Python：如何在一个直方图中绘制多列答案

【问题标题】：Python: How to plot multiple columns in one histogramPython：如何在一个直方图中绘制多列
【发布时间】：2021-03-26 03:57:52
【问题描述】：

我正在学习 python，我坚持的事情是根据 FLT 列绘制一个直方图来指示每个过滤器。我有这个数据框：

    VARLIST:      MJD FLT  FIELD  FLUXCAL  FLUXCALERR     MAG  MAGERR  \
0       OBS:  55161.6   g    NaN  -62.016      23.428     NaN  -0.410   
1       OBS:  55176.6   g    NaN   -8.183      21.252     NaN  -2.820   
2       OBS:  55179.6   g    NaN    0.451      19.109  -4.134  46.053   
3       OBS:  55188.6   g    NaN  511.964      21.218 -11.773   0.045   
4       OBS:  55206.6   g    NaN  682.704      22.329 -12.086   0.036   
..       ...      ...  ..    ...      ...         ...     ...     ...   
259     OBS:  56659.6   z    NaN  193.577      44.434 -10.717   0.249   
260     OBS:  56662.6   z    NaN    2.728      30.422  -6.089  12.109   
261     OBS:  56667.7   z    NaN   51.009      30.915  -9.269   0.658   
262     OBS:  56681.5   z    NaN    8.945      30.450  -7.379   3.696   
263     OBS:  56754.3   z    NaN   12.488      60.586  -7.741   5.268   

     peakMJD  mag_zpt27.5  snr_zpt27.5  magerr_zpt27.5  
0    55206.6    23.018741    -2.647089       -0.410262  
1    55206.6    25.217719    -0.385046       -2.820441  
2    55206.6    28.364559     0.023601       46.014133  
3    55206.6    20.726901    24.128759        0.045009  
4    55206.6    20.414419    30.574768        0.035519  
..       ...          ...          ...             ...  
259  55206.6    21.782866     4.356506        0.249282  
260  55206.6    26.410389     0.089672       12.110811  
261  55206.6    23.230883     1.649976        0.658191  
262  55206.6    25.121049     0.293760        3.696892  
263  55206.6    24.758768     0.206120        5.268770

我的目标是绘制 FLT 列，但要指明不同的过滤器：g、i、r 和 z。通过搜索如何制作直方图，我可以绘制基于 MAG（幅度）的基本图。理想情况下，我想要的是 4 种不同的颜色来表示不同的过滤器。我知道该图会与过滤器重叠 Mag，但我可以接受，因为我需要视觉效果，如果需要，我可以放大。

下面的代码就是我现在所拥有的。它现在很重要，因为我一直在查看文档并且无处可去。需要注意的是，中间是一堆关于我的尝试的cmets。一种是遍历每一行并查看过滤器然后绘制图表，但我无法弄清楚。另一个想法是创建 4 个新列，每个过滤器一个，然后绘制每一列。我被卡住了，无法弄清楚。

#HISTOGRAM
def plot_histogram(source, data_file):
    if source == 'villar':
        filename, ext = os.path.splitext(data_file)
        SnName_villar = filename[34:-6]

        # read in for clarifying info
        ps1_phot_info = pd.read_csv(data_file)

        ra_deg = ps1_phot_info.loc[2][0][11:19] #deg
        dec_deg = ps1_phot_info.loc[3][0][12:19] #deg
        final_z_villar = ps1_phot_info.loc[5][0][17:23] 

        # read in for data
        ps1_phot = pd.read_csv(data_file, skiprows=15, delim_whitespace=True)
        ps1_phot.drop(ps1_phot.tail(1).index,inplace=True)

        ps1_phot['peakMJD'] = ps1_phot.iloc[ps1_phot['FLUXCAL'].idxmax()]["MJD"] 
        
        # Calculate mag. Look at zeropoints (A. Villar = 32.5, YSE = 27.5)
        ps1_phot['mag_zpt27.5'] = np.array(-2.5*np.log10(np.abs(ps1_phot['FLUXCAL'])))+27.5
        ps1_phot['snr_zpt27.5'] = (ps1_phot['FLUXCAL'] / np.abs(ps1_phot['FLUXCALERR']))
        ps1_phot['magerr_zpt27.5'] = np.array(1.086 / ps1_phot['snr_zpt27.5'])



        mask = (ps1_phot['FLUXCAL'].notna()) #& (ps1_phot['FLUXCALERR'] <= 50) 
        ps1_masked = ps1_phot.loc[mask] #has mag obs and reasonable error

        print(ps1_masked)


        ps1_phot['peakMJD'] = ps1_phot.iloc[ps1_phot['FLUXCAL'].idxmax()]["MJD"] 
        print('here')
        print(ps1_phot)

        #Calculate mag. Look at zeropoints (A. Villar = 32.5, YSE = 27.5)
        ps1_phot['mag_zpt27.5'] = np.array(-2.5*np.log10(np.abs(ps1_phot['FLUXCAL'])))+27.5
        ps1_phot['snr_zpt27.5'] = (ps1_phot['FLUXCAL'] / np.abs(ps1_phot['FLUXCALERR']))
        ps1_phot['magerr_zpt27.5'] = np.array(1.086 / ps1_phot['snr_zpt27.5'])



        mask = (ps1_phot['FLUXCAL'].notna()) #& (ps1_phot['FLUXCALERR'] <= 50) 
        ps1_masked = ps1_phot.loc[mask] #has mag obs and reasonable error

