完成作業繳交-林妤軒-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
+    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])
+    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
+    prices_arr = np.array(prices)
+    return len(prices_arr[prices_arr > 1000])
 
 
 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_arr = np.array(stocks)
+    stocks_arr = np.argsort(stocks)[::-1]
+    return stocks_arr[: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
+    total = prices[prices < 500] *50
+    return total.sum()
 
 
 # ============================================================
@@ -77,4 +84,8 @@ def red_double11_prices(prices, stocks):
     提示：np.where 可以巢狀使用
     """
     # TODO: 你的程式碼
-    pass
+    prices_07 = prices[stocks >= 100] * 0.7
+    prices_09 = prices[(stocks >= 20) & (stocks < 100)] * 0.9
+    prices_original = prices[stocks < 20]
+    final_price = np.concatenate([prices_original, prices_07, prices_09])
+    return final_price

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
+    DATA = "/datasets/ecommerce/orders_raw.csv"
+    df = pd.read_csv(DATA)
+    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 +41,8 @@ def green_dtypes(df):
     提示：df.dtypes
     """
     # TODO: 你的程式碼
-    pass
+
+    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.columns = df.columns.str.strip().str.lower()
+    return df
 
 
 def yellow_clean_amount(df):
@@ -63,7 +69,12 @@ def yellow_clean_amount(df):
     提示：.str.replace() + .astype(float)
     """
     # TODO: 你的程式碼
-    pass
+    arr = (df['amount']
+                .astype(str)
+                .str.replace('$', '', regex=False)
+                .str.replace(',', '', regex=False)
+                .astype(float))
+    return arr
 
 
 def yellow_drop_duplicates(df):
@@ -72,7 +83,9 @@ def yellow_drop_duplicates(df):
     提示：df.drop_duplicates()
     """
     # TODO: 你的程式碼
-    pass
+
+    arr = df.drop_duplicates()
+    return arr
 
 
 # ============================================================
@@ -93,4 +106,16 @@ 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'])
+    df['qty'] = df['qty'].fillna(df['qty'].median())
+    df = df.drop_duplicates()
+    return df

homework/m3_pandas_advanced.py

@@ -24,19 +24,42 @@ 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
+    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.shape[0]
 
 
 def green_column_list(df):
     """回傳 DataFrame 的所有欄位名稱 (list)"""
     # 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.columns
 
 
 # ============================================================
@@ -50,7 +73,9 @@ def yellow_top_category(df):
     提示：groupby('category')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
+
+    amount = df.groupby('category')['amount'].sum().sort_values(ascending=False).head(1)
+    return amount
 
 
 def yellow_gold_vip_stats(df):
@@ -60,7 +85,12 @@ def yellow_gold_vip_stats(df):
     提示：df[df['vip_level'] == 'Gold']
     """
     # TODO: 你的程式碼
-    pass
+
+    vip = df[df['vip_level'] == 'Gold']
+    vip_sum = len(vip['order_id'])
+    vip_amount = float(vip['amount'].sum())
+    Gold_Vip = (vip_sum, vip_amount)
+    return Gold_Vip
 
 
 def yellow_region_avg_amount(df):
@@ -70,7 +100,9 @@ def yellow_region_avg_amount(df):
     提示：groupby('region')['amount'].mean()
     """
     # TODO: 你的程式碼
-    pass
+
+    Series = df.groupby('region')['amount'].mean()
+    return Series
 
 
 # ============================================================
@@ -94,4 +126,38 @@ def red_rfm_top5(df):
     提示：groupby('customer_id').agg(...)
     """
     # 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")
+    # R = orders.groupby('customer_id')['order_date'].max()
+    # F = orders.groupby('customer_id')['order_id'].count()
+    # M = orders.groupby('customer_id')['amount'].sum().sort_values(ascending=False).head()
+    # df = (
+    #             orders
+    #             .merge(customers, on = 'customer_id', how='left')
+    #             .merge(products, on = 'product_id', how='left')
+    #     )
+    RFM = (
+    orders.groupby('customer_id')
+    .agg(
+        recency = ('order_date', 'max'),
+        frequency = ('order_id', 'count'),
+        monetary = ('amount', 'sum'),
+    )
+    .reset_index()
+)
+    rfm_named = RFM.merge(
+    customers[['customer_id', 'customer_name']],
+    on = 'customer_id',
+    how='left',
+)
+
+    final_5 = (
+    rfm_named
+    .sort_values("M", ascending=False)
+    .head(5)
+    .reset_index(drop=True)
+    [['customer_id', 'customer_name', 'R', 'F', 'M']]
+)
+
+    return final_5

homework/m4_timeseries.py

@@ -27,7 +27,11 @@ def green_avg_by_month():
     提示：df['order_date'].dt.month
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+
+    result = df.groupby(df["order_date"].dt.month)['amount'].mean().round(1)
+
+    return result
 
 
 def green_top3_dates():
@@ -37,7 +41,9 @@ def green_top3_dates():
     提示：value_counts().head(3)
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    top3 = df['order_date'].dt.date.value_counts().head(3)
+    return top3
 
 
 def green_date_range():
@@ -46,7 +52,11 @@ def green_date_range():
     格式為 pandas Timestamp
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    time_1 = df['order_date'].min()
+    time_2 = df['order_date'].max()
+    result = (time_1, time_2)
+    return result
 
 
 # ============================================================
@@ -60,7 +70,9 @@ def yellow_monthly_revenue():
     提示：set_index('order_date').resample('ME')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    test = df.set_index('order_date').resample('ME')['amount'].sum()
+    return test
 
 
 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
+
+    return monthly_revenue.rolling(window=3).mean()
 
 
 def yellow_category_median(df):
@@ -81,7 +94,8 @@ def yellow_category_median(df):
     提示：groupby + median + sort_values
     """
     # TODO: 你的程式碼
-    pass
+
+    return df.groupby('category')['amount'].median().sort_values(ascending=False)
 
 
 # ============================================================
@@ -101,4 +115,18 @@ def red_monthly_report():
     提示：resample + agg + pct_change
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    df['year_mon'] = df['order_date'].dt.to_period('M')
+    monthly_report = (df.groupby('year_mon')
+                      .agg(
+                        當月訂單數 = ('order_id', 'count'),
+                        當月總營收 = ('amount', 'sum'),
+                        單月不重複客戶數 = ('customer_id', 'nunique'),
+                      )
+                      .sort_index()
+                      )
+    monthly_report['客單價'] = (monthly_report['當月總營收'] / monthly_report['當月訂單數'])
+    monthly_report['月營收成長率'] = (monthly_report['當月總營收'].pct_change()*100)
+    monthly_report = monthly_report.reset_index().rename(columns={'year_mon' : '月份'})
+    monthly_report['月份'] = monthly_report['月份'].astype(str)
+    return monthly_report