def view(key,reciprocals=None,show=True,suspend=False,save=True,name='KMap'):
        '''
        View the KMap.

        Parameters
        ----------
        key : 'L','S','H'
            The key of the database of KMap.
        reciprocals : iterable of 1d ndarray, optional
            The translation vectors of the reciprocal lattice.
        show : logical, optional
            True for showing the view. Otherwise not.
        suspend : logical, optional
            True for suspending the view. Otherwise not.
        save : logical, optional
            True for saving the view. Otherwise not.
        name : str, optional
            The title and filename of the view. Otherwise not.
        '''
        assert key in KMap.database
        if key=='L': reciprocals=np.asarray(reciprocals) or np.array([1.0])*2*np.pi
        elif key=='S': reciprocals=np.asarray(reciprocals) or np.array([[1.0,0.0],[0.0,1.0]])*2*np.pi
        elif key=='H': reciprocals=np.asarray(reciprocals) or np.array([[1.0,-1.0/np.sqrt(3.0)],[0,-2.0/np.sqrt(3.0)]])*2*np.pi
        plt.title(name)
        plt.axis('equal')
        for tag,position in KMap.database[key].items():
            if '1' not in tag:
                coords=reciprocals.T.dot(position)
                assert len(coords)==2
                plt.scatter(coords[0],coords[1])
                plt.text(coords[0],coords[1],'%s(%s1)'%(tag,tag) if len(tag)==1 else tag,ha='center',va='bottom',color='green',fontsize=14)
        if show and suspend: plt.show()
        if show and not suspend: plt.pause(1)
        if save: plt.savefig('%s.png'%name)
        plt.close()

  def export(self, query, n_topics, n_words, title="PCA Export", fname="PCAExport"):
    vec = DictVectorizer()
    
    rows = topics_to_vectorspace(self.model, n_topics, n_words)
    X = vec.fit_transform(rows)
    pca = skPCA(n_components=2)
    X_pca = pca.fit(X.toarray()).transform(X.toarray())
    
    match = []
    for i in range(n_topics):
      topic = [t[1] for t in self.model.show_topic(i, len(self.dictionary.keys()))]
      m = None
      for word in topic:
        if word in query:
          match.append(word)
          break

    pyplot.figure()
    for i in range(X_pca.shape[0]):
      pyplot.scatter(X_pca[i, 0], X_pca[i, 1], alpha=.5)
      pyplot.text(X_pca[i, 0], X_pca[i, 1], s=' '.join([str(i), match[i]]))  
     
    pyplot.title(title)
    pyplot.savefig(fname)
     
    pyplot.close()

def drawVectors(transformed_features, components_, columns, plt, scaled):
  if not scaled:
    return plt.axes() # No cheating ;-)

  num_columns = len(columns)

  # This funtion will project your *original* feature (columns)
  # onto your principal component feature-space, so that you can
  # visualize how "important" each one was in the
  # multi-dimensional scaling
  
  # Scale the principal components by the max value in
  # the transformed set belonging to that component
  xvector = components_[0] * max(transformed_features[:,0])
  yvector = components_[1] * max(transformed_features[:,1])

  ## visualize projections

  # Sort each column by it's length. These are your *original*
  # columns, not the principal components.
  important_features = { columns[i] : math.sqrt(xvector[i]**2 + yvector[i]**2) for i in range(num_columns) }
  important_features = sorted(zip(important_features.values(), important_features.keys()), reverse=True)
  print "Features by importance:\n", important_features

  ax = plt.axes()

  for i in range(num_columns):
    # Use an arrow to project each original feature as a
    # labeled vector on your principal component axes
    plt.arrow(0, 0, xvector[i], yvector[i], color='b', width=0.0005, head_width=0.02, alpha=0.75)
    plt.text(xvector[i]*1.2, yvector[i]*1.2, list(columns)[i], color='b', alpha=0.75)

