python类hist()的实例源码

def plot_volcano(logFC,p_val,sample_name,saveName,logFC_thresh):
    fig=pl.figure()
    ## To plot and save
    pl.scatter(logFC[(p_val>0.05)|(abs(logFC)<logFC_thresh)],-np.log10(p_val[(p_val>0.05)|(abs(logFC)<logFC_thresh)]),color='blue',alpha=0.5);
    pl.scatter(logFC[(p_val<0.05)&(abs(logFC)>logFC_thresh)],-np.log10(p_val[(p_val<0.05)&(abs(logFC)>logFC_thresh)]),color='red');
    pl.hlines(-np.log10(0.05),min(logFC),max(logFC))
    pl.vlines(-logFC_thresh,min(-np.log10(p_val)),max(-np.log10(p_val)))
    pl.vlines(logFC_thresh,min(-np.log10(p_val)),max(-np.log10(p_val)))
    pl.xlim(-3,3)
    pl.xlabel('Log Fold Change')
    pl.ylabel('-log10(p-value)')
    pl.savefig(saveName)
    pl.close(fig)


# def plot_histograms(df_peaks,pntr_list):
#
#     for pntr in pntr_list:
#         colName =pntr[2]+'_Intragenic_position'
#         pl.hist(df_peaks[colName])
#         pl.xlabel(colName)
#         pl.ylabel()
#         pl.show()

def plot_1d(dataset, nbins, data):
    with sns.axes_style('white'):
        plt.rc('font', weight='bold')
        plt.rc('grid', lw=2)
        plt.rc('lines', lw=3)
        plt.figure(1)
        plt.hist(data, bins=np.arange(nbins+1), color='blue')
        plt.ylabel('Count', weight='bold', fontsize=24)
        xticks = list(plt.gca().get_xticks())
        while (nbins-1) / float(xticks[-1]) < 1.1:
            xticks = xticks[:-1]
        while xticks[0] < 0:
            xticks = xticks[1:]
        xticks.append(nbins-1)
        xticks = list(sorted(xticks))
        plt.gca().set_xticks(xticks)
        plt.xlim([int(np.ceil(-0.05*nbins)),int(np.ceil(nbins*1.05))])
        plt.legend(loc='upper right')
        plt.savefig('plots/marginals-{0}.pdf'.format(dataset.replace('_','-')), bbox_inches='tight')
        plt.clf()
        plt.close()

def plot_1d(dataset, nbins):
    data = np.loadtxt('experiments/uci/data/splits/{0}_all.csv'.format(dataset), skiprows=1, delimiter=',')[:,-1]
    with sns.axes_style('white'):
        plt.rc('font', weight='bold')
        plt.rc('grid', lw=2)
        plt.rc('lines', lw=3)
        plt.figure(1)
        plt.hist(data, bins=np.arange(nbins+1), color='blue')
        plt.ylabel('Count', weight='bold', fontsize=24)
        xticks = list(plt.gca().get_xticks())
        while (nbins-1) / float(xticks[-1]) < 1.1:
            xticks = xticks[:-1]
        while xticks[0] < 0:
            xticks = xticks[1:]
        xticks.append(nbins-1)
        xticks = list(sorted(xticks))
        plt.gca().set_xticks(xticks)
        plt.xlim([int(np.ceil(-0.05*nbins)),int(np.ceil(nbins*1.05))])
        plt.legend(loc='upper right')
        plt.savefig('plots/marginals-{0}.pdf'.format(dataset.replace('_','-')), bbox_inches='tight')
        plt.clf()
        plt.close()

def onehist(x,xlabel='',fontsize=12):
    """ 
Script that plots the histogram of x with the corresponding xlabel. 
    """

    pylab.clf()
    pylab.rcParams.update({'font.size': fontsize})
    pylab.hist(x,histtype='stepfilled')
    pylab.legend()
    #### Change the X-axis appropriately ####
    pylab.xlabel(xlabel)
    pylab.ylabel('Number')
    pylab.draw()
    pylab.show()

def threehistsx(x1,x2,x3,x1leg='$x_1$',x2leg='$x_2$',x3leg='$x_3$',fig=1,fontsize=12,bins1=10,bins2=10,bins3=10):
    """
Script that pretty-plots three histograms of quantities x1, x2 and x3.

Arguments:
:param x1,x2,x3: arrays with data to be plotted
:param x1leg, x2leg, x3leg: legends for each histogram  
:param fig: which plot window should I use?

