FinalMethods-checkpoint.ipynb

Kernel: Python 3

import pandas as pd
import numpy as np

PPM = pd.read_csv('NatatmoCleanedForInfiltrationAnalysis.csv', parse_dates=True, index_col=1)

---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
<ipython-input-4-4ed48fd0b1d8> in <module>()
----> 1 PPM = pd.read_csv('NatatmoCleanedForInfiltrationAnalysis.csv', parse_dates=True, index_col=1)

~/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py in parser_f(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, escapechar, comment, encoding, dialect, tupleize_cols, error_bad_lines, warn_bad_lines, skipfooter, skip_footer, doublequote, delim_whitespace, as_recarray, compact_ints, use_unsigned, low_memory, buffer_lines, memory_map, float_precision)
    653                     skip_blank_lines=skip_blank_lines)
    654 
--> 655         return _read(filepath_or_buffer, kwds)
    656 
    657     parser_f.__name__ = name
~/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py in _read(filepath_or_buffer, kwds)
    403 
    404     # Create the parser.
--> 405     parser = TextFileReader(filepath_or_buffer, **kwds)
    406 
    407     if chunksize or iterator:
~/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py in __init__(self, f, engine, **kwds)
    762             self.options['has_index_names'] = kwds['has_index_names']
    763 
--> 764         self._make_engine(self.engine)
    765 
    766     def close(self):
~/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py in _make_engine(self, engine)
    983     def _make_engine(self, engine='c'):
    984         if engine == 'c':
--> 985             self._engine = CParserWrapper(self.f, **self.options)
    986         else:
    987             if engine == 'python':
~/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py in __init__(self, src, **kwds)
   1603         kwds['allow_leading_cols'] = self.index_col is not False
   1604 
-> 1605         self._reader = parsers.TextReader(src, **kwds)
   1606 
   1607         # XXX
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader.__cinit__ (pandas/_libs/parsers.c:4209)()
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._setup_parser_source (pandas/_libs/parsers.c:8873)()
FileNotFoundError: File b'NatatmoCleanedForInfiltrationAnalysis.csv' does not exist

%matplotlib inline
PPM['ppm'].plot()

<matplotlib.axes._subplots.AxesSubplot at 0x7f4384188e80>

delta_CO2 = PPM['ppm'].diff(1)

PPM['Time'] = PPM.index
delta_time = PPM['Time'].diff(1) / np.timedelta64(1,'m')
slopes = delta_CO2 / delta_time

%matplotlib inline
slopes.plot()

<matplotlib.axes._subplots.AxesSubplot at 0x7f438341b8d0>

slopes.describe()

count    1.009790e+05
mean              NaN
std               NaN
min              -inf
25%     -1.200000e+00
50%      0.000000e+00
75%      1.000000e+00
max               inf
dtype: float64

slopes.head()

Time
2016-02-19 13:26:00    NaN
2016-02-19 13:27:00    NaN
2016-02-19 13:27:00    NaN
2016-02-19 13:31:00    NaN
2016-02-19 13:36:00   -1.0
dtype: float64

neg_slopes = slopes[slopes<0]

yearsdecay = (neg_slopes * PPM['ppm'])
(yearsdecay).plot()

<matplotlib.axes._subplots.AxesSubplot at 0x7f4383715d30>

(yearsdecay).head()

Time
2016-02-19 13:26:00      NaN
2016-02-19 13:27:00      NaN
2016-02-19 13:27:00      NaN
2016-02-19 13:31:00      NaN
2016-02-19 13:36:00   -332.0
dtype: float64

made Infiltration csv (perhaps for detailed reference later)

yearsdecay.to_csv('Infiltration_Rate.cvs')

column_names = ['Time', 'ppm/min']
In= pd.read_csv('Infiltration_Rate.cvs', parse_dates=True, index_col=0, names = column_names)
In.head()

	ppm/min
Time
2016-02-19 13:26:00	NaN
2016-02-19 13:27:00	NaN
2016-02-19 13:27:00	NaN
2016-02-19 13:31:00	NaN
2016-02-19 13:36:00	-332.0

In.describe()

	ppm/min
count	4.885000e+04
mean	-inf
std	NaN
min	-inf
25%	-1.046850e+03
50%	-5.160000e+02
75%	-2.460000e+02
max	-2.306667e+01

In = In.replace([np.inf, -np.inf], np.nan)
In.describe()

	ppm/min
count	48848.000000
mean	-1141.663669
std	3186.375410
min	-206960.600000
25%	-1046.400000
50%	-516.000000
75%	-246.000000
max	-23.066667

#In.plot()

In.hist(bins=1000)

array([[<matplotlib.axes._subplots.AxesSubplot object at 0x7f4382e699e8>]], dtype=object)

In.hist(bins=10000)

array([[<matplotlib.axes._subplots.AxesSubplot object at 0x7f4382df5160>]], dtype=object)

In.hist(bins=[-5000,-1000,-900,-850,-800,-750,-700,-650,-550,-500,-450,-400,-350,-300,-250,-200,0])

array([[<matplotlib.axes._subplots.AxesSubplot object at 0x7f437f04c358>]], dtype=object)

Question for Soto: how to make bins small enough to fit each value, or at least equal to the average difference

In.hist(bins=[-1000,-900,-800,-700,-600,-500,-400,-300,-200,-100,0])

array([[<matplotlib.axes._subplots.AxesSubplot object at 0x7f43834fc828>]], dtype=object)

In.hist(bins=[-700,-699,-698,-697,-696,-600,-550,-525,-500,-400,-300,-200,-100,0])

array([[<matplotlib.axes._subplots.AxesSubplot object at 0x7f437de3b2b0>]], dtype=object)

This needs some work

min_val = -4000
max_val = 0
num_bins = 1000
my_bins = np.linspace(min_val, max_val, num_bins)
In.hist(bins=np.r_[-np.inf, my_bins, np.inf])

/ext/anaconda3/lib/python3.5/site-packages/matplotlib/axes/_axes.py:6277: RuntimeWarning: invalid value encountered in add
  patch = _barfunc(bins[:-1]+boffset, height, width,
/ext/anaconda3/lib/python3.5/site-packages/matplotlib/axes/_axes.py:2105: RuntimeWarning: invalid value encountered in double_scalars
  left = [left[i] - width[i] / 2. for i in xrange(len(left))]

array([[<matplotlib.axes._subplots.AxesSubplot object at 0x7f437d8a0b70>]], dtype=object)

In.kdeplot()

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-23-a2f1855ae631> in <module>()
----> 1 In.kdeplot()

/ext/anaconda3/lib/python3.5/site-packages/pandas/core/generic.py in __getattr__(self, name)
   3079             if name in self._info_axis:
   3080                 return self[name]
-> 3081             return object.__getattribute__(self, name)
   3082 
   3083     def __setattr__(self, name, value):
AttributeError: 'DataFrame' object has no attribute 'kdeplot'

 In.plot.area(stacked=False);

In.plot(kind='kde', xlim=[0, 100000])