  return ax

def createResponsePlot(dataframe,plotdir):
    mag = dataframe['MAGPDE'].as_matrix()
    response = (dataframe['TFIRSTPUB'].as_matrix())/60.0
    response[response > 60] = 60 #anything over 60 minutes capped at 6 minutes
    imag5 = (mag >= 5.0).nonzero()[0]
    imag55 = (mag >= 5.5).nonzero()[0]
    fig = plt.figure(figsize=(8,6))
    n,bins,patches = plt.hist(response[imag5],color='g',bins=60,range=(0,60))
    plt.hold(True)
    plt.hist(response[imag55],color='b',bins=60,range=(0,60))
    plt.xlabel('Response Time (min)')
    plt.ylabel('Number of earthquakes')
    plt.xticks(np.arange(0,65,5))
    ymax = text.ceilToNearest(max(n),10)
    yinc = ymax/10
    plt.yticks(np.arange(0,ymax+yinc,yinc))
    plt.grid(True,which='both')
    plt.hold(True)
    x = [20,20]
    y = [0,ymax]
    plt.plot(x,y,'r',linewidth=2,zorder=10)
    s1 = 'Magnitude 5.0, Events = %i' % (len(imag5))
    s2 = 'Magnitude 5.5, Events = %i' % (len(imag55))
    plt.text(35,.85*ymax,s1,color='g')
    plt.text(35,.75*ymax,s2,color='b')
    plt.savefig(os.path.join(plotdir,'response.pdf'))
    plt.savefig(os.path.join(plotdir,'response.png'))
    plt.close()
    print 'Saving response.pdf'

def plotFrame(lines, chop_times,dist,samDist,DetDist,fracEi,Eis):
    modSamDist=dist[-1]+samDist 
    totDist=modSamDist+DetDist
    for i in range(len(dist)):
        plt.plot([-20000,120000],[dist[i],dist[i]],c='k',linewidth=1.)
        for j in range(len(chop_times[i][:])):
            plt.plot(chop_times[i][j],[dist[i],dist[i]],c='white',linewidth=1.)
    
    plt.plot([-20000,120000],[totDist,totDist],c='k',linewidth=2.)    
    
    for i in range(len(lines)):
        x0=-lines[i][0][1]/lines[i][0][0]
        x1=(modSamDist-lines[i][0][1])/lines[i][0][0]
        plt.plot([x0,x1],[0,modSamDist],c='b')
        x2=(totDist-lines[i][0][1])/lines[i][0][0]
        plt.plot([x1,x2],[modSamDist,totDist],c='b')
        newline=[lines[i][0][0]*np.sqrt(1+fracEi),modSamDist-lines[i][0][0]*np.sqrt(1+fracEi)*x1]
        x3=(totDist-newline[1])/(newline[0])
        plt.plot([x1,x3],[modSamDist,totDist],c='r')
        
        newline=[lines[i][0][0]*np.sqrt(1-fracEi),modSamDist-lines[i][0][0]*np.sqrt(1-fracEi)*x1]
        x4=(totDist-newline[1])/(newline[0])
        plt.plot([x1,x4],[modSamDist,totDist],c='r')
        plt.text(x2,totDist+0.2,"{:3.1f}".format(Eis[i]))
        

    plt.xlabel('TOF ($\mu$sec)')  
    plt.ylabel('Distance (m)') 
    plt.xlim(0,100000)
    plt.show()

def plot_confusion_matrix(cm, classes,
                          normalize=False,
                          title='Confusion matrix',
                          cmap=None,
                          zmin=1):
    """This function prints and plots the confusion matrix for the intent classification.

