notebook.community

Edit and run



In [56]:

    
import numpy as np
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt

from scipy import linspace, polyval, polyfit, sqrt, stats, randn
from sklearn import datasets, linear_model
%matplotlib inline



In [57]:

    
# Import sensor data indexed by Timestamp
sensor_df = pd.read_csv('HHtest.txt', names = ["Sensor", "Seconds", "Timestamp", "Temp", "Rel Humid", "Voltage"], index_col = ['Timestamp'], parse_dates = ["Timestamp"])
# Delete unneeded columns
sensor_df.drop(['Sensor','Seconds','Voltage'], axis = 1, inplace = True)
sensor_df[:3]









    Out[57]:






  
    
      
      Temp
      Rel Humid
    
    
      Timestamp
      
      
    
  
  
    
      2016-07-07 14:59:53
      75.20
      60.0
    
    
      2016-07-07 15:15:42
      78.26
      57.1
    
    
      2016-07-07 15:31:30
      76.82
      44.5



In [58]:

    
#sensor_df.set_index(['Timestamp'], drop = False, inplace = True)
#sensor_df[:3]



In [59]:

    
# Resample for every 30 minutes and name according to midpoint
sensor_df = sensor_df.resample('30T', loffset = '-15 min').mean()
sensor_df.head









    Out[59]:





<bound method DataFrame.head of                       Temp  Rel Humid
Timestamp                            
2016-07-07 14:15:00  75.20      60.00
2016-07-07 14:45:00  78.26      57.10
2016-07-07 15:15:00  76.82      43.55
2016-07-07 15:45:00  76.01      45.05
2016-07-07 16:15:00  74.93      46.30
2016-07-07 16:45:00  74.12      49.05
2016-07-07 17:15:00  73.85      47.70
2016-07-07 17:45:00  73.58      48.25
2016-07-07 18:15:00  73.31      51.10
2016-07-07 18:45:00  73.22      50.80
2016-07-07 19:15:00  73.40      52.70
2016-07-07 19:45:00  73.04      51.20
2016-07-07 20:15:00  73.22      52.45
2016-07-07 20:45:00  72.95      53.85
2016-07-07 21:15:00  72.77      53.40
2016-07-07 21:45:00  72.86      54.15
2016-07-07 22:15:00  73.13      54.80
2016-07-07 22:45:00  72.59      53.70
2016-07-07 23:15:00  73.04      55.05
2016-07-07 23:45:00  72.86      55.40
2016-07-08 00:15:00  72.86      55.65
2016-07-08 00:45:00  72.86      55.70
2016-07-08 01:15:00  72.86      55.80
2016-07-08 01:45:00  72.86      55.70
2016-07-08 02:15:00  72.77      56.00
2016-07-08 02:45:00  72.77      56.20
2016-07-08 03:15:00  72.86      56.55
2016-07-08 03:45:00  72.77      56.55
2016-07-08 04:15:00  72.86      56.65
2016-07-08 04:45:00  72.86      56.45
...                    ...        ...
2016-09-14 22:15:00  79.25      55.80
2016-09-14 22:45:00  79.25      55.75
2016-09-14 23:15:00  79.25      55.35
2016-09-14 23:45:00  79.25      54.25
2016-09-15 00:15:00  79.16      53.30
2016-09-15 00:45:00  79.16      52.70
2016-09-15 01:15:00  79.16      52.60
2016-09-15 01:45:00  78.98      52.10
2016-09-15 02:15:00  78.98      51.60
2016-09-15 02:45:00  78.98      50.90
2016-09-15 03:15:00  78.98      50.45
2016-09-15 03:45:00  78.98      49.95
2016-09-15 04:15:00  78.89      49.60
2016-09-15 04:45:00  78.80      49.20
2016-09-15 05:15:00  78.80      49.15
2016-09-15 05:45:00  78.80      48.55
2016-09-15 06:15:00  78.80      48.00
2016-09-15 06:45:00  78.80      48.30
2016-09-15 07:15:00  78.35      41.60
2016-09-15 07:45:00  78.26      41.05
2016-09-15 08:15:00  78.08      41.00
2016-09-15 08:45:00  78.08      40.85
2016-09-15 09:15:00  77.99      40.65
2016-09-15 09:45:00  78.08      39.90
2016-09-15 10:15:00  77.72      39.05
2016-09-15 10:45:00  77.36      38.90
2016-09-15 11:15:00  77.54      43.00
2016-09-15 11:45:00  77.18      47.60
2016-09-15 12:15:00  77.18      54.50
2016-09-15 12:45:00  77.18      62.40

