完成作業繳交 -張詩彤 -AIPE03

homework/m1_numpy.py

@@ -19,18 +19,24 @@
 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
+    arr = np.array([10, 20, 30, 40, 50])
+    return float(np.mean(arr))
     pass
 
 
 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
+    arr = np.array([10, 20, 30, 40, 50])
+    return arr * 2
     pass
 
 
 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
+    arr = np.array([10, 20, 30, 40, 50])
+    return arr[arr > 25]
     pass
 
 
@@ -42,6 +48,8 @@ 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
+    count = np.sum(prices > 1000)
+    return int(count)
     pass
 
 
@@ -51,6 +59,8 @@ def yellow_top3_stock_indices(stocks):
     提示：np.argsort
     """
     # TODO: 你的程式碼
+    index = np.argsort(stocks)[::-1]
+    return index[:3]
     pass
 
 
@@ -60,6 +70,10 @@ def yellow_restock_cost(prices, stocks):
     提示：布林遮罩 + .sum()
     """
     # TODO: 你的程式碼
+    mask = prices < 500
+    number = np.sum(mask)
+    totol_cost = np.sum(prices[mask] * 50)
+    return totol_cost
     pass
 
 
@@ -77,4 +91,14 @@ def red_double11_prices(prices, stocks):
     提示：np.where 可以巢狀使用
     """
     # TODO: 你的程式碼
+    finall_price = np.where(
+        stocks >= 100,
+        prices * 0.7,
+        np.where(
+            stocks >= 20,
+            prices * 0.9,
+            prices
+        )
+    )
+    return finall_price
     pass

homework/m2_pandas_cleaning.py

@@ -20,6 +20,8 @@ def green_read_csv():
     提示：pd.read_csv()
     """
     # TODO: 你的程式碼
+    df = pd.read_csv("../datasets/ecommerce/orders_raw.csv")
+    return df
     pass
 
 
@@ -29,6 +31,7 @@ def green_shape(df):
     提示：df.shape
     """
     # TODO: 你的程式碼
+    return df.shape
     pass
 
 
@@ -38,6 +41,7 @@ def green_dtypes(df):
     提示：df.dtypes
     """
     # TODO: 你的程式碼
+    return df.dtypes
     pass
 
 
@@ -52,6 +56,9 @@ def yellow_clean_columns(df):
     提示：df.columns.str.strip().str.lower()
     """
     # TODO: 你的程式碼
+    new_df = df.copy()
+    new_df.columns = new_df.columns.str.strip().str.lower()
+    return new_df
     pass
 
 
@@ -63,6 +70,9 @@ def yellow_clean_amount(df):
     提示：.str.replace() + .astype(float)
     """
     # TODO: 你的程式碼
+    new_df = df.copy()
+    new_df['amount'] = new_df['amount'].str.replace('$', '', regex=False).str.replace(',', '',regex=False).astype(float)
+    return new_df
     pass
 
 
@@ -72,6 +82,7 @@ def yellow_drop_duplicates(df):
     提示：df.drop_duplicates()
     """
     # TODO: 你的程式碼
+    return df.drop_duplicates()
     pass
 
 
@@ -93,4 +104,11 @@ def red_clean_orders(path):
     提示：pd.to_datetime(errors='coerce')
     """
     # TODO: 你的程式碼
+    df = pd.read_csv(path)
+    df.columns = df.columns.str.strip().str.lower()
+    df['amount'] = df['amount'].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'], how='any')
+    df = df.drop_duplicates()
+    return df
     pass

homework/m3_pandas_advanced.py

@@ -24,18 +24,26 @@ def green_load_and_merge():
     提示：pd.merge(how='left')
     """
     # TODO: 你的程式碼
+    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')
+    merged_df = pd.merge(orders, customers, on='customer_id', how='left')
+    final_df = pd.merge(merged_df, products, on='product_id', how='left')
+    return final_df
     pass
 
 
 def green_row_count(df):
     """回傳 DataFrame 的列數 (int)"""
     # TODO: 你的程式碼
+    return len(df)
     pass
 
 
 def green_column_list(df):
     """回傳 DataFrame 的所有欄位名稱 (list)"""
     # TODO: 你的程式碼
+    return df.columns.tolist()
     pass
 
 
@@ -50,6 +58,9 @@ def yellow_top_category(df):
     提示：groupby('category')['amount'].sum()
     """
     # TODO: 你的程式碼
+    category_revenue = df.groupby('category')['amount'].sum()
+    top_cat = category_revenue.idxmax()
+    return str(top_cat)
     pass
 