    Normalization can be applied by setting `normalize=True`."""
    import numpy as np

    zmax = cm.max()
    plt.imshow(cm, interpolation='nearest', cmap=cmap if cmap else plt.cm.Blues, aspect='auto',
               norm=LogNorm(vmin=zmin, vmax=zmax))
    plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(classes))
    plt.xticks(tick_marks, classes, rotation=90)
    plt.yticks(tick_marks, classes)

    if normalize:
        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
        logger.info("Normalized confusion matrix: \n{}".format(cm))
    else:
        logger.info("Confusion matrix, without normalization: \n{}".format(cm))

    thresh = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, cm[i, j],
                 horizontalalignment="center",
                 color="white" if cm[i, j] > thresh else "black")

    plt.ylabel('True label')
    plt.xlabel('Predicted label')

def autolabel(rects,labels):
    # attach some text labels
    for i,(rect,label) in enumerate(zip(rects,labels)):
        height = rect.get_height()
        plt.text(rect.get_x() + rect.get_width()/2., 1.05*height,
                label,
                ha='left', va='bottom',fontsize=8,rotation=45)

def plot_confusion_matrix(y_true, y_pred, thresh, classes):
    """
    This function plots the (normalized) confusion matrix.
    """

    # obtain class predictions from probabilities
    y_pred = (y_pred>=thresh)*1
    # obtain (unnormalized) confusion matrix
    cm = confusion_matrix(y_true, y_pred)
    # normalize confusion matrix
    cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
    
    plt.figure()
    plt.imshow(cm, interpolation='nearest', cmap=plt.cm.Blues)
    plt.title('Confusion matrix')
    plt.colorbar()
    tick_marks = np.arange(len(classes))
    plt.xticks(tick_marks, classes, rotation=45)
    plt.yticks(tick_marks, classes)

    thresh = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, format(cm[i, j], '.2f'),
                 horizontalalignment="center",
                 color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label')
    plt.show()

def make_equil_plts_2(phi, tad, xeq, gas):
    """
    make_equil_plts_2
    make_equil_plts_2 makes plots from Python function equil; it's the same as make_equil_plts, but with 2 separate figures
    """
    plt.figure(1)
    phitadplt = plt.plot(phi,tad)
    plt.xlabel('Equivalence Ratio')
    plt.ylabel('Temperature (K)')
    plt.title('Adiabatic Flame Temperature')
    
    plt.figure(2)
    plt.ylim(10.**(-14),1)
    plt.xlim(phi[0],phi[49])
    phixeqsemilogyplt = plt.semilogy(phi,xeq) # matplotlib semilogy takes in the correct dimensions! What I mean is that say phi is a list of length 50.  Suppose xeq is a numpy array of shape (50,53).  This will result in 53 different (line) graphs on the same plot, the correct number of line graphs for (50) (x,y) data points/dots!
    plt.xlabel('Equivalence Ratio')
    plt.ylabel('Mole Fraction')
    plt.title('Equilibrium Composition')
    
    j = 10
    for k in range(gas.n_species):
        plt.text(phi[j],1.5*xeq[j,k],gas.species_name(k))
        j = j + 2
        if j > 46:
            j = 10
    plt.show()
    return phitadplt, phixeqsemilogyplt

def main(args):

    histogram = args.histogram
    min_limit = args.min_limit
    max_limit = args.max_limit
    kmer = args.kmer
    output_name = args.output_name

    Kmer_histogram = pd.io.parsers.read_csv(histogram, sep="\t", header=None)
    Kmer_coverage = Kmer_histogram[Kmer_histogram.columns[0]].tolist()
    Kmer_count = Kmer_histogram[Kmer_histogram.columns[1]].tolist()
    Kmer_freq = [Kmer_coverage[i] * Kmer_count[i] for i in range(len(Kmer_coverage))]
    # coverage peak, disregarding initial peak
    kmer_freq_peak = Kmer_freq.index(max(Kmer_freq[min_limit:max_limit]))
    kmer_freq_peak_value = max(Kmer_freq[min_limit:max_limit])

    xmax = max_limit
    ymax = kmer_freq_peak_value + (kmer_freq_peak_value * 0.30)

