NetAtmo_2017.ipynb

Kernel: Python 3 (Anaconda)

NetAtmo Data 2017

%matplotlib notebook
#%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
data = pd.read_csv('NetAtmo_2017.csv', 
                   index_col=1,      # use column 1 as the dates to index the data
                   parse_dates=True) # convert the date string into a date object
data[-5:]

---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
<ipython-input-2-4282bb2de908> in <module>()
      6 data = pd.read_csv('NetAtmo_2017.csv', 
      7                    index_col=1,      # use column 1 as the dates to index the data
----> 8                    parse_dates=True) # convert the date string into a date object
      9 data[-5:]
/projects/anaconda3/lib/python3.5/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)
    644                     skip_blank_lines=skip_blank_lines)
    645 
--> 646         return _read(filepath_or_buffer, kwds)
    647 
    648     parser_f.__name__ = name
/projects/anaconda3/lib/python3.5/site-packages/pandas/io/parsers.py in _read(filepath_or_buffer, kwds)
    387 
    388     # Create the parser.
--> 389     parser = TextFileReader(filepath_or_buffer, **kwds)
    390 
    391     if (nrows is not None) and (chunksize is not None):
/projects/anaconda3/lib/python3.5/site-packages/pandas/io/parsers.py in __init__(self, f, engine, **kwds)
    728             self.options['has_index_names'] = kwds['has_index_names']
    729 
--> 730         self._make_engine(self.engine)
    731 
    732     def close(self):
/projects/anaconda3/lib/python3.5/site-packages/pandas/io/parsers.py in _make_engine(self, engine)
    921     def _make_engine(self, engine='c'):
    922         if engine == 'c':
--> 923             self._engine = CParserWrapper(self.f, **self.options)
    924         else:
    925             if engine == 'python':
/projects/anaconda3/lib/python3.5/site-packages/pandas/io/parsers.py in __init__(self, src, **kwds)
   1388         kwds['allow_leading_cols'] = self.index_col is not False
   1389 
-> 1390         self._reader = _parser.TextReader(src, **kwds)
   1391 
   1392         # XXX
pandas/parser.pyx in pandas.parser.TextReader.__cinit__ (pandas/parser.c:4184)()
pandas/parser.pyx in pandas.parser.TextReader._setup_parser_source (pandas/parser.c:8449)()
FileNotFoundError: File b'NetAtmo_2017.csv' does not exist

Above, we have a sample of how the data we are using is organized and the type of results we acquired for each category.

inside_concentration = data['CO2']
concentration_slope = data['CO2'].diff()/data['Timestamp'].diff()
concentration_slope.plot()

The graph above demonstrates the amount of CO2 over the span of the year 2017. This will be useful in finding how quickly the CO2 levels decay according to what we find the infiltration rate is with the blower door test.

concentration_slope = concentration_slope.where(concentration_slope<0, 0)
concentration_slope = concentration_slope.where(data['CO2']>450, 0)
concentration_slope.plot()

Here, we can see the rate at which the CO2 levels fall.

infiltration_rate = concentration_slope/((inside_concentration - 400.).abs())*3600
infiltration_rate.plot()

ax = infiltration_rate.plot()
ax.set_ylim((-1,1))
ax.grid()
plt.savefig('test.pdf')

infiltration_rate.describe()

infiltration_rate.hist(bins=50)

data['CO2'].plot()

time2 = '2017-01-23 11:00:00'
time1 = '2017-02-6 11:00:00'

data[time2:time1]

#time2 = '2017-01-23 11:00:00'
#time1 = '2017-02-6 11:00:00'
rise = data['CO2'][time2] - data['CO2'][time1]
run = (data['Timestamp'][time2] - data['Timestamp'][time1])


print(data['CO2'][time2])
print(rise)
print('run =',run)
print('slope =', rise/run)
rise / run * 3600 / (data['CO2'][time2]-400)