《利用Python进行数据分析》笔记---第8章绘图和可视化

写在前面的话：

实例中的所有数据都是在GitHub上下载的，打包下载即可。
地址是：http://github.com/pydata/pydata-book

还有一定要说明的：

我使用的是Python2.7，书中的代码有一些有错误，我使用自己的2.7版本调通。

# coding: utf-8from pandas import Series, DataFrameimport pandas as pdimport numpy as npimport matplotlib.pyplot as pltfrom numpy.random import randnfig = plt.figure()ax1 = fig.add_subplot(2,2,1)ax2 = fig.add_subplot(2,2,2)ax3 = fig.add_subplot(2,2,3)plt.plot(randn(50).cumsum(),'k--')_ = ax1.hist(randn(100),bins=20,color='k',alpha=0.3)ax2.scatter(np.arange(30),np.arange(30) + 3 * randn(30))fig,axes = plt.subplots(2,3)axesfig,axes = plt.subplots(2,2,sharex=True,sharey=True)for i in range(2):    for j in range(2):        axes[i,j].hist(randn(500),bins=50,color='k',alpha=0.5)plt.subplots_adjust(wspace=0,hspace=0)plt.plot(randn(30).cumsum(),'ko--')data = randn(30).cumsum()plt.plot(data,'k--',label='Default')plt.plot(data,'k--',drawstyle='steps-post',label='steps-post')plt.legend(loc='best')fig = plt.figure();ax = fig.add_subplot(1,1,1)ax.plot(randn(1000).cumsum())ticks = ax.set_xticks([0,250,500,750,1000])labels = ax.set_xticklabels(['one','two','three','four','five'],rotation=30,fontsize='small')ax.set_title('aadadada dsadad sdad')fig = plt.figure()ax = fig.add_subplot(1,1,1)ax.plot(randn(1000).cumsum(),'k',label = 'one')ax.plot(randn(1000).cumsum(),'k--',label = 'two')ax.plot(randn(1000).cumsum(),'k.',label = 'three')ax.legend(loc = 'best')plt.show()from datetime import datetimefig = plt.figure()ax = fig.add_subplot(1,1,1)data = pd.read_csv('D:\Source Code\pydata-book-master\ch08\spx.csv',index_col = 0,parse_dates = True)spx = data['SPX']spx.plot(ax = ax,style = 'k-')crisis_data = [(datetime(2007,10,11),'Peak of bull market'),(datetime(2008,3,12),'Bear Stearns Fails'),(datetime(2008,9,15),'Lehman Bankruptcy')]for date,label in crisis_data:    ax.annotate(label,xy = (date,spx.asof(date) + 50),        xytext = (date,spx.asof(date) + 200),        arrowprops = dict(facecolor = 'black'),        horizontalalignment = 'left',verticalalignment = 'top')ax.set_xlim(['1/1/2007','1/1/2011'])ax.set_ylim([600,1800])ax.set_title('Important dates in 2008-2009 finacial crisis')plt.show()fig = plt.figure()ax = fig.add_subplot(1,1,1)rect = plt.Rectangle((0.2,0.75),0.4,0.15,color = 'k',alpha = 0.3)circ = plt.Circle((0.7,0.2),0.15,color = 'b',alpha = 0.3)pgon = plt.Polygon([[0.15,0.15],[0.35,0.4],[0.2,0.6]],color = 'g',alpha = 0.5)ax.add_patch(rect)ax.add_patch(circ)ax.add_patch(pgon)plt.show()s = Series(np.random.randn(10).cumsum(),index = np.arange(0,100,10))s.plot(use_index = False)df = DataFrame(np.random.randn(10,4).cumsum(0),    columns = ['A','B','C','D'],    index = np.arange(0,100,10))df.plot()fig,axes = plt.subplots(2,1)data = Series(np.random.randn(16),index = list('abcdefghijklmnop'))data.plot(kind = 'barh',ax = axes[0],color = 'k',alpha = 0.7)data.plot(kind = 'bar',ax = axes[1],color = 'k',alpha = 0.7)df = DataFrame(np.random.randn(6,4),index = ['one','two','three','four','five','six'],    columns = pd.Index(['A','B','C','D'],name = 'Genus'))dfdf.plot(kind = 'bar')df.plot(kind = 'bar',stacked = True,alpha = 0.5)tips = pd.read_csv('D:\Source Code\pydata-book-master\ch08\\tips.csv')party_counts = pd.crosstab(tips.day,tips.size)party_countsparty_counts = party_counts.ix[:,2:5]party_pcts = party_counts.div(party_counts.sum(1).astype(float),axis = 0)party_pctsparty_pcts.plot(kind = 'bar',stacked = True)tips['tip_pct'] = tips['tip'] / tips['total_bill']tips['tip_pct'].hist(bins = 50)tips['tip_pct'].plot(kind = 'kde')comp1 = np.random.normal(0,1,size = 200)comp2 = np.random.normal(10,2,size = 200)values = Series(np.concatenate([comp1,comp2]))valuesvalues.hist(bins = 100,alpha = 0.3,color = 'k',normed = True)values.plot(kind = 'kde',style = 'k--')macro = pd.read_csv('D:\Source Code\pydata-book-master\ch08\macrodata.csv')data = macro[['cpi','m1','tbilrate','unemp']]trans_data = np.log(data).diff().dropna()trans_data[-5:]plt.scatter(trans_data['m1'],trans_data['unemp'])plt.title('Changes in log %s vs. log %s'%('m1','unemp'))pd.scatter_matrix(trans_data,diagonal = 'kde',color = 'k',alpha = 0.3)pd.scatter_matrix(trans_data,diagonal = 'hist',color = 'k',alpha = 0.3)data = pd.read_csv('D:\Source Code\pydata-book-master\ch08\Haiti.csv')datadata[['INCIDENT DATE','LATITUDE','LONGITUDE']][:10]data['CATEGORY'][:6]data.describe()data = data[(data.LATITUDE > 18) & (data.LATITUDE < 20) & (data.LONGITUDE > -75) &           (data.LONGITUDE < -70) & data.CATEGORY.notnull()]def to_cat_list(catstr):    stripped = (x.strip() for x in catstr.split(','))    return [x for x in stripped if x]def get_all_categoties(cat_series):    cat_sets = (set(to_cat_list(x)) for x in cat_series)    return sorted(set.union(*cat_sets))def get_english(cat):    code,names = cat.split('.')    if '|' in names:        names = names.split('|')[1]    return code,names.strip()all_cats = get_all_categoties(data.CATEGORY)english_mapping = dict(get_english(x) for x in all_cats)english_mapping['2a']english_mapping['6c']def get_code(seq):    return [x.split('.')[0] for x in seq if x]all_codes = get_code(all_cats)code_index = pd.Index(np.unique(all_codes))dummy_frame = DataFrame(np.zeros((len(data),len(code_index))),index = data.index,columns = code_index)dummy_frame.ix[:,:6]for row,cat in zip(data.index,data.CATEGORY):    codes = get_code(to_cat_list(cat))    dummy_frame.ix[row,codes] = 1data = data.join(dummy_frame.add_prefix('category_'))from mpl_toolkits.basemap import Basemapdef basic_haiti_map(ax = None,lllat = 17.25,urlat = 20.25,lllon = -75,urlon = -71):    m  = Basemap(ax = ax,projection = 'stere',        lon_0 = (urlon + lllon) / 2,        lat_0 = (urlat + lllat) / 2,        llcrnrlat = lllat,urcrnrlat = urlat,        llcrnrlon = lllon,urcrnrlon = urlon,        resolution = 'f' )    m.drawcoastlines()    m.drawstates()    m.drawcountries()    return mfig,axes = plt.subplots(nrows=2,ncols=2,figsize=(12,10))fig.subplots_adjust(hspace=0.05,wspace=0.05)to_plot = ['2a','1','3c','7a']lllat=17.25;urlat=20.25;lllon=-75;urlon=-71for code,ax in zip(to_plot,axes.flat):    m = basic_haiti_map(ax,lllat=lllat,urlat=urlat,lllon=lllon,urlon=urlon)    cat_data = data[data['category_%s' % code] == 1]    x,y = m(cat_data.LONGITUDE,cat_data.LATITUDE)    m.plot(x,y,'k.',alpha=0.5)    ax.set_title('%s:%s'%(code,english_mapping[code]))shapefile_path = 'D:\Source Code\pydata-book-master\ch08\PortAuPrince_Roads'm.readshapefile(shapefile_path,'roads')