    plt.plot(Kmer_coverage, Kmer_freq)
    plt.title("K-mer length = {}".format(kmer))
    plt.xlim((0, xmax))
    plt.ylim((0, ymax))
    plt.vlines(kmer_freq_peak, 0, kmer_freq_peak_value, colors="r", linestyles="--")
    plt.text(kmer_freq_peak, kmer_freq_peak_value + 2000, str(kmer_freq_peak))
    plotname = "{}".format(output_name)
    plt.savefig(plotname)
    plt.clf()
    return 0

def pylot_show():
  sql = 'select * from douban;'  
  cur.execute(sql)
  rows = cur.fetchall()   # 把表中所有字段读取出来
  count = []   # 每个分类的数量
  category = []  # 分类

  for row in rows:
    count.append(int(row[2]))   
    category.append(row[1])
    y_pos = np.arange(len(category))    # 定义y轴坐标数

    #color = cm.jet(np.array(2)/max(count))

    plt.barh(y_pos, count, color='y', align='center', alpha=0.4)  # alpha图表的填充不透明度(0~1)之间
    plt.yticks(y_pos, category)  # 在y轴上做分类名的标记
    plt.grid(axis = 'x')

  for count, y_pos in zip(count, y_pos):
    # 分类个数在图中显示的位置，就是那些数字在柱状图尾部显示的数字
    plt.text(count+3, y_pos, count,  horizontalalignment='center', verticalalignment='center', weight='bold')  
    plt.ylim(+28.0, -2.0) # 可视化范围，相当于规定y轴范围
    plt.title('douban_top250')   # 图表的标题   fontproperties='simhei'
    plt.ylabel('movie category')     # 图表y轴的标记
    plt.subplots_adjust(bottom = 0.15) 
    plt.xlabel('count')  # 图表x轴的标记
    #plt.savefig('douban.png')   # 保存图片
  plt.show()

def histogram(arrayGenes):
    
    arrayG = np.array(arrayGenes)
    mean = arrayG.mean()
    std = arrayG.std()
    print 'mean = ', mean
    print 'std = ', std
#    mu, sigma = 100, 15
#    x = mu + sigma * np.random.randn(100)
#    
#    print np.random.randn(2)
#    
#    for each in x:
#        print each
# the histogram of the data
    n, bins, patches = plt.hist(arrayG, 60, normed=1, facecolor='g', alpha=0.75)


    plt.xlabel('Smarts')
    plt.ylabel('Probability')
    plt.title('Histogram of IQ')
    plt.text(60, .025, r'$\mu=100,\ \sigma=15$')
    plt.axis([0, 1000, 0, 1000])
    plt.grid(True)
    plt.show()

def labelgridcells(shapefile):
    labelcount=len(shapef.shapes())
    for shape in shapef.shapes():
        x,y= gMap(shape.points[0][0],shape.points[0][1])
        plt.text(x,y,labelcount,color='w')
        #print str(labelcount)+' '+str(shape.points[0][0])+' '+str(shape.points[0][1])
        labelcount-=1

	def plot_traj(self,ap=True,ag=True,fig=[],cps=20,ans=40,**kwargs):

		if fig ==[]:
			fig = plt.figure('trajectory', figsize=(20, 5), dpi=100)

		fig, ax = self.layout.showG('s',fig=fig,nodes=False,**kwargs)
		if ag:
			for i,n in enumerate(self.agents):
				cp=0
				for j,p in enumerate(self.data[n]['p']):
					if j == 0:
						ax.plot(p[0],p[1],'o',color=self.colors[n],label='agent #'+n,**kwargs)
					else: # to avoid multiple label in legend
						ax.plot(p[0],p[1],'o',color=self.colors[n],**kwargs)
					if j%self.checkpoint==0: 
						ax.plot(p[0],p[1],'o',color=self.colors[n],ms=cps)
						plt.text(p[0]-0.2,p[1]-0.2, str(cp), fontsize=10) 
						cp = cp+1
		if ap:
			for i,n in enumerate(self.ap):

