M1 作業 - 林柏彥

homework/m1_numpy.py

@@ -19,19 +19,27 @@
 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.arange(5) + 1) * 10
+    return arr.mean().item()
+
+# print(green_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.arange(5) + 1) * 10 * 2
+    return arr
 
+# print(green_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
+    arr = (np.arange(5) + 1) * 10
+    return arr[arr>25]
+
+# print(green_filter())
 
 
 # ============================================================
@@ -42,7 +50,7 @@ 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 int((prices > 1000).sum())
 
 
 def yellow_top3_stock_indices(stocks):
@@ -51,7 +59,7 @@ def yellow_top3_stock_indices(stocks):
     提示：np.argsort
     """
     # TODO: 你的程式碼
-    pass
+    return np.argsort(-stocks)[:3]
 
 
 def yellow_restock_cost(prices, stocks):
@@ -60,8 +68,18 @@ def yellow_restock_cost(prices, stocks):
     提示：布林遮罩 + .sum()
     """
     # TODO: 你的程式碼
-    pass
-
+    mask = prices<500
+    return sum(50 * prices[mask])
+
+# import pandas as pd
+# C:\python_data\python-da-homework-2026\datasets\ecommerce\products.csv
+# df = pd.read_csv('../datasets/ecommerce/products.csv')
+# print(df['unit_price'])
+# print(df['stock_qty'])
+# print(yellow_expensive_count(df['unit_price']))
+# print(type(yellow_expensive_count(df['unit_price'])))
+# print(yellow_top3_stock_indices(df['stock_qty']))
+# print(yellow_restock_cost(df['unit_price'], df['stock_qty']))
 
 # ============================================================
 # 🔴 挑戰題（25 分）
@@ -77,4 +95,11 @@ def red_double11_prices(prices, stocks):
     提示：np.where 可以巢狀使用
     """
     # TODO: 你的程式碼
-    pass
+    # print(prices, stocks)
+    new_prices = np.where(stocks>=100, prices*0.7, np.where(stocks>=20, prices*0.9, prices))
+    # print(type(new_prices))
+    return new_prices
+
+# import pandas as pd
+# df = pd.read_csv('../datasets/ecommerce/products.csv')
+# print(red_double11_prices(df['unit_price'], df['stock_qty']))

homework/m2_pandas_cleaning.py

@@ -20,7 +20,9 @@ def green_read_csv():
     提示：pd.read_csv()
     """
     # TODO: 你的程式碼
-    pass
+    df = pd.read_csv('datasets/ecommerce/orders_raw.csv')
+    # print(df.head())
+    return df
 
 
 def green_shape(df):
@@ -29,7 +31,7 @@ def green_shape(df):
     提示：df.shape
     """
     # TODO: 你的程式碼
-    pass
+    return df.shape
 
 
 def green_dtypes(df):
@@ -38,8 +40,12 @@ def green_dtypes(df):
     提示：df.dtypes
     """
     # TODO: 你的程式碼
-    pass
+    return df.dtypes
 
+# temp = green_read_csv()
+# print(green_read_csv())
+# print(green_shape(temp))
+# print(green_dtypes(temp))
 
 # ============================================================
 # 🟡 核心題（每題 15 分，共 45 分）
@@ -52,7 +58,9 @@ def yellow_clean_columns(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):
@@ -63,7 +71,9 @@ def yellow_clean_amount(df):
     提示：.str.replace() + .astype(float)
     """
     # TODO: 你的程式碼
-    pass
+    df2 = df.copy()
+    df2['amount'] = df2['amount'].str.replace('$', '').str.replace(',', '').astype(float)
+    return df2
 
 
 def yellow_drop_duplicates(df):
@@ -72,9 +82,12 @@ def yellow_drop_duplicates(df):
     提示：df.drop_duplicates()
     """
     # TODO: 你的程式碼
-    pass
-
+    df2 = df.drop_duplicates()
+    return df2
 
+# print(yellow_clean_columns(temp))
+# print(yellow_clean_amount(temp))
+# print(yellow_drop_duplicates(temp))
 # ============================================================
 # 🔴 挑戰題（25 分）
 # ============================================================
@@ -93,4 +106,15 @@ 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('$', '').str.replace(',', '').astype(float)
+    df['order_date'] = pd.to_datetime(df['order_date'], errors='coerce')
+    df = df.dropna(subset=['order_date', 'amount'])
+    df = df.drop_duplicates()
+
+    return df
+
+# print(red_clean_orders('../datasets/ecommerce/orders_raw.csv').head())
+
+# print(red_clean_orders('../datasets/ecommerce/orders_raw.csv').shape)

