jiangshandaiyou的博客

import numpy as npimport pandas as pd import matplotlib as pltts = pd.Series(np.random.randn(1000), index=pd.date_range("1/1/2000", periods=1000))ts = ts.cumsum()ts.plot(); #The plot method on Series and DataFrame is just a simple wrapper around plt.

import numpy as npimport pandas as pddf = pd.DataFrame([("bird", "Falconiformes", 389.0),("bird", "Psittaciformes", 24.0), ("mammal", "Carnivora", 80.2),("mammal", "Primates", np.nan),("mammal", "Carnivora", 58)], in

import numpy as npimport pandas as pd#Reshaping and pivot tablesdf date variable value 0 2000-01-03 A 1.212728 1 2000-01-04 A -0.001690

import numpy as npimport pandas as pd#在pandas或者numpy中要非常注意NaN与NaN之间并不相同#但是None相当于np.nanNone == None # noqa: E711Truenp.nan == np.nan #还要注意的一点是NaN是floatFalse#Filling missing values: fillnadf = pd.DataFrame(np.random.randn(5, 3),index=["a", "c

import numpy as npimport pandas as pdimport matplotlib as mpl#concatenate 函数df1 = pd.DataFrame(np.random.randn(4,3),index=list("abcd"),columns=list("ABC"))df1 A B C a 0.283456 0.6

#有个小姐姐问我如何根据数值大小将两个96孔板对应读值（ELISA实验比色读值）筛选出来#或者说这个96孔板的某个孔读值大于1，另一个孔板的对应位置孔的读值也大于1，然后把这两个孔的位置和读值拎出来import numpy as npimport pandas as pddf1 = pd.DataFrame(np.random.randn(8,12))df1 0 1 2 3 4 5

import osimport numpy as npimport pandas as pdpath_ = ""file_list = ""count = 0i = 0file_list = os.listdir(path_)#指定engine很重要with pd.ExcelWriter("result.xlsx") as writer: while i < len(file_list): if i%2 == 0: pd.read_exce

import numpy as npimport pandas as pddates = pd.date_range('1/1/2000', periods=8)dfa = pd.DataFrame(np.random.randn(8, 4),index=dates, columns=['A', 'B', 'C', 'D'])dfa A B C D 2000-01-01

#dataframe的增删改查之增import numpy as npimport pandas as pddf = pd.DataFrame(np.random.randn(3,4),index=list("abc"),columns=list("ABCD"))df A B C D a -1.191323 -0.774396 0.2

#主要学习如何构建dataframe#From dict of Series or dictsimport numpy as npimport pandas as pdd = { "one": pd.Series([1.0, 2.0, 3.0], index=["a", "b", "c"]),"two": pd.Series([1.0, 2.0, 3.0, 4.0], index=["a", "b", "c", "d"])}df = pd.DataFrame(d)df

import numpy as npimport pandas as pd#日期作为索引，生成dataframedates = pd.date_range('20210821', periods=6)datesDatetimeIndex(['2021-08-21', '2021-08-22', '2021-08-23', '2021-08-24', '2021-08-25', '2021-08-26'], dtype='datetime