M1 作業 — 施善鏹

homework/m1_numpy.py

@@ -19,19 +19,24 @@
 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])
+    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])
+    mask = arr > 25
+    return arr[mask]
 
 
 # ============================================================
@@ -42,7 +47,8 @@ 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 int(mask.sum())
 
 
 def yellow_top3_stock_indices(stocks):
@@ -51,7 +57,8 @@ def yellow_top3_stock_indices(stocks):
     提示：np.argsort
     """
     # TODO: 你的程式碼
-    pass
+    stocks2 = np.argsort(stocks)# 這部分說的是按照庫存排序 並返回的是 index值不是排序的數值 
+    return stocks2[::-1][:3]
 
 
 def yellow_restock_cost(prices, stocks):
@@ -60,7 +67,11 @@ def yellow_restock_cost(prices, stocks):
     提示：布林遮罩 + .sum()
     """
     # TODO: 你的程式碼
-    pass
+    prices_mask = prices < 500
+    cheap_prices = prices[prices_mask]           
+    cheap_prices_stocks = cheap_prices * 50
+    total_cheap_prices_stocks = cheap_prices_stocks.sum()
+    return total_cheap_prices_stocks
 
 
 # ============================================================
@@ -77,4 +88,7 @@ def red_double11_prices(prices, stocks):
     提示：np.where 可以巢狀使用
     """
     # TODO: 你的程式碼
-    pass
+    prices_11 = np.where(stocks >= 100, prices * 0.7, 
+                         np.where((stocks >= 20) & (stocks <=99), prices*0.9, prices))
+    return prices_11
+

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
+    ras = pd.read_csv('datasets/ecommerce/orders_raw.csv')
+
+    return ras
 
 
 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):
@@ -38,7 +40,7 @@ def green_dtypes(df):
     提示：df.dtypes
     """
     # TODO: 你的程式碼
-    pass
+    return df.dtypes
 
 
 # ============================================================
@@ -52,7 +54,9 @@ 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
 
 
 def yellow_clean_amount(df):
@@ -63,7 +67,11 @@ def yellow_clean_amount(df):
     提示：.str.replace() + .astype(float)
     """
     # TODO: 你的程式碼
-    pass
+    new_df = df.copy()
+    new_df['amount'] = new_df['amount'].astype(str).str.replace('$', '', regex=False)
+    new_df['amount'] = new_df['amount'].astype(str).str.replace(',', '', regex=False).astype(float)
+
+    return new_df
 
 
 def yellow_drop_duplicates(df):
@@ -72,7 +80,10 @@ def yellow_drop_duplicates(df):
     提示：df.drop_duplicates()
     """
     # TODO: 你的程式碼
-    pass
+    new_df = df.copy()
+    new_df = new_df.drop_duplicates()
+
+    return new_df
 
 
 # ============================================================
@@ -93,4 +104,13 @@ def red_clean_orders(path):
     提示：pd.to_datetime(errors='coerce')
     """
     # TODO: 你的程式碼
-    pass
+    df = pd.read_csv(path)
+    new_df = df.copy()
+    new_df.columns = new_df.columns.str.strip().str.lower()
+    new_df['amount'] = new_df['amount'].astype(str).str.replace('$','',regex=False)
+    new_df['amount'] = new_df['amount'].astype(str).str.replace(',','',regex=False).astype(float)
+    new_df['order_date'] = pd.to_datetime(new_df['order_date'],errors='coerce')
+    new_df = new_df.dropna(subset= ['order_date'])
+    new_df = new_df.dropna(subset= ['amount'])
+    new_df = new_df.drop_duplicates()
+    return new_df

homework/m3_pandas_advanced.py

@@ -24,19 +24,28 @@ 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',parse_dates=['order_date'])
+    customers =pd.read_csv('../datasets/ecommerce/customers.csv')
+    products =pd.read_csv('../datasets/ecommerce/products.csv')
+
+    full = (
+        orders
+        .merge(customers, on= 'customer_id', how= 'left')
+        .merge(products, on='product_id',how='left')
+    )
+    return full
 
 
 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)
 
 
 # ============================================================
@@ -50,7 +59,9 @@ def yellow_top_category(df):
     提示：groupby('category')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
+    category_amount = df.groupby('category')['amount'].sum()
+    best_category_amount =category_amount.idxmax()
+    return best_category_amount
 
 
 def yellow_gold_vip_stats(df):
@@ -60,7 +71,11 @@ def yellow_gold_vip_stats(df):
     提示：df[df['vip_level'] == 'Gold']
     """
     # TODO: 你的程式碼
-    pass
+    gold_vip = df[df['vip_level'] == 'Gold']
+    order_count = len(gold_vip)
+    total_amount = gold_vip['amount'].sum
+
+    return(order_count, total_amount)
 
 
 def yellow_region_avg_amount(df):
@@ -70,7 +85,8 @@ 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()
+    return region_mean
 
 
 # ============================================================
@@ -94,4 +110,11 @@ def red_rfm_top5(df):
     提示：groupby('customer_id').agg(...)
     """
     # TODO: 你的程式碼
-    pass
+    rfm = df.groupby('customer_id').agg(customer_name=('customer_name','first'),
+                                       R = ('order_date','max'),
+                                       F = ('order_id','count'),
+                                       M = ('amount','sum'))
+    rfm = rfm.sort_values('M',ascending=False)
+    rfm = rfm.reset_index()
+    top5 = rfm.head()
+    return top5

homework/m4_timeseries.py

@@ -27,8 +27,13 @@ def green_avg_by_month():
     提示：df['order_date'].dt.month
     """
     # TODO: 你的程式碼
-    pass
-
+    df = _load_data()
+    df['year'] = df['order_date'].dt.year
+    df['month']= df['order_date'].dt.month
+    df['weekday'] = df['order_date'].dt.day_name()
+    df['year_month'] = df['order_date'].dt.to_period('M')
+    month_avg_amount = df.groupby('month')['amount'].mean()
+    return month_avg_amount
 
 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
+    df = _load_data()
+    top3_dates = df['order_date'].value_counts().head(3)
+    return top3_dates
 
 
 def green_date_range():
@@ -46,7 +53,8 @@ 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())
 
 
 # ============================================================
@@ -60,19 +68,23 @@ def yellow_monthly_revenue():
     提示：set_index('order_date').resample('ME')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    ts = df.set_index('order_date')
+    month_sum_amount = ts.resample('ME')['amount'].sum()
+
+    return month_sum_amount
 
 
 def yellow_rolling_avg(monthly_revenue):
+
     """
     計算 3 個月移動平均
     接收 yellow_monthly_revenue() 的結果作為輸入
     回傳 Series（同樣 index，values=移動平均，前 2 筆可為 NaN）
     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):
     """
@@ -81,7 +93,9 @@ def yellow_category_median(df):
     提示：groupby + median + sort_values
     """
     # TODO: 你的程式碼
-    pass
+    category_order_median = df.groupby('category')['amount'].median()
+    category_order_median = category_order_median.sort_values(ascending =False)
+    return category_order_median
 
 
 # ============================================================
@@ -101,4 +115,13 @@ def red_monthly_report():
     提示：resample + agg + pct_change
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    ts = df.set_index('order_date')
+    report = ts.resample('ME').agg(
+        order_count=('order_id', 'count'),
+        revenue=('amount', 'sum'),
+        active_customers=('customer_id', 'nunique'),
+    )
+    report['avg_order_value'] = (report['revenue'] / report['order_count']).round(2)
+    report['revenue_growth'] = (report['revenue'].pct_change()*100.).round(2)
+    return report