[3358 rows x 2 columns]>



In [61]:

    
# Import sensor data indexed by Timestamp
LGA_df = pd.read_csv('KLGA.csv', names = ["Timestamp", "Temp", "Rel Humid"], index_col = ['Timestamp'], parse_dates = ["Timestamp"])
#LGA_df = LGA_df.set_index(['Timestamp'])
LGA_df.head









    Out[61]:





<bound method DataFrame.head of                       Temp  Rel Humid
Timestamp                            
2016-07-01 02:00:00  75.22      60.98
2016-07-01 02:05:00  75.22      60.98
2016-07-01 02:10:00  75.22      60.98
2016-07-01 02:15:00  75.22      60.98
2016-07-01 02:20:00  75.22      60.98
2016-07-01 02:25:00  75.22      57.20
2016-07-01 02:30:00  75.22      57.20
2016-07-01 02:35:00  75.22      53.63
2016-07-01 02:40:00  75.22      53.63
2016-07-01 02:45:00  75.22      53.63
2016-07-01 02:50:00  75.22      53.63
2016-07-01 02:51:00  75.02      53.62
2016-07-01 02:55:00  75.22      53.63
2016-07-01 03:00:00  73.42      69.01
2016-07-01 03:05:00  73.42      69.01
2016-07-01 03:10:00  73.42      69.01
2016-07-01 03:15:00  73.42      69.01
2016-07-01 03:20:00  73.42      64.76
2016-07-01 03:25:00  73.42      64.76
2016-07-01 03:30:00  73.42      64.76
2016-07-01 03:35:00  73.42      64.76
2016-07-01 03:40:00  73.42      60.75
2016-07-01 03:45:00  73.42      60.75
2016-07-01 03:50:00  73.42      60.75
2016-07-01 03:51:00  73.94      60.75
2016-07-01 03:55:00  73.42      60.75
2016-07-01 04:00:00  73.42      60.75
2016-07-01 04:05:00  73.42      60.75
2016-07-01 04:10:00  73.42      60.75
2016-07-01 04:15:00  73.42      60.75
...                    ...        ...
2016-09-30 23:50:00  57.20      93.70
2016-09-30 23:51:00  57.92      93.70
2016-09-30 23:55:00  57.20      93.70
2016-10-01 00:00:00  57.20      93.70
2016-10-01 00:05:00  57.20      93.70
2016-10-01 00:10:00  57.20      93.70
2016-10-01 00:15:00  57.20      93.70
2016-10-01 00:20:00  57.20      93.70
2016-10-01 00:25:00  57.20      93.70
2016-10-01 00:30:00  57.20      93.70
2016-10-01 00:35:00  57.20      93.70
2016-10-01 00:40:00  57.20      93.70
2016-10-01 00:45:00  57.20      93.70
2016-10-01 00:50:00  57.20      93.70
2016-10-01 00:51:00  57.92      93.70
2016-10-01 00:55:00  57.20      93.70
2016-10-01 01:00:00  57.20      93.70
2016-10-01 01:05:00  57.20      93.70
2016-10-01 01:10:00  57.20      93.70
2016-10-01 01:15:00  57.20      93.70
2016-10-01 01:20:00  59.00      87.85
2016-10-01 01:25:00  57.20      93.70
2016-10-01 01:27:00  57.92      93.70
2016-10-01 01:30:00  57.20      93.70
2016-10-01 01:35:00  57.20      93.70
2016-10-01 01:40:00  57.20      93.70
2016-10-01 01:45:00  57.20      93.70
2016-10-01 01:50:00  57.20      93.70
2016-10-01 01:51:00  57.92      93.70
2016-10-01 01:55:00  57.20      93.70

[28262 rows x 2 columns]>



In [62]:

    
# Resample for every 30 minutes and name according to midpoint
LGA_df = LGA_df.resample('30T', loffset = '-15 min').mean()
LGA_df[:3]









    Out[62]:






  
    
      
      Temp
      Rel Humid
    
    
      Timestamp
      
      
    
