((cheap_prices * 50).sum(), 0)
+    return total_cost
 
 
 # ============================================================
@@ -77,4 +88,13 @@ def red_double11_prices(prices, stocks):
     提示：np.where 可以巢狀使用
     """
     # TODO: 你的程式碼
-    pass
+    final_price = np.where(
+        stocks >= 100,
+        prices * 0.7,
+        np.where(
+            stocks >= 20,
+            prices * 0.9,
+            prices
+        )
+    )
+    return final_price
diff --git a/homework/m2_pandas_cleaning.py b/homework/m2_pandas_cleaning.py
index fa36bff..40d1c1c 100644
--- a/homework/m2_pandas_cleaning.py
+++ b/homework/m2_pandas_cleaning.py
@@ -20,7 +20,8 @@ def green_read_csv():
     提示：pd.read_csv()
     """
     # TODO: 你的程式碼
-    pass
+    df_raw = pd.read_csv()
+    return df_raw
 
 
 def green_shape(df):
@@ -29,7 +30,9 @@ def green_shape(df):
     提示：df.shape
     """
     # TODO: 你的程式碼
-    pass
+    df_shape = df.shape
+    return df_shape
+
 
 
 def green_dtypes(df):
@@ -38,7 +41,8 @@ def green_dtypes(df):
     提示：df.dtypes
     """
     # TODO: 你的程式碼
-    pass
+    df_dtypes = df.dtypes
+    return df_dtypes
 
 
 # ============================================================
@@ -52,7 +56,9 @@ def yellow_clean_columns(df):
     提示：df.columns.str.strip().str.lower()
     """
     # TODO: 你的程式碼
-    pass
+    df_clean = df.copy()
+    df_clean.columns = df_clean.columns.str.strip().str.lower()
+    return df_clean
 
 
 def yellow_clean_amount(df):
@@ -63,7 +69,16 @@ def yellow_clean_amount(df):
     提示：.str.replace() + .astype(float)
     """
     # TODO: 你的程式碼
-    pass
+    df_clean = df.copy()
+    df_clean['amount'] = (
+    df_clean['amount']
+    .astype(str)
+    .str.replace('$', '', regex = False)
+    .str.replace(',', '', regex = False)
+    .astype(float)
+    )
+    return df_clean
+
 
 
 def yellow_drop_duplicates(df):
@@ -72,7 +87,8 @@ def yellow_drop_duplicates(df):
     提示：df.drop_duplicates()
     """
     # TODO: 你的程式碼
-    pass
+    df_duplicates = df.drop_duplicates()
+    return df_duplicates
 
 
 # ============================================================
@@ -93,4 +109,24 @@ def red_clean_orders(path):
     提示：pd.to_datetime(errors='coerce')
     """
     # TODO: 你的程式碼
-    pass
+    df = pd.read_csv(path)
+    df_before = len(df)
+
+    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 = ['amount', 'order_date'])
+    df = df.drop_duplicates()
+    df_after = len(df)
+    
+    print(f"清理之前{df_before},清理之後{df_after}")
+    print('-----------------------------')
+    return df
diff --git a/homework/m3_pandas_advanced.py b/homework/m3_pandas_advanced.py
index 68410e8..cce46ae 100644
--- a/homework/m3_pandas_advanced.py
+++ b/homework/m3_pandas_advanced.py
@@ -24,19 +24,24 @@ def green_load_and_merge():
     提示：pd.merge(how='left')
     """
     # TODO: 你的程式碼
-    pass
+    df = (
+        orders
+        .merge(customers, on='customer_id', how='left')
+        .merge(products, on='product_id', how='left')
+    )
+    return df
 
 
 def green_row_count(df):
     """回傳 DataFrame 的列數 (int)"""
     # TODO: 你的程式碼
-    pass
+    return len(df)
 
 
 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)
 
