完成作業繳交 -周冠廷 -AIPE03

homework/m1_numpy.py

@@ -11,62 +11,67 @@
 """
 import numpy as np
 
-
 # ============================================================
 # 🟢 送分題（每題 10 分，共 30 分）
 # ============================================================
 
 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 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])
+    result = arr * 2
+    return result
 
 
 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])
+    result = arr[arr > 25]
+    return result    
 
 # ============================================================
 # 🟡 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
 # ============================================================
 
+# ---------- 載入 products.csv ----------
+DATA_PATH = "datasets/ecommerce/products.csv"
+prices = np.genfromtxt(DATA_PATH, delimiter=",", skip_header=1, usecols=3)
+stocks = np.genfromtxt(DATA_PATH, 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
+    return prices[prices>1000].size
 
 
 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 (prices[prices < 500] * 50).sum()
 
 # ============================================================
 # 🔴 挑戰題（25 分）
 # ============================================================
 
+
 def red_double11_prices(prices, stocks):
     """
     雙 11 定價規則（必須向量化，不能用 for-loop）：
@@ -76,5 +81,5 @@ 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
+    return np.where(stocks >= 100, prices * 0.7, 
+             np.where((stocks >= 20) & (stocks <= 99), prices * 0.9, prices))

homework/m2_pandas_cleaning.py

@@ -9,18 +9,20 @@
 """
 import pandas as pd
 
-
 # ============================================================
 # 🟢 送分題（每題 10 分，共 30 分）
 # ============================================================
 
+DATA = '../datasets/ecommerce/orders_raw.csv'
+df = pd.read_csv(DATA)
+
 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
+    return df
 
 
 def green_shape(df):
@@ -29,7 +31,8 @@ def green_shape(df):
     提示：df.shape
     """
     # TODO: 你的程式碼
-    pass
+    return df.shape
+
 
 
 def green_dtypes(df):
@@ -38,7 +41,7 @@ def green_dtypes(df):
     提示：df.dtypes
     """
     # TODO: 你的程式碼
-    pass
+    return df.dtypes
 
 
 # ============================================================
@@ -52,7 +55,9 @@ def yellow_clean_columns(df):
     提示：df.columns.str.strip().str.lower()
     """
     # TODO: 你的程式碼
-    pass
+    new_df = df.copy()
+    new_df.columns = new_df.columns.str.strip().str.lower()
+    return new_df.columns
 
 
 def yellow_clean_amount(df):
@@ -63,7 +68,15 @@ def yellow_clean_amount(df):
     提示：.str.replace() + .astype(float)
     """
     # TODO: 你的程式碼
-    pass
+    df_copy = df.copy() # 複製一份
+    df_copy['amount']=(
+        df_copy['amount']
+        .astype(str)
+        .str.replace('$', '', regex = False)
+        .str.replace(',', '', regex = False)
+        .astype(float)
+    )
+    return df_copy # 整張清理過的表
 
 
 def yellow_drop_duplicates(df):
@@ -72,7 +85,8 @@ def yellow_drop_duplicates(df):
     提示：df.drop_duplicates()
     """
     # TODO: 你的程式碼
-    pass
+    df_drop = df.drop_duplicates()
+    return df_drop
 
 
 # ============================================================
@@ -93,4 +107,23 @@ def red_clean_orders(path):
     提示：pd.to_datetime(errors='coerce')
     """
     # TODO: 你的程式碼
-    pass
+    df = pd.read_csv(path) # 1
+
+    df.columns = df.columns.str.strip().str.lower() # 2
+
+    df['amount']=(
+        df['amount']
+        .astype(str)
+        .str.replace('$', '', regex = False)
+        .str.replace(',', '', regex = False)
+        .astype(float)
+    ) # 3
+
+    df['order_date'] = pd.to_datetime(df['order_date'], errors = 'coerce') # 4
+
+    df = df.dropna(subset = ['amount','order_date']) # 5
+
+    df_drop = df.drop_duplicates() # 6
+    df = df_drop
+    return df
+

