先讀懂資料：Python、NumPy 與 pandas 的最小工具箱

order_id,city,quantity,unit_price,delivery_minutes
1001,台北,2,100,14
1002,台中,1,200,18
1003,高雄,3,100,21
1004,台北,2,150,17
1005,台中,1,200,

python3 -m venv .venv
. .venv/bin/activate
python -m pip install numpy==1.26.3 pandas==2.2.2
python lesson.py

py -3.10 -m venv .venv
.\.venv\Scripts\python.exe -m pip install numpy==1.26.3 pandas==2.2.2
.\.venv\Scripts\python.exe lesson.py

import numpy as np
import pandas as pd

df = pd.read_csv("orders.csv", dtype={"order_id": "string"})
print("原始形狀：", df.shape)
print(df.head().to_string(index=False))
print("缺失數：", df.isna().sum().to_dict())

print("Series：", df["quantity"].shape)
print("DataFrame：", df[["quantity"]].shape)

print(df[["order_id", "city"]].to_string(index=False))

taipei = df["city"] == "台北"
print("逐列條件：", taipei.tolist())
print(df.loc[taipei].to_string(index=False))

print(df.loc[taipei, ["order_id", "quantity"]].to_string(index=False))

print("清單相加：", [1, 2] + [1, 1])
a = np.array([1, 2])
b = np.array([1, 1])
print("陣列相加：", (a + b).tolist())

df["amount"] = df["quantity"] * df["unit_price"]
print("每筆金額：", df["amount"].tolist())
print("總金額：", int(df["amount"].sum()))
print("各城市金額：", df.groupby("city")["amount"].sum().to_dict())

large_orders = df.loc[df["amount"] >= 300, ["order_id", "city", "amount"]]
print(large_orders.to_string(index=False))

data = np.array([1, 2, 3])
print("第一項：", int(data[0]))
print("前兩項：", data[:2].tolist())
print("從第二項起：", data[1:].tolist())

first_two = data[:2].copy()
first_two[0] = 99
print("原陣列仍是：", data.tolist())
print("最大／最小／總和：", int(data.max()), int(data.min()), int(data.sum()))

matrix = np.array([[1, 2], [3, 4], [5, 6]])
print("二維形狀：", matrix.shape)
print("第一列第二欄：", int(matrix[0, 1]))
print("前兩列的第一欄：", matrix[:2, 0].tolist())

print("轉置：", matrix.T.tolist())

print("重新塑形：", matrix.reshape(2, 3).tolist())

known = df["delivery_minutes"].notna()
print("已知配送時間筆數：", int(known.sum()))
print("已知資料平均分鐘：", float(df["delivery_minutes"].mean()))

BSD 3-Clause License

Copyright (c) 2008-2011, AQR Capital Management, LLC, Lambda Foundry, Inc. and PyData Development Team
All rights reserved.

Copyright (c) 2011-2026, Open source contributors.

Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:

* Redistributions of source code must retain the above copyright notice, this
  list of conditions and the following disclaimer.

* Redistributions in binary form must reproduce the above copyright notice,
  this list of conditions and the following disclaimer in the documentation
  and/or other materials provided with the distribution.

* Neither the name of the copyright holder nor the names of its
  contributors may be used to endorse or promote products derived from
  this software without specific prior written permission.

THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.