qhaaha的博客

import pandas as pd import numpy as np#数据透视表（pivot table）import seaborn as sns titanic = sns.load_dataset('titanic')titanic.head() survived pclass sex age sibsp parch fare embarked

Pandas数据合并（join、merge），累计与分组（groupby）import pandas as pd import numpy as npdef make_df(cols, ind): """一个简单的DataFrame""" data = {c: [str(c) + str(i) for i in ind] for c in cols} return pd.DataFrame(data, index=ind) # DataFrame示例make_df('ABC', r

import numpy as np import pandas as pd #处理缺失值#标签的方法：None和NaNvals1 = np.array([1, None, 3, 4])vals1#object型的numpy数组认为对象是python对象，进行快速操作时会更慢array([1, None, 3, 4], dtype=object)#使用NaN：和之前的 object 类型数组不同，这个数组会被编译成 C 代码从而实现快速操作。你可以把 NaN 看作是一个数据类病毒——它

import numpy as np import pandas as pd print(pd.__version__)1.0.5#Pandas 的 Series 对象是一个带索引数据构成的一维数组#Series 对象将一组数据和一组索引绑定在一起，我们可以通过values 属性和 index 属性获取数据data = pd.Series([0.25, 0.5, 0.75, 1])print(data)print(data.values)print(data.index)0

import numpy as np np.random.seed(0)x3 = np.random.randint(10,size=(3,4,5))print(x3)print(type(x3))print(x3.ndim)print(x3.shape)print(x3.size)[[[5 0 3 3 7] [9 3 5 2 4] [7 6 8 8 1] [6 7 7 8 1]] [[5 9 8 9 4] [3 0 3 5 0] [2 3 8 1 3] [3