Python商业数据分析代码.docxVIP

PAGE PAGE 1 1.商业数据分析及其工具 import pandas as pd # 读取本地数据 df = pd.read_csv(/2glkx/data/al2-1.csv) #读取网上数据 import pandas as pd data_url= /alstat/Analysis-with-Programming/master/2014/Python/Numerical-Descriptions-of-the-Data/data.csv df = pd.read_csv(data_url) print (df.head()) print (df.tail()) print (df.columns) Index([uAbra, uApayao, uBenguet, uIfugao, uKalinga], dtype=object) # Extracting row names or the index print (df.index) RangeIndex(start=0, stop=79, step=1) # Transpose data print (df.T) print (df.ix[:, 0].head()) 现在改版ix用loc print (df.ix[10:20, 0:3]) print (df.drop(df.columns[[2, 3]], axis = 1).head()) print (df.describe()) from scipy import stats as ss # Perform one sample t-test using 1500 as the true mean print (ss.ttest_1samp(a = df.ix[:, Abra], popmean = 15000)) Ttest_1sampResult(statistic=-1.1281738488299586, pvalue=0.26270472069109496) print (ss.ttest_1samp(a = df, popmean = 15000)) import matplotlib.pyplot as plt plt.show(df.plot(kind = box)) import seaborn as sns # Do the boxplot plt.show(sns.boxplot(df)) def add_2int(x, y): return x + y print (add_2int(2, 2)) 2 Python商业数据的存取 import pandas as pd import numpy as np a=[apple,pear,watch,money] b=[[1,2,3,4,5],[5,7,8,9,0],[1,3,5,7,9],[2,4,6,8,0]] d=dict(zip(a,b)) d p=pd.DataFrame(d) p p.to_csv(F:\\2glkx\\data\\IBM.csv) pd.read_csv(F:\\2glkx\\data\\al2-1.csv) import pandas as pd import numpy as np df=pd.read_excel(F:\\2glkx\\data\\al2-2.xls) df.head() import pandas as pd import numpy as np #读取数据并创建数据表，名称为data。 data=pd.DataFrame(pd.read_excel(G:\\2glkx\\data\\al2-2.xls)) #查看数据表前5行的内容 data.head() import tushare as ts df = ts.get_hist_data(000875) #从网上取数据 #直接保存 #df.to_csv(:/2glkx/data/000875.csv) #选择数据保存 df.to_csv(F:/2glkx/data/000875.csv,columns=[open,high,low,close]) import pandas as pd import numpy as np df=pd.read_csv(F:/2glkx/data/000875.csv) df.head() import tushare as ts import os filename = F:/2glkx/data/bigfile.csv for code in [000875, 600848, 000981]: df = ts.get_hist_da