In [68]:

    

import pandas
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import pandas as pd


    

In [21]:

    

df = pandas.read_hdf('xenon_test_data.h5')


    

In [11]:

    

df.head()


    

    
Out[11]:







  

    

      

      
run_number
      
event_number
      
s2_area_tailcut_set_by
      
s2_over_tdiff
      
tailcut_set_by
      
s1_1_50p_width
      
s1_1_aft
      
s1_1_area
      
s1_1_center_time
      
s1_1_largest_hit_area
      
...
      
s2_1_largest_hit_area
      
s2_1_posrec_goodness_of_fit
      
s2_1_posrec_goodness_of_fit_nn
      
s2_1_rise_time
      
s2_1_x
      
s2_1_x_nn
      
s2_1_y
      
s2_1_y_nn
      
s2_area_tot
      
unknown_tot
    
  
  

    

      
0
      
8311
      
0
      
0.000000e+00
      
0.000000
      
0
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
...
      
24853.009766
      
5235.186035
      
5601.398438
      
2097.895490
      
39.483608
      
39.881187
      
5.400494
      
5.610683
      
2.248347e+06
      
104.887558
    
    

      
1
      
8311
      
1
      
1.807614e+06
      
0.006926
      
1
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
...
      
33773.347656
      
6311.308594
      
7602.618164
      
1732.494589
      
3.000274
      
3.363387
      
38.043476
      
38.652359
      
1.073046e+06
      
57.850218
    
    

      
2
      
8311
      
2
      
3.333279e+05
      
0.024004
      
1
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
...
      
9166.551758
      
3222.168213
      
4315.865723
      
1890.164546
      
17.401590
      
18.061518
      
22.682072
      
23.084337
      
7.985587e+05
      
38.340455
    
    

      
3
      
8311
      
3
      
6.279493e+05
      
0.013589
      
1
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
...
      
5824.653809
      
1523.922852
      
1529.161743
      
3616.212444
      
-4.440406
      
-4.329351
      
33.723080
      
33.980186
      
2.214664e+05
      
37.059336
    
    

      
4
      
8311
      
4
      
1.807614e+06
      
0.003888
      
4
      
NaN
      
NaN
      
NaN
      
NaN
      
NaN
      
...
      
103230.492188
      
57072.730469
      
59293.273438
      
1676.072953
      
0.600055
      
0.041201
      
40.203674
      
41.187222
      
2.451366e+06
      
105.301023
    
  

5 rows × 260 columns

In [18]:

    

type(df['s2']), df['s2'].head()


    

    
Out[18]:





(pandas.core.series.Series, 0    1.807614e+06
 1    3.333279e+05
 2    6.279493e+05
 3    1.461776e+05
 4    1.135693e+06
 Name: s2, dtype: float64)

In [25]:

    

list(df.columns)


    

    
Out[25]:





