完成繳交作業 -鄭玉 AIPE03

homework/m1_numpy.py

@@ -19,30 +19,36 @@
 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 float(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]
 
 
 # ============================================================
 # 🟡 核心題（每題 15 分，共 45 分）
 # 以下函式會接收從 products.csv 讀出的 prices, stocks 陣列
 # ============================================================
+DATA = 'datasets/ecommerce/products.csv'
+stocks = np.genfromtxt(DATA, delimiter=',', skip_header=1, usecols=4)
+prices = np.genfromtxt(DATA, delimiter=',', skip_header=1, usecols=3)
 
 def yellow_expensive_count(prices):
     """回傳單價 > 1000 的商品數量 (int)"""
     # TODO: 你的程式碼
-    pass
+    return int((prices > 1000).sum())
 
 
 def yellow_top3_stock_indices(stocks):
@@ -51,7 +57,8 @@ def yellow_top3_stock_indices(stocks):
     提示：np.argsort
     """
     # TODO: 你的程式碼
-    pass
+    sorted_stocks = np.argsort(stocks)
+    return sorted_stocks[-3:][::-1]
 
 
 def yellow_restock_cost(prices, stocks):
@@ -60,12 +67,15 @@ def yellow_restock_cost(prices, stocks):
     提示：布林遮罩 + .sum()
     """
     # TODO: 你的程式碼
-    pass
+    return float((prices[prices < 500] * 50).sum())
 
 
 # ============================================================
 # 🔴 挑戰題（25 分）
 # ============================================================
+DATA = 'datasets/ecommerce/products.csv'
+stocks = np.genfromtxt(DATA, delimiter=',', skip_header=1, usecols=4)
+prices = np.genfromtxt(DATA, delimiter=',', skip_header=1, usecols=3)
 
 def red_double11_prices(prices, stocks):
     """
@@ -77,4 +87,8 @@ def red_double11_prices(prices, stocks):
     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),
+    )

homework/m2_pandas_cleaning.py

@@ -13,14 +13,17 @@
 # ============================================================
 # 🟢 送分題（每題 10 分，共 30 分）
 # ============================================================
+DATA = 'datasets/ecommerce/orders_raw.csv'
+
 
 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
+    df = pd.read_csv(DATA)
+    return df
 
 
 def green_shape(df):
@@ -29,7 +32,8 @@ def green_shape(df):
     提示：df.shape
     """
     # TODO: 你的程式碼
-    pass
+    df = pd.read_csv(DATA)
+    return df.shape
 
 
 def green_dtypes(df):
@@ -38,7 +42,8 @@ def green_dtypes(df):
     提示：df.dtypes
     """
     # TODO: 你的程式碼
-    pass
+    df = pd.read_csv(DATA)
+    return df.dtypes
 
 
 # ============================================================
@@ -52,7 +57,10 @@ def yellow_clean_columns(df):
     提示：df.columns.str.strip().str.lower()
     """
     # TODO: 你的程式碼
-    pass
+    df = pd.read_csv(DATA)
+    result = df.copy()
+    result.columns = result.columns.str.strip().str.lower()
+    return result
 
 
 def yellow_clean_amount(df):
@@ -63,7 +71,10 @@ def yellow_clean_amount(df):
     提示：.str.replace() + .astype(float)
     """
     # TODO: 你的程式碼
-    pass
+    df = pd.read_csv(DATA)
+    result = df.copy()
+    result["amount"] = result["amount"].astype(str).str.replace("$", "", regex=False).str.replace(",", "", regex=False).astype(float)
+    return result
 
 
 def yellow_drop_duplicates(df):
@@ -72,7 +83,8 @@ def yellow_drop_duplicates(df):
     提示：df.drop_duplicates()
     """
     # TODO: 你的程式碼
-    pass
+    df = pd.read_csv(DATA)
+    return df.drop_duplicates()
 
 
 # ============================================================
@@ -93,4 +105,10 @@ 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.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()
+    return df

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
+    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")
+    df = df.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)
 
 
 # ============================================================
@@ -50,7 +55,7 @@ def yellow_top_category(df):
     提示：groupby('category')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
+    return df.groupby("category")["amount"].sum().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"]
+    order_count = len(gold)
+    total_amount = gold["amount"].sum()
+    return (order_count, total_amount)
 
 
 def yellow_region_avg_amount(df):
@@ -70,7 +78,7 @@ def yellow_region_avg_amount(df):
     提示：groupby('region')['amount'].mean()
     """
     # TODO: 你的程式碼
-    pass
+    return df.groupby("region")["amount"].mean()
 
 
 # ============================================================
@@ -94,4 +102,11 @@ def red_rfm_top5(df):
     提示：groupby('customer_id').agg(...)
     """
     # TODO: 你的程式碼
-    pass
+    rfm = df.groupby("customer_id").agg(
+        R=("order_date", "max"),
+        F=("order_id", "count"),
+        M=("amount", "sum"),
+        customer_name=("customer_name", "first")
+    ).reset_index()
+    rfm = rfm.sort_values("M", ascending=False).head(5)
+    return rfm[["customer_id", "customer_name", "R", "F", "M"]]

homework/m4_timeseries.py

@@ -11,8 +11,8 @@
 
 def _load_data():
     """輔助函式：讀取並解析日期"""
-    df = pd.read_csv("datasets/ecommerce/orders_enriched.csv",
-                     parse_dates=["order_date"])
+    # TODO: 你的程式碼
+    df = pd.read_csv("datasets/ecommerce/orders_enriched.csv", parse_dates=["order_date"])
     return df
 
 
@@ -27,7 +27,8 @@ def green_avg_by_month():
     提示：df['order_date'].dt.month
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    return df.groupby(df['order_date'].dt.month)['amount'].mean()
 
 
 def green_top3_dates():
@@ -37,7 +38,8 @@ def green_top3_dates():
     提示：value_counts().head(3)
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    return df['order_date'].dt.date.value_counts().head(3)
 
 
 def green_date_range():
@@ -46,7 +48,8 @@ def green_date_range():
     格式為 pandas Timestamp
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    return (df['order_date'].min(), df['order_date'].max())
 
 
 # ============================================================
@@ -60,7 +63,8 @@ def yellow_monthly_revenue():
     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):
@@ -71,7 +75,7 @@ def yellow_rolling_avg(monthly_revenue):
     提示：.rolling(window=3).mean()
     """
     # TODO: 你的程式碼
-    pass
+    return monthly_revenue.rolling(window=3).mean()
 
 
 def yellow_category_median(df):
@@ -81,7 +85,7 @@ def yellow_category_median(df):
     提示：groupby + median + sort_values
     """
     # TODO: 你的程式碼
-    pass
+    return df.groupby('category')['amount'].median().sort_values(ascending=False)
 
 
 # ============================================================
@@ -101,4 +105,9 @@ def red_monthly_report():
     提示：resample + agg + pct_change
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    monthly = df.set_index('order_date').resample('ME').agg({'amount': ['count', 'sum'],'customer_id': 'nunique'})
+    monthly.columns = ['order_count', 'revenue', 'active_customers']
+    monthly['avg_order_value'] = monthly['revenue'] / monthly['order_count']
+    monthly['revenue_growth'] = monthly['revenue'].pct_change()
+    return monthly