        #print(ps1_masked)
        #ps1_phot['g_band'] = ps1_phot.iloc[ps1_phot['FLT']=='g']
        #print("THIS IS THE G BAND")
        #print(ps1_masked)
        #ps1_phot['r_band'] = ps1_phot.iloc[ps1_phot['FLT']=='r']
        #print("THIS IS THE R BAND")
        #print(ps1_masked)
        #ps1_phot['i_band'] = ps1_phot.iloc[ps1_phot['FLT']=='i']
        #print("THIS IS THE I BAND")
        #print(ps1_masked)
        #ps1_phot['z_band'] = ps1_phot.iloc[ps1_phot['FLT']=='z']
        #print("THIS IS THE Z BAND")
        #print(ps1_masked)
        
        #for pb in passbands:
        #    plt.hist(x=ps1_masked[''])

        #numpy.histogram(a, bins=10, range=None, normed=None, weights=None, density=None)[source]
        
        
        #passbands = ('g', 'r', 'i', 'z')
        #for pb in passbands:
        #    #x = passbands[pd]
            
        #    #blah blah code --> Plot histogram
        #    #errorbar only for scatter plot
        #    ax1.errorbar(x=ps1_masked[passbands[pd]]['MJD'] - ps1_masked[passbands[pd]]['peakMJD'], y=ps1_masked[passbands[pd]][f'{yaxis_is}'], yerr=ps1_masked[passbands[pd]][f'{yaxiserr_is}'],
        #    fmt='o', alpha=0.5, color='g', label=f'{x}-PS1')
        #ax1.ticklabel_format(useOffset=False, style='plain')
        
        yaxis_is = 'mag_zpt27.5' # or FLUXCAL
        yaxiserr_is = 'magerr_zpt27.5' # or FLUXCALERR
        
        fig = plt.figure(figsize=(12, 4))
        ax1 = fig.add_subplot(121)

        ax1.set_ylabel('Observations', fontsize=16)
        ax1.set_xlabel('Mag', fontsize=16)
        ax1.tick_params(labelsize=12)
        ax1.set_title(f'{SnName_yse}, z_yse={final_z_yse}; {SnName_villar}, z_villar={final_z_villar}', fontsize=16)

        #Plot

        ps1_phot['mag_zpt27.5'].hist()
        plt.savefig(f"path/to/file/my_plot_{pb}.png")

        plt.tight_layout()
        plt.show()

        fig.savefig(f'./Villar_Data_Graphs/{SnName_villar}_{SnName_yse}_{yaxis_is}_Histogram.png', format='png', bbox_inches='tight', dpi=300)    
        plt.close(fig) 
    
    
    #Read all the files "fileV = sorted(glob.glob('./Villar/ps1_sne_zenodo/*.dat'))" and then supernova type (has the same) 
    # check the redshift to see if the are comparable (range +/- 0.1)

这是我调用上面函数的地方

x = './Villar/ps1_sne_zenodo/PS1_PS1MD_PSc000186.snana.dat'
SnName_villar, final_z_villar, ps1_masked_g, ps1_masked_r, ps1_masked_i, ps1_masked_z = get_dataframes(source='villar', data_file=x, plot_color='c', sntype_label='VIa')

y = './Photpipe/yselc_v3_photoz/GPC1v3_2020add.snana.dat'
SnName_yse, final_z_yse, pp_phot_g, pp_phot_r, pp_phot_i, pp_phot_z = get_dataframes(source='yse', data_file=y, plot_color='b', sntype_label='VIa')

plot_villar_and_yse(SnName_villar, final_z_villar, ps1_masked_g, ps1_masked_r, ps1_masked_i, ps1_masked_z, 
              SnName_yse, final_z_yse, pp_phot_g, pp_phot_r, pp_phot_i, pp_phot_z)


plot_histogram(source='villar', data_file=x)
#Call and plot histogram function

请告诉我你的想法和建议。

【问题讨论】：

标签： python pandas matplotlib histogram

【解决方案1】：

这可以使用Seaborn's histplot function 相对简单地完成。

import pandas as pd
import numpy as np
import seaborn as sns

# construct some sample data
ps1_phot = pd.concat([pd.DataFrame({'FLT': flt, 'MAG': np.random.randn(1000) + i}) for i, flt in enumerate('girz')])

# plot overlapping histograms
sns.histplot(ps1_phot.dropna(subset=['MAG']), x='MAG', hue='FLT')

结果

【讨论】：

非常感谢您。我永远被困在这上面，而你可以用两行来做到这一点。这太棒了，感谢您让我了解 Seaborn 的 histplot 函数！
我想问一下你是怎么得到这些颜色的？我还想问你是如何得到x轴的。 Mag 值应该在 14-26 之间，我对你如何得到负值感到特别困惑
没问题！ Seaborn 使用列的名称来获取轴和图例的标签。负值只是由于我生成的样本数据，因为您没有提供完整的数据集。

【解决方案2】：

seaborn 是要走的路。要绘制分布，您在 seaborn 库中有几个选项：sns.distplot()、sns.kdeplot()、sns.boxplot()、sns.histplot()。我个人喜欢使用 sns.distplot()，因为它提供了显示直方图和曲线的选项。

【讨论】：