['run_number',
 'event_number',
 's2_area_tailcut_set_by',
 's2_over_tdiff',
 'tailcut_set_by',
 's1_1_50p_width',
 's1_1_aft',
 's1_1_area',
 's1_1_center_time',
 's1_1_largest_hit_area',
 's1_1_posrec_goodness_of_fit',
 's1_1_rise_time',
 's1_1_x',
 's1_1_y',
 'alt_s1_interaction_z',
 'alt_s2_interaction_s2_range_50p_area',
 'alt_s2_interaction_s2_range_80p_area',
 'alt_s2_interaction_x',
 'alt_s2_interaction_y',
 'alt_s2_interaction_z',
 'other_s2_area',
 'other_s2_delay_main_s1',
 'other_s2_delay_main_s2',
 'other_s2_pattern_fit',
 'r_pos_correction',
 's1_area_fraction_top_probability',
 's1_largest_hit_area',
 's1_pattern_fit',
 's1_range_80p_area',
 's1_rise_time',
 's1_tight_coincidence',
 's2_pattern_fit',
 's2_range_80p_area',
 's2_rise_time',
 'sum_s1s_before_main_s2',
 'x_nn',
 'x_tpff',
 'y_nn',
 'y_tpff',
 'z_pos_correction',
 'nearest_1e5pe_event',
 'nearest_1e6pe_event',
 'nearest_3e5pe_event',
 'nearest_busy',
 'nearest_busy_off',
 'nearest_busy_on',
 'nearest_event',
 'nearest_hev',
 'nearest_hev_off',
 'nearest_hev_on',
 'nearest_muon_veto_trigger',
 'nearest_s2_area',
 'next_1e5pe_event',
 'next_1e6pe_event',
 'next_3e5pe_event',
 'next_busy',
 'next_busy_off',
 'next_busy_on',
 'next_event',
 'next_hev',
 'next_hev_off',
 'next_hev_on',
 'next_muon_veto_trigger',
 'next_s2_area',
 'previous_1e5pe_event',
 'previous_1e6pe_event',
 'previous_3e5pe_event',
 'previous_busy',
 'previous_busy_off',
 'previous_busy_on',
 'previous_event',
 'previous_hev',
 'previous_hev_off',
 'previous_hev_on',
 'previous_muon_veto_trigger',
 'previous_s2_area',
 'area_before_main_s2',
 'n_true_peaks',
 'total_peak_area',
 'event_duration',
 'event_time',
 'ds_s1_b_n_distinct_channels',
 'int_a_drift_time',
 'int_a_s1_area_correction',
 'int_a_s1_pattern_fit',
 'int_a_s2_area_correction',
 'int_a_x',
 'int_a_y',
 'int_a_z',
 'int_b_drift_time',
 'int_b_s1_area_correction',
 'int_b_s1_pattern_fit',
 'int_b_s2_area_correction',
 'int_b_x',
 'int_b_y',
 'int_b_z',
 's1_2',
 's1_2_area_fraction_top',
 's1_2_center_time',
 's1_2_n_contributing_channels',
 's1_2_range_50p_area',
 's1_a',
 's1_a_area_fraction_top',
 's1_a_center_time',
 's1_a_n_contributing_channels',
 's1_a_range_50p_area',
 's1_b',
 's1_b_area_fraction_top',
 's1_b_center_time',
 's1_b_n_contributing_channels',
 's1_b_range_50p_area',
 's2_2',
 's2_2_area_fraction_top',
 's2_2_center_time',
 's2_2_n_contributing_channels',
 's2_2_range_50p_area',
 's2_a',
 's2_a_area_fraction_top',
 's2_a_center_time',
 's2_a_n_contributing_channels',
 's2_a_range_50p_area',
 's2_b',
 's2_b_area_fraction_top',
 's2_b_center_time',
 's2_b_n_contributing_channels',
 's2_b_range_50p_area',
 'cs1',
 'cs2',
 'cs2_bottom',
 'cs2_top',
 'r',
 'r_3d_nn',
 'r_3d_tpf',
 'r_correction_2d',
 'r_correction_3d_nn',
 'r_correction_3d_tpf',
 'r_observed',
 'r_observed_nn',
 'r_observed_tpf',
 's1_xyz_correction',
 's2_lifetime_correction',
 's2_xy_correction_bottom',
 's2_xy_correction_top',
 's2_xy_correction_tot',
 'ts',
 'x',
 'x_3d_nn',
 'x_3d_tpf',
 'x_observed_nn',
 'x_observed_tpf',
 'y',
 'y_3d_nn',
 'y_3d_tpf',
 'y_observed_nn',
 'y_observed_tpf',
 'z_3d_nn',
 'z_3d_tpf',
 'z_correction_2d',
 'z_correction_3d_nn',
 'z_correction_3d_tpf',
 'z_observed',
 'lone_hit_area',
 'lone_hit_area_fraction_top',
 'lone_hit_center_time',
 'lone_hit_hit_time_std',
 'lone_hit_n_contributing_channels',
 'lone_hit_n_hits',
 'lone_hit_n_saturated_channels',
 'lone_hit_range_50p_area',
 'lone_hit_range_90p_area',
 'lone_hit_x',
 'lone_hit_y',
 's1_area',
 's1_center_time',
 's1_hit_time_std',
 's1_n_contributing_channels',
 's1_n_hits',
 's1_n_saturated_channels',
 's1_range_90p_area',
 's1_x',
 's1_y',
 's2_area',
 's2_center_time',
 's2_hit_time_std',
 's2_n_contributing_channels',
 's2_n_hits',
 's2_n_saturated_channels',
 's2_range_90p_area',
 's2_x',
 's2_y',
 'unknown_area',
 'unknown_area_fraction_top',
 'unknown_center_time',
 'unknown_hit_time_std',
 'unknown_n_contributing_channels',
 'unknown_n_hits',
 'unknown_n_saturated_channels',
 'unknown_range_50p_area',
 'unknown_range_90p_area',
 'unknown_x',
 'unknown_y',
 'drift_time',
 'largest_coincidence',
 'largest_other_s1',
 'largest_other_s2',
 'largest_unknown',
 'largest_veto',
 's1',
 's1_area_fraction_top',
 's1_range_50p_area',
 's2',
 's2_area_fraction_top',
 's2_range_50p_area',
 'x_pax',
 'y_pax',
 'z',
 'area_before_largest_s1',
 'area_before_largest_s2',
 'n_interactions',
 'n_peaks',
 'n_pulses',
 'n_s1',
 'n_s2',
 's1_0_50p_width',
 's1_0_aft',
 's1_0_area',
 's1_0_center_time',
 's1_0_largest_hit_area',
 's1_0_posrec_goodness_of_fit',
 's1_0_rise_time',
 's1_0_x',
 's1_0_y',
 's1_area_tot',
 's2_0_50p_width',
 's2_0_aft',
 's2_0_area',
 's2_0_center_time',
 's2_0_largest_hit_area',
 's2_0_left',
 's2_0_posrec_goodness_of_fit',
 's2_0_posrec_goodness_of_fit_nn',
 's2_0_rise_time',
 's2_0_x',
 's2_0_x_nn',
 's2_0_y',
 's2_0_y_nn',
 's2_1_50p_width',
 's2_1_aft',
 's2_1_area',
 's2_1_center_time',
 's2_1_largest_hit_area',
 's2_1_posrec_goodness_of_fit',
 's2_1_posrec_goodness_of_fit_nn',
 's2_1_rise_time',
 's2_1_x',
 's2_1_x_nn',
 's2_1_y',
 's2_1_y_nn',
 's2_area_tot',
 'unknown_tot',
 'CutAllEnergy',
 'CutFiducialCylinder1T',
 'CutInteractionExists',
 'CutS2Threshold',
 'CutS2AreaFractionTop',
 'CutS2SingleScatter',
 'CutDAQVeto',
 'CutEndOfRunCheck',
 'CutBusyTypeCheck',
 'CutBusyCheck',
 'CutHEVCheck',
 'CutS1SingleScatter',
 'CutS1AreaFractionTop',
 'CutS2PatternLikelihood',
 'CutS2Tails',
 'CutInteractionPeaksBiggest',
 'CutLowEnergyBackground',
 'CutS1LowEnergyRange',
 'CutS2SingleScatterSimple',
 'CutS1PatternLikelihood',
 'CutS2Width',
 'CutS2WidthHigh',
 'CutS2WidthLow',
 'CutS1MaxPMT',
 'CutPreS2Junk']

