完成作業繳交 - 陳峙宏 - AIPE03

homework/m2_pandas_cleaning.py

@@ -20,16 +20,17 @@ def green_read_csv():
     提示：pd.read_csv()
     """
     # TODO: 你的程式碼
-    pass
-
+def green_read_csv():
+    return pd.read_csv("datasets/ecommerce/orders_raw.csv")
 
 def green_shape(df):
     """
     回傳 DataFrame 的 (列數, 欄數) tuple
     提示：df.shape
     """
     # TODO: 你的程式碼
-    pass
+def green_shape(df):
+    return df.shape
 
 
 def green_dtypes(df):
@@ -38,7 +39,8 @@ def green_dtypes(df):
     提示：df.dtypes
     """
     # TODO: 你的程式碼
-    pass
+def green_dtypes(df):
+    return df.dtypes
 
 
 # ============================================================
@@ -52,8 +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):
     """
@@ -63,17 +66,22 @@ 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"]
+        .str.replace("$", "", regex=False)
+        .str.replace(",", "", regex=False)
+        .astype(float)
+    )
+    return new_df
 
 def yellow_drop_duplicates(df):
     """
     移除完全重複的列，回傳去重後的 DataFrame
     提示：df.drop_duplicates()
     """
     # TODO: 你的程式碼
-    pass
-
+    return df.drop_duplicates()
 
 # ============================================================
 # 🔴 挑戰題（25 分）
@@ -93,4 +101,16 @@ 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"]
+        .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()
+
+    return df

homework/m3_pandas_advanced.py

@@ -24,19 +24,26 @@ 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 = pd.merge(orders, customers, on="customer_id", how="left")
+    df = pd.merge(df, 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 df.columns.tolist()
 
 
 # ============================================================
@@ -50,7 +57,7 @@ def yellow_top_category(df):
     提示：groupby('category')['amount'].sum()
     """
     # TODO: 你的程式碼
-    pass
+    return df.groupby("category")["amount"].sum().idxmax()
 
 
 def yellow_gold_vip_stats(df):
@@ -60,7 +67,10 @@ 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)
+    total_amount = gold_df["amount"].sum()
+    return (order_count, total_amount)
 
 
 def yellow_region_avg_amount(df):
@@ -70,7 +80,7 @@ def yellow_region_avg_amount(df):
     提示：groupby('region')['amount'].mean()
     """
     # TODO: 你的程式碼
-    pass
+    return df.groupby("region")["amount"].mean()
 
 
 # ============================================================
@@ -94,4 +104,18 @@ def red_rfm_top5(df):
     提示：groupby('customer_id').agg(...)
     """
     # TODO: 你的程式碼
-    pass
+    df = df.copy()
+    df["order_date"] = pd.to_datetime(df["order_date"], errors="coerce")
+
+    rfm = df.groupby("customer_id").agg(
+        R=("order_date", "max"),
+        F=("order_id", "count"),
+        M=("amount", "sum")
+    ).reset_index()
+
+    names = df[["customer_id", "customer_name"]].drop_duplicates()
+    rfm = pd.merge(rfm, names, on="customer_id", how="left")
+    rfm = rfm.sort_values(by="M", ascending=False).head(5)
+    rfm = rfm[["customer_id", "customer_name", "R", "F", "M"]]
+
+    return rfm

homework/m4_timeseries.py

@@ -27,7 +27,8 @@ def green_avg_by_month():
     提示：df['order_date'].dt.month
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    return df.groupby(df["order_date"].dt.month)["amount"].mean()
 
 
 def green_top3_dates():
@@ -37,7 +38,8 @@ def green_top3_dates():
     提示：value_counts().head(3)
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    return df["order_date"].dt.date.value_counts().head(3)
 
 
 def green_date_range():
@@ -46,7 +48,8 @@ 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 +63,8 @@ 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 +75,7 @@ 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 +85,11 @@ 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 +109,4 @@ def red_monthly_report():
     提示：resample + agg + pct_change
     """
     # TODO: 你的程式碼
-    pass
+

homework/m5_visualization.py

@@ -11,7 +11,6 @@
 import pandas as pd
 import seaborn as sns
 
-
 def _load_data():
     """輔助函式：讀取資料"""
     return pd.read_csv("datasets/ecommerce/orders_enriched.csv",
@@ -29,7 +28,10 @@ def green_bar_category():
     提示：sns.countplot 或 value_counts().plot.bar()
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    fig, ax = plt.subplots()
+    sns.countplot(x="category", data=df, ax=ax)
+    return fig
 
 
 def green_hist_amount():
@@ -39,7 +41,10 @@ def green_hist_amount():
     提示：sns.histplot(bins=20) 或 plt.hist()
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    fig, ax = plt.subplots()
+    sns.histplot(df["amount"], bins=20, ax=ax)
+    return fig
 
 
 def green_set_labels():
@@ -51,8 +56,12 @@ def green_set_labels():
     回傳 matplotlib Figure 物件
     """
     # TODO: 你的程式碼
-    pass
-
+    fig, ax = plt.subplots()
+    ax.bar(["A", "B", "C"], [10, 20, 15])
+    ax.set_title("Sample Bar Chart")
+    ax.set_xlabel("Category")
+    ax.set_ylabel("Value")
+    return fig
 
 # ============================================================
 # 🟡 核心題（每題 15 分，共 45 分）
@@ -68,7 +77,20 @@ def yellow_line_region_trend():
     提示：分別 groupby 再 plot，或用 sns.lineplot(hue='region')
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+
+    monthly = (
+        df.set_index("order_date")
+        .groupby("region")
+        .resample("ME")["amount"]
+        .sum()
+        .reset_index()
+    )
+    monthly = monthly[monthly["region"].isin(["North", "South"])]
+    fig, ax = plt.subplots()
+    sns.lineplot(data=monthly, x="order_date", y="amount",
+                 hue="region", ax=ax)
+    return fig
 
 
 def yellow_box_vip():
@@ -78,7 +100,10 @@ def yellow_box_vip():
     提示：sns.boxplot(x='vip_level', y='amount', data=df)
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    fig, ax = plt.subplots()
+    sns.boxplot(x="vip_level", y="amount", data=df, ax=ax)
+    return fig
 
 
 def yellow_scatter_price_amount():
@@ -88,7 +113,10 @@ def yellow_scatter_price_amount():
     提示：plt.scatter() 或 sns.scatterplot()
     """
     # TODO: 你的程式碼
-    pass
+    df = _load_data()
+    fig, ax = plt.subplots()
+    sns.scatterplot(x="unit_price", y="amount", data=df, ax=ax)
+    return fig
 
 
 # ============================================================
@@ -107,4 +135,3 @@ def red_category_dashboard(category="Electronics"):
     提示：fig, axes = plt.subplots(2, 2, figsize=(14, 10))
     """
     # TODO: 你的程式碼
-    pass