Python进阶教程：数据分析入门（NumPy与Pandas）

1
import numpy as np
2

3
# 从列表创建
4
arr1 = np.array([1, 2, 3, 4, 5])
5
print(arr1, arr1.shape)  # [1 2 3 4 5] (5,)
6

7
# 二维数组
8
arr2 = np.array([[1, 2], [3, 4]])
9
print(arr2.shape)  # (2, 2)
10

11
# 常用创建方式
12
zeros = np.zeros((2, 3))     # 全 0
13
ones = np.ones((2, 2))       # 全 1
14
rand = np.random.rand(3)     # 随机数
15
range_arr = np.arange(0, 10, 2)  # [0 2 4 6 8]

1
import numpy as np
2

3
a = np.array([1, 2, 3])
4
b = np.array([4, 5, 6])
5

6
print(a + b)          # [5 7 9] 向量化运算，无需循环
7
print(a * 2)          # [2 4 6]
8
print(a ** 2)         # [1 4 9]
9
print(a.mean())       # 2.0 均值
10
print(a.sum())        # 6 求和
11
print(a.max())        # 3 最大值
12
print(np.dot(a, b))   # 32 点积

1
import pandas as pd
2

3
# Series：一维数据（带索引）
4
s = pd.Series([10, 20, 30], index=["a", "b", "c"])
5
print(s["b"])  # 20
6

7
# DataFrame：二维表格
8
data = {
9
    "姓名": ["张三", "李四", "王五"],
10
    "年龄": [20, 22, 21],
11
    "成绩": [88.5, 92.0, 95.5],
12
}
13
df = pd.DataFrame(data)
14
print(df)
15
print(df.shape)   # (3, 3)
16
print(df.columns) # 列名

1
import pandas as pd
2

3
# 读取 CSV 文件
4
# df = pd.read_csv("data.csv")
5

6
# 模拟数据
7
df = pd.DataFrame({
8
    "name": ["Alice", "Bob", "Charlie", "David"],
9
    "age": [25, 30, 35, 40],
10
    "salary": [50000, 60000, 70000, 80000],
11
})
12

13
print(df.head())          # 前 5 行
14
print(df.info())          # 数据概览
15
print(df.describe())      # 统计描述
16
print(df["age"].mean())   # 某列均值 32.5
17
print(df[df["salary"] > 60000])  # 条件筛选

1
import pandas as pd
2
import numpy as np
3

4
df = pd.DataFrame({
5
    "name": ["Alice", None, "Charlie"],
6
    "age": [25, None, 35],
7
    "score": [88, 92, None],
8
})
9

10
print(df.isnull().sum())   # 查看缺失值
11
df = df.dropna()           # 删除含缺失值的行
12
df = df.fillna(0)          # 或用 0 填充缺失值
13

14
# 新增计算列
15
df["age_plus"] = df["age"] + 1

1
import pandas as pd
2

3
df = pd.DataFrame({
4
    "部门": ["技术", "技术", "市场", "市场", "市场"],
5
    "员工": ["A", "B", "C", "D", "E"],
6
    "工资": [10000, 12000, 8000, 9000, 9500],
7
})
8

9
# 按部门分组求平均工资
10
grouped = df.groupby("部门")["工资"].mean()
11
print(grouped)
12
# 市场 8833.33
13
# 技术 11000.00
14

15
# 多列聚合
16
print(df.groupby("部门").agg({"工资": ["mean", "max", "sum"]}))

1
import pandas as pd
2

3
# 模拟一份销售数据
4
sales = pd.DataFrame({
5
    "日期": pd.date_range("2026-01-01", periods=30),
6
    "商品": [f"商品{i%3+1}" for i in range(30)],
7
    "销量": [20 + i % 7 * 5 for i in range(30)],
8
    "金额": [100 + i * 3 for i in range(30)],
9
})
10

11
print("=== 数据概览 ===")
12
print(sales.describe())
13

14
print("=== 各商品总销量 ===")
15
print(sales.groupby("商品")["销量"].sum())
16

17
print("=== 销量最高的 3 天 ===")
18
print(sales.nlargest(3, "销量")[["日期", "销量"]])
19

20
print("=== 总销售额 ===")
21
print(f"{sales["金额"].sum():.0f} 元")