利用python进行数据分析

数据结构和序列 元组 固定长度 不可改变 创建方法：逗号分隔/加括号（） tuple将任意序列转化为元组 串联元组 *复制元组 count：统计某个值出现的频率 In [ 1 ] : tup = 4 , 5 , 6 In [ 2 ] : tup Out [ 2 ] : ( 4 , 5 , 6 ) In [ 3 ] : nested_tup = ( 4 , 5 , 6 ) , ( 7 , 8 ) In [ 4 ] : nested_tup Out [ 4 ] : ( ( 4 , 5 , 6 ) , ( 7 , 8 ) ) In [ 5 ] : tuple ( [ 4 , 0 , 2 ] ) Out [ 5 ] : ( 4 , 0 , 2 ) In [ 6 ] : tup = tuple ( 'string' ) In [ 7 ] : tup Out [ 7 ] : ( 's' , 't' , 'r' , 'i' , 'n' , 'g' ) In [ 8 ] : tup [ 0 ] Out [ 8 ] : 's In [ 9 ] : tup = tuple ( [ 'foo' , [ 1 , 2 ] , True ] ) In [ 10 ] : tup [ 2 ] = False - - - - - - - - - - - - - - - - - - - - - - - - - - -

/*--> */ /*--> */ /*--> */ /*--> */ /*--> */ /*--> */ /*--> */ /*--> */ In [1]: import pandas as pd import numpy as np 删除缺失值 ¶ In [2]: df = pd.DataFrame(np.random.randn(6,3)) df.iloc[:4,1] = np.NaN df.iloc[:2,2] = np.NaN df Out[2]: /*--> */ /*--> */ 0 1 2 0 0.230148 NaN NaN 1 0.967690 NaN NaN 2 0.296245 NaN -0.905187 3 1.204742 NaN 1.765566 4 0.463110 1.423042 1.858276 5 1.272618 -0.033120 -1.269821 In [3]: #有2个以上的nan才删除 df.dropna(thresh=2) Out[3]: /*--> */ /*--> */ 0 1 2 2 0.296245 NaN -0.905187 3 1.204742 NaN 1.765566 4 0.463110 1.423042 1.858276 5 1.272618 -0.033120 -1.269821 In [4]: df