  
  
    
      2016-07-01 01:45:00
      75.220000
      60.350000
    
    
      2016-07-01 02:15:00
      75.191429
      54.138571
    
    
      2016-07-01 02:45:00
      73.420000
      67.593333



In [38]:

    
# Join df together for all timestamps that exist in both files
joined_df = LGA_df.join(sensor_df, how = 'inner', lsuffix = '_LGA', rsuffix = '_sensor')
joined_df = joined_df.dropna() # drop NaN values
joined_df









    Out[38]:






  
    
      
      Temp_LGA
      Rel Humid_LGA
      Temp_sensor
      Rel Humid_sensor
    
    
      Timestamp
      
      
      
      
    
  
  
    
      2016-07-07 14:15:00
      85.502857
      67.405714
      75.20
      60.00
    
    
      2016-07-07 14:45:00
      83.920000
      70.441667
      78.26
      57.10
    
    
      2016-07-07 15:15:00
      87.585714
      59.391429
      76.82
      43.55
    
    
      2016-07-07 15:45:00
      85.420000
      63.580000
      76.01
      45.05
    
    
      2016-07-07 16:15:00
      87.714286
      56.904286
      74.93
      46.30
    
    
      2016-07-07 16:45:00
      86.920000
      61.275000
      74.12
      49.05
    
    
      2016-07-07 17:15:00
      84.320000
      66.630000
      73.85
      47.70
    
    
      2016-07-07 17:45:00
      83.920000
      66.006667
      73.58
      48.25
    
    
      2016-07-07 18:15:00
      80.797143
      72.445714
      73.31
      51.10
    
    
      2016-07-07 18:45:00
      78.820000
      77.903333
      73.22
      50.80
    
    
      2016-07-07 19:15:00
      80.282857
      74.831429
      73.40
      52.70
    
    
      2016-07-07 19:45:00
      79.420000
      77.183333
      73.04
      51.20
    
    
      2016-07-07 20:15:00
      79.100000
      78.038571
      73.22
      52.45
    
    
      2016-07-07 20:45:00
      80.320000
      74.938333
      72.95
      53.85
    
    
      2016-07-07 21:15:00
      79.614286
      76.755714
      72.77
      53.40
    
    
      2016-07-07 21:45:00
      78.820000
      78.680000
      72.86
      54.15
    
    
      2016-07-07 22:15:00
      78.842857
      80.788571
      73.13
      54.80
    
    
      2016-07-07 22:45:00
      78.220000
      80.283333
      72.59
      53.70
    
    
      2016-07-07 23:15:00
      77.531429
      82.114286
      73.04
      55.05
    
    
      2016-07-07 23:45:00
      75.520000
      88.688333
      72.86
      55.40
    
    
      2016-07-08 00:15:00
      75.191429
      88.620000
      72.86
      55.65
    
    
      2016-07-08 00:45:00
      74.920000
      89.536667
      72.86
      55.70
    
    
      2016-07-08 01:15:00
      74.420000
      90.977143
      72.86
      55.80
    
    
      2016-07-08 01:45:00
      74.920000
      89.536667
      72.86
      55.70
    
    
      2016-07-08 02:15:00
      75.320000
      88.620000
      72.77
      56.00
    
    
      2016-07-08 02:45:00
      75.220000
      88.620000
      72.77
      56.20
    
    
      2016-07-08 03:15:00
      73.751429
      93.334286
      72.86
      56.55
    
    
      2016-07-08 03:45:00
      75.220000
      88.681667
      72.77
      56.55
    
    
      2016-07-08 04:15:00
      75.834286
      87.154286
      72.86
      56.65
    
    
      2016-07-08 04:45:00
      74.320000
      91.370000
      72.86
      56.45
    
    
      ...
      ...
      ...
      ...
      ...
    
