M1作業-孟祥竣

homework/m1_numpy.py

@@ -19,19 +19,20 @@
 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
-
+    nums = np.array([10, 20, 30, 40, 50])
+    return float(nums.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
-
+    nums = np.array([10, 20, 30, 40, 50])
+    return nums * 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
+    nums = np.array([10, 20, 30, 40, 50])
+    return nums[nums > 25]
 
 
 # ============================================================
@@ -42,26 +43,23 @@ 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
-
+    return np.sum(prices > 1000)
 
 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
-
+    return np.argsort(stocks)[::-1][:3]
 
 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
-
+    return np.sum(prices[prices < 500] * 50)
 
 # ============================================================
 # 🔴 挑戰題（25 分）
@@ -77,4 +75,4 @@ 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

@@ -20,7 +20,8 @@ def green_read_csv():
     提示：pd.read_csv()
     """
     # TODO: 你的程式碼
-    pass
+    original_df = pd.read_csv('datasets/ecommerce/orders_raw.csv')
+    return original_df
 
 
 def green_shape(df):
@@ -29,7 +30,7 @@ def green_shape(df):
     提示：df.shape
     """
     # TODO: 你的程式碼
-    pass
+    return df.shape
 
 
 def green_dtypes(df):
@@ -38,7 +39,7 @@ def green_dtypes(df):
     提示：df.dtypes
     """
     # TODO: 你的程式碼
-    pass
+    return df.dtypes
 
 
 # ============================================================
@@ -52,7 +53,9 @@ def yellow_clean_columns(df):
     提示：df.columns.str.strip().str.lower()
     """
     # TODO: 你的程式碼
-    pass
+    cleaned_df = df.copy()
+    cleaned_df.columns = cleaned_df.columns.str.strip().str.lower()
+    return cleaned_df
 
 
 def yellow_clean_amount(df):
@@ -63,7 +66,9 @@ def yellow_clean_amount(df):
     提示：.str.replace() + .astype(float)
     """
     # TODO: 你的程式碼
-    pass
+    cleaned_df = df.copy()
+    cleaned_df['amount'] = cleaned_df['amount'].str.replace('[\$,]', '', regex=True).astype(float)
+    return cleaned_df
 
 
 def yellow_drop_duplicates(df):
@@ -72,8 +77,9 @@ def yellow_drop_duplicates(df):
     提示：df.drop_duplicates()
     """
     # TODO: 你的程式碼
-    pass
-
+    cleaned_df = df.copy()
+    cleaned_df = cleaned_df.drop_duplicates()
+    return cleaned_df
 
 # ============================================================
 # 🔴 挑戰題（25 分）
@@ -93,4 +99,10 @@ 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'].str.replace('[\$,]', '', regex=True).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 +24,25 @@ 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 = pd.merge(orders, customers, on='customer_id', how='left')
+    df = pd.merge(df, 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 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 df.columns.tolist()
 
 
 # ============================================================
@@ -50,7 +56,9 @@ def yellow_top_category(df):
     提示：groupby('category')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
+    category_revenue = df.groupby('category')['amount'].sum()
+    top_category = category_revenue.idxmax()
+    return top_category
 
 
 def yellow_gold_vip_stats(df):
@@ -60,7 +68,10 @@ def yellow_gold_vip_stats(df):
     提示：df[df['vip_level'] == 'Gold']
     """
     # TODO: 你的程式碼
-    pass
+    gold_vip_orders = df[df['vip_level'] == 'Gold']
+    order_count = gold_vip_orders.shape[0]
+    total_amount = gold_vip_orders['amount'].sum()
+    return order_count, float(total_amount)
 
 
 def yellow_region_avg_amount(df):
@@ -70,7 +81,8 @@ def yellow_region_avg_amount(df):
     提示：groupby('region')['amount'].mean()
     """
     # TODO: 你的程式碼
-    pass
+    region_avg = df.groupby('region')['amount'].mean()
+    return region_avg
 
 
 # ============================================================
@@ -94,4 +106,22 @@ 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({
+        'order_date': 'max',  # Recency
+        'order_id': 'count',  # Frequency
+        'amount': 'sum'       # Monetary
+    }).reset_index()
+
+    rfm.columns = [
+        'customer_id',
+        'customer_name',
+        'R',
+        'F',
+        'M'
+    ]
+    rfm = rfm.sort_values(
+        by='M',
+        ascending=False
+    ).head(5)
+
+    return rfm

homework/m4_timeseries.py

@@ -27,7 +27,9 @@ def green_avg_by_month():
     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()
 
 
 def green_top3_dates():
@@ -37,7 +39,8 @@ 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 +49,10 @@ def green_date_range():
     格式為 pandas Timestamp
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    min_date = df['order_date'].min()
+    max_date = df['order_date'].max()
+    return min_date, max_date
 
 
 # ============================================================
@@ -60,7 +66,12 @@ 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 +82,7 @@ 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 +92,8 @@ def yellow_category_median(df):
     提示：groupby + median + sort_values
     """
     # TODO: 你的程式碼
-    pass
+    category_median = df.groupby('category')['amount'].median()
+    return category_median.sort_values(ascending=False) 
 
 
 # ============================================================
@@ -101,4 +113,18 @@ def red_monthly_report():
     提示：resample + agg + pct_change
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    monthly_report = df.set_index('order_date').resample('ME').agg({
+        'order_id': 'count', 
+        'amount': 'sum',      
+        'customer_id': pd.Series.nunique
+    })
+    monthly_report = monthly_report.rename(columns={
+        'order_id': 'order_count',
+        'amount': 'revenue',
+        'customer_id': 'active_customers'
+    })
+    monthly_report['avg_order_value'] = monthly_report['amount'] / monthly_report['order_id']
+    monthly_report['revenue_growth'] = monthly_report['amount'].pct_change() *  100
+    monthly_report.rename(columns={ 'order_id': 'order_count', 'amount': 'revenue'}, inplace=True)
+    return monthly_report