 
 # ============================================================
@@ -50,8 +55,8 @@ def yellow_top_category(df):
     提示：groupby('category')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
-
+    df_category = df.groupby('category')['amount'].sum()
+    return df_category.idxmax()
 
 def yellow_gold_vip_stats(df):
     """
@@ -60,7 +65,10 @@ def yellow_gold_vip_stats(df):
     提示：df[df['vip_level'] == 'Gold']
     """
     # TODO: 你的程式碼
-    pass
+    gold = df[df['vip_level'] == 'Gold']
+    gold_count = len(gold)
+    gold_total = gold['amount'].sum()
+    return (gold_count, gold_total)
 
 
 def yellow_region_avg_amount(df):
@@ -70,7 +78,13 @@ def yellow_region_avg_amount(df):
     提示：groupby('region')['amount'].mean()
     """
     # TODO: 你的程式碼
-    pass
+    region_mean = (
+        df.groupby('region')['amount']
+        .mean()
+        .round(2)
+        .sort_values(ascending=False)
+    )
+    return region_mean
 
 
 # ============================================================
@@ -94,4 +108,16 @@ 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()
+        .sort_values('m', ascending=False)
+        .head(5)
+    )
+
+    return rfm
diff --git a/homework/m4_timeseries.py b/homework/m4_timeseries.py
index 047af6a..a64bd72 100644
--- a/homework/m4_timeseries.py
+++ b/homework/m4_timeseries.py
@@ -27,7 +27,12 @@ def green_avg_by_month():
     提示：df['order_date'].dt.month
     """
     # TODO: 你的程式碼
-    pass
+    avg_month = (
+        df.groupby(df['order_date'].dt.month)['amount']
+        .mean()
+        .round(2)
+    )
+    return avg_month
 
 
 def green_top3_dates():
@@ -37,7 +42,9 @@ def green_top3_dates():
     提示：value_counts().head(3)
     """
     # TODO: 你的程式碼
-    pass
+    top3_dates = df['order_date'].dt.date.value_counts().head(3)
+    return top3_dates
+
 
 
 def green_date_range():
@@ -46,7 +53,9 @@ def green_date_range():
     格式為 pandas Timestamp
     """
     # TODO: 你的程式碼
-    pass
+    earliest = df['order_date'].min()
+    latest = df['order_date'].max()
+    return (earliest, latest)
 
 
 # ============================================================
@@ -60,7 +69,10 @@ def yellow_monthly_revenue():
     提示：set_index('order_date').resample('ME')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
+    monthly_revenue = (
+        df.set_index('order_date').resample('ME')['amount'].sum()
+    )
+    return monthly_revenue
 
 
 def yellow_rolling_avg(monthly_revenue):
@@ -71,7 +83,8 @@ def yellow_rolling_avg(monthly_revenue):
     提示：.rolling(window=3).mean()
     """
     # TODO: 你的程式碼
-    pass
+    rolling_avg = monthly_revenue.rolling(window=3).mean()
+    return rolling_avg
 
 
 def yellow_category_median(df):
@@ -81,7 +94,13 @@ def yellow_category_median(df):
     提示：groupby + median + sort_values
     """
     # TODO: 你的程式碼
-    pass
+    category_median = (
+        df.groupby('category')['amount']
+        .mean()
+        .round(1)
+        .sort_values(ascending=False)
+    )
+    return category_median
 