Example:
x1=Lbol(AD), x2=Lbol(JD), x3=Lbol(EHF10)

>>> threehists(x1,x2,x3,38,44,'AD','JD','EHF10','$\log L_{\\rm bol}$ (erg s$^{-1}$)')

Inspired by http://www.scipy.org/Cookbook/Matplotlib/Multiple_Subplots_with_One_Axis_Label.
    """
    pylab.rcParams.update({'font.size': fontsize})
    pylab.figure(fig)
    pylab.clf()

    pylab.subplot(3,1,1)
    pylab.hist(x1,label=x1leg,color='b',bins=bins1)
    pylab.legend(loc='best',frameon=False)

    pylab.subplot(3,1,2)
    pylab.hist(x2,label=x2leg,color='r',bins=bins2)
    pylab.legend(loc='best',frameon=False)

    pylab.subplot(3,1,3)
    pylab.hist(x3,label=x3leg,color='y',bins=bins3)
    pylab.legend(loc='best',frameon=False)

    pylab.minorticks_on()
    pylab.subplots_adjust(hspace=0.15)
    pylab.draw()
    pylab.show()

def plot_feat_hist(data_name_list, filename=None):
    pylab.clf()
    num_rows = 1 + (len(data_name_list) - 1) / 2
    num_cols = 1 if len(data_name_list) == 1 else 2
    pylab.figure(figsize=(5 * num_cols, 4 * num_rows))

    for i in range(num_rows):
        for j in range(num_cols):
            pylab.subplot(num_rows, num_cols, 1 + i * num_cols + j)
            x, name = data_name_list[i * num_cols + j]
            pylab.title(name)
            pylab.xlabel('Value')
            pylab.ylabel('Density')
            # the histogram of the data
            max_val = np.max(x)
            if max_val <= 1.0:
                bins = 50
            elif max_val > 50:
                bins = 50
            else:
                bins = max_val
            n, bins, patches = pylab.hist(
                x, bins=bins, normed=1, facecolor='green', alpha=0.75)

            pylab.grid(True)

    if not filename:
        filename = "feat_hist_%s.png" % name

    pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")

def plot_feat_hist(data_name_list, filename=None):
    if len(data_name_list) > 1:
        assert filename is not None

    pylab.figure(num=None, figsize=(8, 6))
    num_rows = int(1 + (len(data_name_list) - 1) / 2)
    num_cols = int(1 if len(data_name_list) == 1 else 2)
    pylab.figure(figsize=(5 * num_cols, 4 * num_rows))

    for i in range(num_rows):
        for j in range(num_cols):
            pylab.subplot(num_rows, num_cols, 1 + i * num_cols + j)
            x, name = data_name_list[i * num_cols + j]
            pylab.title(name)
            pylab.xlabel('Value')
            pylab.ylabel('Fraction')
            # the histogram of the data
            max_val = np.max(x)
            if max_val <= 1.0:
                bins = 50
            elif max_val > 50:
                bins = 50
            else:
                bins = max_val
            n, bins, patches = pylab.hist(
                x, bins=bins, normed=1, alpha=0.75)

            pylab.grid(True)

    if not filename:
        filename = "feat_hist_%s.png" % name.replace(" ", "_")

    pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")

def plot_feat_hist(data_name_list, filename=None):
    pylab.clf()
    num_rows = 1 + (len(data_name_list) - 1) / 2
    num_cols = 1 if len(data_name_list) == 1 else 2
    pylab.figure(figsize=(5 * num_cols, 4 * num_rows))

    for i in range(num_rows):
        for j in range(num_cols):
            pylab.subplot(num_rows, num_cols, 1 + i * num_cols + j)
            x, name = data_name_list[i * num_cols + j]
            pylab.title(name)
            pylab.xlabel('Value')
            pylab.ylabel('Density')
            # the histogram of the data
            max_val = np.max(x)
            if max_val <= 1.0:
                bins = 50
            elif max_val > 50:
                bins = 50
            else:
                bins = max_val
            n, bins, patches = pylab.hist(
                x, bins=bins, normed=1, facecolor='green', alpha=0.75)

            pylab.grid(True)

    if not filename:
        filename = "feat_hist_%s.png" % name

    pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")

def plot_feat_hist(data_name_list, filename=None):
    if len(data_name_list)>1:
        assert filename is not None

    pylab.figure(num=None, figsize=(8, 6))
    num_rows = 1 + (len(data_name_list) - 1) / 2
    num_cols = 1 if len(data_name_list) == 1 else 2
    pylab.figure(figsize=(5 * num_cols, 4 * num_rows))