    
      2016-09-14 22:15:00
      75.817143
      60.508571
      79.25
      55.80
    
    
      2016-09-14 22:45:00
      73.700000
      58.958333
      79.25
      55.75
    
    
      2016-09-14 23:15:00
      71.908571
      56.222857
      79.25
      55.35
    
    
      2016-09-14 23:45:00
      71.600000
      54.900000
      79.25
      54.25
    
    
      2016-09-15 00:15:00
      69.825714
      56.440000
      79.16
      53.30
    
    
      2016-09-15 00:45:00
      69.800000
      57.078333
      79.16
      52.70
    
    
      2016-09-15 01:15:00
      69.028571
      53.751429
      79.16
      52.60
    
    
      2016-09-15 01:45:00
      68.000000
      50.860000
      78.98
      52.10
    
    
      2016-09-15 02:15:00
      68.000000
      52.000000
      78.98
      51.60
    
    
      2016-09-15 02:45:00
      66.800000
      58.590000
      78.98
      50.90
    
    
      2016-09-15 03:15:00
      66.174286
      58.135714
      78.98
      50.45
    
    
      2016-09-15 03:45:00
      66.200000
      55.930000
      78.98
      49.95
    
    
      2016-09-15 04:15:00
      64.477143
      59.540000
      78.89
      49.60
    
    
      2016-09-15 04:45:00
      64.400000
      58.895000
      78.80
      49.20
    
    
      2016-09-15 05:15:00
      64.348571
      58.434286
      78.80
      49.15
    
    
      2016-09-15 05:45:00
      64.100000
      57.565000
      78.80
      48.55
    
    
      2016-09-15 06:15:00
      62.651429
      59.300000
      78.80
      48.00
    
    
      2016-09-15 06:45:00
      63.500000
      57.485000
      78.80
      48.30
    
    
      2016-09-15 07:15:00
      64.348571
      55.670000
      78.35
      41.60
    
    
      2016-09-15 07:45:00
      64.400000
      55.670000
      78.26
      41.05
    
    
      2016-09-15 08:15:00
      65.917143
      50.331429
      78.08
      41.00
    
    
      2016-09-15 08:45:00
      66.500000
      48.380000
      78.08
      40.85
    
    
      2016-09-15 09:15:00
      67.742857
      45.918571
      77.99
      40.65
    
    
      2016-09-15 09:45:00
      69.200000
      43.153333
      78.08
      39.90
    
    
      2016-09-15 10:15:00
      69.825714
      40.340000
      77.72
      39.05
    
    
      2016-09-15 10:45:00
      70.100000
      40.388333
      77.36
      38.90
    
    
      2016-09-15 11:15:00
      69.825714
      40.340000
      77.54
      43.00
    
    
      2016-09-15 11:45:00
      70.700000
      39.145000
      77.18
      47.60
    
    
      2016-09-15 12:15:00
      71.522857
      37.228571
      77.18
      54.50
    
    
      2016-09-15 12:45:00
      71.600000
      37.106667
      77.18
      62.40
    
  

3063 rows × 4 columns



In [64]:

    
#Plot all data wrt time
fig_size = np.array(mpl.rcParams['figure.figsize']) # size of plot
fig_size *=2 # increase size of plot
joined_df.plot(figsize = fig_size) # plot data









    Out[64]:





<matplotlib.axes._subplots.AxesSubplot at 0x11b223450>



In [44]:

    
# Linear regression between temp at LGA and temp from sensor (without time data) using linear_model from sklearn 
TempLGA = np.transpose(np.matrix(joined_df['Temp_LGA']))
Tempsensor = np.transpose(np.matrix(joined_df['Temp_sensor']))

regr = linear_model.LinearRegression()
regr.fit(TempLGA, Tempsensor)

#z = polyfit(TempLGA, Tempsensor, 4) # polyfit for fitting
#p = np.poly1d(z) #polynomial of fit









    Out[44]:





LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)



In [90]:

    
# Attempt multivariable linear regression
LGA_data = np.transpose(np.array([joined_df['Temp_LGA'], joined_df['Rel Humid_LGA'],]))
print (LGA_data.shape)
sensor_data = np.transpose(np.array([joined_df['Temp_sensor'], joined_df['Rel Humid_sensor'],]))
print (sensor_data.shape)

mult_regr = linear_model.LinearRegression()
mult_regr.fit(LGA_data, sensor_data)
mult_regr.params()
#mult_regr.predict(LGA_data[:20]).shape









    



(3063, 2)
(3063, 2)






    Out[90]:





(20, 2)



In [85]:

    
plt.plot()









    Out[85]:





(2, 3)



In [86]:

    
plt.plot()









    Out[86]:





[]



