完成作業繳交 - 楊祖平 - AIPE03

homework/m1_numpy.py

@@ -18,50 +18,69 @@
 
 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
+    # TODO:
+    arr = np.array([10, 20, 30, 40, 50])
+    return arr.mean()
+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
+    # TODO: 
+    arr = np.array([10, 20, 30, 40, 50])
+    return arr * 2
+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
+    # TODO: 
+    arr = np.array([10, 20, 30, 40, 50])
+    return arr[arr > 25]
+print(green_filter())
 
 
 # ============================================================
 # 🟡 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'
+prices = np.genfromtxt(DATA, delimiter=',', skip_header=1 , usecols=3)
+stocks = np.genfromtxt(DATA,delimiter=',', skip_header=1, usecols=4)
 
 def yellow_expensive_count(prices):
     """回傳單價 > 1000 的商品數量 (int)"""
-    # TODO: 你的程式碼
-    pass
+    # TODO:
+    return len(prices[prices > 1000])
 
+print(yellow_expensive_count(prices))
 
 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
+    # TODO:
+    idx = np.argsort(stocks)
+    top3_stocks = idx [-3:][::-1]
+    return top3_stocks
+
+print(yellow_top3_stock_indices(stocks))
+
 
 
 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
+    # TODO:
+    mask = prices < 500
+    price_500 = prices[mask]
+    total_500 = (price_500 * 50).sum()
+    return total_500
 
+print(yellow_restock_cost(prices, stocks))
 
 # ============================================================
 # 🔴 挑戰題（25 分）
@@ -76,5 +95,14 @@ def red_double11_prices(prices, stocks):
     回傳每個商品的雙 11 售價 (ndarray)
     提示：np.where 可以巢狀使用
     """
-    # TODO: 你的程式碼
-    pass
+    # TODO:
+    prices_07 = prices[stocks >= 100]* 0.7
+    prices_09 = prices[(stocks >= 20) & (stocks <= 99)] * 0.9
+    prices_original = prices[stocks < 20]
+
+    finall_price = np.concatenate([prices_07, prices_09, prices_original])
+
+    #運用np.where取代if-else的方式
+    finall_price2 = np.where(stocks >= 100, prices * 0.7,#庫存大於100 ,true:價格x0.7
+                             np.where(stocks >= 20,prices * 0.9 ,prices))#庫存 >= 20 ,true:價格x0.9,庫存 < 20,false:價格原價
+    return finall_price2

homework/m2_pandas_cleaning.py

@@ -8,8 +8,7 @@
 資料路徑：datasets/ecommerce/orders_raw.csv
 """
 import pandas as pd
-
-
+df = pd.read_csv('datasets/ecommerce/orders_raw.csv')
 # ============================================================
 # 🟢 送分題（每題 10 分，共 30 分）
 # ============================================================
@@ -19,26 +18,29 @@ 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
+    # TODO:
+    DATA ='datasets/ecommerce/orders_raw.csv'
+    df = pd.read_csv(DATA)
+    return df
 
 
 def green_shape(df):
     """
     回傳 DataFrame 的 (列數, 欄數) tuple
     提示：df.shape
     """
-    # TODO: 你的程式碼
-    pass
+    # TODO: 
+    return df.shape
+
 
 
 def green_dtypes(df):
     """
     回傳 DataFrame 的欄位型別 (Series)
     提示：df.dtypes
     """
-    # TODO: 你的程式碼
-    pass
+    # TODO: 
+    return df.dtypes
 
 
 # ============================================================
@@ -51,8 +53,11 @@ def yellow_clean_columns(df):
     回傳清理後的 DataFrame（不要修改原始 df）
     提示：df.columns.str.strip().str.lower()
     """
-    # TODO: 你的程式碼
-    pass
+    # TODO: 
+    new_df = df.copy()
+    new_df = new_df.columns.str.strip().str.lower()
+    return new_df
+
 
 
 def yellow_clean_amount(df):
@@ -62,17 +67,26 @@ def yellow_clean_amount(df):
     回傳清理後的 DataFrame（不要修改原始 df）
     提示：.str.replace() + .astype(float)
     """
-    # TODO: 你的程式碼
-    pass
+    # TODO: 
+    new_df = df.copy()
+
+    new_df['amount'] = (
+        new_df['amount']
+        .astype(str)
+        .str.replace('$' ,'', regex=False)
+        .str.replace(',' ,'', regex=False)
+        .astype(float)
+    )
+    return new_df
 
 
 def yellow_drop_duplicates(df):
     """
     移除完全重複的列，回傳去重後的 DataFrame
     提示：df.drop_duplicates()
     """
-    # TODO: 你的程式碼
-    pass
+    # TODO:
+    return df.drop_duplicates()
 