 
@@ -60,6 +71,10 @@ def yellow_gold_vip_stats(df):
     提示：df[df['vip_level'] == 'Gold']
     """
     # TODO: 你的程式碼
+    gold_df = df[df['vip_level'] == 'Gold']
+    order_count = len(gold_df)
+    total_amount = gold_df['amount'].sum()
+    return int(order_count), float(total_amount)
     pass
 
 
@@ -70,6 +85,8 @@ def yellow_region_avg_amount(df):
     提示：groupby('region')['amount'].mean()
     """
     # TODO: 你的程式碼
+    region_avg = df.groupby('region')['amount'].mean()
+    return region_avg
     pass
 
 
@@ -94,4 +111,11 @@ 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(
+        R=('order_date', 'max'),
+        F=('order_date', 'count'),
+        M=('amount', 'sum')
+    ).reset_index()
+    rfm_sorted = rfm.sort_values(by='M', ascending=False)
+    return rfm_sorted.head(5)
     pass

homework/m4_timeseries.py

@@ -11,7 +11,7 @@
 
 def _load_data():
     """輔助函式：讀取並解析日期"""
-    df = pd.read_csv("datasets/ecommerce/orders_enriched.csv",
+    df = pd.read_csv("../datasets/ecommerce/orders_enriched.csv",
                      parse_dates=["order_date"])
     return df
 
@@ -27,6 +27,9 @@ def green_avg_by_month():
     提示：df['order_date'].dt.month
     """
     # TODO: 你的程式碼
+    df = _load_data()
+    monthly_avg = df.groupby(df['order_date'].dt.month)['amount'].mean()
+    return monthly_avg
     pass
 
 
@@ -37,6 +40,9 @@ def green_top3_dates():
     提示：value_counts().head(3)
     """
     # TODO: 你的程式碼
+    df = _load_data()
+    date_counts = df['order_date'].value_counts()
+    return date_counts.head(3)
     pass
 
 
@@ -46,6 +52,10 @@ def green_date_range():
     格式為 pandas Timestamp
     """
     # TODO: 你的程式碼
+    df = _load_data()
+    min_date = df['order_date'].min()
+    max_date = df['order_date'].max()
+    return (min_date, max_date)
     pass
 
 
@@ -60,6 +70,9 @@ def yellow_monthly_revenue():
     提示：set_index('order_date').resample('ME')['amount'].sum()
     """
     # TODO: 你的程式碼
+    df = _load_data()
+    monthly_rev = df.set_index('order_date').resample('ME')['amount'].sum()
+    return monthly_rev
     pass
 
 
@@ -71,6 +84,8 @@ def yellow_rolling_avg(monthly_revenue):
     提示：.rolling(window=3).mean()
     """
     # TODO: 你的程式碼
+    rolling_avg = monthly_revenue.rolling(window=3).mean()
+    return rolling_avg
     pass
 
 
@@ -81,6 +96,8 @@ def yellow_category_median(df):
     提示：groupby + median + sort_values
     """
     # TODO: 你的程式碼
+    category_median = df.groupby('category')['amount'].median().sort_values(ascending=False)
+    return category_median
     pass
 
 
@@ -101,4 +118,14 @@ def red_monthly_report():
     提示：resample + agg + pct_change
     """
     # TODO: 你的程式碼
+    df = _load_data()
+    df = df.set_index('order_date')
+    report = df.resample('ME').agg(
+        order_count=('amount', 'count'),
+        revenue=('amount', 'sum'),
+        active_customers=('customer_id', 'nunique')
+    )
+    report['avg_order_value'] = report['revenue'] / report['order_count']
+    report['revenue_growth'] = report['revenue'].pct_change()
+    return report
     pass

homework/m5_visualization.py

@@ -14,7 +14,7 @@
 
 def _load_data():
     """輔助函式：讀取資料"""
-    return pd.read_csv("datasets/ecommerce/orders_enriched.csv",
+    return pd.read_csv("../datasets/ecommerce/orders_enriched.csv",
                        parse_dates=["order_date"])
 
 
@@ -29,6 +29,11 @@ def green_bar_category():
     提示：sns.countplot 或 value_counts().plot.bar()
     """
     # TODO: 你的程式碼
+    df = _load_data()
+    fig, ax = plt.subplots(figsize=(10, 6))
+    sns.countplot(data=df, x='category', ax=ax)
+    ax.set_title("Order Count by Category")
+    return fig
     pass
 