In [45]:

    
plt.plot(TempLGA, Tempsensor, '.', TempLGA, regr.predict(TempLGA))
#plt.plot(TempLGA, Tempsensor, '.', TempLGA, p(TempLGA), '--')









    Out[45]:





[<matplotlib.lines.Line2D at 0x11c389c90>,
 <matplotlib.lines.Line2D at 0x11c389d50>]



In [51]:

    
TempLGA_arr = np.array(joined_df['Temp_LGA'][:30])
Tempsensor_arr = np.array(joined_df['Temp_sensor'][:30])
pd.rolling_corr(TempLGA_arr, Tempsensor_arr, 10).plot()









    



/Users/Zelda/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:3: FutureWarning: pd.rolling_corr is deprecated for ndarrays and will be removed in a future version
  app.launch_new_instance()






    



---------------------------------------------------------------------------
Exception                                 Traceback (most recent call last)
<ipython-input-51-5a6da8260e90> in <module>()
      1 TempLGA_arr = np.array(joined_df['Temp_LGA'][:30])
      2 Tempsensor_arr = np.array(joined_df['Temp_sensor'][:30])
----> 3 pd.rolling_corr(TempLGA_arr, Tempsensor_arr, 10).plot()

/Users/Zelda/anaconda/lib/python2.7/site-packages/pandas/stats/moments.pyc in rolling_corr(arg1, arg2, window, pairwise, **kwargs)
    316                          pairwise=pairwise,
    317                          func_kw=['other', 'pairwise'],
--> 318                          **kwargs)
    319 
    320 

/Users/Zelda/anaconda/lib/python2.7/site-packages/pandas/stats/moments.pyc in ensure_compat(dispatch, name, arg, func_kw, *args, **kwargs)
    238                       FutureWarning, stacklevel=3)
    239 
--> 240     result = getattr(r, name)(*args, **kwds)
    241 
    242     if is_ndarray:

/Users/Zelda/anaconda/lib/python2.7/site-packages/pandas/core/window.pyc in corr(self, other, pairwise, **kwargs)
    855     def corr(self, other=None, pairwise=None, **kwargs):
    856         return super(Rolling, self).corr(other=other, pairwise=pairwise,
--> 857                                          **kwargs)
    858 
    859 

/Users/Zelda/anaconda/lib/python2.7/site-packages/pandas/core/window.pyc in corr(self, other, pairwise, **kwargs)
    725 
    726         return _flex_binary_moment(self._selected_obj, other._selected_obj,
--> 727                                    _get_corr, pairwise=bool(pairwise))
    728 
    729 

/Users/Zelda/anaconda/lib/python2.7/site-packages/pandas/core/window.pyc in _flex_binary_moment(arg1, arg2, f, pairwise)
   1263     if (isinstance(arg1, (np.ndarray, Series)) and
   1264             isinstance(arg2, (np.ndarray, Series))):
-> 1265         X, Y = _prep_binary(arg1, arg2)
   1266         return f(X, Y)
   1267 

/Users/Zelda/anaconda/lib/python2.7/site-packages/pandas/core/window.pyc in _prep_binary(arg1, arg2)
   1398 def _prep_binary(arg1, arg2):
   1399     if not isinstance(arg2, type(arg1)):
-> 1400         raise Exception('Input arrays must be of the same type!')
   1401 
   1402     # mask out values, this also makes a common index...

Exception: Input arrays must be of the same type!



In [ ]:



In [ ]:

	Temp	Rel Humid
Timestamp
2016-07-07 14:59:53	75.20	60.0
2016-07-07 15:15:42	78.26	57.1
2016-07-07 15:31:30	76.82	44.5

	Temp	Rel Humid
Timestamp
2016-07-01 01:45:00	75.220000	60.350000
2016-07-01 02:15:00	75.191429	54.138571
2016-07-01 02:45:00	73.420000	67.593333