    for i in range(num_rows):
        for j in range(num_cols):
            pylab.subplot(num_rows, num_cols, 1 + i * num_cols + j)
            x, name = data_name_list[i * num_cols + j]
            pylab.title(name)
            pylab.xlabel('Value')
            pylab.ylabel('Fraction')
            # the histogram of the data
            max_val = np.max(x)
            if max_val <= 1.0:
                bins = 50
            elif max_val > 50:
                bins = 50
            else:
                bins = max_val
            n, bins, patches = pylab.hist(
                x,  normed=1, facecolor='blue', alpha=0.75)

            pylab.grid(True)

    if not filename:
        filename = "feat_hist_%s.png" % name.replace(" ", "_")

    pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")

def plot_feat_hist(data_name_list, filename=None):
    if len(data_name_list)>1:
        assert filename is not None

    pylab.figure(num=None, figsize=(8, 6))
    num_rows = 1 + (len(data_name_list) - 1) / 2
    num_cols = 1 if len(data_name_list) == 1 else 2
    pylab.figure(figsize=(5 * num_cols, 4 * num_rows))

    for i in range(num_rows):
        for j in range(num_cols):
            pylab.subplot(num_rows, num_cols, 1 + i * num_cols + j)
            x, name = data_name_list[i * num_cols + j]
            pylab.title(name)
            pylab.xlabel('Value')
            pylab.ylabel('Fraction')
            # the histogram of the data
            max_val = np.max(x)
            if max_val <= 1.0:
                bins = 50
            elif max_val > 50:
                bins = 50
            else:
                bins = max_val
            n, bins, patches = pylab.hist(
                x,  normed=1, facecolor='blue', alpha=0.75)

            pylab.grid(True)

    if not filename:
        filename = "feat_hist_%s.png" % name.replace(" ", "_")

    pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")

def twohists(x1,x2,xmin,xmax,range=None,x1leg='$x_1$',x2leg='$x_2$',xlabel='',fig=1,sharey=False,fontsize=12,bins1=10,bins2=10):
    """
Script that plots two histograms of quantities x1 and x2
sharing the same X-axis.

:param x1,x2: arrays with data to be plotted
:param xmin,xmax: lower and upper range of plotted values, will be used to set a consistent x-range
    for both histograms.
:param x1leg, x2leg: legends for each histogram 
:param xlabel: self-explanatory.
:param bins1,bins2: number of bins in each histogram
:param fig: which plot window should I use?
:param range: in the form (xmin,xmax), same as range argument for hist and applied to both
    histograms.

Inspired by `Scipy <http://www.scipy.org/Cookbook/Matplotlib/Multiple_Subplots_with_One_Axis_Label>`_.
    """

    pylab.rcParams.update({'font.size': fontsize})
    fig=pylab.figure(fig)
    pylab.clf()

    a=fig.add_subplot(2,1,1)
    if sharey==True:
        b=fig.add_subplot(2,1,2, sharex=a, sharey=a)
    else:
        b=fig.add_subplot(2,1,2, sharex=a)

    a.hist(x1,bins1,label=x1leg,color='b',histtype='stepfilled',range=range)
    a.legend(loc='best',frameon=False)
    a.set_xlim(xmin,xmax)

    b.hist(x2,bins2,label=x2leg,color='r',histtype='stepfilled',range=range)
    b.legend(loc='best',frameon=False)

    pylab.setp(a.get_xticklabels(), visible=False)

    b.set_xlabel(xlabel)
    b.set_ylabel('Number',verticalalignment='bottom')
    pylab.minorticks_on()
    pylab.subplots_adjust(hspace=0.15)
    pylab.draw()
    pylab.show()

def threehists(x1,x2,x3,xmin,xmax,x1leg='$x_1$',x2leg='$x_2$',x3leg='$x_3$',xlabel='',fig=1,sharey=False,fontsize=12):
    """
Script that plots three histograms of quantities x1, x2 and x3 
sharing the same X-axis.

Arguments:
- x1,x2,x3: arrays with data to be plotted
- xmin,xmax: lower and upper range of plotted values, will be used to set a consistent x-range for both histograms.
- x1leg, x2leg, x3leg: legends for each histogram   
- xlabel: self-explanatory.
- sharey: sharing the Y-axis among the histograms?
- fig: which plot window should I use?

