Skip to content

完成作業繳交 - 黃樺裕 - AIPE08 #17

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
cdexswzaq0110 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

完成作業繳交 - 黃樺裕 - AIPE08 #17

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 14 additions & 14 deletions homework/m1_numpy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,20 +18,20 @@

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]


# ============================================================
Expand All @@ -41,26 +41,23 @@ 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
return (prices > 1000).sum()


def yellow_top3_stock_indices(stocks):
"""
回傳庫存最多的前 3 個商品的索引位置 (ndarray, 由大到小排)
提示：np.argsort
"""
# TODO: 你的程式碼
pass
return np.argsort(stocks)[-3:][::-1]


def yellow_restock_cost(prices, stocks):
"""
單價 < 500 的商品，每種各進貨 50 個，回傳總花費 (float/int)
提示：布林遮罩 + .sum()
"""
# TODO: 你的程式碼
pass
return (prices[prices < 500] * 50).sum()


# ============================================================
Expand All @@ -76,5 +73,8 @@ def red_double11_prices(prices, stocks):
回傳每個商品的雙 11 售價 (ndarray)
提示：np.where 可以巢狀使用
"""
# TODO: 你的程式碼
pass
return np.where(
stocks >= 100,
prices * 0.7,
np.where(stocks >= 20, prices * 0.9, prices)
)
57 changes: 41 additions & 16 deletions homework/m2_pandas_cleaning.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
資料路徑：datasets/ecommerce/orders_raw.csv
"""
import pandas as pd

DATA = '../datasets/ecommerce/orders_raw.csv'

# ============================================================
# 🟢 送分題（每題 10 分，共 30 分）
Expand All @@ -19,26 +19,23 @@ def green_read_csv():
讀取 orders_raw.csv，回傳原始 DataFrame（不做任何清理）
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):
"""
回傳 DataFrame 的 (列數, 欄數) tuple
提示：df.shape
"""
# TODO: 你的程式碼
pass
print('原始形狀:', df.shape)
return df.shape


def green_dtypes(df):
"""
回傳 DataFrame 的欄位型別 (Series)
提示：df.dtypes
"""
# TODO: 你的程式碼
pass
return df.dtypes


# ============================================================
Expand All @@ -51,8 +48,8 @@ def yellow_clean_columns(df):
回傳清理後的 DataFrame（不要修改原始 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):
Expand All @@ -62,17 +59,22 @@ def yellow_clean_amount(df):
回傳清理後的 DataFrame（不要修改原始 df）
提示：.str.replace() + .astype(float)
"""
# TODO: 你的程式碼
pass
df['amount'] = (
df['amount']
.astype(str)
.str.replace('$', '', regex=False)
.str.replace(',', '', regex=False)
.astype(float)
)
return 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()


# ============================================================
Expand All @@ -92,5 +94,28 @@ def red_clean_orders(path):
回傳：清理後的 DataFrame
提示：pd.to_datetime(errors='coerce')
"""
# TODO: 你的程式碼
pass
# 1.
df = pd.read_csv(path)

# 2.
df.columns = df.columns.str.strip().str.lower()

# 3.
df['amount'] = (
df['amount']
.astype(str)
.str.replace('$', '', regex=False)
.str.replace(',', '', regex=False)
.astype(float)
)

# 4.
df['order_date'] = pd.to_datetime(df['order_date'], errors='coerce')

# 5.
df = df.dropna(subset=['order_date']).dropna(subset=['amount'])

# 6.
df = df.drop_duplicates()

return df
76 changes: 62 additions & 14 deletions homework/m3_pandas_advanced.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,20 +23,25 @@ def green_load_and_merge():
- 再 LEFT JOIN products.csv ON product_id
提示：pd.merge(how='left')
"""
# TODO: 你的程式碼
pass
DATA = 'datasets/ecommerce'
orders = pd.read_csv(f'{DATA}/orders_clean.csv', parse_dates=['order_date'])
customers = pd.read_csv(f'{DATA}/customers.csv')
products = pd.read_csv(f'{DATA}/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
# PS:df.shape[1]欄位數
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
return list(df.columns)


# ============================================================
Expand All @@ -49,8 +54,12 @@ def yellow_top_category(df):
回傳該類別名稱 (str)
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):
Expand All @@ -59,8 +68,10 @@ def yellow_gold_vip_stats(df):
回傳 tuple: (訂單數 int, 總金額 float)
提示：df[df['vip_level'] == 'Gold']
"""
# TODO: 你的程式碼
pass
gold = df[df['vip_level'] == 'Gold']
gold_stat = gold['amount'].agg(['count', 'sum'])

return (int(gold_stat['count']), float(gold_stat['sum']))


def yellow_region_avg_amount(df):
Expand All @@ -69,8 +80,14 @@ def yellow_region_avg_amount(df):
回傳 Series（index=region, values=平均金額）
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


# ============================================================
Expand All @@ -93,5 +110,36 @@ 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'),
)
.reset_index()
)

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')

top5 = (
rfm[['customer_id', 'customer_name', 'R', 'F', 'M']]
.sort_values('M', ascending=False)
.head(5)
.reset_index(drop=True)
)

return top5
Loading
Loading