 
@@ -39,6 +44,11 @@ def green_hist_amount():
     提示：sns.histplot(bins=20) 或 plt.hist()
     """
     # TODO: 你的程式碼
+    df = _load_data()
+    fig, ax = plt.subplots(figsize=(10, 6))
+    sns.histplot(data=df, x='amount', bins=20, ax=ax)
+    ax.set_title("Distribution of Order Amounts")
+    return fig
     pass
 
 
@@ -51,6 +61,13 @@ def green_set_labels():
     回傳 matplotlib Figure 物件
     """
     # TODO: 你的程式碼
+    data = {'A': 100, 'B': 200, 'C': 300}
+    fig, ax = plt.subplots()
+    ax.bar(data.keys(), data.values())
+    ax.set_title("Simple Bar Chart")
+    ax.set_xlabel("Category")
+    ax.set_ylabel("Values")
+    return fig
     pass
 
 
@@ -68,6 +85,15 @@ def yellow_line_region_trend():
     提示：分別 groupby 再 plot，或用 sns.lineplot(hue='region')
     """
     # TODO: 你的程式碼
+    df = _load_data()
+    target_regions = df[df['region'].isin(['North', 'South'])]
+    trend_data = target_regions.groupby([target_regions['order_date'].dt.month, 'region'])['amount'].sum().unstack()
+    fig, ax = plt.subplots(figsize=(10, 6))
+    sns.lineplot(data=target_regions, x=target_regions['order_date'].dt.month, y='amount', hue='region', estimator='sum', ax=ax)
+    ax.set_title("Monthly Revenue Trend: North vs South")
+    ax.set_xlabel("Month")
+    ax.set_ylabel("Total Revenue")
+    return fig
     pass
 
 
@@ -78,6 +104,11 @@ def yellow_box_vip():
     提示：sns.boxplot(x='vip_level', y='amount', data=df)
     """
     # TODO: 你的程式碼
+    df = _load_data()
+    fig, ax = plt.subplots(figsize=(10, 6))
+    sns.boxplot(data=df, x='vip_level', y='amount', ax=ax)
+    ax.set_title("Order Amount Distribution by VIP Level")
+    return fig
     pass
 
 
@@ -88,6 +119,11 @@ def yellow_scatter_price_amount():
     提示：plt.scatter() 或 sns.scatterplot()
     """
     # TODO: 你的程式碼
+    df = _load_data()
+    fig, ax = plt.subplots(figsize=(10, 6))
+    sns.scatterplot(data=df, x='unit_price', y='amount', ax=ax)
+    ax.set_title("Unit Price vs Order Amount")
+    return fig
     pass
 
 
@@ -107,4 +143,26 @@ def red_category_dashboard(category="Electronics"):
     提示：fig, axes = plt.subplots(2, 2, figsize=(14, 10))
     """
     # TODO: 你的程式碼
+    df = _load_data()
+    cat_df = df[df['category'] == category].copy()
+    fig, axes = plt.subplots(2, 2, figsize=(14, 10))
+    fig.suptitle(f"Dashboard: {category}", fontsize=20)
+    monthly_rev = cat_df.set_index('order_date').resample('ME')['amount'].sum()
+    axes[0, 0].plot(monthly_rev.index, monthly_rev.values, marker='o', color='b')
+    axes[0, 0].set_title("Monthly Revenue Trend")
+    axes[0, 0].tick_params(axis='x', rotation=45)
+
+    region_rev = cat_df.groupby('region')['amount'].sum().sort_values(ascending=False)
+    sns.barplot(x=region_rev.index, y=region_rev.values, ax=axes[0, 1])
+    axes[0, 1].set_title("Revenue by Region")
+
+    top5_prod = cat_df.groupby('product_name')['amount'].sum().nlargest(5)
+    sns.barplot(x=top5_prod.values, y=top5_prod.index, ax=axes[1, 0], orient='h')
+    axes[1, 0].set_title("Top 5 Products by Revenue")
+
+    sns.histplot(cat_df['amount'], bins=15, kde=True, ax=axes[1, 1])
+    axes[1, 1].set_title("Order Amount Distribution")
+
+    plt.tight_layout(rect=[0, 0.03, 1, 0.95])
+    return fig
     pass