homework/m3_pandas_advanced.py

@@ -24,21 +24,41 @@ def green_load_and_merge():
     提示：pd.merge(how='left')
     """
     # TODO: 你的程式碼
-    pass
+    df1 = pd.read_csv('datasets/ecommerce/orders_clean.csv')
+    df2 = pd.read_csv('datasets/ecommerce/customers.csv')
+    df3 = pd.read_csv('datasets/ecommerce/products.csv')
+
+    df = (
+        df1
+        .merge(df2, on='customer_id', how='left')
+        .merge(df3, on='product_id', how='left')
+    )
+
+    # print(df.head())
+    # print(df.shape)
+    # print(df.columns)
+
+    return df
 
 
 def green_row_count(df):
     """回傳 DataFrame 的列數 (int)"""
     # TODO: 你的程式碼
-    pass
+    # print(len(df))
+    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)
 
 
+# temp = green_load_and_merge()
+# leng = green_row_count(temp)
+# leng = green_column_list(temp)
+# print(leng)
+
 # ============================================================
 # 🟡 核心題（每題 15 分，共 45 分）
 # ============================================================
@@ -50,7 +70,9 @@ def yellow_top_category(df):
     提示：groupby('category')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
+    product = df.groupby('category')['amount'].sum().idxmax()
+    # print(product)
+    return product
 
 
 def yellow_gold_vip_stats(df):
@@ -60,7 +82,9 @@ def yellow_gold_vip_stats(df):
     提示：df[df['vip_level'] == 'Gold']
     """
     # TODO: 你的程式碼
-    pass
+    order_nums = df[df['vip_level'] == 'Gold']['order_id'].count()
+    order_sum = df[df['vip_level'] == 'Gold']['amount'].sum()
+    return (order_nums, order_sum)
 
 
 def yellow_region_avg_amount(df):
@@ -70,7 +94,15 @@ def yellow_region_avg_amount(df):
     提示：groupby('region')['amount'].mean()
     """
     # TODO: 你的程式碼
-    pass
+    avg_money = df.groupby('region')['amount'].mean()
+    # print(avg_money)
+    # print(type(avg_money))
+    return avg_money
+
+# temp = green_load_and_merge()
+# tmp = yellow_top_category(temp)
+# tmp = yellow_gold_vip_stats(temp)
+# tmp = yellow_region_avg_amount(temp)
 
 
 # ============================================================
@@ -94,4 +126,21 @@ 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')
+    )
+
+    cus_name = df[['customer_id', 'customer_name']].drop_duplicates()
+
+    rfm = rfm.merge(
+        cus_name,
+        on= 'customer_id',
+        how='right'
+    ).sort_values('M', ascending=False)
+    rfm = rfm.head(5).reset_index()[['customer_id', 'customer_name', 'R', 'F', 'M']]
+    # print(rfm)
+    return rfm
+
+# tmp = red_rfm_top5(temp)

homework/m4_timeseries.py

@@ -27,8 +27,9 @@ def green_avg_by_month():
     提示：df['order_date'].dt.month
     """
     # TODO: 你的程式碼
-    pass
-
+    df = _load_data()
+    ans = df.groupby(df['order_date'].dt.month)['amount'].mean()
+    return ans
 
 def green_top3_dates():
     """
@@ -37,7 +38,9 @@ def green_top3_dates():
     提示：value_counts().head(3)
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    ans = df['order_date'].dt.date.value_counts().head(3)
+    return ans
 
 
 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()
+    # temp = (df['order_date'].min(), df['order_date'].max())
+    # print(type(temp))
+    return (df['order_date'].min(), df['order_date'].max())
 
 
 # ============================================================
@@ -60,7 +66,8 @@ 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 +78,7 @@ 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):
@@ -81,8 +88,16 @@ 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)
 
+# tmp = _load_data()
+# tmp = green_avg_by_month()
+# tmp = green_top3_dates()
+# tmp = green_date_range()
+# tmp = yellow_monthly_revenue()
+# tmp = yellow_rolling_avg(tmp)
+# tmp = yellow_category_median(_load_data())
+# print(tmp)
 
 # ============================================================
 # 🔴 挑戰題（25 分）
@@ -101,4 +116,15 @@ def red_monthly_report():
     提示：resample + agg + pct_change
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    ans = df.groupby(df['order_date'].dt.to_period('M')).agg(
+        order_count= ('order_id', 'count'),
+        revenue= ('amount', 'sum'),
+        active_customers= ('customer_id', 'nunique'),
+    ).sort_index()
+
+    ans['avg_order_value'] = ans['revenue'] / ans['order_count']
+    ans['revenue_growth'] = ans['revenue'].pct_change() * 100
+    return ans
+
+# print(red_monthly_report())