 
 # ============================================================
@@ -92,5 +106,26 @@ def red_clean_orders(path):
     回傳：清理後的 DataFrame
     提示：pd.to_datetime(errors='coerce')
     """
-    # TODO: 你的程式碼
-    pass
+    # TODO: 
+    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
+
+my_path = 'datasets/ecommerce/orders_raw.csv'
+print(red_clean_orders(my_path))

homework/m3_pandas_advanced.py

@@ -10,7 +10,11 @@
   - datasets/ecommerce/products.csv
 """
 import pandas as pd
+import numpy as np
 
+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')
 
 # ============================================================
 # 🟢 送分題（每題 10 分，共 30 分）
@@ -23,20 +27,22 @@ def green_load_and_merge():
     - 再 LEFT JOIN products.csv ON product_id
     提示：pd.merge(how='left')
     """
-    # TODO: 你的程式碼
-    pass
-
-
+    # TODO:
+    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
+    # TODO:
+    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
+    # TODO: 
+    return list(df.columns)
 
 
 # ============================================================
@@ -49,8 +55,9 @@ def yellow_top_category(df):
     回傳該類別名稱 (str)
     提示：groupby('category')['amount'].sum()
     """
-    # TODO: 你的程式碼
-    pass
+    # TODO:
+    category = df.groupby('category')['amount'].sum().sort_values(ascending=False)
+    return category.index[0]
 
 
 def yellow_gold_vip_stats(df):
@@ -59,8 +66,18 @@ def yellow_gold_vip_stats(df):
     回傳 tuple: (訂單數 int, 總金額 float)
     提示：df[df['vip_level'] == 'Gold']
     """
-    # TODO: 你的程式碼
-    pass
+    # TODO:
+    # Gold_df = df[df["vip_level"] == "Gold"]
+    Gold_amount = int(df[df["vip_level"] == "Gold"]["amount"].count())
+    Gold_total = float(df[df["vip_level"] == "Gold"]["amount"].sum())
+
+    # df = pd.DataFrame({
+    # "VIP":['Gold'],
+    # "訂單數":[Gold_amount],
+    # "總金額":[Gold_total]
+    # # })
+
+    return (Gold_amount,Gold_total)
 
 
 def yellow_region_avg_amount(df):
@@ -69,9 +86,10 @@ def yellow_region_avg_amount(df):
     回傳 Series（index=region, values=平均金額）
     提示：groupby('region')['amount'].mean()
     """
-    # TODO: 你的程式碼
-    pass
-
+    # TODO:
+    df_mean = df.groupby("region")["amount"].mean().sort_values(ascending=False)
+    print(df_mean)
+    return df_mean
 
 # ============================================================
 # 🔴 挑戰題（25 分）
@@ -93,5 +111,25 @@ def red_rfm_top5(df):
 
     提示：groupby('customer_id').agg(...)
     """
-    # TODO: 你的程式碼
-    pass
+    # TODO:  
+    rfm = df.groupby('customer_id').agg(
+              R=('order_date', 'max'),
+              F=('order_id', 'count'),
+              M=('amount', 'sum'),
+         ).reset_index() #計算 RFM過程.
+
+    name_map = df[['customer_id', 'customer_name']].drop_duplicates() #重複的customer_id/customer_name去除.
+    rfm_named = rfm.merge(name_map, on='customer_id', how='left') #把整理好的customer_id/customer_name合併.
+
+    top5 = (
+    rfm_named
+    .sort_values('M', ascending=False)
+    .head(5)
+    .reset_index(drop=True)
+    [['customer_id', 'customer_name', 'R', 'F', 'M']]
+    )  #按M由大到小排序,取前5筆
+
+    return top5
+
+
+