Example:
x1=Lbol(AD), x2=Lbol(JD), x3=Lbol(EHF10)

>>> threehists(x1,x2,x3,38,44,'AD','JD','EHF10','$\log L_{\\rm bol}$ (erg s$^{-1}$)',sharey=True)

Inspired by `Scipy <http://www.scipy.org/Cookbook/Matplotlib/Multiple_Subplots_with_One_Axis_Label>`_.
    """
    pylab.rcParams.update({'font.size': fontsize})
    fig=pylab.figure(fig)
    pylab.clf()

    a=fig.add_subplot(3,1,1)
    if sharey==True:
        b=fig.add_subplot(3,1,2, sharex=a, sharey=a)
        c=fig.add_subplot(3,1,3, sharex=a, sharey=a)
    else:
        b=fig.add_subplot(3,1,2, sharex=a)
        c=fig.add_subplot(3,1,3, sharex=a)      

    a.hist(x1,label=x1leg,color='b',histtype='stepfilled')
    a.legend(loc='best',frameon=False)
    a.set_xlim(xmin,xmax)

    b.hist(x2,label=x2leg,color='r',histtype='stepfilled')
    b.legend(loc='best',frameon=False)

    c.hist(x3,label=x3leg,color='y',histtype='stepfilled')
    c.legend(loc='best',frameon=False)

    pylab.setp(a.get_xticklabels(), visible=False)
    pylab.setp(b.get_xticklabels(), visible=False)

    c.set_xlabel(xlabel)
    b.set_ylabel('Number')
    pylab.minorticks_on()
    pylab.subplots_adjust(hspace=0.15)
    pylab.draw()
    pylab.show()

def fourcumplot(x1,x2,x3,x4,xmin,xmax,x1leg='$x_1$',x2leg='$x_2$',x3leg='$x_3$',x4leg='$x_3$',xlabel='',ylabel='$N(x>x\')$',fig=1,sharey=False,fontsize=12,bins1=50,bins2=50,bins3=50,bins4=50):
    """
Script that plots the cumulative histograms of four variables x1, x2, x3 and x4
sharing the same X-axis. For each bin, Y is the fraction of the sample 
with values above X.

Arguments:

- x1,x2,x3,x4: arrays with data to be plotted
- xmin,xmax: lower and upper range of plotted values, will be used to set a consistent x-range
for both histograms.
- x1leg, x2leg, x3leg, x4leg: legends for each histogram    
- xlabel: self-explanatory.
- sharey: sharing the Y-axis among the histograms?
- bins1,bins2,...: number of bins in each histogram
- fig: which plot window should I use?

Inspired by `Scipy <http://www.scipy.org/Cookbook/Matplotlib/Multiple_Subplots_with_One_Axis_Label>`_.

v1 Jun. 2012: inherited from fourhists.
    """
    pylab.rcParams.update({'font.size': fontsize})
    fig=pylab.figure(fig)
    pylab.clf()

    a=fig.add_subplot(4,1,1)
    if sharey==True:
        b=fig.add_subplot(4,1,2, sharex=a, sharey=a)
        c=fig.add_subplot(4,1,3, sharex=a, sharey=a)
        d=fig.add_subplot(4,1,4, sharex=a, sharey=a)
    else:
        b=fig.add_subplot(4,1,2, sharex=a)
        c=fig.add_subplot(4,1,3, sharex=a)      
        d=fig.add_subplot(4,1,4, sharex=a)

    a.hist(x1,bins1,label=x1leg,color='b',cumulative=-True,normed=True,histtype='stepfilled')
    a.legend(loc='best',frameon=False)
    a.set_xlim(xmin,xmax)

    b.hist(x2,bins2,label=x2leg,color='r',cumulative=-True,normed=True,histtype='stepfilled')
    b.legend(loc='best',frameon=False)

    c.hist(x3,bins3,label=x3leg,color='y',cumulative=-True,normed=True,histtype='stepfilled')
    c.legend(loc='best',frameon=False)

    d.hist(x4,bins4,label=x4leg,color='g',cumulative=-True,normed=True,histtype='stepfilled')
    d.legend(loc='best',frameon=False)

    pylab.setp(a.get_xticklabels(), visible=False)
    pylab.setp(b.get_xticklabels(), visible=False)
    pylab.setp(c.get_xticklabels(), visible=False)

    d.set_xlabel(xlabel)
    c.set_ylabel(ylabel)
    pylab.minorticks_on()
    pylab.subplots_adjust(hspace=0.15)
    pylab.draw()
    pylab.show()