qiujiahao123的博客

import numpy#delimiter分隔符，dtype数据格式word_alcho = numpy.genfromtxt("D:\qiujiahao4.txt",delimiter=",",dtype="str")#print (type(word_alcho))print (word_alcho[0])['1' '2' '3' '4' 'qiu']print (word_alcho[

import pandas as pdimport matplotlib.pyplot as pltreviews = pd.read_csv("D:\\test\\fandango_scores.csv")clos = ["Fandango_Ratingvalue","RT_norm","IMDB_norm","RT_norm_round","Metacritic_norm_round"]

sklearn中的cross validation模块，最主要的函数是如下函数： sklearn.cross_validation.cross_val_score。他的调用形式是scores = cross_validation.cross_val_score(clf, raw data, raw target, cv=5, score_func=None) 参数解释： clf是不同的分类器，

import pandas as pdimport numpy as npnum_info=pd.read_csv("D:/test/fandango_scores.csv")num_info.head(1) FILM RottenTomatoes RottenTomatoes_User Metacritic

import pandas as pdimport numpy as npnum_info=pd.read_csv("D:/test/UNRATE.csv")num_info["DATE"] = pd.to_datetime(num_info["DATE"]) #将其转化成时间的格式print (num_info.head(2)) DATE VALUE0 1948-01-

#series 是值的集合#DataFrame 是series的集合#Panel是DataFrame的集合import pandas as pdfandango = pd.read_csv("D:\\test\\fandango_score_comparison.csv")series_film=fandango["FILM"]series_rt=fandango["RottenToma

import pandas as pdimport numpy as npfood_info = pd.read_csv("D:\\test\\titanic_train.csv") #此处需要转义food_info.head(2) PassengerId Survived Pclass Name Sex

import pandas as pdfood_info = pd.read_csv("D:\\test\\food_info.csv") #此处需要转义print(food_info.head(2)) NDB_No Shrt_Desc Water_(g) Energ_Kcal Protein_(g) \0 1001 BUTT

import pandas as pdfood_info = pd.read_csv("D:\\test\\food_info.csv") #此处需要转义print (type(food_info)) first_row = food_info.head() #默认是前5行print (food_info.shape) (8618, 36)print (food_info.l

import pandas as pdfood_info = pd.read_csv("D:\\test\\food_info.csv") #此处需要转义print (type(food_info))<class 'pandas.core.frame.DataFrame'>first_row = food_info.head() #默认是前5行print (first_row)first

import numpy as npa = np.sin(py.arange(12).reshape(3,4))print (a)[[ 0. 0.84147098 0.90929743 0.14112001] [-0.7568025 -0.95892427 -0.2794155 0.6569866 ] [ 0.98935825 0.41211849 -0.544

import numpy as npa = np.arange(3)print (a)print (np.exp(a)) #e的0，1，2次幂print (np.sqrt(a))#开根号[0 1 2][ 1. 2.71828183 7.3890561 ][ 0. 1. 1.41421356]a = np.floor(10*np.r

import numpy as npa = np.arange(15) #生成0到15的数组print (a)b= a.reshape(3,5) #生成3行5列的矩阵print (b)[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14][[ 0 1 2 3 4] [ 5 6 7 8 9] [10 11 12 13 14]]b.

import pandas as pdimport matplotlib.pyplot as pltreviews = pd.read_csv("D:\\test\\percent-bachelors-degrees-women-usa.csv")plt.plot(reviews["Year"],reviews["Biology"])plt.show()plt.plot(reviews["Y