In [26]:

    

df['event_number'].hist()


    

    
Out[26]:





<matplotlib.axes._subplots.AxesSubplot at 0x7efe3f961f60>






    

In [15]:

    

!pwd


    

    




/ML_platform_tests/tutorial/chris

In [28]:

    

df['CutAllEnergy'].value_counts()


    

    
Out[28]:





False    101166
True         68
Name: CutAllEnergy, dtype: int64

In [30]:

    

df2 = df[df['CutAllEnergy']]


    

In [36]:

    

plt.plot(df2.cs1, df2.cs2, '.')


    

    
Out[36]:





[<matplotlib.lines.Line2D at 0x7efe3f825c88>]






    

In [39]:

    

plt.plot(df2.x, df2.z, '.')


    

    
Out[39]:





[<matplotlib.lines.Line2D at 0x7efe3d0be940>]






    

In [38]:

    

plt.plot(df.x, df.y, '.')


    

    
Out[38]:





[<matplotlib.lines.Line2D at 0x7efe3d0824e0>]






    

In [42]:

    

df['r'] = np.sqrt(df['x']**2 + df['y']**2)


    

In [46]:

    

df['r'].hist()


    

    
Out[46]:





<matplotlib.axes._subplots.AxesSubplot at 0x7efe380c1da0>






    

In [57]:

    

E = 40
plt.scatter(df2['cs1'], df2['cs2'])
plt.xlim(0, 300)
plt.ylim(0, 20e3)


    

    
Out[57]:





(0, 20000.0)






    

In [63]:

    

df2.loc[:, ('cs1', 'cs2')].head()


    

    
Out[63]:







  

    

      

      
cs1
      
cs2
    
  
  

    

      
152
      
778.113314
      
39673.505884
    
    

      
682
      
11.019045
      
1750.988897
    
    

      
1897
      
250.581678
      
7822.072664
    
    

      
3796
      
1266.924975
      
76882.724028
    
    

      
5781
      
13.925521
      
2272.624209
    
  

In [71]:

    

pd.to_datetime(df2['event_time']).head()


    

    
Out[71]:





152    2017-03-30 05:28:01.948269350
682    2017-03-30 05:28:57.160364610
1897   2017-03-30 05:31:05.326684670
3796   2017-03-30 05:34:32.639400520
5781   2017-03-30 05:37:59.041098160
Name: event_time, dtype: datetime64[ns]

In [72]:

    

df2.index = pd.to_datetime(df2['event_time'])


    

In [76]:

    

df2['z'].plot()


    

    
Out[76]:





<matplotlib.axes._subplots.AxesSubplot at 0x7efe30a2c0f0>






    

In [78]:

    

df['CutLowEnergyBackground'].value_counts()


    

    
Out[78]:





False    101213
True         21
Name: CutLowEnergyBackground, dtype: int64

In [82]:

    

df3 = df[df['CutLowEnergyBackground']]
plt.scatter(df3.cs1, df3.cs2)
plt.xlabel('cs1 [PE]')
plt.ylabel('cs1 [PE]')
plt.xscale('log')
plt.yscale('log')


    

In [86]:

    

df3 = df[df['CutAllEnergy']]
plt.scatter(df3.s2, df3.z)
plt.xlabel('s2 [PE]')
plt.ylabel('z [PE]')


    

    
Out[86]:





Text(0,0.5,'z [PE]')






    

In [ ]: