完成作業-鄭典-AIPE03

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
+    np_mean = np.array([10, 20, 30, 40, 50])
+    return float(np.mean(np_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
+    np_double = np.array([10, 20, 30, 40, 50]) * 2
+    return np_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
+    np_filter = np.array([10, 20, 30, 40, 50])
+    return np_filter[np_filter > 25]
 
 
 # ============================================================
@@ -42,7 +45,10 @@ 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_expensive = prices > 1000
+    num_expensive = mask_expensive.sum()
+    return num_expensive
+
 
 
 def yellow_top3_stock_indices(stocks):
@@ -51,7 +57,9 @@ def yellow_top3_stock_indices(stocks):
     提示：np.argsort
     """
     # TODO: 你的程式碼
-    pass
+    sorted_stock = np.argsort(stocks)
+    top3_stock = sorted_stock[-3:][::-1]
+    return top3_stock
 
 
 def yellow_restock_cost(prices, stocks):
@@ -60,7 +68,10 @@ def yellow_restock_cost(prices, stocks):
     提示：布林遮罩 + .sum()
     """
     # TODO: 你的程式碼
-    pass
+    mask_cheap = prices < 500
+    cheap_prices = prices[mask_cheap]
+    total_cost = round((cheap_prices * 50).sum(), 0)
+    return total_cost
 
 
 # ============================================================
@@ -77,4 +88,13 @@ def red_double11_prices(prices, stocks):
     提示：np.where 可以巢狀使用
     """
     # TODO: 你的程式碼
-    pass
+    final_price = np.where(
+        stocks >= 100,
+        prices * 0.7,
+        np.where(
+            stocks >= 20,
+            prices * 0.9,
+            prices
+        )
+    )
+    return final_price

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
+    df_raw = pd.read_csv()
+    return df_raw
 
 
 def green_shape(df):
@@ -29,7 +30,9 @@ def green_shape(df):
     提示：df.shape
     """
     # TODO: 你的程式碼
-    pass
+    df_shape = df.shape
+    return df_shape
+
 
 
 def green_dtypes(df):
@@ -38,7 +41,8 @@ def green_dtypes(df):
     提示：df.dtypes
     """
     # TODO: 你的程式碼
-    pass
+    df_dtypes = df.dtypes
+    return df_dtypes
 
 
 # ============================================================
@@ -52,7 +56,9 @@ def yellow_clean_columns(df):
     提示：df.columns.str.strip().str.lower()
     """
     # TODO: 你的程式碼
-    pass
+    df_clean = df.copy()
+    df_clean.columns = df_clean.columns.str.strip().str.lower()
+    return df_clean
 
 
 def yellow_clean_amount(df):
@@ -63,7 +69,16 @@ def yellow_clean_amount(df):
     提示：.str.replace() + .astype(float)
     """
     # TODO: 你的程式碼
-    pass
+    df_clean = df.copy()
+    df_clean['amount'] = (
+    df_clean['amount']
+    .astype(str)
+    .str.replace('$', '', regex = False)
+    .str.replace(',', '', regex = False)
+    .astype(float)
+    )
+    return df_clean
+
 
 
 def yellow_drop_duplicates(df):
@@ -72,7 +87,8 @@ def yellow_drop_duplicates(df):
     提示：df.drop_duplicates()
     """
     # TODO: 你的程式碼
-    pass
+    df_duplicates = df.drop_duplicates()
+    return df_duplicates
 
 
 # ============================================================
@@ -93,4 +109,24 @@ 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_before = len(df)
+
+    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()
+    df_after = len(df)
+
+    print(f"清理之前{df_before},清理之後{df_after}")
+    print('-----------------------------')
+    return df

homework/m3_pandas_advanced.py

@@ -24,19 +24,24 @@ def green_load_and_merge():
     提示：pd.merge(how='left')
     """
     # TODO: 你的程式碼
-    pass
+    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.columns)
 
 
 # ============================================================
@@ -50,8 +55,8 @@ def yellow_top_category(df):
     提示：groupby('category')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
-
+    df_category = df.groupby('category')['amount'].sum()
+    return df_category.idxmax()
 
 def yellow_gold_vip_stats(df):
     """
@@ -60,7 +65,10 @@ def yellow_gold_vip_stats(df):
     提示：df[df['vip_level'] == 'Gold']
     """
     # TODO: 你的程式碼
-    pass
+    gold = df[df['vip_level'] == 'Gold']
+    gold_count = len(gold)
+    gold_total = gold['amount'].sum()
+    return (gold_count, gold_total)
 
 
 def yellow_region_avg_amount(df):
@@ -70,7 +78,13 @@ 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 +108,16 @@ 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(
+            r = ('order_date', 'max'),
+            f = ('order_id', 'count'),
+            m = ('amount', 'sum'),
+        )
+        .reset_index()
+        .sort_values('m', ascending=False)
+        .head(5)
+    )
+
+    return rfm

homework/m4_timeseries.py

@@ -27,7 +27,12 @@ def green_avg_by_month():
     提示：df['order_date'].dt.month
     """
     # TODO: 你的程式碼
-    pass
+    avg_month = (
+        df.groupby(df['order_date'].dt.month)['amount']
+        .mean()
+        .round(2)
+    )
+    return avg_month
 
 
 def green_top3_dates():
@@ -37,7 +42,9 @@ def green_top3_dates():
     提示：value_counts().head(3)
     """
     # TODO: 你的程式碼
-    pass
+    top3_dates = df['order_date'].dt.date.value_counts().head(3)
+    return top3_dates
+
 
 
 def green_date_range():
@@ -46,7 +53,9 @@ def green_date_range():
     格式為 pandas Timestamp
     """
     # TODO: 你的程式碼
-    pass
+    earliest = df['order_date'].min()
+    latest = df['order_date'].max()
+    return (earliest, latest)
 
 
 # ============================================================
@@ -60,7 +69,10 @@ def yellow_monthly_revenue():
     提示：set_index('order_date').resample('ME')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
+    monthly_revenue = (
+        df.set_index('order_date').resample('ME')['amount'].sum()
+    )
+    return monthly_revenue
 
 
 def yellow_rolling_avg(monthly_revenue):
@@ -71,7 +83,8 @@ 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 +94,13 @@ def yellow_category_median(df):
     提示：groupby + median + sort_values
     """
     # TODO: 你的程式碼
-    pass
+    category_median = (
+        df.groupby('category')['amount']
+        .mean()
+        .round(1)
+        .sort_values(ascending=False)
+    )
+    return category_median
 
 
 # ============================================================
@@ -101,4 +120,25 @@ def red_monthly_report():
     提示：resample + agg + pct_change
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    df = df.set_index('order_date')
+
+    monthly_report = (
+        df.resample('ME')
+        .agg(
+            總訂單數 = ('order_id', 'count'),
+            總營收 = ('amount', 'sum'),
+            活躍客戶數 = ('customer_id', 'nunique'),
+        )
+        .sort_index()
+    )
+
+    monthly_report['客單價'] = (
+        monthly_report['總營收']/monthly_report['總訂單數']
+    ).round(1)
+
+    monthly_report['月營收成長率'] = (
+        monthly_report['總營收'].pct_change() * 100
+    ).round(2)
+
+    return monthly_report