Python开发之Pandas的简单使用（二）

前言：主要是Pandas的数据合并join、merge，Series的复合索引、DataFrame复合索引。

---

1.数据合并之join

代码：

import pandas as pd

t1 = pd.DataFrame({'V': [0, 0],
                   'W': [0, 0],
                   'X': [0, 0],
                   'Y': [0, 0],
                   'Z': [0, 0]}).astype("float")
t2 = pd.DataFrame({'0': [1, 1, 1],
                   '1': [1, 1, 1],
                   '2': [1, 1, 1],
                   '3': [1, 1, 1]}).astype("float")

print("t1:")
print(t1)
print("*"*100)
print("t2:")
print(t2)
print("*"*100)
print("t1.join(t2)")
print(t1.join(t2))
print("*"*100)
print("t2.join(t1)")
print(t2.join(t1))

输出：

2.数据合并之merge

代码：

import pandas as pd
t1 = pd.DataFrame({'M': [1.0, 1.0, 1.0],
                   'N': [1.0, 1.0, 1.0],
                   'O': ["a", "b", "c"],
                   'P': [1.0, 1.0, 1.0]})
t2 = pd.DataFrame({'V': [0.0, 0.0],
                   'W': [0.0, 0.0],
                   'X': ["c", "d"],
                   'Y': [0.0, 0.0],
                   'Z': [0.0, 0.0]})

print("t1:")
print(t1)
print("*"*100)
print("t2:")
print(t2)
print("*"*100)

#默认的合并方式inner，并集
print("t1.merge(t2):")
print(t1.merge(t2,left_on="O",right_on="X"))
print("*"*100)
print("t1.merge(t2,inner)")
print(t1.merge(t2,left_on="O",right_on="X",how="inner"))
print("*"*100)

#outer，交集，nan补全
print("t1.merge(t2,outer)")
print(t1.merge(t2,left_on="O",right_on="X",how="outer"))
print("*"*100)

#left，左边为准，nan补全
print("t1.merge(t2,left)")
print(t1.merge(t2,left_on="O",right_on="X",how="left"))
print("*"*100)

#right，右边为准，nan补全
print("t1.merge(t2,right)")
print(t1.merge(t2,left_on="O",right_on="X",how="right"))
print("*"*100)

3.Series复合索引

import pandas as pd

a = pd.DataFrame({'a': [0, 1, 2, 3, 4, 5, 6],
                  'b': [7, 6, 5, 4, 3, 2, 1],
                  'c': ["one", "one", "one", "two", "two", "two", "two"],
                  'd': ["h",  "j", "k",  "l",  "m",  "n",  "o"]})
X = a.set_index(["c","d"])["a"]
print(X)
print(X["one","h"])
print("*"*100)

print(X.swaplevel())
print("*"*100)
print(X.swaplevel()["h"])
print("*"*100)
print(X.index.levels)

输出：

4.DataFrame复合索引

import pandas as pd

a = pd.DataFrame({'a': [0, 1, 2, 3, 4, 5, 6],
                  'b': [7, 6, 5, 4, 3, 2, 1],
                  'c': ["one", "one", "one", "two", "two", "two", "two"],
                  'd': ["h",  "j", "k",  "l",  "m",  "n",  "o"]})

x = a.set_index(["c","d"])[["a"]]
print(x)
print("*"*100)
print(x.loc["one"])
print("*"*100)
print(x.loc["one"].loc["h"])
print(x.loc["one"].loc["j"])
print("*"*100)
print(x.swaplevel().loc["h"])

输出：

---

结束！