				if n =='6' or n == '9':
					color='r'
				else :
					color='g'
				ax.plot(self.data[n]['p'][0,0],self.data[n]['p'][0,1]
						,'^',color=color,label='AP #'+n,ms=ans)

		ax.grid('off')
		ax.legend(numpoints=1)
		return fig,ax

def draw_path(order, boundaries=None):

    if boundaries:
        (p1, p2, p3), (p1a, p2a, p3a) = boundaries
        b_dict = {p1: "p1", p1a: "p1a", p2: "p2", p2a: "p2a", p3: "p3", p3a: "p3a"}
    else:
        b_dict = {}

    locations = hack_locations
    locations2 = np.zeros(locations.shape)
    for i in order:
        locations2[i, :] = locations[order[i], :]

    print locations
    print order
    print locations2

    x1 = []
    y1 = []
    delta = 0.0
    for i in order:
        x1.append(locations[i, 0] - delta)
        y1.append(locations[i, 1] - delta)
        delta -= 0.005
    x1.append(locations[order[0], 0])
    y1.append(locations[order[0], 1])
    plt.xlim((-0.1, 1.2))
    plt.ylim((-0.1, 1.2))
    plt.plot(x1, y1, marker="x", linestyle="-", color="b")
    for i, o in enumerate(order):
        plt.text(x1[i], y1[i] + 0.01, "%d %s" % (i, b_dict.get(i, "")))

 def _autolabel(self, plt, rects):
     """a method to label the height of the bar in the bar chart"""
     
     for rect in rects:
         height = int(rect.get_height())
         if (height > 0):
             plt.text(rect.get_x()+rect.get_width()/2., 1.03*height, '%s' % int(height))

def execute(bins=10, ylim=False):
    data = pandas.merge(load_terms(), load_search_results().rename(columns={'identifier': 'term_id'}), on=['term_id'], how='inner')
    data = data[data['term_name'].apply(lambda x: len(x.split(';')[0]) > 5)]
    data = data[data['term_id'].apply(lambda x: x.startswith('A'))]
    data = pandas.merge(data, load_radiopaedia_terms(), on=['term_id', 'term_name'], how='inner')
    # load_radiopaedia_terms()
    # g = sns.pairplot(data, vars=['search_results_log', 'pagerank', 'difficulty_prob'])
    # for ax in g.axes.flat:
        # if ax.get_xlabel() in ['difficulty_prob', 'pagerank']:
            # ax.set_xlim(0, 1)
        # if ax.get_ylabel() in ['difficulty_prob', 'pagerank']:
            # ax.set_ylim(0, 1)
        # if min(ax.get_xticks()) < 0:
            # ax.set_xlim(0, max(ax.get_xticks()))
        # if min(ax.get_yticks()) < 0:
            # ax.set_ylim(0, max(ax.get_yticks()))
    # output.savefig('importance_pair', tight_layout=False)
    rcParams['figure.figsize'] = 30, 20
    for term_name, difficulty_prob, pagerank in data[['term_name', 'difficulty_prob', 'pagerank']].values:
        plt.plot(1 - difficulty_prob, pagerank, color='red', marker='s', markersize=10)
        plt.text(1 - difficulty_prob, pagerank, term_name)
        if ylim:
            plt.ylim(0, 0.5)
        plt.xlabel('Predicted error rate')
        plt.ylabel('Pagerank')
    output.savefig('importance_pagerank')

def polim(axe, polluant='O3'):
    """
    Raccourcis pour tracer les lignes horizontales décrivant les seuils
    réglementaires pour les polluants
    """