	Temp_LGA	Rel Humid_LGA	Temp_sensor	Rel Humid_sensor
Timestamp
2016-07-07 14:15:00	85.502857	67.405714	75.20	60.00
2016-07-07 14:45:00	83.920000	70.441667	78.26	57.10
2016-07-07 15:15:00	87.585714	59.391429	76.82	43.55
2016-07-07 15:45:00	85.420000	63.580000	76.01	45.05
2016-07-07 16:15:00	87.714286	56.904286	74.93	46.30
2016-07-07 16:45:00	86.920000	61.275000	74.12	49.05
2016-07-07 17:15:00	84.320000	66.630000	73.85	47.70
2016-07-07 17:45:00	83.920000	66.006667	73.58	48.25
2016-07-07 18:15:00	80.797143	72.445714	73.31	51.10
2016-07-07 18:45:00	78.820000	77.903333	73.22	50.80
2016-07-07 19:15:00	80.282857	74.831429	73.40	52.70
2016-07-07 19:45:00	79.420000	77.183333	73.04	51.20
2016-07-07 20:15:00	79.100000	78.038571	73.22	52.45
2016-07-07 20:45:00	80.320000	74.938333	72.95	53.85
2016-07-07 21:15:00	79.614286	76.755714	72.77	53.40
2016-07-07 21:45:00	78.820000	78.680000	72.86	54.15
2016-07-07 22:15:00	78.842857	80.788571	73.13	54.80
2016-07-07 22:45:00	78.220000	80.283333	72.59	53.70
2016-07-07 23:15:00	77.531429	82.114286	73.04	55.05
2016-07-07 23:45:00	75.520000	88.688333	72.86	55.40
2016-07-08 00:15:00	75.191429	88.620000	72.86	55.65
2016-07-08 00:45:00	74.920000	89.536667	72.86	55.70
2016-07-08 01:15:00	74.420000	90.977143	72.86	55.80
2016-07-08 01:45:00	74.920000	89.536667	72.86	55.70
2016-07-08 02:15:00	75.320000	88.620000	72.77	56.00
2016-07-08 02:45:00	75.220000	88.620000	72.77	56.20
2016-07-08 03:15:00	73.751429	93.334286	72.86	56.55
2016-07-08 03:45:00	75.220000	88.681667	72.77	56.55
2016-07-08 04:15:00	75.834286	87.154286	72.86	56.65
2016-07-08 04:45:00	74.320000	91.370000	72.86	56.45
...	...	...	...	...
2016-09-14 22:15:00	75.817143	60.508571	79.25	55.80
2016-09-14 22:45:00	73.700000	58.958333	79.25	55.75
2016-09-14 23:15:00	71.908571	56.222857	79.25	55.35
2016-09-14 23:45:00	71.600000	54.900000	79.25	54.25
2016-09-15 00:15:00	69.825714	56.440000	79.16	53.30
2016-09-15 00:45:00	69.800000	57.078333	79.16	52.70
2016-09-15 01:15:00	69.028571	53.751429	79.16	52.60
2016-09-15 01:45:00	68.000000	50.860000	78.98	52.10
2016-09-15 02:15:00	68.000000	52.000000	78.98	51.60
2016-09-15 02:45:00	66.800000	58.590000	78.98	50.90
2016-09-15 03:15:00	66.174286	58.135714	78.98	50.45
2016-09-15 03:45:00	66.200000	55.930000	78.98	49.95
2016-09-15 04:15:00	64.477143	59.540000	78.89	49.60
2016-09-15 04:45:00	64.400000	58.895000	78.80	49.20
2016-09-15 05:15:00	64.348571	58.434286	78.80	49.15
2016-09-15 05:45:00	64.100000	57.565000	78.80	48.55
2016-09-15 06:15:00	62.651429	59.300000	78.80	48.00
2016-09-15 06:45:00	63.500000	57.485000	78.80	48.30
2016-09-15 07:15:00	64.348571	55.670000	78.35	41.60
2016-09-15 07:45:00	64.400000	55.670000	78.26	41.05
2016-09-15 08:15:00	65.917143	50.331429	78.08	41.00
2016-09-15 08:45:00	66.500000	48.380000	78.08	40.85
2016-09-15 09:15:00	67.742857	45.918571	77.99	40.65
2016-09-15 09:45:00	69.200000	43.153333	78.08	39.90
2016-09-15 10:15:00	69.825714	40.340000	77.72	39.05
2016-09-15 10:45:00	70.100000	40.388333	77.36	38.90
2016-09-15 11:15:00	69.825714	40.340000	77.54	43.00
2016-09-15 11:45:00	70.700000	39.145000	77.18	47.60
2016-09-15 12:15:00	71.522857	37.228571	77.18	54.50
2016-09-15 12:45:00	71.600000	37.106667	77.18	62.40