 
 # ============================================================
@@ -101,4 +120,25 @@ def red_monthly_report():
     提示：resample + agg + pct_change
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    df = df.set_index('order_date')
+
+    monthly_report = (
+        df.resample('ME')
+        .agg(
+            總訂單數 = ('order_id', 'count'),
+            總營收 = ('amount', 'sum'),
+            活躍客戶數 = ('customer_id', 'nunique'),
+        )
+        .sort_index()
+    )
+
+    monthly_report['客單價'] = (
+        monthly_report['總營收']/monthly_report['總訂單數']
+    ).round(1)
+
+    monthly_report['月營收成長率'] = (
+        monthly_report['總營收'].pct_change() * 100
+    ).round(2)
+
+    return monthly_report
diff --git a/homework/m5_visualization.py b/homework/m5_visualization.py
index 7e7335d..41475e7 100644
--- a/homework/m5_visualization.py
+++ b/homework/m5_visualization.py
@@ -29,7 +29,21 @@ def green_bar_category():
     提示：sns.countplot 或 value_counts().plot.bar()
     """
     # TODO: 你的程式碼
-    pass
+    cate_count = df['category'].value_counts().reset_index()
+    cate_count.columns = ['category', 'order_count']
+
+    fig, ax = plt.subplots(figsize=(8,4))
+    sns.barplot(
+        data = cate_count,
+        x = 'category',
+        y = 'order_count',
+        hue = 'category',
+        palette = 'viridis',
+        legend = False,
+        ax = ax,
+    )
+    plt.tight_layout()
+    return plt
 
 
 def green_hist_amount():
@@ -39,7 +53,17 @@ def green_hist_amount():
     提示：sns.histplot(bins=20) 或 plt.hist()
     """
     # TODO: 你的程式碼
-    pass
+    fig, ax = plt.subplots(figsize = (8,4))
+    sns.histplot(
+        data = df,
+        x = 'amount',
+        bins = 20,
+        ax = ax,
+    )
+    ax.set_xlabel('Amount(NT$)')
+    ax.set_ylabel('Frequency')
+    plt.tight_layout()
+    return fig
 
 
 def green_set_labels():
@@ -51,7 +75,26 @@ def green_set_labels():
     回傳 matplotlib Figure 物件
     """
     # TODO: 你的程式碼
-    pass
+    cate_count = df['category'].value_counts().reset_index()
+    cate_count.columns = ['category', 'order_count']
+
+    fig, ax = plt.subplots(figsize=(8,4))
+    sns.barplot(
+        data = cate_count,
+        x = 'category',
+        y = 'order_count',
+        hue = 'category',
+        palette = 'viridis',
+        legend = False,
+        ax = ax,
+    )
+    ax.set_title('Order Count by Category', fontweight='bold')
+    ax.set_xlabel('Category')
+    ax.set_ylabel('Order Count')
+
+    plt.tight_layout()
+    return fig
+
 
 
 # ============================================================
@@ -68,7 +111,32 @@ def yellow_line_region_trend():
     提示：分別 groupby 再 plot，或用 sns.lineplot(hue='region')
     """
     # TODO: 你的程式碼
-    pass
+    ns_df = df[df['region'].isin(['North', 'South'])].copy()
+    ns_df['month'] = ns_df['order_date'].dt.to_period('M')
+
+    monthly_ns = (
+        ns_df.groupby(['month', 'region'])['amount']
+        .sum()
+        .reset_index()
+    )
+    monthly_ns['month'] = monthly_ns['month'].astype(str)
+
+    fig, ax = plt.subplots(figsize = (10, 4))
+    sns.lineplot(
+        data = monthly_ns,
+        hue = 'region',
+        x = 'month',
+        y = 'amount',
+        marker = 'o',
+        linewidth = 2,
+    )
+    ax.set_title('Monthly Revenue: North vs South', fontweight='bold')
+    ax.set_xlabel('Month')
+    ax.set_ylabel('Revenue(NT$)')
+    plt.xticks(rotation = 45)
+    ax.legend(title = 'Region')
+    plt.tight_layout
+    return fig
 
 
 def yellow_box_vip():
@@ -78,7 +146,21 @@ def yellow_box_vip():
     提示：sns.boxplot(x='vip_level', y='amount', data=df)
     """
     # TODO: 你的程式碼
-    pass
+    fig, ax = plt.subplots(figsize=(9, 5))
+    sns.boxplot(
+        data = df,
+        x = 'vip_level',
+        y = 'amount',
+        hue = 'vip_level',
+        palette = 'Set3',
+        legend = False,
+        ax = ax
+    )
+    ax.set_title('Order Amount Distribution by VIP Level', fontweight='bold')
+    ax.set_xlabel('VIP Level')
+    ax.set_ylabel('Amount(NT$)')
+    plt.tight_layout()
+    return fig
 
