Python Pandas学习之Pandas数据结构详解

目录

• 1Pandas介绍
• 2Pandas数据结构
• 2.1Series
• 2.2DataFrame

# 导入pandas
import pandas as pd

pd.Series(data=None, index=None, dtype=None)

pd.Series([6.7,5.6,3,10,2], index=[1,2,3,4,5])

color_count = pd.Series({"red":100, "blue":200, "green": 500, "yellow":1000})
color_count

color_count.index

# 结果
Index(["blue", "green", "red", "yellow"], dtype="object")

color_count.values

# 结果
array([ 200,  500,  100, 1000])

color_count[2]

# 结果
100

# 导入pandas
import pandas as pd

pd.DataFrame(data=None, index=None, columns=None)

# 生成10名同学，5门功课的数据
score = np.random.randint(40, 100, (10, 5))

# 结果
array([[46, 93, 49, 70, 53],
       [42, 86, 65, 50, 87],
       [41, 74, 44, 87, 64],
       [62, 57, 45, 46, 86],
       [82, 46, 72, 85, 63],
       [82, 77, 61, 55, 41],
       [48, 41, 48, 52, 58],
       [90, 53, 95, 96, 78],
       [77, 49, 51, 76, 56],
       [79, 91, 75, 95, 66]])

# 使用Pandas中的数据结构
score_df = pd.DataFrame(score)

# 构造行索引序列
subjects = ["语文", "数学", "英语", "物理", "化学"]

# 构造列索引序列
stu = ["同学" + str(i) for i in range(score.shape[0])]

# 添加行索引
data = pd.DataFrame(score, columns=subjects, index=stu)

data.shape

# 结果
(10, 5)

data.index

# 结果
Index(["同学0", "同学1", "同学2", "同学3", "同学4", "同学5", "同学6", "同学7", "同学8", "同学9"], dtype="object")

data.columns

# 结果
Index(["语文", "数学", "英语", "政治", "体育"], dtype="object")

data.values

array([[46, 93, 49, 70, 53],
       [42, 86, 65, 50, 87],
       [41, 74, 44, 87, 64],
       [62, 57, 45, 46, 86],
       [82, 46, 72, 85, 63],
       [82, 77, 61, 55, 41],
       [48, 41, 48, 52, 58],
       [90, 53, 95, 96, 78],
       [77, 49, 51, 76, 56],
       [79, 91, 75, 95, 66]])

data.T

data.head(5)

data.tail(5)

stu = ["学生_" + str(i) for i in range(score_df.shape[0])]

# 必须整体全部修改
data.index = stu

# 错误修改方式
data.index[3] = "学生_3"  #  错误

# 重置索引,drop=False
data.reset_index()

df = pd.DataFrame({"month": [1, 4, 7, 10],
                    "year": [2012, 2014, 2013, 2014],
                    "sale":[55, 40, 84, 31]})
                    
 df = df.set_index(["year", "month"])