homework/m3_pandas_advanced.py

@@ -15,6 +15,11 @@
 # ============================================================
 # 🟢 送分題（每題 10 分，共 30 分）
 # ============================================================
+order = pd.read_csv('..\datasets\ecommerce\orders_clean.csv')
+customers = pd.read_csv('..\datasets\ecommerce\customers.csv')
+products = pd.read_csv('..\datasets\ecommerce\products.csv')
+
+
 
 def green_load_and_merge():
     """
@@ -24,19 +29,22 @@ def green_load_and_merge():
     提示：pd.merge(how='left')
     """
     # TODO: 你的程式碼
-    pass
+    oc = order.merge(customers, on = 'customer_id',how = 'left' )
+    df = oc.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
-
+    count = df.shape[0]    
+    return count
 
 def green_column_list(df):
     """回傳 DataFrame 的所有欄位名稱 (list)"""
     # TODO: 你的程式碼
-    pass
+    column_names = df.columns.tolist()
+    return column_names
 
 
 # ============================================================
@@ -50,7 +58,8 @@ def yellow_top_category(df):
     提示：groupby('category')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
+    category_rev = df.groupby('category')['amount'].sum().idxmax()
+    return category_rev
 
 
 def yellow_gold_vip_stats(df):
@@ -60,7 +69,10 @@ def yellow_gold_vip_stats(df):
     提示：df[df['vip_level'] == 'Gold']
     """
     # TODO: 你的程式碼
-    pass
+    gold_df = df[df['vip_level'] == 'Gold']
+    order_count = len(gold_df) # 數出vip是gold等級的有幾張訂單
+    gold_amount = gold_df['amount'].sum() 
+    return (int(order_count), float(gold_amount))
 
 
 def yellow_region_avg_amount(df):
@@ -70,7 +82,8 @@ 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 +107,14 @@ 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',
+        'order_id': 'count',
+        'amount': 'sum'
+    }).reset_index()
+
+    rfm.columns = ['customer_id', 'customer_name', 'R', 'F', 'M']
+
+    top5 = rfm.sort_values(by='M', ascending=False).head(5)
+
+    return top5

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()
+    mon_avg = df.groupby(df['order_date'].dt.month)['amount'].mean()
+    return mon_avg
 
 
 def green_top3_dates():
@@ -37,7 +39,9 @@ def green_top3_dates():
     提示：value_counts().head(3)
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    result = df['order_id'].value_counts().head(3)
+    return result
 
 
 def green_date_range():
@@ -46,7 +50,11 @@ def green_date_range():
     格式為 pandas Timestamp
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    earliest = df['order_date'].min()
+    latest = df['order_date'].max()
+
+    return (earliest, latest)
 
 
 # ============================================================
@@ -60,7 +68,9 @@ def yellow_monthly_revenue():
     提示：set_index('order_date').resample('ME')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    monthly_revenue = df.set_index('order_date').resample('ME')['amount'].sum()
+    return monthly_revenue
 
 
 def yellow_rolling_avg(monthly_revenue):
@@ -71,7 +81,8 @@ def yellow_rolling_avg(monthly_revenue):
     提示：.rolling(window=3).mean()
     """
     # TODO: 你的程式碼
-    pass
+    rolling_avg = monthly_revenue.rolling(window=3).mean()
+    return rolling_avg
 
 
 def yellow_category_median(df):
@@ -81,7 +92,9 @@ def yellow_category_median(df):
     提示：groupby + median + sort_values
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    category_med = df.groupby('category')['amount'].median().sort_values(ascending=False)
+    return category_med
 
 
 # ============================================================
@@ -101,4 +114,19 @@ def red_monthly_report():
     提示：resample + agg + pct_change
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data
+    temp_df = df.set_index('order_date')
+
+    report = temp_df.resample('ME').agg({
+        'order_id': 'count',         
+        'amount': 'sum',         
+        'customer_id': 'nunique'    
+    })
+
+    report.columns = ['order_count', 'revenue', 'active_customers']
+
+    report['avg_order_value'] = report['revenue'] / report['order_count']
+
+    report['revenue_growth'] = report['revenue'].pct_change()
+
+    return report