 
 def yellow_scatter_price_amount():
@@ -88,7 +170,20 @@ def yellow_scatter_price_amount():
     提示：plt.scatter() 或 sns.scatterplot()
     """
     # TODO: 你的程式碼
-    pass
+    fig, ax = plt.subplots(figsize=(8, 4))
+    sns.scatterplot(
+        data = df,
+        x = 'unit_price',
+        y = 'amount',
+        alpha = 0.5,
+        ax = ax
+    )
+    ax.set_title('Unit Price vs Amount')
+    ax.set_xlabel('Unit Price(NT$)')
+    ax.set_ylabel('Amount(NT$)')
+    plt.tight_layout()
+    return fig
+
 
 
 # ============================================================
@@ -107,4 +202,35 @@ def red_category_dashboard(category="Electronics"):
     提示：fig, axes = plt.subplots(2, 2, figsize=(14, 10))
     """
     # TODO: 你的程式碼
-    pass
+    cat_df = df[df['category'] == category].copy()
+    cat_df['month'] = cat_df['order_date'].dt.to_period('M').astype(str)
+    
+    fig, axes = plt.subplots(2, 2, figsize=(14, 10))
+    fig.suptitle(f'{category} Dashboard', fontsize=16, fontweight='bold')
+    
+    monthly = cat_df.groupby('month')['amount'].sum().reset_index()
+    sns.lineplot(data=monthly, x='month', y='amount', marker='o', ax=axes[0, 0])
+    axes[0, 0].set_title('Monthly Revenue Trend')
+    axes[0, 0].set_xlabel('Month')
+    axes[0, 0].set_ylabel('Revenue')
+    axes[0, 0].tick_params(axis='x', rotation=45)
+    
+    region = cat_df.groupby('region')['amount'].sum().reset_index()
+    sns.barplot(data=region, x='region', y='amount', palette='viridis', ax=axes[0, 1])
+    axes[0, 1].set_title('Revenue by Region')
+    axes[0, 1].set_xlabel('Region')
+    axes[0, 1].set_ylabel('Revenue')
+    
+    top5 = cat_df.groupby('product_name')['amount'].sum().nlargest(5).reset_index()
+    sns.barplot(data=top5, x='amount', y='product_name', palette='viridis', 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=cat_df, x='amount', bins=20, 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..b727f27 100644
--- a/homework/m6_plotly_capstone.py
+++ b/homework/m6_plotly_capstone.py
@@ -26,7 +26,23 @@ def green_plotly_bar():
     提示：px.bar()
     """
     # TODO: 你的程式碼
-    pass
+    category_revenue = (
+        df_enriched.groupby('category')['amount']
+        .sum()
+        .reset_index()
+        .sort_values('amount', ascending = False)
+    )
+
+    fig = px.bar(
+        data_frame = category_revenue,
+        x = 'category',
+        y = 'amount',
+        color = 'category',
+        title = 'Total Revenue by Category',
+        labels = {'amount' : 'Revenue(NT$)', 'category' : 'Categoty'}
+    )
+    return fig
+
 
 
 def green_plotly_line():
@@ -37,7 +53,23 @@ def green_plotly_line():
     提示：先 groupby 月份算總營收，再 px.line()
     """
     # TODO: 你的程式碼
-    pass
+    monthly = (
+        df_enriched.groupby(df_enriched['order_date'].dt.to_period('M'))['amount']
+        .sum()
+        .reset_index()
+    )
+    monthly['order_date'] = monthly['order_date'].astype(str)
+
+    fig = px.line(
+        data_frame = monthly,
+        x = 'order_date',
+        y = 'amount',
+        markers = True,
+        title = 'Monthly Revenue Trend',
+        labels = {'order_date' : 'Month', 'amount' : 'Revenue(NT$)'},
+    )
+    return fig
+
 
