Pandas中Series序列的具体实现

import pandas as pd
import numpy as np
# 方式1：从列表创建（默认整数索引 0,1,2...）
scores = [85, 92, 78, 90, 88]
s1 = pd.Series(scores)
print("从列表创建的Series：")
print(s1)
# 方式2：指定自定义索引
names = ["小明", "小红", "小刚", "小丽", "小强"]
s2 = pd.Series(scores, index=names)
print("\n指定索引的Series：")
print(s2)
# 方式3：从NumPy数组创建
arr = np.array([15.2, 16.1, 14.8, 15.5])
s3 = pd.Series(arr, index=["1月", "2月", "3月", "4月"], name="月均温度")
print("\n带名称的Series：")
print(s3)

import pandas as pd
# 字典：键=姓名，值=分数
score_dict = {"小明":85, "小红":92, "小刚":78, "小丽":90}
s4 = pd.Series(score_dict)
print("从字典创建的Series：")
print(s4)

import pandas as pd
import numpy as np
# 含NaN的Series（缺失值）
s5 = pd.Series([85, np.nan, 92, 78, np.nan], index=["小明", "小红", "小刚", "小丽", "小强"])
print("含缺失值的Series：")
print(s5)

import pandas as pd
s = pd.Series([85, 92, 78, 90], index=["小明", "小红", "小刚", "小丽"])
# 取值：通过标签
print("小红的分数：", s["小红"])  # 92
# 赋值：通过标签
s["小刚"] = 80
print("\n修改小刚分数后：")
print(s)
# 多标签取值（返回新Series）
print("\n小明和小丽的分数：")
print(s[["小明", "小丽"]])

import pandas as pd
s = pd.Series([85, 92, 78, 90], index=["小明", "小红", "小刚", "小丽"])
# 直接用整数（简易写法）
print("第2个元素（位置1）：", s[1])  # 92
# 用iloc（明确位置索引，推荐）
print("第4个元素（位置3）：", s.iloc[3])  # 90
# 位置切片
print("\n位置0-2的元素：")
print(s.iloc[0:3])

import pandas as pd
s = pd.Series([85, 92, 78, 90, 88], index=["小明", "小红", "小刚", "小丽", "小强"])
# 筛选分数≥90的元素
high_score = s[s >= 90]
print("90分以上的学生：")
print(high_score)
# 筛选分数在80-90之间的元素
mid_score = s[(s >= 80) & (s < 90)]
print("\n80-90分的学生：")
print(mid_score)

import pandas as pd
import numpy as np
s = pd.Series([85, np.nan, 92, 78], index=["小明", "小红", "小刚", "小丽"], name="分数")
print("底层数组：", s.values)
print("索引：", s.index)
print("数据类型：", s.dtype)
print("形状：", s.shape)
print("名称：", s.name)
print("缺失值判断：")
print(s.isnull())

import pandas as pd
import numpy as np
s = pd.Series([85, np.nan, 92, 78, 90], index=["小明", "小红", "小刚", "小丽", "小强"])
# 基础统计
print("均值（自动忽略NaN）：", s.mean())  # 86.25
print("中位数：", s.median())            # 87.5
print("最大值/最小值：", s.max(), "/", s.min())  # 92 / 78
print("标准差：", s.std())              # 6.18...
# 描述性统计（一键生成）
print("\n描述性统计：")
print(s.describe())

import pandas as pd
import numpy as np
s = pd.Series([85, np.nan, 92, 78, np.nan], index=["小明", "小红", "小刚", "小丽", "小强"])
# 1. 删除缺失值
s_drop = s.dropna()
print("删除缺失值后：")
print(s_drop)
# 2. 填充缺失值（均值/中位数/固定值）
s_fill_mean = s.fillna(s.mean())  # 均值填充
s_fill_0 = s.fillna(0)            # 固定值填充
print("\n均值填充缺失值：")
print(s_fill_mean)

import pandas as pd
s = pd.Series([85, 92, 78, 90], index=["小明", "小红", "小刚", "小丽"])
# 按值升序排序
s_sort_val = s.sort_values()
print("按分数升序：")
print(s_sort_val)
# 按索引降序排序
s_sort_idx = s.sort_index(ascending=False)
print("\n按姓名降序：")
print(s_sort_idx)

import pandas as pd
s = pd.Series([85, 92, 78, 59, 90], index=["小明", "小红", "小刚", "小亮", "小丽"])
# 替换单个值（不及格→60）
s_replace = s.replace(59, 60)
print("替换不及格分数后：")
print(s_replace)
# 映射（分数→等级）
grade_map = {x: "优秀" if x>=90 else "良好" if x>=80 else "及格" for x in s}
s_grade = s.map(grade_map)
print("\n分数映射为等级：")
print(s_grade)

import pandas as pd
import numpy as np
# 1. Series → NumPy数组
s = pd.Series([85, 92, 78, 90], index=["小明", "小红", "小刚", "小丽"])
arr = s.values
print("Series转数组：", arr)  # [85 92 78 90]
# 2. Series → 列表
lst = s.tolist()
print("Series转列表：", lst)  # [85, 92, 78, 90]
# 3. NumPy数组 → Series
arr2 = np.array([15.2, 16.1, 14.8])
s2 = pd.Series(arr2, index=["1月", "2月", "3月"])
print("\n数组转Series：")
print(s2)
# 4. 列表 → Series
lst2 = [88, 76, 95]
s3 = pd.Series(lst2, index=["小强", "小芳", "小伟"])
print("\n列表转Series：")
print(s3)

import pandas as pd
import numpy as np
# 创建日期索引的Series（7天温度）
dates = pd.date_range(start="2026-01-01", periods=7)
temp = pd.Series(np.random.normal(5, 3, 7).round(1), index=dates, name="日温")
# 查看数据
print("7天温度数据：")
print(temp)
# 筛选1月3日之后的温度
print("\n1月3日之后的温度：")
print(temp[temp.index >= "2026-01-03"])
# 计算周平均温度
print("\n周平均温度：", temp.mean())

import pandas as pd
import numpy as np
# 模拟学生分数（含缺失值）
scores = pd.Series([85, np.nan, 92, 78, np.nan, 88, 95], 
                   index=["小明", "小红", "小刚", "小丽", "小强", "小芳", "小伟"])
# 步骤1：统计缺失值数量
nan_count = scores.isnull().sum()
print("缺失值数量：", nan_count)
# 步骤2：用中位数填充缺失值
scores_filled = scores.fillna(scores.median())
print("\n填充后的分数：")
print(scores_filled)
# 步骤3：筛选优秀学生（≥90）
excellent = scores_filled[scores_filled >= 90]
print("\n优秀学生：")
print(excellent)