完成 M1 完成作業繳交 - 許傑雅

homework/m1_numpy.py

@@ -19,19 +19,22 @@
 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(np.mean(arr))
 
 
 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])
 
 
 # ============================================================
@@ -42,7 +45,8 @@ 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
+    mask = prices > 1000
+    return mask.sum()
 
 
 def yellow_top3_stock_indices(stocks):
@@ -51,7 +55,9 @@ def yellow_top3_stock_indices(stocks):
     提示：np.argsort
     """
     # TODO: 你的程式碼
-    pass
+    stocks_3 = np.argsort(stocks)
+    return (stocks_3[::-1][:3])
+
 
 
 def yellow_restock_cost(prices, stocks):
@@ -60,7 +66,8 @@ def yellow_restock_cost(prices, stocks):
     提示：布林遮罩 + .sum()
     """
     # TODO: 你的程式碼
-    pass
+    prices_500 = prices[prices < 500]*50
+    return (prices_500.sum())
 
 
 # ============================================================
@@ -77,4 +84,16 @@ def red_double11_prices(prices, stocks):
     提示：np.where 可以巢狀使用
     """
     # TODO: 你的程式碼
-    pass
+    prices = np.array(prices)
+    stocks = np.array(stocks)
+
+    new_prices = np.where(
+        stocks >= 100,                       
+        prices * 0.7,                        
+        np.where(
+            stocks >= 20,                    
+            prices * 0.9,                    
+            prices                           
+    )
+)
+    return new_prices

homework/m2_pandas_cleaning.py

@@ -20,7 +20,7 @@ def green_read_csv():
     提示：pd.read_csv()
     """
     # TODO: 你的程式碼
-    pass
+    return pd.read_csv('datasets/ecommerce/orders_raw.csv')
 
 
 def green_shape(df):
@@ -29,7 +29,7 @@ def green_shape(df):
     提示：df.shape
     """
     # TODO: 你的程式碼
-    pass
+    return df.shape
 
 
 def green_dtypes(df):
@@ -38,7 +38,7 @@ def green_dtypes(df):
     提示：df.dtypes
     """
     # TODO: 你的程式碼
-    pass
+    return df.dtypes
 
 
 # ============================================================
@@ -52,7 +52,9 @@ def yellow_clean_columns(df):
     提示：df.columns.str.strip().str.lower()
     """
     # TODO: 你的程式碼
-    pass
+    df_new = df.copy()
+    df_new.columns = df_new.columns.str.strip().str.lower()
+    return df_new
 
 
 def yellow_clean_amount(df):
@@ -63,7 +65,15 @@ def yellow_clean_amount(df):
     提示：.str.replace() + .astype(float)
     """
     # TODO: 你的程式碼
-    pass
+    df_amount = df.copy()
+    df_amount['amount'] = (
+        df_amount['amount']
+        .astype(str)
+        .str.replace('$', '', regex=False)
+        .str.replace(',', '', regex=False)
+        .astype(float)
+    )
+    return df_amount
 
 
 def yellow_drop_duplicates(df):
@@ -72,7 +82,7 @@ def yellow_drop_duplicates(df):
     提示：df.drop_duplicates()
     """
     # TODO: 你的程式碼
-    pass
+    return df.drop_duplicates()
 
 
 # ============================================================
@@ -93,4 +103,10 @@ 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=['order_date','amount']) # 只要這兩個欄位中任一個有缺失值，該列就會被剔除。
+    df = df.drop_duplicates()
+    return df

homework/m3_pandas_advanced.py

@@ -24,19 +24,27 @@ 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')
+        .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)
 
 
 # ============================================================
@@ -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().sort_values(ascending=False)
+    return category_rev.idxmax()
 
 
 def yellow_gold_vip_stats(df):
@@ -60,7 +69,11 @@ 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 = int(len(gold_df))
+    total_amount = float(gold_df['amount'].sum())
+
+    return (order_count, total_amount)
 
 
 def yellow_region_avg_amount(df):
@@ -70,7 +83,13 @@ def yellow_region_avg_amount(df):
     提示：groupby('region')['amount'].mean()
     """
     # TODO: 你的程式碼
-    pass
+    region_mean = (
+    df.groupby('region')['amount']
+      .mean()
+      .round(2)
+      .sort_values(ascending=False)
+    )
+    return region_mean
 
 
 # ============================================================
@@ -94,4 +113,11 @@ 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()
+    result = rfm.sort_values('M',ascending=False).head()
+    return result[["customer_id", "customer_name", "R", "F", "M"]]

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()  # 必須先讀取資料，否則會報錯
+    ts = df.groupby(df['order_date'].dt.month)
+    return ts['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'].value_counts().head(3)
 
 
 def green_date_range():
@@ -46,7 +49,8 @@ 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 +64,8 @@ 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 +76,8 @@ def yellow_rolling_avg(monthly_revenue):
     提示：.rolling(window=3).mean()
     """
     # TODO: 你的程式碼
-    pass
+    monthly_rev = yellow_monthly_revenue()
+    return monthly_rev.rolling(window=3).mean()
 
 
 def yellow_category_median(df):
@@ -81,7 +87,13 @@ def yellow_category_median(df):
     提示：groupby + median + sort_values
     """
     # TODO: 你的程式碼
-    pass
+    result = (
+        df.groupby('category')['amount']
+          .median()
+          .sort_values(ascending=False)
+    )
+
+    return result
 
 
 # ============================================================
@@ -101,4 +113,13 @@ def red_monthly_report():
     提示：resample + agg + pct_change
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    report = df.set_index('order_date').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() * 100
+    return report