 
 def green_plotly_pie():
@@ -48,7 +80,20 @@ def green_plotly_pie():
     提示：px.pie()
     """
     # TODO: 你的程式碼
-    pass
+    vip_count = (
+        df_enriched['vip_level'].value_counts()
+        .reset_index()
+    )
+    vip_count.columns = ['vip_level', 'order_count']
+
+    fig = px.pie (
+        data_frame = vip_count,
+        names = 'vip_level',
+        values = 'order_count',
+        title = 'VIP Level Share',
+        hole = 0.4,
+    )
+    return fig
 
 
 # ============================================================
@@ -63,7 +108,28 @@ def yellow_clean_and_merge(raw_path, customers_path, products_path):
     回傳：合併後的 DataFrame
     """
     # TODO: 你的程式碼
-    pass
+    df = pd.read_csv(raw_path)
+    customers = pd.read_csv(customers_path)
+    products = pd.read_csv(products_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=['amount', 'order_date'])
+    df = df.drop_duplicates()
+
+    df = (
+        df
+        .merge(customers, on = 'customer_id', how = 'left')
+        .merge(products, on = 'product_id', how = 'left')
+    )
+    return df
 
 
 def yellow_kpi_summary(df):
@@ -77,7 +143,17 @@ def yellow_kpi_summary(df):
     }
     """
     # TODO: 你的程式碼
-    pass
+    total_revenue = round(df['amount'].sum(), 2)
+    order_count = len(df)
+    active_customers = df['customer_id'].nunique()
+    avg_order_value = round(total_revenue / order_count, 2)
+
+    return {
+        'total_revenue': total_revenue,
+        'order_count': order_count,
+        'active_customers': active_customers,
+        'avg_order_value': avg_order_value
+    }
 
 
 def yellow_plotly_scatter(df):
@@ -91,7 +167,15 @@ def yellow_plotly_scatter(df):
     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='product_unit_price v.s. order_unit_price' 
+    )
+    return fig
 
 
 # ============================================================
@@ -115,4 +199,57 @@ def red_dashboard():
     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'
+    )
+
+    monthly = (
+        df.groupby(df['order_date'].dt.to_period('M'))['amount']
+        .sum().reset_index()
+    )
+    monthly['order_date'] = monthly['order_date'].astype(str)
+
+    top10 = (
+        df.groupby('product_name')['amount']
+        .sum().nlargest(10).reset_index()
+        .sort_values('amount')
+    )
+
+    region = (
+        df.groupby('region')['amount']
+        .sum().reset_index()
+        .sort_values('amount', ascending = False)
+    )
+
+    category = (
+        df.groupby('category')['amount']
+        .sum().reset_index()
+    )
+
+    fig = make_subplots(
+        rows = 2, cols = 2,
+        subplot_titles=('Monthly Revenue Trend',
+                    'Top 10 Products',
+                    'Revenue by Region',
+                    'Category Share'),
+        specs=[[{'type': 'xy'},     {'type': 'xy'}],
+           [{'type': 'xy'},     {'type': 'domain'}]],
+    )
+
+    fig.add_trace(go.Scatter(x=monthly['order_date'], y=monthly['amount'],
+                         mode='lines+markers', name='Monthly'), row=1, col=1)
+    fig.add_trace(go.Bar(x=top10['product_name'], y=top10['amount'],
+                     name='Top Products'), row=1, col=2)
+    fig.add_trace(go.Bar(x=region['region'], y=region['amount'],
+                     name='Region'), row=2, col=1)
+    fig.add_trace(go.Pie(labels=category['category'], values=category['amount'],
+                     name='Category', hole=0.4), row=2, col=2)
+
+    fig.update_layout(
+    title_text='E-Commerce Sales Dashboard — 2025【解答版】',
+    height=750, showlegend=False,
+    )
+
+    return fig