    seuils = {'O3': (150, 180, 240),
              'NO2': (135, 200, 400),
              'SO2': (200, 300, 500)}
    labs = ['MVR', 'IR', 'A']
    if polluant not in seuils.keys():
        return axe
    colors = ('green', 'orange', 'red')
    xlim = axe.get_xlim()
    for i in range(len(seuils[polluant])):
        seuil = seuils[polluant][i]
        color = colors[i]
        x0 = xlim[0]
        x1 = xlim[1]
        axe.hlines(seuil, x0, x1, color, label='_nolegend_')
    for i in range(len(seuils[polluant])):  # Deuxième passe pour inscrire les
        # valeurs, sinon le texte de la première ligne est décalée (bug MPL??)
        seuil = seuils[polluant][i]
        color = colors[i]
        x0 = xlim[0]
        t = "%s (%s)" % (labs[i], seuil)
        plt.text(x0, seuil, t, color=color, ha='left', va='bottom', weight='bold')
    plt.ylim(0, seuils[polluant][-1] + 100)
    plt.draw()
    return axe

def plotOEMSEarlyLateReplicatedOriginsWTandMUT(oemfilestrain1,oemfilestrain2,oemfilestrain3,oemfilestrain4,reptime):
    
    # Grab OEMS for early and late replicated origins for strain 1
    oemsEarlyLateRO_strain1 = rt.getOEMSForEarlyvsLateReplicatedOriginsAllChromosomes(reptime,oemfilestrain1)
    
    # Grab OEMS for early and late replicated origins for strain 2
    oemsEarlyLateRO_strain2 = rt.getOEMSForEarlyvsLateReplicatedOriginsAllChromosomes(reptime,oemfilestrain2)
    
    # Grab OEMS for early and late replicated origins for strain 3
    oemsEarlyLateRO_strain3 = rt.getOEMSForEarlyvsLateReplicatedOriginsAllChromosomes(reptime,oemfilestrain3)
    
    # Grab OEMS for early and late replicated origin for strain 4
    oemsEarlyLateRO_strain4 = rt.getOEMSForEarlyvsLateReplicatedOriginsAllChromosomes(reptime,oemfilestrain4)
    
    bp = plt.boxplot([oemsEarlyLateRO_strain1['early'],oemsEarlyLateRO_strain1['late'],oemsEarlyLateRO_strain2['early'],oemsEarlyLateRO_strain2['late'],oemsEarlyLateRO_strain3['early'],oemsEarlyLateRO_strain3['late'],oemsEarlyLateRO_strain4['early'],oemsEarlyLateRO_strain4['late']],1)
    
    for line in bp['medians']:
        x1, y = line.get_xydata()[0]
        x2 = line.get_xydata()[1][0]
        x = (x1+x2)/2
        plt.text(x, y, '%.3f' % y,horizontalalignment='center')
        
    plt.xticks(range(1,9),('Early-WT','Late-WT','Early-pif1m2KO','Late-pif1m2KO','Early-rrm3dKO','Late-rrm3dKO','Early-rrm3d_pif1m2KO','Late-rrm3d_pif1m2KO'))

    plt.ylabel('OEM')

    plt.title('OEMs of Early and Late Replicating Origins')
    
    plt.show()

def plot_data(years, stat, win_type):
    data = get_data('data/%s_top_%s.dat' % (years, stat))
    plt.figure(1)
    min_x, max_x = sys.maxint, 0
    min_y, max_y = sys.maxint, 0

    for datum in data:
        name, value, passes_filter, home_wins, total_wins = datum
        if win_type == 'home':
            wins = home_wins
        elif win_type == 'total':
            wins = total_wins
        else:
            print "Warning: invalid win_type. Defaulted to 'home'."
            wins = home_wins

        if passes_filter:
            color = 'k'
        else:
            color = 'r'
        plt.text(wins, value, name, size='large', color=color)
        min_x, max_x = min(min_x, wins), max(max_x, wins)
        min_y, max_y = min(min_y, value), max(max_y, value)

    plt.xlim(min_x - max_x/10.0, max_x + max_x/10.0)
    plt.ylim(min_y - max_y/10.0, max_y + max_y/10.0)

    # X and Y labels
    plt.ylabel(stat, size='large')
    plt.xlabel('# of %s wins' % win_type, size='large')

    plt.show()